diff --git a/Introduction-to-Pandas--master.ipynb b/Introduction-to-Pandas--master.ipynb
index c4772f0eb03a5aaefbea6892b61d2340987f7880..752090b33060577d84ba86af91932d8ad9edf04e 100644
--- a/Introduction-to-Pandas--master.ipynb
+++ b/Introduction-to-Pandas--master.ipynb
@@ -87,7 +87,7 @@
"* [Task 5](#task5)\n",
"* [Task 6](#task6)\n",
"* [Task 7](#task7)\n",
- "* [Bonus Task](#taskb)"
+ "* [Task 7B](#task7b)"
]
},
{
@@ -1308,23 +1308,203 @@
]
},
{
- "cell_type": "markdown",
+ "cell_type": "code",
+ "execution_count": 20,
"metadata": {
"slideshow": {
"slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Age</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Name</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Liu</th>\n",
+ " <td>1681</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rowland</th>\n",
+ " <td>3136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rivers</th>\n",
+ " <td>3136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Waters</th>\n",
+ " <td>3249</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rice</th>\n",
+ " <td>1521</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Age\n",
+ "Name \n",
+ "Liu 1681\n",
+ "Rowland 3136\n",
+ "Rivers 3136\n",
+ "Waters 3249\n",
+ "Rice 1521"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "def mysquare(number: float) -> float:\n",
+ " return number*number\n",
+ "\n",
+ "df_sample.apply(mysquare).head()\n",
+ "# or: df_sample.apply(lambda x: x*x).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "skip"
}
},
+ "outputs": [],
"source": [
- "Logical operations allowed as well"
+ "import numpy as np"
]
},
{
"cell_type": "code",
- "execution_count": 20,
+ "execution_count": 22,
"metadata": {
"slideshow": {
"slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Age</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Name</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Liu</th>\n",
+ " <td>1681</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rowland</th>\n",
+ " <td>3136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rivers</th>\n",
+ " <td>3136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Waters</th>\n",
+ " <td>3249</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rice</th>\n",
+ " <td>1521</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Age\n",
+ "Name \n",
+ "Liu 1681\n",
+ "Rowland 3136\n",
+ "Rivers 3136\n",
+ "Waters 3249\n",
+ "Rice 1521"
+ ]
+ },
+ "execution_count": 22,
+ "metadata": {},
+ "output_type": "execute_result"
}
+ ],
+ "source": [
+ "df_sample.apply(np.square).head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ },
+ "tags": []
+ },
+ "source": [
+ "Logical operations allowed as well"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {
+ "tags": []
},
"outputs": [
{
@@ -1415,7 +1595,7 @@
"Hall True"
]
},
- "execution_count": 20,
+ "execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
@@ -1424,6 +1604,88 @@
"df_sample > 40"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Age</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Name</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Liu</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rowland</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rivers</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Waters</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rice</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Age\n",
+ "Name \n",
+ "Liu True\n",
+ "Rowland True\n",
+ "Rivers True\n",
+ "Waters True\n",
+ "Rice True"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_sample.apply(mysquare).head() == df_sample.apply(lambda x: x*x).head()"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {
@@ -1435,7 +1697,7 @@
"source": [
"## Task 1\n",
"<a name=\"task1\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Create data frame with\n",
" - 6 names of dinosaurs, \n",
@@ -1463,7 +1725,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 25,
"metadata": {
"exercise": "task",
"slideshow": {
@@ -1482,7 +1744,7 @@
},
{
"cell_type": "code",
- "execution_count": 22,
+ "execution_count": 26,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -1552,7 +1814,7 @@
"Favourite Color violet gray "
]
},
- "execution_count": 22,
+ "execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
@@ -1575,25 +1837,12 @@
}
},
"source": [
- "Some more `DataFrame` examples"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 23,
- "metadata": {
- "slideshow": {
- "slide_type": "skip"
- }
- },
- "outputs": [],
- "source": [
- "import numpy as np"
+ "### More `DataFrame` examples"
]
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": 27,
"metadata": {},
"outputs": [
{
@@ -1678,7 +1927,7 @@
"4 1.2 2018-02-26 -0.718282 entries Same"
]
},
- "execution_count": 24,
+ "execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
@@ -1696,7 +1945,7 @@
},
{
"cell_type": "code",
- "execution_count": 25,
+ "execution_count": 28,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -1785,7 +2034,7 @@
"1 1.2 2018-02-26 1.718282 column Same"
]
},
- "execution_count": 25,
+ "execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
@@ -1796,7 +2045,7 @@
},
{
"cell_type": "code",
- "execution_count": 26,
+ "execution_count": 29,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -1858,7 +2107,7 @@
"4 1.2 2018-02-26 -0.72 entries Same"
]
},
- "execution_count": 26,
+ "execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
@@ -1869,7 +2118,7 @@
},
{
"cell_type": "code",
- "execution_count": 27,
+ "execution_count": 30,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -1885,7 +2134,7 @@
"dtype: object"
]
},
- "execution_count": 27,
+ "execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
@@ -1896,7 +2145,7 @@
},
{
"cell_type": "code",
- "execution_count": 28,
+ "execution_count": 31,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -1955,7 +2204,7 @@
},
{
"cell_type": "code",
- "execution_count": 117,
+ "execution_count": 32,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -2038,7 +2287,7 @@
"Walt Malcolm David Kelley False"
]
},
- "execution_count": 117,
+ "execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
@@ -2058,7 +2307,7 @@
"source": [
"## Task 2\n",
"<a name=\"task2\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Read in `data-nest.csv` to `DataFrame`; call it `df` \n",
" *(Data was produced with [JUBE](http://www.fz-juelich.de/ias/jsc/EN/Expertise/Support/Software/JUBE/_node.html))*\n",
@@ -2068,7 +2317,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 33,
"metadata": {
"exercise": "task"
},
@@ -2084,12 +2333,12 @@
}
],
"source": [
- "!cat nest-data.csv | head -3"
+ "!cat data-nest.csv | head -3"
]
},
{
"cell_type": "code",
- "execution_count": 118,
+ "execution_count": 34,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -2313,7 +2562,7 @@
"[5 rows x 21 columns]"
]
},
- "execution_count": 118,
+ "execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
@@ -2360,8 +2609,19 @@
"source": [
"## Slicing of Data Frames\n",
"\n",
- "* Pandas documentation: [Detailed documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html), [short documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/10min.html#selection)\n",
- "\n",
+ "* Slicing: Select a sub-range / sub-set of entire data frame\n",
+ "* Pandas documentation: [Detailed documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html), [short documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/10min.html#selection)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "source": [
"### Quick Slices\n",
"\n",
"* Use square-bracket operators to slice data frame quickly: `[]`\n",
@@ -2372,7 +2632,7 @@
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 35,
"metadata": {},
"outputs": [
{
@@ -2439,7 +2699,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 32,
+ "execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
@@ -2450,8 +2710,13 @@
},
{
"cell_type": "code",
- "execution_count": 33,
- "metadata": {},
+ "execution_count": 36,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "fragment"
+ },
+ "tags": []
+ },
"outputs": [
{
"data": {
@@ -2464,7 +2729,7 @@
"Name: C, dtype: float64"
]
},
- "execution_count": 33,
+ "execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
@@ -2474,14 +2739,23 @@
]
},
{
- "cell_type": "code",
- "execution_count": 34,
+ "cell_type": "markdown",
"metadata": {
"slideshow": {
- "slide_type": "fragment"
+ "slide_type": "subslide"
},
"tags": []
},
+ "source": [
+ "* Instead of column name in quotes and square brackets: Name of column _directly_"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {
+ "tags": []
+ },
"outputs": [
{
"data": {
@@ -2494,7 +2768,7 @@
"Name: C, dtype: float64"
]
},
- "execution_count": 34,
+ "execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
@@ -2503,6 +2777,14 @@
"df_demo.C"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "* I'm not a friend, because no spaces allowed \n",
+ " (And **Pandas as early as possible** means labelling columns well and adding spaces)"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {
@@ -2517,7 +2799,7 @@
},
{
"cell_type": "code",
- "execution_count": 35,
+ "execution_count": 38,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -2588,7 +2870,7 @@
"4 1.2 -0.718282"
]
},
- "execution_count": 35,
+ "execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
@@ -2606,13 +2888,13 @@
}
},
"source": [
- "* Use numerical values in brackets to slice along rows\n",
+ "* Use numerical values in brackets to slice **along rows**\n",
"* Use ranges just like with Python lists"
]
},
{
"cell_type": "code",
- "execution_count": 36,
+ "execution_count": 39,
"metadata": {},
"outputs": [
{
@@ -2670,7 +2952,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 36,
+ "execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
@@ -2681,7 +2963,7 @@
},
{
"cell_type": "code",
- "execution_count": 37,
+ "execution_count": 40,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -2744,7 +3026,7 @@
"3 1.2 2018-02-26 0.986231 entries Same"
]
},
- "execution_count": 37,
+ "execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
@@ -2766,7 +3048,7 @@
},
{
"cell_type": "code",
- "execution_count": 38,
+ "execution_count": 41,
"metadata": {},
"outputs": [
{
@@ -2824,7 +3106,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 38,
+ "execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
@@ -2835,7 +3117,7 @@
},
{
"cell_type": "code",
- "execution_count": 39,
+ "execution_count": 42,
"metadata": {},
"outputs": [
{
@@ -2893,7 +3175,7 @@
"4 1.2 2018-02-26 -0.718282 entries Same"
]
},
- "execution_count": 39,
+ "execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
@@ -2920,7 +3202,7 @@
},
{
"cell_type": "code",
- "execution_count": 40,
+ "execution_count": 43,
"metadata": {
"tags": []
},
@@ -2980,7 +3262,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 40,
+ "execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
@@ -2998,12 +3280,12 @@
"tags": []
},
"source": [
- "* Also slice rows (second argument)"
+ "* Also slice along columns (second argument)"
]
},
{
"cell_type": "code",
- "execution_count": 41,
+ "execution_count": 44,
"metadata": {},
"outputs": [
{
@@ -3052,7 +3334,7 @@
"2 1.2 -1.304068"
]
},
- "execution_count": 41,
+ "execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
@@ -3076,7 +3358,7 @@
},
{
"cell_type": "code",
- "execution_count": 42,
+ "execution_count": 45,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3167,7 +3449,7 @@
"entries 1.2 2018-02-26 -0.718282 Same"
]
},
- "execution_count": 42,
+ "execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
@@ -3179,7 +3461,7 @@
},
{
"cell_type": "code",
- "execution_count": 43,
+ "execution_count": 46,
"metadata": {},
"outputs": [
{
@@ -3242,7 +3524,7 @@
"entries 1.2 2018-02-26 -0.718282 Same"
]
},
- "execution_count": 43,
+ "execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
@@ -3253,7 +3535,7 @@
},
{
"cell_type": "code",
- "execution_count": 44,
+ "execution_count": 47,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3319,7 +3601,7 @@
"entries 1.2 -0.718282"
]
},
- "execution_count": 44,
+ "execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
@@ -3349,7 +3631,7 @@
},
{
"cell_type": "code",
- "execution_count": 45,
+ "execution_count": 48,
"metadata": {},
"outputs": [
{
@@ -3407,7 +3689,7 @@
"3 1.2 2018-02-26 0.986231 entries Same"
]
},
- "execution_count": 45,
+ "execution_count": 48,
"metadata": {},
"output_type": "execute_result"
}
@@ -3418,7 +3700,7 @@
},
{
"cell_type": "code",
- "execution_count": 46,
+ "execution_count": 49,
"metadata": {},
"outputs": [
{
@@ -3432,7 +3714,7 @@
"Name: C, dtype: bool"
]
},
- "execution_count": 46,
+ "execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
@@ -3443,7 +3725,7 @@
},
{
"cell_type": "code",
- "execution_count": 47,
+ "execution_count": 50,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3496,7 +3778,7 @@
"4 1.2 2018-02-26 -0.718282 entries Same"
]
},
- "execution_count": 47,
+ "execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
@@ -3526,7 +3808,7 @@
},
{
"cell_type": "code",
- "execution_count": 48,
+ "execution_count": 51,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3597,7 +3879,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 48,
+ "execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
@@ -3608,11 +3890,12 @@
},
{
"cell_type": "code",
- "execution_count": 49,
+ "execution_count": 52,
"metadata": {
"slideshow": {
- "slide_type": "subslide"
- }
+ "slide_type": "fragment"
+ },
+ "tags": []
},
"outputs": [
{
@@ -3683,7 +3966,7 @@
"2 1.2 2018-02-26 -1.304068 has Same -2.504068"
]
},
- "execution_count": 49,
+ "execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
@@ -3693,18 +3976,114 @@
"df_demo.head(3)"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ },
+ "tags": []
+ },
+ "source": [
+ "* `.insert()` allows to specify position of insertion\n",
+ "* `.shape` gives tuple of size of data frame, `vertical, horizontal`"
+ ]
+ },
{
"cell_type": "code",
- "execution_count": 50,
- "metadata": {},
- "outputs": [],
+ "execution_count": 53,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>C</th>\n",
+ " <th>D</th>\n",
+ " <th>E</th>\n",
+ " <th>E2</th>\n",
+ " <th>F</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1.2</td>\n",
+ " <td>2018-02-26</td>\n",
+ " <td>-2.718282</td>\n",
+ " <td>This</td>\n",
+ " <td>Same</td>\n",
+ " <td>7.389056</td>\n",
+ " <td>-3.918282</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1.2</td>\n",
+ " <td>2018-02-26</td>\n",
+ " <td>1.718282</td>\n",
+ " <td>column</td>\n",
+ " <td>Same</td>\n",
+ " <td>2.952492</td>\n",
+ " <td>0.518282</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>1.2</td>\n",
+ " <td>2018-02-26</td>\n",
+ " <td>-1.304068</td>\n",
+ " <td>has</td>\n",
+ " <td>Same</td>\n",
+ " <td>1.700594</td>\n",
+ " <td>-2.504068</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B C D E E2 F\n",
+ "0 1.2 2018-02-26 -2.718282 This Same 7.389056 -3.918282\n",
+ "1 1.2 2018-02-26 1.718282 column Same 2.952492 0.518282\n",
+ "2 1.2 2018-02-26 -1.304068 has Same 1.700594 -2.504068"
+ ]
+ },
+ "execution_count": 53,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "df_demo.insert(df_demo.shape[1] - 1, \"E2\", df_demo[\"C\"] ** 2)"
+ "df_demo.insert(df_demo.shape[1] - 1, \"E2\", df_demo[\"C\"] ** 2)\n",
+ "df_demo.head(3)"
]
},
{
"cell_type": "code",
- "execution_count": 51,
+ "execution_count": 54,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -3783,7 +4162,7 @@
"4 1.2 2018-02-26 -0.718282 entries Same 0.515929 -1.918282"
]
},
- "execution_count": 51,
+ "execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
@@ -3794,7 +4173,7 @@
},
{
"cell_type": "code",
- "execution_count": 52,
+ "execution_count": 55,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3906,7 +4285,7 @@
"5 1.3 2018-02-27 -0.777000 has it? Same NaN 23.000000"
]
},
- "execution_count": 52,
+ "execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
@@ -3933,7 +4312,7 @@
},
{
"cell_type": "code",
- "execution_count": 53,
+ "execution_count": 56,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3986,7 +4365,7 @@
"1 Second 1"
]
},
- "execution_count": 53,
+ "execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
@@ -3998,7 +4377,7 @@
},
{
"cell_type": "code",
- "execution_count": 54,
+ "execution_count": 57,
"metadata": {},
"outputs": [
{
@@ -4047,7 +4426,7 @@
"1 Second 2"
]
},
- "execution_count": 54,
+ "execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
@@ -4070,7 +4449,7 @@
},
{
"cell_type": "code",
- "execution_count": 55,
+ "execution_count": 58,
"metadata": {},
"outputs": [
{
@@ -4131,7 +4510,7 @@
"1 Second 2"
]
},
- "execution_count": 55,
+ "execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
@@ -4153,7 +4532,7 @@
},
{
"cell_type": "code",
- "execution_count": 56,
+ "execution_count": 59,
"metadata": {},
"outputs": [
{
@@ -4214,7 +4593,7 @@
"3 Second 2"
]
},
- "execution_count": 56,
+ "execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
@@ -4236,7 +4615,7 @@
},
{
"cell_type": "code",
- "execution_count": 57,
+ "execution_count": 60,
"metadata": {},
"outputs": [
{
@@ -4291,7 +4670,7 @@
"1 Second 1 Second 2"
]
},
- "execution_count": 57,
+ "execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
@@ -4313,7 +4692,7 @@
},
{
"cell_type": "code",
- "execution_count": 58,
+ "execution_count": 61,
"metadata": {},
"outputs": [
{
@@ -4365,7 +4744,7 @@
"1 Second 1 2"
]
},
- "execution_count": 58,
+ "execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
@@ -4385,7 +4764,7 @@
"source": [
"## Task 3\n",
"<a name=\"task3\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Add a column to the Nest data frame form Task 2 called `Threads` which is the total number of threads across all nodes (i.e. the product of threads per task and tasks per node and nodes)\n",
"* Tell me when you're done with status icon in BigBlueButton: 👍"
@@ -4393,7 +4772,7 @@
},
{
"cell_type": "code",
- "execution_count": 59,
+ "execution_count": 62,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -4610,7 +4989,7 @@
"[5 rows x 22 columns]"
]
},
- "execution_count": 59,
+ "execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
@@ -4622,7 +5001,7 @@
},
{
"cell_type": "code",
- "execution_count": 60,
+ "execution_count": 63,
"metadata": {
"exercise": "solution"
},
@@ -4640,7 +5019,7 @@
" dtype='object')"
]
},
- "execution_count": 60,
+ "execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
@@ -4671,7 +5050,7 @@
},
{
"cell_type": "code",
- "execution_count": 61,
+ "execution_count": 64,
"metadata": {
"exercise": "task",
"slideshow": {
@@ -4686,7 +5065,7 @@
},
{
"cell_type": "code",
- "execution_count": 62,
+ "execution_count": 65,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -4700,7 +5079,7 @@
},
{
"cell_type": "code",
- "execution_count": 63,
+ "execution_count": 66,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -4742,7 +5121,7 @@
},
{
"cell_type": "code",
- "execution_count": 64,
+ "execution_count": 67,
"metadata": {
"slideshow": {
"slide_type": "-"
@@ -4755,7 +5134,7 @@
},
{
"cell_type": "code",
- "execution_count": 65,
+ "execution_count": 68,
"metadata": {},
"outputs": [
{
@@ -4794,7 +5173,7 @@
},
{
"cell_type": "code",
- "execution_count": 66,
+ "execution_count": 69,
"metadata": {},
"outputs": [
{
@@ -4828,10 +5207,10 @@
"source": [
"## Task 4\n",
"<a name=\"task4\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"\n",
- "* Sort the data frame by threads\n",
+ "* Sort the Nest data frame by threads\n",
"* Plot `\"Presim. Time / s\"` and `\"Sim. Time / s\"` of our data frame `df` as a function of threads\n",
"* Use a dashed, red line for `\"Presim. Time / s\"`, a blue line for `\"Sim. Time / s\"` (see [API description](https://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.plot))\n",
"* Don't forget to label your axes and to add a legend _(1st rule of plotting)_\n",
@@ -4840,7 +5219,7 @@
},
{
"cell_type": "code",
- "execution_count": 67,
+ "execution_count": 70,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -4849,12 +5228,12 @@
},
"outputs": [],
"source": [
- "df.sort_values([\"Threads\", \"Nodes\", \"Tasks/Node\", \"Threads/Task\"], inplace=True)"
+ "df.sort_values([\"Threads\", \"Nodes\", \"Tasks/Node\", \"Threads/Task\"], inplace=True) # multi-level sort"
]
},
{
"cell_type": "code",
- "execution_count": 68,
+ "execution_count": 71,
"metadata": {
"exercise": "solution"
},
@@ -4894,7 +5273,7 @@
"* Each data frame hast a `.plot()` function (see [API](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.plot.html))\n",
"* Plots with Matplotlib\n",
"* Important API options:\n",
- " - `kind`: `line` (default), `bar[h]`, `hist`, `box`, `kde`, `scatter`, `hexbin`\n",
+ " - `kind`: `'line'` (default), `'bar[h]'`, `'hist'`, `'box'`, `'kde'`, `'scatter'`, `'hexbin'`\n",
" - `subplots`: Make a sub-plot for each column (good together with `sharex`, `sharey`)\n",
" - `figsize`\n",
" - `grid`: Add a grid to plot (use Matplotlib options)\n",
@@ -4909,7 +5288,7 @@
" * `title`: Add title to plot (Use a list of strings if `subplots=True`)\n",
" * `legend`: Add a legend\n",
" * `table`: If `true`, add table of data under plot\n",
- " - `**kwds`: Every non-parsed keyword is passed through to Matplotlib's plotting methods"
+ " - `**kwds`: Non-parsed keyword passed to Matplotlib's plotting methods"
]
},
{
@@ -4925,7 +5304,7 @@
},
{
"cell_type": "code",
- "execution_count": 69,
+ "execution_count": 72,
"metadata": {
"slideshow": {
"slide_type": "-"
@@ -4962,7 +5341,7 @@
},
{
"cell_type": "code",
- "execution_count": 70,
+ "execution_count": 73,
"metadata": {
"slideshow": {
"slide_type": "-"
@@ -4990,12 +5369,13 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "* I prefer slicing first, as it allows for further operations on the sliced data frame"
+ "* I prefer slicing first: \n",
+ " → Allows for further operations on the sliced data frame"
]
},
{
"cell_type": "code",
- "execution_count": 71,
+ "execution_count": 74,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5029,7 +5409,7 @@
},
{
"cell_type": "code",
- "execution_count": 72,
+ "execution_count": 75,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -5055,7 +5435,7 @@
},
{
"cell_type": "code",
- "execution_count": 73,
+ "execution_count": 76,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5090,11 +5470,11 @@
"source": [
"## Task 5\n",
"<a name=\"task5\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "Use the NEST data frame `df` to:\n",
+ "Use the Nest data frame `df` to:\n",
"\n",
- "1. Make the threads the index of the data frame (`.set_index()`)\n",
+ "1. Make threads index of the data frame (`.set_index()`)\n",
"2. Plot `\"Presim. Program / s\"` and `\"Sim. Time / s`\" individually\n",
"3. Plot them onto one common canvas!\n",
"4. Make them have the same line colors and styles as before\n",
@@ -5104,7 +5484,7 @@
},
{
"cell_type": "code",
- "execution_count": 74,
+ "execution_count": 77,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -5118,7 +5498,7 @@
},
{
"cell_type": "code",
- "execution_count": 75,
+ "execution_count": 78,
"metadata": {
"exercise": "solution"
},
@@ -5142,7 +5522,7 @@
},
{
"cell_type": "code",
- "execution_count": 76,
+ "execution_count": 79,
"metadata": {
"exercise": "solution"
},
@@ -5166,7 +5546,7 @@
},
{
"cell_type": "code",
- "execution_count": 77,
+ "execution_count": 80,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -5194,7 +5574,7 @@
},
{
"cell_type": "code",
- "execution_count": 78,
+ "execution_count": 81,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -5234,7 +5614,7 @@
},
{
"cell_type": "code",
- "execution_count": 79,
+ "execution_count": 82,
"metadata": {},
"outputs": [
{
@@ -5278,7 +5658,7 @@
},
{
"cell_type": "code",
- "execution_count": 80,
+ "execution_count": 83,
"metadata": {},
"outputs": [
{
@@ -5300,7 +5680,7 @@
},
{
"cell_type": "code",
- "execution_count": 81,
+ "execution_count": 84,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5326,11 +5706,12 @@
},
{
"cell_type": "code",
- "execution_count": 82,
+ "execution_count": 85,
"metadata": {
"slideshow": {
"slide_type": "fragment"
- }
+ },
+ "tags": []
},
"outputs": [
{
@@ -5353,7 +5734,7 @@
},
{
"cell_type": "code",
- "execution_count": 83,
+ "execution_count": 86,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5385,7 +5766,7 @@
},
{
"cell_type": "code",
- "execution_count": 119,
+ "execution_count": 87,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5394,12 +5775,14 @@
"outputs": [
{
"data": {
- "image/png": "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\n",
+ "image/png": "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\n",
"text/plain": [
"<Figure size 864x432 with 2 Axes>"
]
},
- "metadata": {},
+ "metadata": {
+ "needs_background": "light"
+ },
"output_type": "display_data"
}
],
@@ -5452,7 +5835,7 @@
},
{
"cell_type": "code",
- "execution_count": 85,
+ "execution_count": 88,
"metadata": {},
"outputs": [
{
@@ -5488,7 +5871,7 @@
},
{
"cell_type": "code",
- "execution_count": 86,
+ "execution_count": 89,
"metadata": {},
"outputs": [
{
@@ -5524,7 +5907,7 @@
},
{
"cell_type": "code",
- "execution_count": 87,
+ "execution_count": 90,
"metadata": {
"slideshow": {
"slide_type": "-"
@@ -5570,7 +5953,7 @@
},
{
"cell_type": "code",
- "execution_count": 89,
+ "execution_count": 91,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -5584,7 +5967,7 @@
},
{
"cell_type": "code",
- "execution_count": 90,
+ "execution_count": 92,
"metadata": {},
"outputs": [
{
@@ -5617,7 +6000,7 @@
},
{
"cell_type": "code",
- "execution_count": 91,
+ "execution_count": 93,
"metadata": {},
"outputs": [
{
@@ -5637,7 +6020,7 @@
},
{
"cell_type": "code",
- "execution_count": 92,
+ "execution_count": 94,
"metadata": {},
"outputs": [
{
@@ -5657,7 +6040,7 @@
},
{
"cell_type": "code",
- "execution_count": 93,
+ "execution_count": 95,
"metadata": {},
"outputs": [
{
@@ -5677,7 +6060,7 @@
},
{
"cell_type": "code",
- "execution_count": 94,
+ "execution_count": 96,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5701,7 +6084,7 @@
},
{
"cell_type": "code",
- "execution_count": 95,
+ "execution_count": 97,
"metadata": {},
"outputs": [
{
@@ -5721,7 +6104,7 @@
},
{
"cell_type": "code",
- "execution_count": 96,
+ "execution_count": 98,
"metadata": {},
"outputs": [
{
@@ -5763,7 +6146,7 @@
"outputs": [
{
"data": {
- "image/png": "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\n",
+ "image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
@@ -5806,7 +6189,7 @@
"outputs": [
{
"data": {
- "image/png": "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\n",
+ "image/png": "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\n",
"text/plain": [
"<Figure size 432x432 with 3 Axes>"
]
@@ -5830,9 +6213,9 @@
"source": [
"## Task 6\n",
"<a name=\"task6\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "* To your `df` NEST data frame, add a column with the unaccounted time (`Unaccounted Time / s`), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time. \n",
+ "* To your `df` Nest data frame, add a column with the unaccounted time (`Unaccounted Time / s`), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time. \n",
"(*I know this is technically not super correct, but it will do for our example.*)\n",
"* Plot a stacked bar plot of all these columns (except for program runtime) over the threads\n",
"* Tell me when you're done with status icon in BigBlueButton: 👍"
@@ -6327,7 +6710,7 @@
},
{
"cell_type": "code",
- "execution_count": 108,
+ "execution_count": 107,
"metadata": {},
"outputs": [
{
@@ -6606,7 +6989,7 @@
"[6 rows x 21 columns]"
]
},
- "execution_count": 108,
+ "execution_count": 107,
"metadata": {},
"output_type": "execute_result"
}
@@ -6638,7 +7021,7 @@
},
{
"cell_type": "code",
- "execution_count": 109,
+ "execution_count": 108,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -6651,7 +7034,7 @@
},
{
"cell_type": "code",
- "execution_count": 110,
+ "execution_count": 109,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -6728,7 +7111,7 @@
" 0.518282 2.952492 NaN"
]
},
- "execution_count": 110,
+ "execution_count": 109,
"metadata": {},
"output_type": "execute_result"
}
@@ -6744,7 +7127,7 @@
},
{
"cell_type": "code",
- "execution_count": 111,
+ "execution_count": 110,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -6777,9 +7160,9 @@
"source": [
"## Task 7\n",
"<a name=\"task7\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "* Create a pivot table based on the NEST `df` data frame\n",
+ "* Create a pivot table based on the Nest `df` data frame\n",
"* Let the `x` axis show the number of nodes; display the values of the simulation time `\"Sim. Time / s\"` for the tasks per node and threads per task configurations\n",
"* Please plot a bar plot\n",
"* Tell me when you're done with status icon in BigBlueButton: 👍"
@@ -6787,7 +7170,7 @@
},
{
"cell_type": "code",
- "execution_count": 116,
+ "execution_count": 111,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -6819,16 +7202,24 @@
"metadata": {
"exercise": "task",
"slideshow": {
- "slide_type": "fragment"
- }
+ "slide_type": "subslide"
+ },
+ "tags": []
},
"source": [
- "<a name=\"taskb\"></a>\n",
+ "## Task 7B (like <em>B</em>onus)\n",
+ "<a name=\"task7b\"></a>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "\n",
+ "- Same pivot table as before (that is, `x` with nodes, and columns for Tasks/Node and Threads/Task)\n",
+ "- But now, use `Sim. Time / s` and `Presim. Time / s` as values to show\n",
+ "- Show them as a **stack** of those two values inside the pivot table\n",
+ "- Use Panda's functionality as much as possible!\n",
+ "\n",
+ "Impossible?\n",
"\n",
- "* Bonus task\n",
- " - Same pivot table as before (that is, `x` with nodes, and columns for Tasks/Node and Threads/Task)\n",
- " - But now, use `Sim. Time / s` and `Presim. Time / s` as values to show\n",
- " - Show them as a stack of those two values inside the pivot table"
+ "* I gave up!\n",
+ "* Person who does this best / first: Personal certificate with my recommendation 😄"
]
},
{
@@ -6858,7 +7249,7 @@
"source": [
"<span class=\"feedback\">Feedback to <a href=\"mailto:a.herten@fz-juelich.de\">a.herten@fz-juelich.de</a></span>\n",
"\n",
- "Next slide: Further reading"
+ "_Next slide: Further reading_"
]
},
{
diff --git a/Introduction-to-Pandas--slides.html b/Introduction-to-Pandas--slides.html
index 7a7361cb56d48b15692ca118e61cf6d9bd820f90..30fb9e311ba62d73b35425d2c6c250fd6073f869 100644
--- a/Introduction-to-Pandas--slides.html
+++ b/Introduction-to-Pandas--slides.html
@@ -14415,7 +14415,7 @@ div.jp-OutputPrompt {
<li><a href="#task5">Task 5</a></li>
<li><a href="#task6">Task 6</a></li>
<li><a href="#task7">Task 7</a></li>
-<li><a href="#taskb">Bonus Task</a></li>
+<li><a href="#task7b">Task 7B</a></li>
</ul>
</div>
@@ -15706,16 +15706,188 @@ div.jp-OutputPrompt {
</div>
-</div><div class="fragment">
+</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
+<div class="jp-Cell-inputWrapper">
+<div class="jp-InputArea jp-Cell-inputArea">
+<div class="jp-InputPrompt jp-InputArea-prompt">In [20]:</div>
+<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
+ <div class="CodeMirror cm-s-jupyter">
+<div class=" highlight hl-ipython3"><pre><span></span><span class="k">def</span> <span class="nf">mysquare</span><span class="p">(</span><span class="n">number</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">number</span><span class="o">*</span><span class="n">number</span>
+
+<span class="n">df_sample</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">mysquare</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
+<span class="c1"># or: df_sample.apply(lambda x: x*x).head()</span>
+</pre></div>
+
+ </div>
+</div>
+</div>
+</div>
+
+<div class="jp-Cell-outputWrapper">
+
+
+<div class="jp-OutputArea jp-Cell-outputArea">
+
+<div class="jp-OutputArea-child">
+
+
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[20]:</div>
+
+
+
+<div class="jp-RenderedHTMLCommon jp-RenderedHTML jp-OutputArea-output jp-OutputArea-executeResult" data-mime-type="text/html">
+<div>
+<style scoped>
+ .dataframe tbody tr th:only-of-type {
+ vertical-align: middle;
+ }
+
+ .dataframe tbody tr th {
+ vertical-align: top;
+ }
+
+ .dataframe thead th {
+ text-align: right;
+ }
+</style>
+<table border="1" class="dataframe">
+ <thead>
+ <tr style="text-align: right;">
+ <th></th>
+ <th>Age</th>
+ </tr>
+ <tr>
+ <th>Name</th>
+ <th></th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <th>Liu</th>
+ <td>1681</td>
+ </tr>
+ <tr>
+ <th>Rowland</th>
+ <td>3136</td>
+ </tr>
+ <tr>
+ <th>Rivers</th>
+ <td>3136</td>
+ </tr>
+ <tr>
+ <th>Waters</th>
+ <td>3249</td>
+ </tr>
+ <tr>
+ <th>Rice</th>
+ <td>1521</td>
+ </tr>
+ </tbody>
+</table>
+</div>
+</div>
+
+</div>
+
+</div>
+
+</div>
+
+</div></div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
+<div class="jp-Cell-inputWrapper">
+<div class="jp-InputArea jp-Cell-inputArea">
+<div class="jp-InputPrompt jp-InputArea-prompt">In [22]:</div>
+<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
+ <div class="CodeMirror cm-s-jupyter">
+<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_sample</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">square</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
+</pre></div>
+
+ </div>
+</div>
+</div>
+</div>
+
+<div class="jp-Cell-outputWrapper">
+
+
+<div class="jp-OutputArea jp-Cell-outputArea">
+
+<div class="jp-OutputArea-child">
+
+
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[22]:</div>
+
+
+
+<div class="jp-RenderedHTMLCommon jp-RenderedHTML jp-OutputArea-output jp-OutputArea-executeResult" data-mime-type="text/html">
+<div>
+<style scoped>
+ .dataframe tbody tr th:only-of-type {
+ vertical-align: middle;
+ }
+
+ .dataframe tbody tr th {
+ vertical-align: top;
+ }
+
+ .dataframe thead th {
+ text-align: right;
+ }
+</style>
+<table border="1" class="dataframe">
+ <thead>
+ <tr style="text-align: right;">
+ <th></th>
+ <th>Age</th>
+ </tr>
+ <tr>
+ <th>Name</th>
+ <th></th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <th>Liu</th>
+ <td>1681</td>
+ </tr>
+ <tr>
+ <th>Rowland</th>
+ <td>3136</td>
+ </tr>
+ <tr>
+ <th>Rivers</th>
+ <td>3136</td>
+ </tr>
+ <tr>
+ <th>Waters</th>
+ <td>3249</td>
+ </tr>
+ <tr>
+ <th>Rice</th>
+ <td>1521</td>
+ </tr>
+ </tbody>
+</table>
+</div>
+</div>
+
+</div>
+
+</div>
+
+</div>
+
+</div></div></section><section>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<p>Logical operations allowed as well</p>
</div>
-</div></div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
+</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [20]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [23]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_sample</span> <span class="o">></span> <span class="mi">40</span>
@@ -15734,7 +15906,7 @@ div.jp-OutputPrompt {
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[20]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[23]:</div>
@@ -15816,11 +15988,95 @@ div.jp-OutputPrompt {
</div>
+</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
+<div class="jp-Cell-inputWrapper">
+<div class="jp-InputArea jp-Cell-inputArea">
+<div class="jp-InputPrompt jp-InputArea-prompt">In [24]:</div>
+<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
+ <div class="CodeMirror cm-s-jupyter">
+<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_sample</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">mysquare</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span> <span class="o">==</span> <span class="n">df_sample</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="o">*</span><span class="n">x</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
+</pre></div>
+
+ </div>
+</div>
+</div>
+</div>
+
+<div class="jp-Cell-outputWrapper">
+
+
+<div class="jp-OutputArea jp-Cell-outputArea">
+
+<div class="jp-OutputArea-child">
+
+
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[24]:</div>
+
+
+
+<div class="jp-RenderedHTMLCommon jp-RenderedHTML jp-OutputArea-output jp-OutputArea-executeResult" data-mime-type="text/html">
+<div>
+<style scoped>
+ .dataframe tbody tr th:only-of-type {
+ vertical-align: middle;
+ }
+
+ .dataframe tbody tr th {
+ vertical-align: top;
+ }
+
+ .dataframe thead th {
+ text-align: right;
+ }
+</style>
+<table border="1" class="dataframe">
+ <thead>
+ <tr style="text-align: right;">
+ <th></th>
+ <th>Age</th>
+ </tr>
+ <tr>
+ <th>Name</th>
+ <th></th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <th>Liu</th>
+ <td>True</td>
+ </tr>
+ <tr>
+ <th>Rowland</th>
+ <td>True</td>
+ </tr>
+ <tr>
+ <th>Rivers</th>
+ <td>True</td>
+ </tr>
+ <tr>
+ <th>Waters</th>
+ <td>True</td>
+ </tr>
+ <tr>
+ <th>Rice</th>
+ <td>True</td>
+ </tr>
+ </tbody>
+</table>
+</div>
+</div>
+
+</div>
+
+</div>
+
+</div>
+
</div></div></section></section><section><section>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h2 id="Task-1">Task 1<a class="anchor-link" href="#Task-1">¶</a></h2><p><a name="task1"></a>
-<span style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
+<span class="task" style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
<ul>
<li>Create data frame with<ul>
<li>6 names of dinosaurs, </li>
@@ -15836,7 +16092,7 @@ div.jp-OutputPrompt {
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [21]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [25]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">happy_dinos</span> <span class="o">=</span> <span class="p">{</span>
@@ -15855,7 +16111,7 @@ div.jp-OutputPrompt {
</div></div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [22]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [26]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">happy_dinos</span> <span class="o">=</span> <span class="p">{</span>
@@ -15880,7 +16136,7 @@ div.jp-OutputPrompt {
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[22]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[26]:</div>
@@ -15944,13 +16200,12 @@ div.jp-OutputPrompt {
</div></div></section><section>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
-<p>Some more <code>DataFrame</code> examples</p>
-
+<h3 id="More-DataFrame-examples">More <code>DataFrame</code> examples<a class="anchor-link" href="#More-DataFrame-examples">¶</a></h3>
</div>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [24]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [27]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">({</span>
@@ -15976,7 +16231,7 @@ div.jp-OutputPrompt {
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[24]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[27]:</div>
@@ -16061,7 +16316,7 @@ div.jp-OutputPrompt {
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [25]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [28]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">sort_values</span><span class="p">(</span><span class="s2">"C"</span><span class="p">)</span>
@@ -16080,7 +16335,7 @@ div.jp-OutputPrompt {
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[25]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[28]:</div>
@@ -16165,7 +16420,7 @@ div.jp-OutputPrompt {
</div></div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [26]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [29]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">tail</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span>
@@ -16184,7 +16439,7 @@ div.jp-OutputPrompt {
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[26]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[29]:</div>
@@ -16245,7 +16500,7 @@ div.jp-OutputPrompt {
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [27]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [30]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
@@ -16264,7 +16519,7 @@ div.jp-OutputPrompt {
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[27]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[30]:</div>
@@ -16285,7 +16540,7 @@ dtype: object</pre>
</div></div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [28]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [31]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="n">df_demo</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">to_latex</span><span class="p">())</span>
@@ -16350,7 +16605,7 @@ dtype: object</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [117]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [32]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">pd</span><span class="o">.</span><span class="n">read_json</span><span class="p">(</span><span class="s2">"data-lost.json"</span><span class="p">)</span><span class="o">.</span><span class="n">set_index</span><span class="p">(</span><span class="s2">"Character"</span><span class="p">)</span><span class="o">.</span><span class="n">sort_index</span><span class="p">()</span>
@@ -16369,7 +16624,7 @@ dtype: object</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[117]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[32]:</div>
@@ -16447,7 +16702,7 @@ dtype: object</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h2 id="Task-2">Task 2<a class="anchor-link" href="#Task-2">¶</a></h2><p><a name="task2"></a>
-<span style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
+<span class="task" style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
<ul>
<li>Read in <code>data-nest.csv</code> to <code>DataFrame</code>; call it <code>df</code><br>
<em>(Data was produced with <a href="http://www.fz-juelich.de/ias/jsc/EN/Expertise/Support/Software/JUBE/_node.html">JUBE</a>)</em></li>
@@ -16459,10 +16714,10 @@ dtype: object</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [30]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [33]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>cat nest-data.csv <span class="p">|</span> head -3
+<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span>cat data-nest.csv <span class="p">|</span> head -3
</pre></div>
</div>
@@ -16496,7 +16751,7 @@ dtype: object</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [118]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [34]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_csv</span><span class="p">(</span><span class="s2">"data-nest.csv"</span><span class="p">)</span>
@@ -16516,7 +16771,7 @@ dtype: object</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[118]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[34]:</div>
@@ -16721,8 +16976,14 @@ dtype: object</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h2 id="Slicing-of-Data-Frames">Slicing of Data Frames<a class="anchor-link" href="#Slicing-of-Data-Frames">¶</a></h2><ul>
+<li>Slicing: Select a sub-range / sub-set of entire data frame</li>
<li>Pandas documentation: <a href="https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html">Detailed documentation</a>, <a href="https://pandas.pydata.org/pandas-docs/stable/user_guide/10min.html#selection">short documentation</a></li>
</ul>
+
+</div>
+</div><div class="fragment">
+<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
+</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h3 id="Quick-Slices">Quick Slices<a class="anchor-link" href="#Quick-Slices">¶</a></h3><ul>
<li>Use square-bracket operators to slice data frame quickly: <code>[]</code><ul>
<li>Use column name to select column</li>
@@ -16736,7 +16997,7 @@ dtype: object</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [32]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [35]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">head</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span>
@@ -16755,7 +17016,7 @@ dtype: object</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[32]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[35]:</div>
@@ -16821,10 +17082,10 @@ dtype: object</pre>
</div>
-</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
+</div></div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [33]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [36]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="s1">'C'</span><span class="p">]</span>
@@ -16843,7 +17104,7 @@ dtype: object</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[33]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[36]:</div>
@@ -16863,10 +17124,18 @@ Name: C, dtype: float64</pre>
</div>
-</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
+</div></div></section><section>
+<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
+</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
+<ul>
+<li>Instead of column name in quotes and square brackets: Name of column <em>directly</em></li>
+</ul>
+
+</div>
+</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [34]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [37]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">C</span>
@@ -16885,7 +17154,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[34]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[37]:</div>
@@ -16905,7 +17174,16 @@ Name: C, dtype: float64</pre>
</div>
-</div></div></section><section>
+</div>
+<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
+</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
+<ul>
+<li>I'm not a friend, because no spaces allowed<br>
+(And <strong>Pandas as early as possible</strong> means labelling columns well and adding spaces)</li>
+</ul>
+
+</div>
+</div></section><section>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<ul>
@@ -16917,7 +17195,7 @@ Name: C, dtype: float64</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [35]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [38]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">my_slice</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'A'</span><span class="p">,</span> <span class="s1">'C'</span><span class="p">]</span>
@@ -16937,7 +17215,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[35]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[38]:</div>
@@ -17005,7 +17283,7 @@ Name: C, dtype: float64</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<ul>
-<li>Use numerical values in brackets to slice along rows</li>
+<li>Use numerical values in brackets to slice <strong>along rows</strong></li>
<li>Use ranges just like with Python lists</li>
</ul>
@@ -17013,7 +17291,7 @@ Name: C, dtype: float64</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [36]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [39]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="mi">3</span><span class="p">]</span>
@@ -17032,7 +17310,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[36]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[39]:</div>
@@ -17093,7 +17371,7 @@ Name: C, dtype: float64</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [37]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [40]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="mi">6</span><span class="p">:</span><span class="mi">2</span><span class="p">]</span>
@@ -17112,7 +17390,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[37]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[40]:</div>
@@ -17181,7 +17459,7 @@ Name: C, dtype: float64</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [38]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [41]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="mi">3</span><span class="p">]</span>
@@ -17200,7 +17478,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[38]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[41]:</div>
@@ -17261,7 +17539,7 @@ Name: C, dtype: float64</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [39]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [42]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">sort_values</span><span class="p">(</span><span class="s2">"C"</span><span class="p">)[</span><span class="mi">1</span><span class="p">:</span><span class="mi">3</span><span class="p">]</span>
@@ -17280,7 +17558,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[39]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[42]:</div>
@@ -17349,7 +17627,7 @@ Name: C, dtype: float64</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [40]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [43]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">iloc</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="mi">3</span><span class="p">]</span>
@@ -17368,7 +17646,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[40]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[43]:</div>
@@ -17430,14 +17708,14 @@ Name: C, dtype: float64</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<ul>
-<li>Also slice rows (second argument)</li>
+<li>Also slice along columns (second argument)</li>
</ul>
</div>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [41]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [44]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">iloc</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="mi">3</span><span class="p">,</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">]]</span>
@@ -17456,7 +17734,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[41]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[44]:</div>
@@ -17518,7 +17796,7 @@ Name: C, dtype: float64</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [42]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [45]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo_indexed</span> <span class="o">=</span> <span class="n">df_demo</span><span class="o">.</span><span class="n">set_index</span><span class="p">(</span><span class="s2">"D"</span><span class="p">)</span>
@@ -17538,7 +17816,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[42]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[45]:</div>
@@ -17624,7 +17902,7 @@ Name: C, dtype: float64</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [43]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [46]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo_indexed</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span><span class="s2">"entries"</span><span class="p">]</span>
@@ -17643,7 +17921,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[43]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[46]:</div>
@@ -17708,7 +17986,7 @@ Name: C, dtype: float64</pre>
</div></div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [44]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [47]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo_indexed</span><span class="o">.</span><span class="n">loc</span><span class="p">[[</span><span class="s2">"has"</span><span class="p">,</span> <span class="s2">"entries"</span><span class="p">],</span> <span class="p">[</span><span class="s2">"A"</span><span class="p">,</span> <span class="s2">"C"</span><span class="p">]]</span>
@@ -17727,7 +18005,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[44]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[47]:</div>
@@ -17802,7 +18080,7 @@ Name: C, dtype: float64</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [45]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [48]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span> <span class="o">></span> <span class="mi">0</span><span class="p">]</span>
@@ -17821,7 +18099,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[45]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[48]:</div>
@@ -17882,7 +18160,7 @@ Name: C, dtype: float64</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [46]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [49]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span> <span class="o">></span> <span class="mi">0</span>
@@ -17901,7 +18179,7 @@ Name: C, dtype: float64</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[46]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[49]:</div>
@@ -17924,7 +18202,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [47]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [50]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[(</span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span> <span class="o"><</span> <span class="mi">0</span><span class="p">)</span> <span class="o">&</span> <span class="p">(</span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"D"</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"entries"</span><span class="p">)]</span>
@@ -17943,7 +18221,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[47]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[50]:</div>
@@ -18012,7 +18290,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [48]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [51]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">head</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span>
@@ -18031,7 +18309,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[48]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[51]:</div>
@@ -18097,10 +18375,10 @@ Name: C, dtype: bool</pre>
</div>
-</div></div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
+</div></div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [49]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [52]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"F"</span><span class="p">]</span> <span class="o">=</span> <span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span> <span class="o">-</span> <span class="n">df_demo</span><span class="p">[</span><span class="s2">"A"</span><span class="p">]</span>
@@ -18120,7 +18398,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[49]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[52]:</div>
@@ -18190,13 +18468,23 @@ Name: C, dtype: bool</pre>
</div>
-</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs ">
+</div></div></section><section>
+<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
+</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
+<ul>
+<li><code>.insert()</code> allows to specify position of insertion</li>
+<li><code>.shape</code> gives tuple of size of data frame, <code>vertical, horizontal</code></li>
+</ul>
+
+</div>
+</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [50]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [53]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="n">df_demo</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"E2"</span><span class="p">,</span> <span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span> <span class="o">**</span> <span class="mi">2</span><span class="p">)</span>
+<span class="n">df_demo</span><span class="o">.</span><span class="n">head</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span>
</pre></div>
</div>
@@ -18204,10 +18492,92 @@ Name: C, dtype: bool</pre>
</div>
</div>
-</div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
+<div class="jp-Cell-outputWrapper">
+
+
+<div class="jp-OutputArea jp-Cell-outputArea">
+
+<div class="jp-OutputArea-child">
+
+
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[53]:</div>
+
+
+
+<div class="jp-RenderedHTMLCommon jp-RenderedHTML jp-OutputArea-output jp-OutputArea-executeResult" data-mime-type="text/html">
+<div>
+<style scoped>
+ .dataframe tbody tr th:only-of-type {
+ vertical-align: middle;
+ }
+
+ .dataframe tbody tr th {
+ vertical-align: top;
+ }
+
+ .dataframe thead th {
+ text-align: right;
+ }
+</style>
+<table border="1" class="dataframe">
+ <thead>
+ <tr style="text-align: right;">
+ <th></th>
+ <th>A</th>
+ <th>B</th>
+ <th>C</th>
+ <th>D</th>
+ <th>E</th>
+ <th>E2</th>
+ <th>F</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <th>0</th>
+ <td>1.2</td>
+ <td>2018-02-26</td>
+ <td>-2.718282</td>
+ <td>This</td>
+ <td>Same</td>
+ <td>7.389056</td>
+ <td>-3.918282</td>
+ </tr>
+ <tr>
+ <th>1</th>
+ <td>1.2</td>
+ <td>2018-02-26</td>
+ <td>1.718282</td>
+ <td>column</td>
+ <td>Same</td>
+ <td>2.952492</td>
+ <td>0.518282</td>
+ </tr>
+ <tr>
+ <th>2</th>
+ <td>1.2</td>
+ <td>2018-02-26</td>
+ <td>-1.304068</td>
+ <td>has</td>
+ <td>Same</td>
+ <td>1.700594</td>
+ <td>-2.504068</td>
+ </tr>
+ </tbody>
+</table>
+</div>
+</div>
+
+</div>
+
+</div>
+
+</div>
+
+</div></div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [51]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [54]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">tail</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span>
@@ -18226,7 +18596,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[51]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[54]:</div>
@@ -18303,7 +18673,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [52]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [55]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
@@ -18325,7 +18695,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[52]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[55]:</div>
@@ -18440,7 +18810,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [53]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [56]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_1</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">({</span><span class="s2">"Key"</span><span class="p">:</span> <span class="p">[</span><span class="s2">"First"</span><span class="p">,</span> <span class="s2">"Second"</span><span class="p">],</span> <span class="s2">"Value"</span><span class="p">:</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">]})</span>
@@ -18460,7 +18830,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[53]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[56]:</div>
@@ -18512,7 +18882,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [54]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [57]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_2</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">({</span><span class="s2">"Key"</span><span class="p">:</span> <span class="p">[</span><span class="s2">"First"</span><span class="p">,</span> <span class="s2">"Second"</span><span class="p">],</span> <span class="s2">"Value"</span><span class="p">:</span> <span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">]})</span>
@@ -18532,7 +18902,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[54]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[57]:</div>
@@ -18592,7 +18962,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [55]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [58]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">([</span><span class="n">df_1</span><span class="p">,</span> <span class="n">df_2</span><span class="p">])</span>
@@ -18611,7 +18981,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[55]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[58]:</div>
@@ -18681,7 +19051,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [56]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [59]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">([</span><span class="n">df_1</span><span class="p">,</span> <span class="n">df_2</span><span class="p">],</span> <span class="n">ignore_index</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -18700,7 +19070,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[56]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[59]:</div>
@@ -18770,7 +19140,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [57]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [60]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">([</span><span class="n">df_1</span><span class="p">,</span> <span class="n">df_2</span><span class="p">],</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
@@ -18789,7 +19159,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[57]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[60]:</div>
@@ -18855,7 +19225,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [58]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [61]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">pd</span><span class="o">.</span><span class="n">merge</span><span class="p">(</span><span class="n">df_1</span><span class="p">,</span> <span class="n">df_2</span><span class="p">,</span> <span class="n">on</span><span class="o">=</span><span class="s2">"Key"</span><span class="p">)</span>
@@ -18874,7 +19244,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[58]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[61]:</div>
@@ -18930,7 +19300,7 @@ Name: C, dtype: bool</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h2 id="Task-3">Task 3<a class="anchor-link" href="#Task-3">¶</a></h2><p><a name="task3"></a>
-<span style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
+<span class="task" style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
<ul>
<li>Add a column to the Nest data frame form Task 2 called <code>Threads</code> which is the total number of threads across all nodes (i.e. the product of threads per task and tasks per node and nodes)</li>
<li>Tell me when you're done with status icon in BigBlueButton: 👍</li>
@@ -18940,7 +19310,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [59]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [62]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="p">[</span><span class="s2">"Threads"</span><span class="p">]</span> <span class="o">=</span> <span class="n">df</span><span class="p">[</span><span class="s2">"Nodes"</span><span class="p">]</span> <span class="o">*</span> <span class="n">df</span><span class="p">[</span><span class="s2">"Tasks/Node"</span><span class="p">]</span> <span class="o">*</span> <span class="n">df</span><span class="p">[</span><span class="s2">"Threads/Task"</span><span class="p">]</span>
@@ -18960,7 +19330,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[59]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[62]:</div>
@@ -19142,7 +19512,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [60]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [63]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="o">.</span><span class="n">columns</span>
@@ -19161,7 +19531,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[60]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[63]:</div>
@@ -19199,7 +19569,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [61]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [64]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
@@ -19214,7 +19584,7 @@ Name: C, dtype: bool</pre>
</div></div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [62]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [65]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">x</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">linspace</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="o">*</span><span class="n">np</span><span class="o">.</span><span class="n">pi</span><span class="p">,</span> <span class="mi">400</span><span class="p">)</span>
@@ -19229,7 +19599,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [63]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [66]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">()</span>
@@ -19281,7 +19651,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [64]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [67]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">y2</span> <span class="o">=</span> <span class="n">y</span><span class="o">/</span><span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="n">y</span><span class="o">*</span><span class="mf">1.5</span><span class="p">)</span>
@@ -19295,7 +19665,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [65]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [68]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">()</span>
@@ -19347,7 +19717,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [66]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [69]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">()</span>
@@ -19390,9 +19760,9 @@ Name: C, dtype: bool</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h2 id="Task-4">Task 4<a class="anchor-link" href="#Task-4">¶</a></h2><p><a name="task4"></a>
-<span style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
+<span class="task" style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
<ul>
-<li>Sort the data frame by threads</li>
+<li>Sort the Nest data frame by threads</li>
<li>Plot <code>"Presim. Time / s"</code> and <code>"Sim. Time / s"</code> of our data frame <code>df</code> as a function of threads</li>
<li>Use a dashed, red line for <code>"Presim. Time / s"</code>, a blue line for <code>"Sim. Time / s"</code> (see <a href="https://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.plot">API description</a>)</li>
<li>Don't forget to label your axes and to add a legend <em>(1st rule of plotting)</em></li>
@@ -19403,10 +19773,10 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [67]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [70]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="o">.</span><span class="n">sort_values</span><span class="p">([</span><span class="s2">"Threads"</span><span class="p">,</span> <span class="s2">"Nodes"</span><span class="p">,</span> <span class="s2">"Tasks/Node"</span><span class="p">,</span> <span class="s2">"Threads/Task"</span><span class="p">],</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="o">.</span><span class="n">sort_values</span><span class="p">([</span><span class="s2">"Threads"</span><span class="p">,</span> <span class="s2">"Nodes"</span><span class="p">,</span> <span class="s2">"Tasks/Node"</span><span class="p">,</span> <span class="s2">"Threads/Task"</span><span class="p">],</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="c1"># multi-level sort</span>
</pre></div>
</div>
@@ -19417,7 +19787,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [68]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [71]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">()</span>
@@ -19465,7 +19835,7 @@ Name: C, dtype: bool</pre>
<li>Each data frame hast a <code>.plot()</code> function (see <a href="https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.plot.html">API</a>)</li>
<li>Plots with Matplotlib</li>
<li>Important API options:<ul>
-<li><code>kind</code>: <code>line</code> (default), <code>bar[h]</code>, <code>hist</code>, <code>box</code>, <code>kde</code>, <code>scatter</code>, <code>hexbin</code></li>
+<li><code>kind</code>: <code>'line'</code> (default), <code>'bar[h]'</code>, <code>'hist'</code>, <code>'box'</code>, <code>'kde'</code>, <code>'scatter'</code>, <code>'hexbin'</code></li>
<li><code>subplots</code>: Make a sub-plot for each column (good together with <code>sharex</code>, <code>sharey</code>)</li>
<li><code>figsize</code></li>
<li><code>grid</code>: Add a grid to plot (use Matplotlib options)</li>
@@ -19482,7 +19852,7 @@ Name: C, dtype: bool</pre>
<li><code>table</code>: If <code>true</code>, add table of data under plot</li>
</ul>
</li>
-<li><code>**kwds</code>: Every non-parsed keyword is passed through to Matplotlib's plotting methods</li>
+<li><code>**kwds</code>: Non-parsed keyword passed to Matplotlib's plotting methods</li>
</ul>
</li>
</ul>
@@ -19499,7 +19869,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [69]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [72]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">2</span><span class="p">));</span>
@@ -19546,7 +19916,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [70]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [73]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">y</span><span class="o">=</span><span class="s2">"C"</span><span class="p">,</span> <span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">2</span><span class="p">));</span>
@@ -19586,14 +19956,15 @@ Name: C, dtype: bool</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<ul>
-<li>I prefer slicing first, as it allows for further operations on the sliced data frame</li>
+<li>I prefer slicing first:<br>
+→ Allows for further operations on the sliced data frame</li>
</ul>
</div>
</div></div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [71]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [74]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">kind</span><span class="o">=</span><span class="s2">"bar"</span><span class="p">);</span>
@@ -19641,7 +20012,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [72]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [75]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="o">.</span><span class="n">bar</span><span class="p">();</span>
@@ -19680,7 +20051,7 @@ Name: C, dtype: bool</pre>
</div></div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [73]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [76]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">kind</span><span class="o">=</span><span class="s2">"bar"</span><span class="p">,</span> <span class="n">legend</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span> <span class="mi">4</span><span class="p">),</span> <span class="n">ylim</span><span class="o">=</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">),</span> <span class="n">title</span><span class="o">=</span><span class="s2">"This is a C plot"</span><span class="p">);</span>
@@ -19720,10 +20091,10 @@ Name: C, dtype: bool</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h2 id="Task-5">Task 5<a class="anchor-link" href="#Task-5">¶</a></h2><p><a name="task5"></a>
-<span style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
-<p>Use the NEST data frame <code>df</code> to:</p>
+<span class="task" style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
+<p>Use the Nest data frame <code>df</code> to:</p>
<ol>
-<li>Make the threads the index of the data frame (<code>.set_index()</code>)</li>
+<li>Make threads index of the data frame (<code>.set_index()</code>)</li>
<li>Plot <code>"Presim. Program / s"</code> and <code>"Sim. Time / s</code>" individually</li>
<li>Plot them onto one common canvas!</li>
<li>Make them have the same line colors and styles as before</li>
@@ -19735,7 +20106,7 @@ Name: C, dtype: bool</pre>
</div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [74]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [77]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="o">.</span><span class="n">set_index</span><span class="p">(</span><span class="s2">"Threads"</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -19749,7 +20120,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [75]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [78]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="p">[</span><span class="s2">"Presim. Time / s"</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">3</span><span class="p">));</span>
@@ -19788,7 +20159,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [76]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [79]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="p">[</span><span class="s2">"Sim. Time / s"</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">3</span><span class="p">));</span>
@@ -19827,7 +20198,7 @@ Name: C, dtype: bool</pre>
</div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [77]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [80]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="p">[</span><span class="s2">"Presim. Time / s"</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="p">();</span>
@@ -19867,7 +20238,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [78]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [81]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">ax</span> <span class="o">=</span> <span class="n">df</span><span class="p">[[</span><span class="s2">"Presim. Time / s"</span><span class="p">,</span> <span class="s2">"Sim. Time / s"</span><span class="p">]]</span><span class="o">.</span><span class="n">plot</span><span class="p">();</span>
@@ -19912,7 +20283,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [79]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [82]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="p">[[</span><span class="s2">"Presim. Time / s"</span><span class="p">,</span> <span class="s2">"Sim. Time / s"</span><span class="p">]]</span><span class="o">.</span><span class="n">plot</span><span class="p">();</span>
@@ -19967,7 +20338,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [80]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [83]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[[</span><span class="s2">"A"</span><span class="p">,</span> <span class="s2">"C"</span><span class="p">,</span> <span class="s2">"F"</span><span class="p">]]</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">kind</span><span class="o">=</span><span class="s2">"bar"</span><span class="p">,</span> <span class="n">stacked</span><span class="o">=</span><span class="kc">True</span><span class="p">);</span>
@@ -20006,7 +20377,7 @@ Name: C, dtype: bool</pre>
</div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [81]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [84]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"F"</span><span class="p">]</span> <span class="o"><</span> <span class="mi">0</span><span class="p">][[</span><span class="s2">"A"</span><span class="p">,</span> <span class="s2">"C"</span><span class="p">,</span> <span class="s2">"F"</span><span class="p">]]</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">kind</span><span class="o">=</span><span class="s2">"bar"</span><span class="p">,</span> <span class="n">stacked</span><span class="o">=</span><span class="kc">True</span><span class="p">);</span>
@@ -20045,7 +20416,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [82]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [85]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"F"</span><span class="p">]</span> <span class="o"><</span> <span class="mi">0</span><span class="p">][[</span><span class="s2">"A"</span><span class="p">,</span> <span class="s2">"C"</span><span class="p">,</span> <span class="s2">"F"</span><span class="p">]]</span>\
@@ -20085,7 +20456,7 @@ Name: C, dtype: bool</pre>
</div></div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [83]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [86]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"F"</span><span class="p">]</span> <span class="o"><</span> <span class="mi">0</span><span class="p">,</span> <span class="p">[</span><span class="s2">"A"</span><span class="p">,</span> <span class="s2">"F"</span><span class="p">]]</span>\
@@ -20130,7 +20501,7 @@ Name: C, dtype: bool</pre>
</div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [119]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [87]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"F"</span><span class="p">]</span> <span class="o"><</span> <span class="mi">0</span><span class="p">,</span> <span class="p">[</span><span class="s2">"A"</span><span class="p">,</span> <span class="s2">"F"</span><span class="p">]]</span>\
@@ -20167,7 +20538,7 @@ Name: C, dtype: bool</pre>
<div class="jp-RenderedImage jp-OutputArea-output ">
-<img src="data:image/png;base64,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
+<img src="data:image/png;base64,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
"
>
</div>
@@ -20205,7 +20576,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [85]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [88]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">ax</span> <span class="o">=</span> <span class="n">df_demo</span><span class="p">[</span><span class="s2">"C"</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">4</span><span class="p">))</span>
@@ -20252,7 +20623,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [86]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [89]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">4</span><span class="p">))</span>
@@ -20302,7 +20673,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [87]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [90]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">fig</span><span class="p">,</span> <span class="p">(</span><span class="n">ax1</span><span class="p">,</span> <span class="n">ax2</span><span class="p">)</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">(</span><span class="n">ncols</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">sharey</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span> <span class="mi">4</span><span class="p">))</span>
@@ -20356,7 +20727,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [89]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [91]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="kn">import</span> <span class="nn">seaborn</span> <span class="k">as</span> <span class="nn">sns</span>
@@ -20371,7 +20742,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [90]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [92]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[[</span><span class="s2">"A"</span><span class="p">,</span> <span class="s2">"C"</span><span class="p">]]</span><span class="o">.</span><span class="n">plot</span><span class="p">();</span>
@@ -20418,7 +20789,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [91]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [93]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">sns</span><span class="o">.</span><span class="n">palplot</span><span class="p">(</span><span class="n">sns</span><span class="o">.</span><span class="n">color_palette</span><span class="p">())</span>
@@ -20457,7 +20828,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [92]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [94]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">sns</span><span class="o">.</span><span class="n">palplot</span><span class="p">(</span><span class="n">sns</span><span class="o">.</span><span class="n">color_palette</span><span class="p">(</span><span class="s2">"hls"</span><span class="p">,</span> <span class="mi">10</span><span class="p">))</span>
@@ -20496,7 +20867,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [93]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [95]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">sns</span><span class="o">.</span><span class="n">palplot</span><span class="p">(</span><span class="n">sns</span><span class="o">.</span><span class="n">color_palette</span><span class="p">(</span><span class="s2">"hsv"</span><span class="p">,</span> <span class="mi">20</span><span class="p">))</span>
@@ -20535,7 +20906,7 @@ Name: C, dtype: bool</pre>
</div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [94]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [96]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">sns</span><span class="o">.</span><span class="n">palplot</span><span class="p">(</span><span class="n">sns</span><span class="o">.</span><span class="n">color_palette</span><span class="p">(</span><span class="s2">"Paired"</span><span class="p">,</span> <span class="mi">10</span><span class="p">))</span>
@@ -20574,7 +20945,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [95]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [97]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">sns</span><span class="o">.</span><span class="n">palplot</span><span class="p">(</span><span class="n">sns</span><span class="o">.</span><span class="n">color_palette</span><span class="p">(</span><span class="s2">"cubehelix"</span><span class="p">,</span> <span class="mi">8</span><span class="p">))</span>
@@ -20613,7 +20984,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [96]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [98]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">sns</span><span class="o">.</span><span class="n">palplot</span><span class="p">(</span><span class="n">sns</span><span class="o">.</span><span class="n">color_palette</span><span class="p">(</span><span class="s2">"colorblind"</span><span class="p">,</span> <span class="mi">10</span><span class="p">))</span>
@@ -20687,7 +21058,7 @@ Name: C, dtype: bool</pre>
<div class="jp-RenderedImage jp-OutputArea-output ">
-<img src="data:image/png;base64,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
+<img src="data:image/png;base64,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
"
>
</div>
@@ -20749,7 +21120,7 @@ Name: C, dtype: bool</pre>
<div class="jp-RenderedImage jp-OutputArea-output ">
-<img src="data:image/png;base64,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
+<img src="data:image/png;base64,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
"
>
</div>
@@ -20764,9 +21135,9 @@ Name: C, dtype: bool</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h2 id="Task-6">Task 6<a class="anchor-link" href="#Task-6">¶</a></h2><p><a name="task6"></a>
-<span style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
+<span class="task" style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
<ul>
-<li>To your <code>df</code> NEST data frame, add a column with the unaccounted time (<code>Unaccounted Time / s</code>), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time.<br>
+<li>To your <code>df</code> Nest data frame, add a column with the unaccounted time (<code>Unaccounted Time / s</code>), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time.<br>
(<em>I know this is technically not super correct, but it will do for our example.</em>)</li>
<li>Plot a stacked bar plot of all these columns (except for program runtime) over the threads</li>
<li>Tell me when you're done with status icon in BigBlueButton: 👍</li>
@@ -21220,7 +21591,7 @@ Name: C, dtype: bool</pre>
</div><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [108]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [107]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="o">.</span><span class="n">groupby</span><span class="p">(</span><span class="s2">"Nodes"</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
@@ -21239,7 +21610,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[108]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[107]:</div>
@@ -21487,7 +21858,7 @@ Name: C, dtype: bool</pre>
</div></section><section><div class="jp-Cell jp-CodeCell jp-Notebook-cell jp-mod-noOutputs ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [109]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [108]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_demo</span><span class="p">[</span><span class="s2">"H"</span><span class="p">]</span> <span class="o">=</span> <span class="p">[(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span><span class="o">**</span><span class="n">n</span> <span class="k">for</span> <span class="n">n</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">5</span><span class="p">)]</span>
@@ -21501,7 +21872,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [110]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [109]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_pivot</span> <span class="o">=</span> <span class="n">df_demo</span><span class="o">.</span><span class="n">pivot_table</span><span class="p">(</span>
@@ -21525,7 +21896,7 @@ Name: C, dtype: bool</pre>
<div class="jp-OutputArea-child">
- <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[110]:</div>
+ <div class="jp-OutputPrompt jp-OutputArea-prompt">Out[109]:</div>
@@ -21597,7 +21968,7 @@ Name: C, dtype: bool</pre>
</div></div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [111]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [110]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_pivot</span><span class="o">.</span><span class="n">plot</span><span class="p">();</span>
@@ -21637,9 +22008,9 @@ Name: C, dtype: bool</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h2 id="Task-7">Task 7<a class="anchor-link" href="#Task-7">¶</a></h2><p><a name="task7"></a>
-<span style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
+<span class="task" style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
<ul>
-<li>Create a pivot table based on the NEST <code>df</code> data frame</li>
+<li>Create a pivot table based on the Nest <code>df</code> data frame</li>
<li>Let the <code>x</code> axis show the number of nodes; display the values of the simulation time <code>"Sim. Time / s"</code> for the tasks per node and threads per task configurations</li>
<li>Please plot a bar plot</li>
<li>Tell me when you're done with status icon in BigBlueButton: 👍</li>
@@ -21649,7 +22020,7 @@ Name: C, dtype: bool</pre>
</div><div class="fragment"><div class="jp-Cell jp-CodeCell jp-Notebook-cell ">
<div class="jp-Cell-inputWrapper">
<div class="jp-InputArea jp-Cell-inputArea">
-<div class="jp-InputPrompt jp-InputArea-prompt">In [116]:</div>
+<div class="jp-InputPrompt jp-InputArea-prompt">In [111]:</div>
<div class="jp-CodeMirrorEditor jp-Editor jp-InputArea-editor" data-type="inline">
<div class="CodeMirror cm-s-jupyter">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="o">.</span><span class="n">pivot_table</span><span class="p">(</span>
@@ -21689,21 +22060,25 @@ Name: C, dtype: bool</pre>
</div>
-</div></div><div class="fragment">
+</div></div></section><section>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
-<p><a name="taskb"></a></p>
+<h2 id="Task-7B-(like-Bonus)">Task 7B (like <em>B</em>onus)<a class="anchor-link" href="#Task-7B-(like-Bonus)">¶</a></h2><p><a name="task7b"></a>
+<span class="task" style="padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;">TASK</em></span></p>
<ul>
-<li>Bonus task<ul>
<li>Same pivot table as before (that is, <code>x</code> with nodes, and columns for Tasks/Node and Threads/Task)</li>
<li>But now, use <code>Sim. Time / s</code> and <code>Presim. Time / s</code> as values to show</li>
-<li>Show them as a stack of those two values inside the pivot table</li>
+<li>Show them as a <strong>stack</strong> of those two values inside the pivot table</li>
+<li>Use Panda's functionality as much as possible!</li>
</ul>
-</li>
+<p>Impossible?</p>
+<ul>
+<li>I gave up!</li>
+<li>Person who does this best / first: Personal certificate with my recommendation 😄</li>
</ul>
</div>
-</div></div></section></section><section><section>
+</div></section></section><section><section>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<h2 id="Conclusion">Conclusion<a class="anchor-link" href="#Conclusion">¶</a></h2><ul>
@@ -21723,7 +22098,7 @@ Name: C, dtype: bool</pre>
<div class="jp-Cell-inputWrapper"><div class="jp-InputPrompt jp-InputArea-prompt">
</div><div class="jp-RenderedHTMLCommon jp-RenderedMarkdown jp-MarkdownOutput " data-mime-type="text/markdown">
<p><span class="feedback">Feedback to <a href="mailto:a.herten@fz-juelich.de">a.herten@fz-juelich.de</a></span></p>
-<p>Next slide: Further reading</p>
+<p><em>Next slide: Further reading</em></p>
</div>
</div></section></section><section><section>
diff --git a/Introduction-to-Pandas--slides.ipynb b/Introduction-to-Pandas--slides.ipynb
index ea4d0ba3941c53f13b43229aff01ad14faa446c3..d47f43ab2e52d125b1029e5682774be885c0bbc2 100644
--- a/Introduction-to-Pandas--slides.ipynb
+++ b/Introduction-to-Pandas--slides.ipynb
@@ -63,7 +63,7 @@
"* [Task 5](#task5)\n",
"* [Task 6](#task6)\n",
"* [Task 7](#task7)\n",
- "* [Bonus Task](#taskb)"
+ "* [Task 7B](#task7b)"
]
},
{
@@ -1284,23 +1284,203 @@
]
},
{
- "cell_type": "markdown",
+ "cell_type": "code",
+ "execution_count": 20,
"metadata": {
"slideshow": {
"slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Age</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Name</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Liu</th>\n",
+ " <td>1681</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rowland</th>\n",
+ " <td>3136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rivers</th>\n",
+ " <td>3136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Waters</th>\n",
+ " <td>3249</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rice</th>\n",
+ " <td>1521</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Age\n",
+ "Name \n",
+ "Liu 1681\n",
+ "Rowland 3136\n",
+ "Rivers 3136\n",
+ "Waters 3249\n",
+ "Rice 1521"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "def mysquare(number: float) -> float:\n",
+ " return number*number\n",
+ "\n",
+ "df_sample.apply(mysquare).head()\n",
+ "# or: df_sample.apply(lambda x: x*x).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "skip"
}
},
+ "outputs": [],
"source": [
- "Logical operations allowed as well"
+ "import numpy as np"
]
},
{
"cell_type": "code",
- "execution_count": 20,
+ "execution_count": 22,
"metadata": {
"slideshow": {
"slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Age</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Name</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Liu</th>\n",
+ " <td>1681</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rowland</th>\n",
+ " <td>3136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rivers</th>\n",
+ " <td>3136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Waters</th>\n",
+ " <td>3249</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rice</th>\n",
+ " <td>1521</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Age\n",
+ "Name \n",
+ "Liu 1681\n",
+ "Rowland 3136\n",
+ "Rivers 3136\n",
+ "Waters 3249\n",
+ "Rice 1521"
+ ]
+ },
+ "execution_count": 22,
+ "metadata": {},
+ "output_type": "execute_result"
}
+ ],
+ "source": [
+ "df_sample.apply(np.square).head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ },
+ "tags": []
+ },
+ "source": [
+ "Logical operations allowed as well"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {
+ "tags": []
},
"outputs": [
{
@@ -1391,7 +1571,7 @@
"Hall True"
]
},
- "execution_count": 20,
+ "execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
@@ -1400,6 +1580,88 @@
"df_sample > 40"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Age</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Name</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Liu</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rowland</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rivers</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Waters</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Rice</th>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Age\n",
+ "Name \n",
+ "Liu True\n",
+ "Rowland True\n",
+ "Rivers True\n",
+ "Waters True\n",
+ "Rice True"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_sample.apply(mysquare).head() == df_sample.apply(lambda x: x*x).head()"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {
@@ -1411,7 +1673,7 @@
"source": [
"## Task 1\n",
"<a name=\"task1\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Create data frame with\n",
" - 6 names of dinosaurs, \n",
@@ -1423,7 +1685,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 25,
"metadata": {
"exercise": "task",
"slideshow": {
@@ -1442,7 +1704,7 @@
},
{
"cell_type": "code",
- "execution_count": 22,
+ "execution_count": 26,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -1512,7 +1774,7 @@
"Favourite Color violet gray "
]
},
- "execution_count": 22,
+ "execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
@@ -1535,25 +1797,12 @@
}
},
"source": [
- "Some more `DataFrame` examples"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 23,
- "metadata": {
- "slideshow": {
- "slide_type": "skip"
- }
- },
- "outputs": [],
- "source": [
- "import numpy as np"
+ "### More `DataFrame` examples"
]
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": 27,
"metadata": {},
"outputs": [
{
@@ -1638,7 +1887,7 @@
"4 1.2 2018-02-26 -0.718282 entries Same"
]
},
- "execution_count": 24,
+ "execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
@@ -1656,7 +1905,7 @@
},
{
"cell_type": "code",
- "execution_count": 25,
+ "execution_count": 28,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -1745,7 +1994,7 @@
"1 1.2 2018-02-26 1.718282 column Same"
]
},
- "execution_count": 25,
+ "execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
@@ -1756,7 +2005,7 @@
},
{
"cell_type": "code",
- "execution_count": 26,
+ "execution_count": 29,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -1818,7 +2067,7 @@
"4 1.2 2018-02-26 -0.72 entries Same"
]
},
- "execution_count": 26,
+ "execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
@@ -1829,7 +2078,7 @@
},
{
"cell_type": "code",
- "execution_count": 27,
+ "execution_count": 30,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -1845,7 +2094,7 @@
"dtype: object"
]
},
- "execution_count": 27,
+ "execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
@@ -1856,7 +2105,7 @@
},
{
"cell_type": "code",
- "execution_count": 28,
+ "execution_count": 31,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -1915,7 +2164,7 @@
},
{
"cell_type": "code",
- "execution_count": 117,
+ "execution_count": 32,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -1998,7 +2247,7 @@
"Walt Malcolm David Kelley False"
]
},
- "execution_count": 117,
+ "execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
@@ -2018,7 +2267,7 @@
"source": [
"## Task 2\n",
"<a name=\"task2\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Read in `data-nest.csv` to `DataFrame`; call it `df` \n",
" *(Data was produced with [JUBE](http://www.fz-juelich.de/ias/jsc/EN/Expertise/Support/Software/JUBE/_node.html))*\n",
@@ -2028,7 +2277,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 33,
"metadata": {
"exercise": "task"
},
@@ -2044,12 +2293,12 @@
}
],
"source": [
- "!cat nest-data.csv | head -3"
+ "!cat data-nest.csv | head -3"
]
},
{
"cell_type": "code",
- "execution_count": 118,
+ "execution_count": 34,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -2273,7 +2522,7 @@
"[5 rows x 21 columns]"
]
},
- "execution_count": 118,
+ "execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
@@ -2320,8 +2569,19 @@
"source": [
"## Slicing of Data Frames\n",
"\n",
- "* Pandas documentation: [Detailed documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html), [short documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/10min.html#selection)\n",
- "\n",
+ "* Slicing: Select a sub-range / sub-set of entire data frame\n",
+ "* Pandas documentation: [Detailed documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html), [short documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/10min.html#selection)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "source": [
"### Quick Slices\n",
"\n",
"* Use square-bracket operators to slice data frame quickly: `[]`\n",
@@ -2332,7 +2592,7 @@
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 35,
"metadata": {},
"outputs": [
{
@@ -2399,7 +2659,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 32,
+ "execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
@@ -2410,8 +2670,13 @@
},
{
"cell_type": "code",
- "execution_count": 33,
- "metadata": {},
+ "execution_count": 36,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "fragment"
+ },
+ "tags": []
+ },
"outputs": [
{
"data": {
@@ -2424,7 +2689,7 @@
"Name: C, dtype: float64"
]
},
- "execution_count": 33,
+ "execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
@@ -2434,14 +2699,23 @@
]
},
{
- "cell_type": "code",
- "execution_count": 34,
+ "cell_type": "markdown",
"metadata": {
"slideshow": {
- "slide_type": "fragment"
+ "slide_type": "subslide"
},
"tags": []
},
+ "source": [
+ "* Instead of column name in quotes and square brackets: Name of column _directly_"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {
+ "tags": []
+ },
"outputs": [
{
"data": {
@@ -2454,7 +2728,7 @@
"Name: C, dtype: float64"
]
},
- "execution_count": 34,
+ "execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
@@ -2463,6 +2737,14 @@
"df_demo.C"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "* I'm not a friend, because no spaces allowed \n",
+ " (And **Pandas as early as possible** means labelling columns well and adding spaces)"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {
@@ -2477,7 +2759,7 @@
},
{
"cell_type": "code",
- "execution_count": 35,
+ "execution_count": 38,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -2548,7 +2830,7 @@
"4 1.2 -0.718282"
]
},
- "execution_count": 35,
+ "execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
@@ -2566,13 +2848,13 @@
}
},
"source": [
- "* Use numerical values in brackets to slice along rows\n",
+ "* Use numerical values in brackets to slice **along rows**\n",
"* Use ranges just like with Python lists"
]
},
{
"cell_type": "code",
- "execution_count": 36,
+ "execution_count": 39,
"metadata": {},
"outputs": [
{
@@ -2630,7 +2912,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 36,
+ "execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
@@ -2641,7 +2923,7 @@
},
{
"cell_type": "code",
- "execution_count": 37,
+ "execution_count": 40,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -2704,7 +2986,7 @@
"3 1.2 2018-02-26 0.986231 entries Same"
]
},
- "execution_count": 37,
+ "execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
@@ -2726,7 +3008,7 @@
},
{
"cell_type": "code",
- "execution_count": 38,
+ "execution_count": 41,
"metadata": {},
"outputs": [
{
@@ -2784,7 +3066,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 38,
+ "execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
@@ -2795,7 +3077,7 @@
},
{
"cell_type": "code",
- "execution_count": 39,
+ "execution_count": 42,
"metadata": {},
"outputs": [
{
@@ -2853,7 +3135,7 @@
"4 1.2 2018-02-26 -0.718282 entries Same"
]
},
- "execution_count": 39,
+ "execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
@@ -2880,7 +3162,7 @@
},
{
"cell_type": "code",
- "execution_count": 40,
+ "execution_count": 43,
"metadata": {
"tags": []
},
@@ -2940,7 +3222,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 40,
+ "execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
@@ -2958,12 +3240,12 @@
"tags": []
},
"source": [
- "* Also slice rows (second argument)"
+ "* Also slice along columns (second argument)"
]
},
{
"cell_type": "code",
- "execution_count": 41,
+ "execution_count": 44,
"metadata": {},
"outputs": [
{
@@ -3012,7 +3294,7 @@
"2 1.2 -1.304068"
]
},
- "execution_count": 41,
+ "execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
@@ -3036,7 +3318,7 @@
},
{
"cell_type": "code",
- "execution_count": 42,
+ "execution_count": 45,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3127,7 +3409,7 @@
"entries 1.2 2018-02-26 -0.718282 Same"
]
},
- "execution_count": 42,
+ "execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
@@ -3139,7 +3421,7 @@
},
{
"cell_type": "code",
- "execution_count": 43,
+ "execution_count": 46,
"metadata": {},
"outputs": [
{
@@ -3202,7 +3484,7 @@
"entries 1.2 2018-02-26 -0.718282 Same"
]
},
- "execution_count": 43,
+ "execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
@@ -3213,7 +3495,7 @@
},
{
"cell_type": "code",
- "execution_count": 44,
+ "execution_count": 47,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3279,7 +3561,7 @@
"entries 1.2 -0.718282"
]
},
- "execution_count": 44,
+ "execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
@@ -3309,7 +3591,7 @@
},
{
"cell_type": "code",
- "execution_count": 45,
+ "execution_count": 48,
"metadata": {},
"outputs": [
{
@@ -3367,7 +3649,7 @@
"3 1.2 2018-02-26 0.986231 entries Same"
]
},
- "execution_count": 45,
+ "execution_count": 48,
"metadata": {},
"output_type": "execute_result"
}
@@ -3378,7 +3660,7 @@
},
{
"cell_type": "code",
- "execution_count": 46,
+ "execution_count": 49,
"metadata": {},
"outputs": [
{
@@ -3392,7 +3674,7 @@
"Name: C, dtype: bool"
]
},
- "execution_count": 46,
+ "execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
@@ -3403,7 +3685,7 @@
},
{
"cell_type": "code",
- "execution_count": 47,
+ "execution_count": 50,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3456,7 +3738,7 @@
"4 1.2 2018-02-26 -0.718282 entries Same"
]
},
- "execution_count": 47,
+ "execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
@@ -3486,7 +3768,7 @@
},
{
"cell_type": "code",
- "execution_count": 48,
+ "execution_count": 51,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3557,7 +3839,7 @@
"2 1.2 2018-02-26 -1.304068 has Same"
]
},
- "execution_count": 48,
+ "execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
@@ -3568,11 +3850,12 @@
},
{
"cell_type": "code",
- "execution_count": 49,
+ "execution_count": 52,
"metadata": {
"slideshow": {
- "slide_type": "subslide"
- }
+ "slide_type": "fragment"
+ },
+ "tags": []
},
"outputs": [
{
@@ -3643,7 +3926,7 @@
"2 1.2 2018-02-26 -1.304068 has Same -2.504068"
]
},
- "execution_count": 49,
+ "execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
@@ -3653,18 +3936,114 @@
"df_demo.head(3)"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ },
+ "tags": []
+ },
+ "source": [
+ "* `.insert()` allows to specify position of insertion\n",
+ "* `.shape` gives tuple of size of data frame, `vertical, horizontal`"
+ ]
+ },
{
"cell_type": "code",
- "execution_count": 50,
- "metadata": {},
- "outputs": [],
+ "execution_count": 53,
+ "metadata": {
+ "slideshow": {
+ "slide_type": "fragment"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>C</th>\n",
+ " <th>D</th>\n",
+ " <th>E</th>\n",
+ " <th>E2</th>\n",
+ " <th>F</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1.2</td>\n",
+ " <td>2018-02-26</td>\n",
+ " <td>-2.718282</td>\n",
+ " <td>This</td>\n",
+ " <td>Same</td>\n",
+ " <td>7.389056</td>\n",
+ " <td>-3.918282</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1.2</td>\n",
+ " <td>2018-02-26</td>\n",
+ " <td>1.718282</td>\n",
+ " <td>column</td>\n",
+ " <td>Same</td>\n",
+ " <td>2.952492</td>\n",
+ " <td>0.518282</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>1.2</td>\n",
+ " <td>2018-02-26</td>\n",
+ " <td>-1.304068</td>\n",
+ " <td>has</td>\n",
+ " <td>Same</td>\n",
+ " <td>1.700594</td>\n",
+ " <td>-2.504068</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B C D E E2 F\n",
+ "0 1.2 2018-02-26 -2.718282 This Same 7.389056 -3.918282\n",
+ "1 1.2 2018-02-26 1.718282 column Same 2.952492 0.518282\n",
+ "2 1.2 2018-02-26 -1.304068 has Same 1.700594 -2.504068"
+ ]
+ },
+ "execution_count": 53,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "df_demo.insert(df_demo.shape[1] - 1, \"E2\", df_demo[\"C\"] ** 2)"
+ "df_demo.insert(df_demo.shape[1] - 1, \"E2\", df_demo[\"C\"] ** 2)\n",
+ "df_demo.head(3)"
]
},
{
"cell_type": "code",
- "execution_count": 51,
+ "execution_count": 54,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -3743,7 +4122,7 @@
"4 1.2 2018-02-26 -0.718282 entries Same 0.515929 -1.918282"
]
},
- "execution_count": 51,
+ "execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
@@ -3754,7 +4133,7 @@
},
{
"cell_type": "code",
- "execution_count": 52,
+ "execution_count": 55,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3866,7 +4245,7 @@
"5 1.3 2018-02-27 -0.777000 has it? Same NaN 23.000000"
]
},
- "execution_count": 52,
+ "execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
@@ -3893,7 +4272,7 @@
},
{
"cell_type": "code",
- "execution_count": 53,
+ "execution_count": 56,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -3946,7 +4325,7 @@
"1 Second 1"
]
},
- "execution_count": 53,
+ "execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
@@ -3958,7 +4337,7 @@
},
{
"cell_type": "code",
- "execution_count": 54,
+ "execution_count": 57,
"metadata": {},
"outputs": [
{
@@ -4007,7 +4386,7 @@
"1 Second 2"
]
},
- "execution_count": 54,
+ "execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
@@ -4030,7 +4409,7 @@
},
{
"cell_type": "code",
- "execution_count": 55,
+ "execution_count": 58,
"metadata": {},
"outputs": [
{
@@ -4091,7 +4470,7 @@
"1 Second 2"
]
},
- "execution_count": 55,
+ "execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
@@ -4113,7 +4492,7 @@
},
{
"cell_type": "code",
- "execution_count": 56,
+ "execution_count": 59,
"metadata": {},
"outputs": [
{
@@ -4174,7 +4553,7 @@
"3 Second 2"
]
},
- "execution_count": 56,
+ "execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
@@ -4196,7 +4575,7 @@
},
{
"cell_type": "code",
- "execution_count": 57,
+ "execution_count": 60,
"metadata": {},
"outputs": [
{
@@ -4251,7 +4630,7 @@
"1 Second 1 Second 2"
]
},
- "execution_count": 57,
+ "execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
@@ -4273,7 +4652,7 @@
},
{
"cell_type": "code",
- "execution_count": 58,
+ "execution_count": 61,
"metadata": {},
"outputs": [
{
@@ -4325,7 +4704,7 @@
"1 Second 1 2"
]
},
- "execution_count": 58,
+ "execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
@@ -4345,7 +4724,7 @@
"source": [
"## Task 3\n",
"<a name=\"task3\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Add a column to the Nest data frame form Task 2 called `Threads` which is the total number of threads across all nodes (i.e. the product of threads per task and tasks per node and nodes)\n",
"* Tell me when you're done with status icon in BigBlueButton: \ud83d\udc4d"
@@ -4353,7 +4732,7 @@
},
{
"cell_type": "code",
- "execution_count": 59,
+ "execution_count": 62,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -4570,7 +4949,7 @@
"[5 rows x 22 columns]"
]
},
- "execution_count": 59,
+ "execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
@@ -4582,7 +4961,7 @@
},
{
"cell_type": "code",
- "execution_count": 60,
+ "execution_count": 63,
"metadata": {
"exercise": "solution"
},
@@ -4600,7 +4979,7 @@
" dtype='object')"
]
},
- "execution_count": 60,
+ "execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
@@ -4631,7 +5010,7 @@
},
{
"cell_type": "code",
- "execution_count": 61,
+ "execution_count": 64,
"metadata": {
"exercise": "task",
"slideshow": {
@@ -4646,7 +5025,7 @@
},
{
"cell_type": "code",
- "execution_count": 62,
+ "execution_count": 65,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -4660,7 +5039,7 @@
},
{
"cell_type": "code",
- "execution_count": 63,
+ "execution_count": 66,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -4702,7 +5081,7 @@
},
{
"cell_type": "code",
- "execution_count": 64,
+ "execution_count": 67,
"metadata": {
"slideshow": {
"slide_type": "-"
@@ -4715,7 +5094,7 @@
},
{
"cell_type": "code",
- "execution_count": 65,
+ "execution_count": 68,
"metadata": {},
"outputs": [
{
@@ -4754,7 +5133,7 @@
},
{
"cell_type": "code",
- "execution_count": 66,
+ "execution_count": 69,
"metadata": {},
"outputs": [
{
@@ -4788,10 +5167,10 @@
"source": [
"## Task 4\n",
"<a name=\"task4\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"\n",
- "* Sort the data frame by threads\n",
+ "* Sort the Nest data frame by threads\n",
"* Plot `\"Presim. Time / s\"` and `\"Sim. Time / s\"` of our data frame `df` as a function of threads\n",
"* Use a dashed, red line for `\"Presim. Time / s\"`, a blue line for `\"Sim. Time / s\"` (see [API description](https://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.plot))\n",
"* Don't forget to label your axes and to add a legend _(1st rule of plotting)_\n",
@@ -4800,7 +5179,7 @@
},
{
"cell_type": "code",
- "execution_count": 67,
+ "execution_count": 70,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -4809,12 +5188,12 @@
},
"outputs": [],
"source": [
- "df.sort_values([\"Threads\", \"Nodes\", \"Tasks/Node\", \"Threads/Task\"], inplace=True)"
+ "df.sort_values([\"Threads\", \"Nodes\", \"Tasks/Node\", \"Threads/Task\"], inplace=True) # multi-level sort"
]
},
{
"cell_type": "code",
- "execution_count": 68,
+ "execution_count": 71,
"metadata": {
"exercise": "solution"
},
@@ -4854,7 +5233,7 @@
"* Each data frame hast a `.plot()` function (see [API](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.plot.html))\n",
"* Plots with Matplotlib\n",
"* Important API options:\n",
- " - `kind`: `line` (default), `bar[h]`, `hist`, `box`, `kde`, `scatter`, `hexbin`\n",
+ " - `kind`: `'line'` (default), `'bar[h]'`, `'hist'`, `'box'`, `'kde'`, `'scatter'`, `'hexbin'`\n",
" - `subplots`: Make a sub-plot for each column (good together with `sharex`, `sharey`)\n",
" - `figsize`\n",
" - `grid`: Add a grid to plot (use Matplotlib options)\n",
@@ -4869,7 +5248,7 @@
" * `title`: Add title to plot (Use a list of strings if `subplots=True`)\n",
" * `legend`: Add a legend\n",
" * `table`: If `true`, add table of data under plot\n",
- " - `**kwds`: Every non-parsed keyword is passed through to Matplotlib's plotting methods"
+ " - `**kwds`: Non-parsed keyword passed to Matplotlib's plotting methods"
]
},
{
@@ -4885,7 +5264,7 @@
},
{
"cell_type": "code",
- "execution_count": 69,
+ "execution_count": 72,
"metadata": {
"slideshow": {
"slide_type": "-"
@@ -4922,7 +5301,7 @@
},
{
"cell_type": "code",
- "execution_count": 70,
+ "execution_count": 73,
"metadata": {
"slideshow": {
"slide_type": "-"
@@ -4950,12 +5329,13 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "* I prefer slicing first, as it allows for further operations on the sliced data frame"
+ "* I prefer slicing first: \n",
+ " \u2192 Allows for further operations on the sliced data frame"
]
},
{
"cell_type": "code",
- "execution_count": 71,
+ "execution_count": 74,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -4989,7 +5369,7 @@
},
{
"cell_type": "code",
- "execution_count": 72,
+ "execution_count": 75,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -5015,7 +5395,7 @@
},
{
"cell_type": "code",
- "execution_count": 73,
+ "execution_count": 76,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5050,11 +5430,11 @@
"source": [
"## Task 5\n",
"<a name=\"task5\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "Use the NEST data frame `df` to:\n",
+ "Use the Nest data frame `df` to:\n",
"\n",
- "1. Make the threads the index of the data frame (`.set_index()`)\n",
+ "1. Make threads index of the data frame (`.set_index()`)\n",
"2. Plot `\"Presim. Program / s\"` and `\"Sim. Time / s`\" individually\n",
"3. Plot them onto one common canvas!\n",
"4. Make them have the same line colors and styles as before\n",
@@ -5064,7 +5444,7 @@
},
{
"cell_type": "code",
- "execution_count": 74,
+ "execution_count": 77,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -5078,7 +5458,7 @@
},
{
"cell_type": "code",
- "execution_count": 75,
+ "execution_count": 78,
"metadata": {
"exercise": "solution"
},
@@ -5102,7 +5482,7 @@
},
{
"cell_type": "code",
- "execution_count": 76,
+ "execution_count": 79,
"metadata": {
"exercise": "solution"
},
@@ -5126,7 +5506,7 @@
},
{
"cell_type": "code",
- "execution_count": 77,
+ "execution_count": 80,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -5154,7 +5534,7 @@
},
{
"cell_type": "code",
- "execution_count": 78,
+ "execution_count": 81,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -5194,7 +5574,7 @@
},
{
"cell_type": "code",
- "execution_count": 79,
+ "execution_count": 82,
"metadata": {},
"outputs": [
{
@@ -5238,7 +5618,7 @@
},
{
"cell_type": "code",
- "execution_count": 80,
+ "execution_count": 83,
"metadata": {},
"outputs": [
{
@@ -5260,7 +5640,7 @@
},
{
"cell_type": "code",
- "execution_count": 81,
+ "execution_count": 84,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5286,11 +5666,12 @@
},
{
"cell_type": "code",
- "execution_count": 82,
+ "execution_count": 85,
"metadata": {
"slideshow": {
"slide_type": "fragment"
- }
+ },
+ "tags": []
},
"outputs": [
{
@@ -5313,7 +5694,7 @@
},
{
"cell_type": "code",
- "execution_count": 83,
+ "execution_count": 86,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5345,7 +5726,7 @@
},
{
"cell_type": "code",
- "execution_count": 119,
+ "execution_count": 87,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5354,12 +5735,14 @@
"outputs": [
{
"data": {
- "image/png": "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\n",
+ "image/png": "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\n",
"text/plain": [
"<Figure size 864x432 with 2 Axes>"
]
},
- "metadata": {},
+ "metadata": {
+ "needs_background": "light"
+ },
"output_type": "display_data"
}
],
@@ -5412,7 +5795,7 @@
},
{
"cell_type": "code",
- "execution_count": 85,
+ "execution_count": 88,
"metadata": {},
"outputs": [
{
@@ -5448,7 +5831,7 @@
},
{
"cell_type": "code",
- "execution_count": 86,
+ "execution_count": 89,
"metadata": {},
"outputs": [
{
@@ -5484,7 +5867,7 @@
},
{
"cell_type": "code",
- "execution_count": 87,
+ "execution_count": 90,
"metadata": {
"slideshow": {
"slide_type": "-"
@@ -5530,7 +5913,7 @@
},
{
"cell_type": "code",
- "execution_count": 89,
+ "execution_count": 91,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -5544,7 +5927,7 @@
},
{
"cell_type": "code",
- "execution_count": 90,
+ "execution_count": 92,
"metadata": {},
"outputs": [
{
@@ -5577,7 +5960,7 @@
},
{
"cell_type": "code",
- "execution_count": 91,
+ "execution_count": 93,
"metadata": {},
"outputs": [
{
@@ -5597,7 +5980,7 @@
},
{
"cell_type": "code",
- "execution_count": 92,
+ "execution_count": 94,
"metadata": {},
"outputs": [
{
@@ -5617,7 +6000,7 @@
},
{
"cell_type": "code",
- "execution_count": 93,
+ "execution_count": 95,
"metadata": {},
"outputs": [
{
@@ -5637,7 +6020,7 @@
},
{
"cell_type": "code",
- "execution_count": 94,
+ "execution_count": 96,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -5661,7 +6044,7 @@
},
{
"cell_type": "code",
- "execution_count": 95,
+ "execution_count": 97,
"metadata": {},
"outputs": [
{
@@ -5681,7 +6064,7 @@
},
{
"cell_type": "code",
- "execution_count": 96,
+ "execution_count": 98,
"metadata": {},
"outputs": [
{
@@ -5723,7 +6106,7 @@
"outputs": [
{
"data": {
- "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAEKCAYAAAD0Luk/AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAAxbElEQVR4nO3de3Qc5X038O8zM3uRdb/sriSTmBgCBIqbvqEFJzlxfDAYYYwc2+lx4jSl4NeEUqD0DQQoHKcEMBRyXGIHt6U54Y1L2tQJxpDGDikhnPCaU2OXhBBzK5BiW7Ik677SXmee94/ZXc2u9ippZ2/fzzkGaW/6eRDPd+aZ5yKklBJERFSTlFIXQEREpcMQICKqYQwBIqIaxhAgIqphDAEiohrGECAiqmElCYH9+/djzZo1WLNmDR566KFSlEBERChBCAQCAdx///3Ys2cP9u/fjyNHjuDQoUN2l0FERAA0u3+gruswDAOBQACLFi1CNBqFy+XK+/2jo1MwjLnPb2tvb8DwsH/O7y+WcqyrHGsCWFchyrEmgHUVaj51KYpAa2t9xudFKWYM79mzBw8//DDcbjf+6I/+CDt37oQQwu4yiIhqnu1XAm+++SZ+9KMf4YUXXkBjYyO++tWv4jvf+Q62bNmS1/uHh/3zuhLweBoxNDQ55/cXSznWVY41AayrEOVYE8C6CjWfuhRFoL29IfPzcy1qrl566SUsX74c7e3tcDqdWL9+PQ4fPmx3GUREhBKEwHnnnYdDhw5henoaUkr8/Oc/x4UXXmh3GUREhBJ0B33605/GsWPHsH79ejgcDlx44YXYunWr3WUQERFKEAIAsHXr1jk3/E+MjeETThcucLsXuCoiotpTcTOG/VJir9+P3waDpS6FiKjiVVwIOIWABuD56elSl0JEVPFK0h00H02qgikhMKzrpS6FiKjiVdyVwJRhQCoCS11OcH4ZEdH8VFwIhAyJ4aiOczQNw7oOvzQQEkBUABJgMBARFaDiuoMWCYErFi3CWU4XooZEFBLQDQgAQghoioBDmH9UAIoEmAtEROlVXAj0NjUiFDVmPS4BSCkR1iXCsccEAEUIOBQBh6LAAcCwf6kkIqKyVXEhUAgJQJcSui4RjF8thCOYlgacigIN5gFgLhBRrarqEEglARgAArqBgG5AEeaVglOYVwoqAE2a9xUYDERUC2oqBFIZ0uweSr2voIjYfARFgSol1Nj9BQYDEVWbmg6BVPH7CoZESjCY4eAQAlrs3woAlVcNRFThGAI5mMFg/kPHTGsvBKDAHI2kxcKB3UlEVGkYAnMkJaDDvOkcij0W705SBcyrBkWBFutOUsBgIKLywxBYQNbupEhKdxJvQBNROWIIFFm8OyndDWhViQWDEAgZBiQAhcFARDZiCJRA4opBl4jEHlMiUYzremLGc/weg8pAIKIiKkkI/PznP8euXbswPT2NT3/607j77rtLUUZZsU5si99jUAQgMDPjWYWEBg5XJaKFY/sCcsePH8e2bdvw2GOP4dlnn8WxY8fw4osv2l1GRTCkGQxB3cBkJIrxiI6RaBTDuo5JaSAozKGsUnDhPCKaG9uvBH72s5/hyiuvRGdnJwBgx44dcLlcdpdRkVLvLwQsN57V2L2F+I1nVfL+AhHlJqS0t5nYtm0bHA4H3n//fQwNDWHlypX4y7/8S4g8T2UHQ2FEi1xjNRBAYjVV68qq+R5nIqoNtl8J6LqOI0eOYM+ePVi0aBH+/M//HPv27cP69evzev/ERCDtKqL5am2rx+jI1JzfXyzFris+uc2hzJ71nInH04ihocmi1TRXrCt/5VgTwLoKNZ+6FEWgvb0h8/NzLWquOjo6sHz5crS1tcHtduPSSy/Fa6+9ZncZNUda7i/4ozpGI1GMWu4vBIQ5t8Hg/QWimmJ7CKxcuRIvvfQSJiYmoOs6fvnLX+KCCy6wuwzCzI3nQOzG81g0+cbzZDSKCHdtI6pqtncH/f7v/z62bNmCL37xi4hEIvjUpz6FDRs22F0GpZF643lSNzAaiZoL6GFmOQw1NlxVheAiekQVriTzBDZu3IiNGzeW4kfTHEgJSCQvhwHMzGNQLRPclPhaSQwFoorAGcM0Z4YEEFtEz7qlZ/zKIT4qKb4fgwpwIT2iMsMQoAWVWHo77Qqr5kJ6mkheflvhnAaikmEIkC1mLaQXY93NLbH8duxxTngjKj6GAJVUut3cgNl7M1hvRkspeTOaaIEwBKgspdubAYhdGYQj8BtG2pvRDAeiwjAEqKIY0gyIsG5kvBmduN/AXd2IcmIIUMXjzWiiuWMIUNUq9Ga0AoYD1Z6KC4EjgSAchkSbqqJVVeHgWgZUoIw3o2OL7KlpdndjMFC1qrgQ+H+BAIYiM4tJNykK2hQFraqKNlVFm6IwIGhOpAT0tJPfZq4aHIqSuNfAHd6oGlRcCHSoKsYi0cTevBOGgQnDwO+is3cZSBcQZ4YcUKVkQFBeUq8arBv5CDFzxeAQAmFj5oqC4UCVouJCYHNzE4KLdEwaBkYNAyO6jmFdT3w9ouuJTWfSBoTfD2AmIOJXDfGQ4BUE5ZK4ES0ldOu9hkgU47o+qztJ49BVKmMVFwKAeQbWpKpoUlUscTiSnpNSzj0gYqwBEf/TGvteY0BQBhLm0tzpupNUy01odidROanIEMgmV0AozW68P+xPhMJILCBG8wyIZkVJBEJbyhUEA4JSpZv0lm7oqnWnN141kJ2qLgSyEUKgRdNwpsOBMzNcQYxYrhriIWENiHHDwHiWgLCGAgOC0sk4dDU2Osk64U0Dg4GKq6ZCIBvrFUReAZHmCiIeEO+n+XxrQFi7mBgQFGcdnZQ84Y3dSVQ8JQ2Bhx56CKOjo3jwwQdLWUZOBQdEliuI1IAQMAPCOz2Fxtj8B2tIqAyImparOykRDNzpjeaoZCHw8ssvY9++ffjsZz9bqhIWRK6AmLAExGjsRnU8IHSY/5OPGQbGAsHZn40MXUwMiJo2qzspZac3zTI6KWQYkOBkN8qsJCEwNjaGHTt24Ctf+QrefPPNUpRgCyEEmlUVzaqKj+QIiGmHgr6pYPqAMAy8l/rZyNDFxICoWdad3hLdSfFhq9YlMriwHlkIKe3/Nbj55pvxhS98Af39/Th8+HBB3UGDoTBm35KtLoaUGI/qGIpEcTocwelI1Pw6Yn6t5/gvpgBodWjoiP3xODR0OB3ocGhod2gMCIKA+XtizoKOzWmIdS8J/n7UFNuvBPbu3Yuuri4sX74cTz31VMHvn5gIIBQ15vzzW9vqMToyNef3F0u6ujwAPFAA1Wn+cZsBMRHvXrLMhRgxDIzFriAMAMORKIYjUbyV8nMEgJaUm9Pxr1tSriAq6ViVg3Ksq5Ca0nUnFWvFVY+nEUNDkwv3gQukGutSFIH29oaMz9seAj/5yU8wNDSE3t5ejI+PY3p6Gg888ADuuusuu0upSIoQaFFVtKjqrOesAZE6kmnM0sU0GptM924kkvT+1IBYrBioC0fRmiYgqPqk7U7CzOgkZ8roJHYnVQfbQ+C73/1u4uunnnoKhw8fZgAsEGtALE15LmNAxK4oDMwOiFeCMzerFZgBkbpQX/wKQmFAVKW5jE6iysJ5AjUiV0CMp3Qxjeg6xiFxOhKFAbOLaSR2Izv1CiIeEJm6mBgQ1SXX6CSHwg18KklJQ2D9+vVYv359KUsgmAHRGhtZZNXaVo/hYX8iIFKvIMZiVxDWgECWgGjlFURVs3YnxSW6kxQBJ5DoTopKyfkMZYJXApSVNSDOSnnOkBJjsSGtqSFRaECkzoVgQFSHRHeSLs3l32PdSQhHMKHr7E4qAwwBmjNFiEQDnikg4pPkFiIg4l838fSxosnYn6jB7qRywBCgorAGRCrdcg/CusRG/J6ERPaAUMfG0KwoaE/ZC6JNVdHMK4iKlbU7KTbZTbVcNSgwTxYABsR8MATIdmqBARG/mogHhI7sVxCpS323MiAqVrrRSQBmdneDgKLEVluNTXRTAQgpLV/X7npKvw0GcTQcwv8pp3kCRNnkExDhRQ58MDaVNiAMAMOGgeF0VxAAWlK6luJfNzEgKkpid7fYlUMk5fn4f8l4UAiBxMqrSmx2tBJ7ncBMl1M1+W0wiL1+P7yO7M08Q4AqRjwgWuvr0BlKnjWu57hJHb+CGI7NsGZAVLf4SX88KBDbIzpV/IrC/FpAhiOYlIYZGEJU9MS456enoQE5t8tlCFBVUIVAu6qiPcMVxJglFEbnEBDxhfna03Qxca2dyjVzRWF+F5ESAX3mBCPdLnCVcsN6RNfRqChw5vj1ZAhQ1SskIKxXEeOWgDit6zit63gnQ0C0KQq69TAWRYzEVUQTA6LiZdwFDulmTSOxRWgpwkEI8+a6IczNiT7icmJc16GAVwJEGeUKiFFrF1OOgHh7LHNApO5JzYCobJlmTVtHM2kpcyAUaT4vAUgxM1TWkHKmT8ryExQICJihYsQSJX6D2xBILPUSBRA1DEQNCV0CEhJSAmerGg6Gwmk+OxlDgCgDVQh0qCo60gRENLWLSdcxoQoMBsMYM8wGwRoQqV1MGtJ0MTEgKl4+o5lk7JXx2xWWfyWZuV8hEA1HMK7rlp9jNvTZLjY+6nIBAN7Usy++zxAgmgMtTUDEl21ODYjUKwjAPHsb0nUMZQmIdFcQjQyIimQdzTSX90iYV6aF+qjLhfPVuqyvYQgQLbB0AREXlTIxgzp1JFNBAZFmJBMDguaCIUBkI00IeDQNnjTPWQMidbmNtAGR+tmYHRAfnlbhjI0SYUBQOgwBojKRKyBSh7fGv88aEFPmrmIakHYlV15BEEOAqAJoQsCrafCmeS4Su4JIDYgRw8CEJSAGdR2DGa4grEtsWOdCMCCqX0lCYNeuXThw4AAAYMWKFbj99ttLUQZRVXBkCYj6ljq8f3oyaQb1aAEB4UCGexCqigZuSl8VbA+BQ4cO4aWXXsK+ffsghMCWLVvws5/9DJdddpndpRBVPaeiZL2CSL33kBoQETAgqp3tIeDxeHDHHXfA6XQCAM466yz09fXZXQZRzXMIAZ+mwafNbgYiKTep5xIQabuYYgFB5UNIWbqVL373u99h06ZN+Nd//VeceeaZeb1nMBRG9qkPRFRMYcPAcCSKoUgUp8NRDEUiOB2J4nQkivHo7EBI5RICHU4NHQ4NHQ4HPA4t9r0DjSrvQSw0FYDP5cz4fMluDL/zzju4/vrr8bWvfS3vAACAiYkAQlEj9wsziE/oKTflWNdcanonFMLLwSDGdB0tqorlbndi5mIp67JDOdZVrJrcAD4E4ENQAYdqnvpjpospdbOgEcPAZOwKIiQlToYiOBmKAAgkfa5TiKRtRq3dTPU2dDGV439DYH51OVQFPm+ZhcDRo0dx880346677sKaNWtKUQIVwTuhEA5OT0MF4BYCfsPAwelpAFjwIKDylK2LKRzvYtJ1BFwaTvoDie8nYx0SYSlxStdxKk0XUzwg4t1K7ZaAWMR7EHNmewj09/fjxhtvxI4dO7B8+XK7fzwV0cvBIFTMrF/uAAAp8XIwyBAgOC0B0dpWj1HMzKi2BsRIylBXfx4B4RIieUc5BkTebA+B73znOwiFQnjwwQcTj23atAlf+MIX7C6FFtiYrsOd8j+bFnucKBtnjiuItF1MloAIMSDmzPYQuPvuu3H33Xfb/WPJBi2qCr9hxLuHAZhj0FvSrKFDlC+nEOjUNHTmERCJUUwFBIS1i+lDmoQ7EkVrDQUEZwzTglnudpv3AKSEBjMA9NjjRMWQLSBC1i6mlG6mKUtA9Os6+uMBEZi5UW0NiNSriLoqCgiGAC2YeL9/sUcHEeXDlSMgUuc/jOg6xqSBSX1mFFNSQFi4U7uYKjggGAK0oD7qcrHRp7LnEgJdmoaulIBobavHqZRlNqzdTPEriGCWgKi0KwiGABGRhUtR0KUoswICAIKGkbxQn+Xr6UxdTBbu1HkQloBYpChF/7ulwxAgoppmneDomfbjItWR8WrWnSMg0u0FYQ2IoJTo03X0ZQmIxHIblrkQrQv7V07CECCimpU6wXEiquNgyNzNrdBuTbeioFtR0J0jIFKHu+YTEIvGx9GiKLP2gmhTVdTN8wqCIUBENWvWBEchoMceX8h7W4UGRLzLKR4Q04aBacNAuqU264RILNQ3l4BgCBBRzSqHCY75BESoTsPx8em0VxABKXEyGsXJNJ9dJwTOcrtwt7c5489nCBBRzSr3CY7xgGhtrMdHIsnPBVJvUlvuQwQsATEQzb7uMkOAapodq55S+Uqd4BiWsmImONYpCuoyXEHEA2Kw7wRC48PAuWdm/ByGANUsrnpKqRMcPZqKi1yVfyJQpyjQ3v9vNP3Hs3C1dQCXr8r4WoYA1SyuekpA8gTHct1PoCBSAv5JGC/8O9z+SbiV7JPTGAJUs8rhpiDRnEkJjI9CDJ6CMtgPMXgKIv7vwBTipzEasm/CxRCgmlXuNwWJAACGAeP0EJS3351p5Af6IYZOQYSCGd8mAUiXC9GmzCODAIYA1TCuekplRdchRoaSz+gHzcY+GIkknaxYSUUB2j2Qvi5IbxcMTyektwvhyUmEfnEArpaOrD+WIUA1i6ueUklEIxCnB2c39qcHIfTMwzmlqgIen9nQe7sgvZ2Qnk7IDh+QZoSQAzAff+vXWcspSQg8++yz2L17NyKRCK655hps3ry5FGUQcdVTKp5IGGJoINbQWxr74SEII3M/vXQ4AE8npC/W2Hs60XjOUowr9UCBXZWOs86B45zzsr7G9hAYGBjAjh078NRTT8HpdGLTpk24+OKLcfbZZ9tdChHR/IWCs87qlcF+YHQYIjZpKx3pckP6ugBvp9mF4+uC4ekCWtqAlOUelLZ6oEijlmwPgUOHDuGSSy5BS0sLAGD16tU4ePAg/uIv/sLuUoiIEHn3bYRf+SXk2CgiHg/w8eVwnHXO7BcGpiAGZhp7JX6GPz6a9fNl3aKZxt7bDcNr9tmjqQUog70FbA+BwcFBeDyexPderxevvfZa3u9vaqpD9knQubW21c/zE4qjHOsqx5qA5LqE5d+aEFCFgArAAGDEZoDGn9OEgCLM0XUSgAGJgG5goQaFluPxKseagPKoK/DWMUy/8O9QVA2ioQHR8XHgZ/vRMH4xHJoDsr8PRn8fjP6TwMR49g9rbILStRhKVxdE1xlQuruhdHYDTc0LspHMXI9Xrg4k20NAprk8KuQATUwEEIpmH/eaTblOBinHusqlJgHzhElAQFEEPK31mBibhioEhJQQQkCVQHxOTFQi6UQh/usVkUAk9cNjn28IYErXETUyX77nUi7Hy6ocawLKoC4pgYlxhJ7+EZzj41D1KNRQEGo4BEXXgf95L+3vCgDI5tbYSJzO2GgcH6SnC6hvmP1iHcDo9LzLnc/xcqgKfF5nxudtDwGfz4cjR44kvh8cHITX67W7DCojSY28sJzNCwEBCRUCCgAhzde1OjREIcxT+cS/zf+v08nSLZv4+S4JOBUVYRUI6DoihsTc44DKhmEA46NQBvotN2hjffehIDINCZAA0NoO6euONfadiZu0cNfZ+BcovrxCIBqNQksZgjQ+Po7m5uyTENL55Cc/iZ07d2JkZAR1dXV47rnn8I1vfKPgz6HKYzb2ZkPviDXymjAbeBUzjXyi0Y438ha5GvT51ueSgFtVEVEkpqVESDcYBpXAMCBGTiePwol/HQlnfJsEYLjdMOrqYdQtgnS7ETIk9IZG1G/eal/9JZQ1BF5//XXcdNNNOH36NC699FLcd999aGgwL3muueYa7Nu3r+Af6PP5cOutt+LLX/4yIpEINm7ciGXLls2teipL8TN7RYikxl4FoMS6bZIb+hnFbOTzJSWgQaBZEQgpAn7dmFc3ES2gaNQcYpl6Vn96ACLLkslSVYEOn+Ws3jzDD0+MI/TCAQhVAxwOKIYOPRyG65LP2vd3KrGsIXD//ffj61//On7v934P27dvx5YtW/C9730PTqczbd9+vtauXYu1a9fO+f1UHqyNvWb5k6uxL4eGPh9SAk4ItCoqgiowFdVhVErxlS4xxj7lrH54MPsYe81hTqjyxWbO+rrNCVXtnrRj7B2diwFVS4wO0jweaJlGB1WprCEQDAaxYsUKAMAjjzyCm2++GXfeeSe++c1v2lIclYesjX3sTyU39rkIAHUScGoqpg0DQXYRLZz4GPuhmcZeGTgFjJ7OPsbe6YL0dgKWCVWGtwtobZ81xj4Xx1nnJBr9kt+wLoGsIWAYBoaHh9He3g4AeOihh7Bp0yZ8+9vfXpAhT1ReUhv7BkWBdGiJPvuMjb3tlZaGKoEmRYFLEZjSDUTYRZS/wHTSWX1wdAjOkycgxkayvk3WLTIbe28XjPjZvacTaG4tuLGn9LKGwLXXXot169bhvvvuw4oVK1BXV4fdu3fjS1/6EgYGBuyqkRZYYjROrM9eS7lBG2/smxwaQjXY2GcT7yJysIsovSn/TPfNQP/MEseTyWPsDSTf8pf1jZC+zuRF0DxdQGNTWUyoqmZZQ6C3txfLli2D0zkzxrS7uxv79u3Dv/zLvxS9OJqfdI19fCIVz+znJ10XUc2QEpgcT1oiIXGWP+XP/tamZkhfF5xnfAjBFo85ezbTGHuyRdYQ6Ovrw0c+8pFZjzc3N+P8888vWlFUGOs4e4diaeylhBo7w2djXxzxLiK3IhI7lFWN+KYliTN6S2MfDGR/a2sbpNc8qzcXQuuE7OgE6hYBABra6jFVY33v5SprCNx4442JYaA33XQTdu7cmXhux44d+MxnPlPc6iiJtbHXFMsNWimhxM7wZ42xl2zsi01KwAGBdoeGgEOrvC4iwwBGTkOJ35yNb1gyeAoiHMr4NikE0NYx04UTu0ErPT7AxT0ZKkXWELAOAz1+/HjG52hh5dPYA7EGn4192VCEQJ0EXJqKKSkRjOrl9d9E180hlqnDLodOZR9jryhAh3d2Y9/hAxyZtjqhSpE1BKwjgFJHA3F00PxZG3unEKjX1KTGXrHOoGVjXzEUCTRCwO1QMaUbCNs9iiixaUk/whPD0P7ng9imJQM5xthr5jr28SUS4o19uyftpiVUHfK+EqC5y3Rmr8T77CXQ4XRAIpj3ejhU/hxSoFlREVIBfzG6iMLhpPH1ib1nR4YSY+yjmL2KpHS6zC4b38wOVYanC2jr4LDLGpRznsD4+DiklNB1PfE1AOj6Qi2+Wz2sjb2qzCyZkOjGyXBmT9VLAHDHRhHNuYsoGJjVhaMM9gNjI9knVLnroHZ1I9rug+GzNPYcY08WWUPg7bffxiWXXJJo+C+++OLEc7XcHTSrsQegKkpejT3P7GtTvIuoTlPhNzJ0EcXH2A+dio3IiTX8E2NZP1suqk/01yeWS/B0AU3NaG1vqLkZsFSYrCHw5ptv2lVHWcrU2Me7cdjYU6FUCTT5/QgO9iHYfxKIL3E8dArCP5n1vbKxKdHQJyZUebuAhkabqqdqxLs9MYpl0xIHAI2NPc2DlBJyfBT6QB+MgX7oA/0wBvthDPRBBsxNRjLt+CRbWmfWsfd0ml05nk6grvQ7cVH1qbkQEIB5M9bajRPfuMS68iUbe8qDNAzI0WHoA30YnRrB9Lvvwxg8BX2wHwgFM79RCChtHVA7uyG8nQh7OhHuMEfmcIw92alqQyDRjRPfwCTW2Lc7NKiqOruxj2FjT+lIXYcxPARjoA967IxeHzwFY/AUENu0JO0mgooCpcML1dcN1dcFxdsNxdsJxdsJ4ZhZjqUOQEiYo4h0/hKSjWwPgaNHj+KBBx5ANBpFS0sLHnjgASxevHjOn2dt7DUhoOU4s3cqCgTY2JMp8sZvEHrxpzBGTkNp64Dz05dC7fAmunGMwVhXztAAoGeeUAVVg7OrG+jwmg29L9bYd/gg8hxj77KMIgroOn9HyRa2h8Btt92Gxx57DOeddx5++MMf4r777sPu3bvzfr8KgTpVSTT2CmY2GeeZPeVLhkMIH34Jwf/4sflLYhjQf/ffCLz7VvY3OpxQvZ1QO+MNfRcUTyeUdg+8nS0YGsp+czcXIYEGCLg1zRxFVEsL01FJ2BoC4XAYt9xyC8477zwAwLnnnot//ud/LugzmlUFui7Z2FNeZDA4030z0A9j0Py3HB3O/kvjckP1dUHt7Ibq7TLP6n3dEC3tEDaMsdck0CIEQg6NXURUVLaGgNPpRG9vLwBzItquXbuwatWqgj6D/y9QOnJ6KqmRjzf6cnw0+xtVFcJdB+FyQzgdkEKFEZhG010PlsFcGJHoIpqWEtPsIqIiELJIa0McOHAA27dvT3ps6dKleOKJJxAOh3HHHXdgfHwcf//3fw8HF6GiPEgpoU9OIHzyBCJ9JxHuO4Fw30mE+05CHx/L+l61qRnOxWfA2bUYzsVnwNG9GCP79iI6MQHVPTMaxwiFoLW0YPHX7iny36ZwIcOAP6pDAIklwyOGxJTB7S4pMxWAz+XM+HzRQiCTqakp3HDDDWhpacEjjzyStGFNPoaH/TDmsSCXx9M4737bYijHukpVk5QScmIscUZvDPRDH+yDMXAKcjr7piVKSysUn9mFo3aaffbC2wVl0ewx9pE3foPA0983b9w6nEAkDBmNom7dF+H42IUF123H8UrMV7HQBTBlGAil2fu4XPfMZV2FmU9dDlXBOd7mjM+X5MbwkiVLcO+995bB5TaVkjQMyLGRme6bwf5Yg98PZNu0RAgore2JPnvFa461V71dEO66vH++2dB/MWl0kHvF6jkFgF3SnbKpEmhWFIQVBZO6jij3PqYC2BoCx44dw/PPP4+zzz4b69atAwB4vV48/vjjdpZBRZQ65NK1YjW0c86HMTIEY+BU7Ix+ZuhlfIx9WkIkj7H3dUPxdMJ7/kcxPJHlfQVwfOzCsm7082VubAO0cu9jKpCtIXD++efjrbdyDMGjihV+/VcIPP0khAQgJfQT/4Pp//vtxBDMjFQVqscH1dcNxddlDrv0dUPp8EJos+8XKS4XgIUJgWqTuvcxUS5VO2OYikdGwomlEWbWxekzZ88iy+rYmgOqr9Ns7OMNvdccYy9U/ioupPjexw2ahilF2L+xDVUM/p9HGRnBIKLHf2fenI3PnB3ogzFyOvtYXUUxh1y63RBOJ2RER/3WWyFa7RljTyYpAbeqoMXSRcT5BpSKIUCQgemZ1S4TZ/d9GB8byfo+UbfIvDkb68YJ//oVGNNTEE534qa/DIcgWtugtHvs+KtQBu7Y3secb0CpGAI1xPBPJo/CiXXjyInxrO8TDY0zQy7jXTjebojGpuR9qDs6EXj6++ZQS8uQS/eK1cX+q1EehATqIeDSNEzFlqRgFhBDoMqYY+zHk1e7jI3GkVPZx9iLpmZzmYTYOPvWc87ChKsZSn1+m5ZU4pDLWqRJoFkIhGNLUkR5WVDTGAIVShpGyqYlffmNsQfMdex9XbGljbvMETmeLoi6RUmvq/M0wl/g5KdqGXJZ/QScEmjVVARiXUS8d1ybGAJlThoGjJHTM2f08Zu0g6eAcCjzG+Nj7GOLn6mdi80G39sJ4XTZ9xegsiYksMjSRZRu1jFVN4ZAmZDRaNLCZ+ZonD5zHftoJPMbFXOMvZI4s4/12Xs6IbgmE+WJs45rF0PAZjISgTE0kJg5G++3Hz89COh65jdqGlRPfB17S2Pf4eUYe1oQnHVcm9h6FIkMh8wJValj7IeHso+xdzoTyySosZE4wtsNpa2DY+zJFqmzjoPsIqpqDIF5koHpWUMuE5uWZCHcdbGROObN2ZaPLoXf3QrR3MrGnspCfNaxWxGY0g3OOq5SDIE8GVP+pP76+BBMmWMde1HfYFkALTYax9sN0dScNMa+3tOI6TJbSprI7CISaFZUhDjruCoxBCyklJCTE5bdqfoT3TnSn72BFk3NKd04sXXsG/IbY09UzgRmZh1PSYkAZx1XjZoMASllyhj7mbN7GZjO+l6ltS397NmUMfZE1UhIoAECbs46rhpVHQKJMfaW9XCOjw4idPIEEMoxxr6tY6bP3tMF4euG6u2EcLkzv4+oRsRnHYccGqY467iiVVwITD/5ONSPX5w0K1XqOozhoTRLJZzKMcZesWxa0p2YTKV4OyEchW17SVR7BFyxUUScdVy5ShYCx44dwx//8R/j9ddfL+h9xvgIQj/4LrSPfgzC0KEPnoIxdCr7GHtVg+o1Ny1pOHMJgo0dsTH2PnN/WSKaM846rmwlaQEDgQDuvfdeRCJZztIzkONjwNQkor86PPtJh9PctMTbBaVzsbnnrLfLHGOvqgCAtjLc0J2oGnDWcWUqSQg8+OCDuOaaa/Dqq6/O7QMUBcLphOPC/wXVtzjWhdPFTUuISoyzjiuP7SHw/PPPIxgM4oorrpjT+x3dZwCaA47WViy+8eY5fYbHU57DNsuxrnKsCWBdhShlTRFDYjIaRTBNELS21ZegotyqrS41x/NFC4EDBw5g+/btSY8tXboUfr8fTzzxxJw/Vw+FoIfDcC6/dE7dOp4y7Q4qx7rKsSaAdRWiHGoy50TKpFnHrW31GB2ZKmld6VRjXQ5Vgc+beaBL0UKgp6cHPT09SY/t3bsX//AP/4DNmzcnHuvt7cWTTz6JhoaGvD5X1Dei7lOruGY9UYVIN+uYyoet3UGf//zn8fnPfz7x/bnnnov9+/cX9BmLNv9vGLzhRFRxrLOOnYqCMZF9LUWyB++iEpGthARaHBpaNQ0ulU1QqZX0v8Bbb71Vyh9PRCUUn3Xc7NCgWRZTJHtxphQRlRBnHZcar8WIqOTis45bNQ1uVQGvC+zDECCishGfddzs0KApjAI7MASIqKxICTilOeu40aGBWVBcDAEiKkvxvY5bNQ117CIqGoYAEZW1+F7HLQ4VDl4WLDiGABGVPSkBhxRoUVQ0OTSoHFK6YBgCRFQx4rOO2zQVizQVzIL5YwgQUcWJ73XcqmlwctbxvPDoEVHF0iTQwlnH88IZw0RU4WZmHU9LiQBnHReEVwJEVBWEBOo567hgDAEiqiqcdVwYhgARVR3rrOMGTeWs4ywYAkRUtQRmFqbjrOP0GAJEVPXis46bOet4FttHBw0ODuLuu+/G4OAg3G43HnnkEZxxxhl2l0FENUZKwAkBR2yvY39Uh8H9Le2/Erj99tuxcuVKPP300+jt7cUjjzxidwlEVMM46ziZrVcCIyMjePPNN/Hd734XALBhwwYsX77czhKIiAAASmzWsVvT4DcMhHWj1CWVhJDSvuuhX//61/ibv/kbfOITn8B//ud/oru7G/fccw8WL15sVwlERLNIKTGtG/DrOvRSF7PAVAA+lzPj80ULgQMHDmD79u1Jjy1ZsgSvvPIKdu/ejZUrV2Lv3r145plnsGfPnrw/d3jYD2Me0wE9nkYMDU3O+f3FUo51lWNNAOsqRDnWBJRvXW0dDTh+erLsZh23ttVjdGRqTu91qArO8TZnfL5o3UE9PT3o6elJeuyDDz7A5z73OaxcuRIAcNVVV+G+++4rVglERAVRhUB9rItoyjAQ0g2UURYUha03hj/84Q/D5/PhxRdfBAC88MILuOCCC+wsgYgop1qadWz7ENFdu3Zh27ZtePjhh9HQ0IAHH3zQ7hKIiHIyh5Sas44DisR0mXURLRTbQ2Dp0qUF3QMgIiql+Kxjl6Zh2jAQrLIuIs4YJiLKQ7XOOuZ+AkREebLOOg6qwFQVzDpmCBARFUgAqJOAy7KRTaVmAbuDiIjmSKmCvY4rs2oiojJSyXsdszuIiGhBVOZex7wSICJaQJW21zFDgIioCCpl1jFDgIioSOJ7HbeV8V7HDAEiIhuU617HDAEiIpuU46xjjg4iIrJRuc065pUAEVEJxGcdJ/Y6LlEdDAEiohKamXWslmTWMUOAiKgMaBCJWceqjbOObQ+BEydOYPPmzejt7cWf/Mmf4OTJk3aXQERUpsxZx22ainqbhpTaHgKPPvoo1qxZg/379+Pyyy/Hjh077C6BiKispc46LibbQ8AwDPj9fgBAIBCA2+22uwQioooQn3XcoqlFm3UspLR3bNIHH3yATZs2QVVVRCIR/OAHP8CSJUvsLIGIqOIYUsKv65gqcHtLFYDP5cz4fNFC4MCBA9i+fXvSY0uXLkUoFMJ1112HVatW4ac//Sl27dqFZ555BiLPGyHDw34Y81iaz+NpxNDQ5JzfXyzlWFc51gSwrkKUY00A6yqUtS5DAH7DQCjPMHCoCs7xNmd8vmiTxXp6etDT05P02MjICHp6erBq1SoAwOrVq7Ft2zaMjo6ira2tWKUQEVUNJdZFFFIEpnQDkXmuV23rPYHW1la4XC4cOXIEAHD06FHU19czAIiICmAuTCfQoqhodGhQ5jGk1NZlI4QQ2LVrF77xjW8gGAyivr4eO3futLMEIqKqYd3reEpKBKN6QfcLgBKsHbRs2TLs3bvX7h9LRFS1FAk0QqBOU+GXEmHdyP+9RayLiIhsNJdZx1xFlIioqiTvdRzN0UHEECAiqkLxWcfIMeOY3UFERFVMyXGnmCFARFTDGAJERDWMIUBEVMMYAkRENYwhQERUwxgCREQ1jCFARFTDKm6ymLIAu+ssxGcUQznWVY41AayrEOVYE8C6CjXXunK9z/adxYiIqHywO4iIqIYxBIiIahhDgIiohjEEiIhqGEOAiKiGMQSIiGoYQ4CIqIYxBIiIahhDgIiohjEEiIhqWNWHwNGjR7Fhwwb09vbiT//0T3Hy5MlZr+nr68Mf/MEfoLe3F729vbjuuutKXlM4HMZtt92Gnp4efO5zn8O7775b1JqsHn30UezcuTPtc3Yfq3zrKsXx6uvrw+bNm3HFFVfghhtuwNTUVNrX2HG8nn32WVx55ZW47LLL8OSTT856/o033sCGDRuwevVq/PVf/zWi0WhR6ii0rl27dmHlypWJ45PuNcXg9/tx1VVX4cSJE7OeK9WxylVX0Y6VrHIrV66Ub7zxhpRSyr1798qvfOUrs15z8OBBec8995RVTf/0T/+UqOnw4cNy48aNRa9rYmJC3nnnnXLZsmXyW9/6VtrX2H2s8q2rFMdr69at8sc//rGUUspdu3bJv/3bv531GjuO16lTp+TKlSvl6OionJqakmvXrpXvvPNO0mvWrFkjX331VSmllHfeead88skni1pTvnVdf/318r/+67+KXovVr371K3nVVVfJCy64QB4/fnzW86U4VvnUVaxjVdVXAuFwGLfccgvOO+88AMC5556L/v7+Wa/7zW9+g7fffhvr16/Hl7/8Zbz11lslr+kXv/gFrr76agDAH/7hH2J0dBR9fX1FqwsAnn/+eZx55pn4sz/7s4yvsfNYFVKX3ccrEonglVdewerVqwEA69evx8GDB2e9zo7jdejQIVxyySVoaWnBokWLsHr16qRaTp48iWAwiI9//ONZa7W7LgB4/fXX8fjjj2Pt2rW49957EQqFil7Xv/3bv2Hbtm3wer2znivVscpVF1C8Y1XVIeB0OtHb2wsAMAwDu3btwqpVq2a9zuVyYd26dXjqqadw3XXX4cYbb0Q4HC5pTYODg/B4PInvPR4PTp06VZSa4tatW4etW7dCVdWMr7HzWBVSl93Ha3R0FA0NDdA0LfHzBgYGZr3OjuOV+nf3er1JtaQ7NulqXWi56pqamsLHPvYxfO1rX8O+ffswMTGBxx57rOh13X///bjooovyqtmuY5WrrmIeq4rbTyCTAwcOYPv27UmPLV26FE888QTC4TDuuOMORKNRXH/99bPee9NNNyW+XrFiBb75zW/ivffeS5ytl6KmdBRlYTI7W125FOtYzbeudIp5vM4888xZrxNi9rrtxTxecTLNavDWWnI9Xyy5fm59fT0ef/zxxPfXXnst7rrrLtx6661Fry2TUh2rXIp5rKomBHp6etDT0zPr8ampKdxwww1oaWnB7t274XA4Zr1mz549uOqqq9Da2grA/EWIn+GVqiav14uhoSEsWbIEADA0NJTxMnGh6spHsY7VfOuy+3hFIhFcfPHF0HUdqqpm/HnFPF5xPp8PR44cSXw/ODiYVIvP58Pp06cT3y/ksZlPXX19fTh06BA2btwIoDjHplClOla5FPNYVXV3EADcdtttWLJkCR599FE4nc60r3nllVfwwx/+EABw+PBhGIaBpUuXlrSmFStWYP/+/QCAI0eOwOVyobu7u2g15cvuY5Uvu4+Xw+HARRddhJ/85CcAgKeffhqf+cxnZr3OjuP1yU9+Ei+//DJGRkYQCATw3HPPJdWyePFiuFwuHD16NGutCy1XXW63Gw8//DCOHz8OKSWefPJJXHbZZUWvK5tSHatcinqsFvxWcxn57W9/K8855xx55ZVXyquvvlpeffXVcsuWLVJKKb///e/Lv/u7v5NSmqMYrrnmGrlmzRq5fv36xMidUtYUDAbl7bffLq+88kq5bt06+frrrxetplTf+ta3kkbhlOpYFVJXKY7XiRMn5Je+9CXZ09Mjr732Wjk2NjarLruO1zPPPCPXrFkjL7/8cvmP//iPUkopt2zZIl977TUppZRvvPGG3LBhg7ziiivkX/3VX8lQKFSUOgqt6+DBg4nn77jjDtvqktIcpRcfhVMOxypXXcU6VtxekoiohlV9dxAREWXGECAiqmEMASKiGsYQICKqYQwBIqIaVjWTxYhKQdd1fO9738Ozzz4LXdcRiUSwcuVK3HLLLRnngBCVEw4RJZqHe+65B+Pj47j//vvR2NiI6elpfPWrX0V9fT0efvjhUpdHlBNDgGiOjh8/jrVr1+Kll15CQ0ND4vGhoSG8+uqruPzyy0tYHVF+eE+AaI6OHTuGs88+OykAAHPlSQYAVQqGANEcKYoCwzBKXQbRvDAEiOZo2bJleO+99+D3+5MeHxgYwNatWxEMBktUGVH+GAJEc+Tz+bB27VrcddddiSDw+/34+te/jpaWFrjd7hJXSJQbbwwTzUM0GsVjjz2G5557DqqqIhwOY9WqVbjppps4RJQqAkOAiKiGsTuIiKiGMQSIiGoYQ4CIqIYxBIiIahhDgIiohjEEiIhqGEOAiKiG/X/axOsX+y+blgAAAABJRU5ErkJggg==\n",
+ "image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
@@ -5766,7 +6149,7 @@
"outputs": [
{
"data": {
- "image/png": "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\n",
+ "image/png": "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\n",
"text/plain": [
"<Figure size 432x432 with 3 Axes>"
]
@@ -5790,9 +6173,9 @@
"source": [
"## Task 6\n",
"<a name=\"task6\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "* To your `df` NEST data frame, add a column with the unaccounted time (`Unaccounted Time / s`), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time. \n",
+ "* To your `df` Nest data frame, add a column with the unaccounted time (`Unaccounted Time / s`), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time. \n",
"(*I know this is technically not super correct, but it will do for our example.*)\n",
"* Plot a stacked bar plot of all these columns (except for program runtime) over the threads\n",
"* Tell me when you're done with status icon in BigBlueButton: \ud83d\udc4d"
@@ -6287,7 +6670,7 @@
},
{
"cell_type": "code",
- "execution_count": 108,
+ "execution_count": 107,
"metadata": {},
"outputs": [
{
@@ -6566,7 +6949,7 @@
"[6 rows x 21 columns]"
]
},
- "execution_count": 108,
+ "execution_count": 107,
"metadata": {},
"output_type": "execute_result"
}
@@ -6598,7 +6981,7 @@
},
{
"cell_type": "code",
- "execution_count": 109,
+ "execution_count": 108,
"metadata": {
"slideshow": {
"slide_type": "subslide"
@@ -6611,7 +6994,7 @@
},
{
"cell_type": "code",
- "execution_count": 110,
+ "execution_count": 109,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -6688,7 +7071,7 @@
" 0.518282 2.952492 NaN"
]
},
- "execution_count": 110,
+ "execution_count": 109,
"metadata": {},
"output_type": "execute_result"
}
@@ -6704,7 +7087,7 @@
},
{
"cell_type": "code",
- "execution_count": 111,
+ "execution_count": 110,
"metadata": {
"slideshow": {
"slide_type": "fragment"
@@ -6737,9 +7120,9 @@
"source": [
"## Task 7\n",
"<a name=\"task7\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "* Create a pivot table based on the NEST `df` data frame\n",
+ "* Create a pivot table based on the Nest `df` data frame\n",
"* Let the `x` axis show the number of nodes; display the values of the simulation time `\"Sim. Time / s\"` for the tasks per node and threads per task configurations\n",
"* Please plot a bar plot\n",
"* Tell me when you're done with status icon in BigBlueButton: \ud83d\udc4d"
@@ -6747,7 +7130,7 @@
},
{
"cell_type": "code",
- "execution_count": 116,
+ "execution_count": 111,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -6779,16 +7162,24 @@
"metadata": {
"exercise": "task",
"slideshow": {
- "slide_type": "fragment"
- }
+ "slide_type": "subslide"
+ },
+ "tags": []
},
"source": [
- "<a name=\"taskb\"></a>\n",
+ "## Task 7B (like <em>B</em>onus)\n",
+ "<a name=\"task7b\"></a>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "\n",
+ "- Same pivot table as before (that is, `x` with nodes, and columns for Tasks/Node and Threads/Task)\n",
+ "- But now, use `Sim. Time / s` and `Presim. Time / s` as values to show\n",
+ "- Show them as a **stack** of those two values inside the pivot table\n",
+ "- Use Panda's functionality as much as possible!\n",
+ "\n",
+ "Impossible?\n",
"\n",
- "* Bonus task\n",
- " - Same pivot table as before (that is, `x` with nodes, and columns for Tasks/Node and Threads/Task)\n",
- " - But now, use `Sim. Time / s` and `Presim. Time / s` as values to show\n",
- " - Show them as a stack of those two values inside the pivot table"
+ "* I gave up!\n",
+ "* Person who does this best / first: Personal certificate with my recommendation \ud83d\ude04"
]
},
{
@@ -6818,7 +7209,7 @@
"source": [
"<span class=\"feedback\">Feedback to <a href=\"mailto:a.herten@fz-juelich.de\">a.herten@fz-juelich.de</a></span>\n",
"\n",
- "Next slide: Further reading"
+ "_Next slide: Further reading_"
]
},
{
diff --git a/Introduction-to-Pandas--solution.ipynb b/Introduction-to-Pandas--solution.ipynb
index 56ad4445dd94eaf4473c98eac8961078e8b80ed8..40dcf5483accfd8b596db07758484bd9968a01a5 100644
--- a/Introduction-to-Pandas--solution.ipynb
+++ b/Introduction-to-Pandas--solution.ipynb
@@ -44,7 +44,7 @@
"* [Task 5](#task5)\n",
"* [Task 6](#task6)\n",
"* [Task 7](#task7)\n",
- "* [Bonus Task](#taskb)"
+ "* [Task 7B](#task7b)"
]
},
{
@@ -72,7 +72,7 @@
"source": [
"## Task 1\n",
"<a name=\"task1\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Create data frame with\n",
" - 6 names of dinosaurs, \n",
@@ -100,7 +100,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 25,
"metadata": {
"exercise": "task",
"slideshow": {
@@ -119,7 +119,7 @@
},
{
"cell_type": "code",
- "execution_count": 22,
+ "execution_count": 26,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -189,7 +189,7 @@
"Favourite Color violet gray "
]
},
- "execution_count": 22,
+ "execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
@@ -215,7 +215,7 @@
"source": [
"## Task 2\n",
"<a name=\"task2\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Read in `data-nest.csv` to `DataFrame`; call it `df` \n",
" *(Data was produced with [JUBE](http://www.fz-juelich.de/ias/jsc/EN/Expertise/Support/Software/JUBE/_node.html))*\n",
@@ -225,7 +225,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 33,
"metadata": {
"exercise": "task"
},
@@ -241,12 +241,12 @@
}
],
"source": [
- "!cat nest-data.csv | head -3"
+ "!cat data-nest.csv | head -3"
]
},
{
"cell_type": "code",
- "execution_count": 118,
+ "execution_count": 34,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -470,7 +470,7 @@
"[5 rows x 21 columns]"
]
},
- "execution_count": 118,
+ "execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
@@ -491,7 +491,7 @@
"source": [
"## Task 3\n",
"<a name=\"task3\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Add a column to the Nest data frame form Task 2 called `Threads` which is the total number of threads across all nodes (i.e. the product of threads per task and tasks per node and nodes)\n",
"* Tell me when you're done with status icon in BigBlueButton: \ud83d\udc4d"
@@ -499,7 +499,7 @@
},
{
"cell_type": "code",
- "execution_count": 59,
+ "execution_count": 62,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -716,7 +716,7 @@
"[5 rows x 22 columns]"
]
},
- "execution_count": 59,
+ "execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
@@ -728,7 +728,7 @@
},
{
"cell_type": "code",
- "execution_count": 60,
+ "execution_count": 63,
"metadata": {
"exercise": "solution"
},
@@ -746,7 +746,7 @@
" dtype='object')"
]
},
- "execution_count": 60,
+ "execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
@@ -757,7 +757,7 @@
},
{
"cell_type": "code",
- "execution_count": 61,
+ "execution_count": 64,
"metadata": {
"exercise": "task",
"slideshow": {
@@ -781,10 +781,10 @@
"source": [
"## Task 4\n",
"<a name=\"task4\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"\n",
- "* Sort the data frame by threads\n",
+ "* Sort the Nest data frame by threads\n",
"* Plot `\"Presim. Time / s\"` and `\"Sim. Time / s\"` of our data frame `df` as a function of threads\n",
"* Use a dashed, red line for `\"Presim. Time / s\"`, a blue line for `\"Sim. Time / s\"` (see [API description](https://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.plot))\n",
"* Don't forget to label your axes and to add a legend _(1st rule of plotting)_\n",
@@ -793,7 +793,7 @@
},
{
"cell_type": "code",
- "execution_count": 67,
+ "execution_count": 70,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -802,12 +802,12 @@
},
"outputs": [],
"source": [
- "df.sort_values([\"Threads\", \"Nodes\", \"Tasks/Node\", \"Threads/Task\"], inplace=True)"
+ "df.sort_values([\"Threads\", \"Nodes\", \"Tasks/Node\", \"Threads/Task\"], inplace=True) # multi-level sort"
]
},
{
"cell_type": "code",
- "execution_count": 68,
+ "execution_count": 71,
"metadata": {
"exercise": "solution"
},
@@ -845,11 +845,11 @@
"source": [
"## Task 5\n",
"<a name=\"task5\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "Use the NEST data frame `df` to:\n",
+ "Use the Nest data frame `df` to:\n",
"\n",
- "1. Make the threads the index of the data frame (`.set_index()`)\n",
+ "1. Make threads index of the data frame (`.set_index()`)\n",
"2. Plot `\"Presim. Program / s\"` and `\"Sim. Time / s`\" individually\n",
"3. Plot them onto one common canvas!\n",
"4. Make them have the same line colors and styles as before\n",
@@ -859,7 +859,7 @@
},
{
"cell_type": "code",
- "execution_count": 74,
+ "execution_count": 77,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -873,7 +873,7 @@
},
{
"cell_type": "code",
- "execution_count": 75,
+ "execution_count": 78,
"metadata": {
"exercise": "solution"
},
@@ -897,7 +897,7 @@
},
{
"cell_type": "code",
- "execution_count": 76,
+ "execution_count": 79,
"metadata": {
"exercise": "solution"
},
@@ -921,7 +921,7 @@
},
{
"cell_type": "code",
- "execution_count": 77,
+ "execution_count": 80,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -949,7 +949,7 @@
},
{
"cell_type": "code",
- "execution_count": 78,
+ "execution_count": 81,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -986,9 +986,9 @@
"source": [
"## Task 6\n",
"<a name=\"task6\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "* To your `df` NEST data frame, add a column with the unaccounted time (`Unaccounted Time / s`), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time. \n",
+ "* To your `df` Nest data frame, add a column with the unaccounted time (`Unaccounted Time / s`), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time. \n",
"(*I know this is technically not super correct, but it will do for our example.*)\n",
"* Plot a stacked bar plot of all these columns (except for program runtime) over the threads\n",
"* Tell me when you're done with status icon in BigBlueButton: \ud83d\udc4d"
@@ -1154,9 +1154,9 @@
"source": [
"## Task 7\n",
"<a name=\"task7\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "* Create a pivot table based on the NEST `df` data frame\n",
+ "* Create a pivot table based on the Nest `df` data frame\n",
"* Let the `x` axis show the number of nodes; display the values of the simulation time `\"Sim. Time / s\"` for the tasks per node and threads per task configurations\n",
"* Please plot a bar plot\n",
"* Tell me when you're done with status icon in BigBlueButton: \ud83d\udc4d"
@@ -1164,7 +1164,7 @@
},
{
"cell_type": "code",
- "execution_count": 116,
+ "execution_count": 111,
"metadata": {
"exercise": "solution",
"slideshow": {
@@ -1196,16 +1196,24 @@
"metadata": {
"exercise": "task",
"slideshow": {
- "slide_type": "fragment"
- }
+ "slide_type": "subslide"
+ },
+ "tags": []
},
"source": [
- "<a name=\"taskb\"></a>\n",
+ "## Task 7B (like <em>B</em>onus)\n",
+ "<a name=\"task7b\"></a>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "\n",
+ "- Same pivot table as before (that is, `x` with nodes, and columns for Tasks/Node and Threads/Task)\n",
+ "- But now, use `Sim. Time / s` and `Presim. Time / s` as values to show\n",
+ "- Show them as a **stack** of those two values inside the pivot table\n",
+ "- Use Panda's functionality as much as possible!\n",
+ "\n",
+ "Impossible?\n",
"\n",
- "* Bonus task\n",
- " - Same pivot table as before (that is, `x` with nodes, and columns for Tasks/Node and Threads/Task)\n",
- " - But now, use `Sim. Time / s` and `Presim. Time / s` as values to show\n",
- " - Show them as a stack of those two values inside the pivot table"
+ "* I gave up!\n",
+ "* Person who does this best / first: Personal certificate with my recommendation \ud83d\ude04"
]
},
{
@@ -1216,7 +1224,7 @@
"source": [
"<span class=\"feedback\">Feedback to <a href=\"mailto:a.herten@fz-juelich.de\">a.herten@fz-juelich.de</a></span>\n",
"\n",
- "Next slide: Further reading"
+ "_Next slide: Further reading_"
]
}
],
diff --git a/Introduction-to-Pandas--tasks.ipynb b/Introduction-to-Pandas--tasks.ipynb
index 344b85f70398391fc38ea9813a5aa046b275ff8b..4cb524efe1e3f38f219ccbdc11763c217637032a 100644
--- a/Introduction-to-Pandas--tasks.ipynb
+++ b/Introduction-to-Pandas--tasks.ipynb
@@ -44,7 +44,7 @@
"* [Task 5](#task5)\n",
"* [Task 6](#task6)\n",
"* [Task 7](#task7)\n",
- "* [Bonus Task](#taskb)"
+ "* [Task 7B](#task7b)"
]
},
{
@@ -72,7 +72,7 @@
"source": [
"## Task 1\n",
"<a name=\"task1\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Create data frame with\n",
" - 6 names of dinosaurs, \n",
@@ -100,7 +100,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 25,
"metadata": {
"exercise": "task",
"slideshow": {
@@ -128,7 +128,7 @@
"source": [
"## Task 2\n",
"<a name=\"task2\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Read in `data-nest.csv` to `DataFrame`; call it `df` \n",
" *(Data was produced with [JUBE](http://www.fz-juelich.de/ias/jsc/EN/Expertise/Support/Software/JUBE/_node.html))*\n",
@@ -138,7 +138,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 33,
"metadata": {
"exercise": "task"
},
@@ -154,7 +154,7 @@
}
],
"source": [
- "!cat nest-data.csv | head -3"
+ "!cat data-nest.csv | head -3"
]
},
{
@@ -168,7 +168,7 @@
"source": [
"## Task 3\n",
"<a name=\"task3\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"* Add a column to the Nest data frame form Task 2 called `Threads` which is the total number of threads across all nodes (i.e. the product of threads per task and tasks per node and nodes)\n",
"* Tell me when you're done with status icon in BigBlueButton: \ud83d\udc4d"
@@ -176,7 +176,7 @@
},
{
"cell_type": "code",
- "execution_count": 61,
+ "execution_count": 64,
"metadata": {
"exercise": "task",
"slideshow": {
@@ -200,10 +200,10 @@
"source": [
"## Task 4\n",
"<a name=\"task4\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
"\n",
- "* Sort the data frame by threads\n",
+ "* Sort the Nest data frame by threads\n",
"* Plot `\"Presim. Time / s\"` and `\"Sim. Time / s\"` of our data frame `df` as a function of threads\n",
"* Use a dashed, red line for `\"Presim. Time / s\"`, a blue line for `\"Sim. Time / s\"` (see [API description](https://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.plot))\n",
"* Don't forget to label your axes and to add a legend _(1st rule of plotting)_\n",
@@ -221,11 +221,11 @@
"source": [
"## Task 5\n",
"<a name=\"task5\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "Use the NEST data frame `df` to:\n",
+ "Use the Nest data frame `df` to:\n",
"\n",
- "1. Make the threads the index of the data frame (`.set_index()`)\n",
+ "1. Make threads index of the data frame (`.set_index()`)\n",
"2. Plot `\"Presim. Program / s\"` and `\"Sim. Time / s`\" individually\n",
"3. Plot them onto one common canvas!\n",
"4. Make them have the same line colors and styles as before\n",
@@ -244,9 +244,9 @@
"source": [
"## Task 6\n",
"<a name=\"task6\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "* To your `df` NEST data frame, add a column with the unaccounted time (`Unaccounted Time / s`), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time. \n",
+ "* To your `df` Nest data frame, add a column with the unaccounted time (`Unaccounted Time / s`), which is the difference of program runtime, average neuron build time, minimal edge build time, minimal initialization time, presimulation time, and simulation time. \n",
"(*I know this is technically not super correct, but it will do for our example.*)\n",
"* Plot a stacked bar plot of all these columns (except for program runtime) over the threads\n",
"* Tell me when you're done with status icon in BigBlueButton: \ud83d\udc4d"
@@ -263,9 +263,9 @@
"source": [
"## Task 7\n",
"<a name=\"task7\"></a>\n",
- "<span style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
"\n",
- "* Create a pivot table based on the NEST `df` data frame\n",
+ "* Create a pivot table based on the Nest `df` data frame\n",
"* Let the `x` axis show the number of nodes; display the values of the simulation time `\"Sim. Time / s\"` for the tasks per node and threads per task configurations\n",
"* Please plot a bar plot\n",
"* Tell me when you're done with status icon in BigBlueButton: \ud83d\udc4d"
@@ -276,16 +276,24 @@
"metadata": {
"exercise": "task",
"slideshow": {
- "slide_type": "fragment"
- }
+ "slide_type": "subslide"
+ },
+ "tags": []
},
"source": [
- "<a name=\"taskb\"></a>\n",
+ "## Task 7B (like <em>B</em>onus)\n",
+ "<a name=\"task7b\"></a>\n",
+ "<span class=\"task\" style=\"padding: 2px 8px; color: white; background-color: #b9d25f; float: right; text-weight: bolder;\">TASK</em></span>\n",
+ "\n",
+ "- Same pivot table as before (that is, `x` with nodes, and columns for Tasks/Node and Threads/Task)\n",
+ "- But now, use `Sim. Time / s` and `Presim. Time / s` as values to show\n",
+ "- Show them as a **stack** of those two values inside the pivot table\n",
+ "- Use Panda's functionality as much as possible!\n",
+ "\n",
+ "Impossible?\n",
"\n",
- "* Bonus task\n",
- " - Same pivot table as before (that is, `x` with nodes, and columns for Tasks/Node and Threads/Task)\n",
- " - But now, use `Sim. Time / s` and `Presim. Time / s` as values to show\n",
- " - Show them as a stack of those two values inside the pivot table"
+ "* I gave up!\n",
+ "* Person who does this best / first: Personal certificate with my recommendation \ud83d\ude04"
]
},
{
@@ -296,7 +304,7 @@
"source": [
"<span class=\"feedback\">Feedback to <a href=\"mailto:a.herten@fz-juelich.de\">a.herten@fz-juelich.de</a></span>\n",
"\n",
- "Next slide: Further reading"
+ "_Next slide: Further reading_"
]
}
],
diff --git a/static-slides-bundle.tar.gz b/static-slides-bundle.tar.gz
index 46644d766f9fb9de6e14523c213acc73c69a37fb..f3a7ec5f46b469894608bba0c447e4f0cf5b585b 100644
Binary files a/static-slides-bundle.tar.gz and b/static-slides-bundle.tar.gz differ