diff --git a/src/plotting/postprocessing_plotting.py b/src/plotting/postprocessing_plotting.py
index 8efd54bb23035eed4cf51e94235bf8de7ff2a481..3902bacc2d6f62c3dcdf821f13d93c7048a54b1a 100644
--- a/src/plotting/postprocessing_plotting.py
+++ b/src/plotting/postprocessing_plotting.py
@@ -70,8 +70,9 @@ class AbstractPlotClass:
INFO: MyCustomPlot finished after 00:00:11 (hh:mm:ss)
"""
+
def __init__(self, plot_folder, plot_name, resolution=500):
- """Set up plot folder and name, and plot resolution (default 500dpi)"""
+ """Set up plot folder and name, and plot resolution (default 500dpi)."""
self.plot_folder = plot_folder
self.plot_name = plot_name
self.resolution = resolution
@@ -81,7 +82,7 @@ class AbstractPlotClass:
raise NotImplementedError
def _save(self, **kwargs):
- """Standard save method to store plot locally. Name of and path to plot need to be set on initialisation."""
+ """Store plot locally. Name of and path to plot need to be set on initialisation."""
plot_name = os.path.join(os.path.abspath(self.plot_folder), f"{self.plot_name}.pdf")
logging.debug(f"... save plot to {plot_name}")
plt.savefig(plot_name, dpi=self.resolution, **kwargs)
@@ -91,27 +92,26 @@ class AbstractPlotClass:
@TimeTrackingWrapper
class PlotMonthlySummary(AbstractPlotClass):
"""
- Show a monthly summary over all stations for each lead time ("ahead") as box and whiskers plot. The plot is saved
- in data_path with name monthly_summary_box_plot.pdf and 500dpi resolution.
+ Show a monthly summary over all stations for each lead time ("ahead") as box and whiskers plot.
+
+ The plot is saved in data_path with name monthly_summary_box_plot.pdf and 500dpi resolution.
.. image:: ../../../../../_source/_plots/monthly_summary_box_plot.png
:width: 400
+ :param stations: all stations to plot
+ :param data_path: path, where the data is located
+ :param name: full name of the local files with a % as placeholder for the station name
+ :param target_var: display name of the target variable on plot's axis
+ :param window_lead_time: lead time to plot, if window_lead_time is higher than the available lead time or not given
+ the maximum lead time from data is used. (default None -> use maximum lead time from data).
+ :param plot_folder: path to save the plot (default: current directory)
+
"""
def __init__(self, stations: List, data_path: str, name: str, target_var: str, window_lead_time: int = None,
plot_folder: str = "."):
- """
- Sets attributes and create plot
-
- :param stations: all stations to plot
- :param data_path: path, where the data is located
- :param name: full name of the local files with a % as placeholder for the station name
- :param target_var: display name of the target variable on plot's axis
- :param window_lead_time: lead time to plot, if window_lead_time is higher than the available lead time or not given
- the maximum lead time from data is used. (default None -> use maximum lead time from data).
- :param plot_folder: path to save the plot (default: current directory)
- """
+ """Set attributes and create plot."""
super().__init__(plot_folder, "monthly_summary_box_plot")
self._data_path = data_path
self._data_name = name
@@ -122,8 +122,10 @@ class PlotMonthlySummary(AbstractPlotClass):
def _prepare_data(self, stations: List) -> xr.DataArray:
"""
- Pre-process data required to plot. For each station, load locally saved predictions, extract the CNN prediction
- and the observation and group them into monthly bins (no aggregation, only sorting them).
+ Pre.process data required to plot.
+
+ For each station, load locally saved predictions, extract the CNN prediction and the observation and group them
+ into monthly bins (no aggregation, only sorting them).
:param stations: all stations to plot
:return: The entire data set, flagged with the corresponding month.
@@ -152,9 +154,11 @@ class PlotMonthlySummary(AbstractPlotClass):
def _get_window_lead_time(self, window_lead_time: int):
"""
- Extract the lead time from data and arguments. If window_lead_time is not given, extract this information from
- data itself by the number of ahead dimensions. If given, check if data supports the give length. If the number
- of ahead dimensions in data is lower than the given lead time, data's lead time is used.
+ Extract the lead time from data and arguments.
+
+ If window_lead_time is not given, extract this information from data itself by the number of ahead dimensions.
+ If given, check if data supports the give length. If the number of ahead dimensions in data is lower than the
+ given lead time, data's lead time is used.
:param window_lead_time: lead time from arguments to validate
:return: validated lead time, comes either from given argument or from data itself
@@ -166,8 +170,7 @@ class PlotMonthlySummary(AbstractPlotClass):
def _plot(self, target_var: str):
"""
- Main plot function that creates a monthly grouped box plot over all stations but with separate boxes for each
- lead time step.
+ Create a monthly grouped box plot over all stations but with separate boxes for each lead time step.
:param target_var: display name of the target variable on plot's axis
"""
@@ -185,10 +188,11 @@ class PlotMonthlySummary(AbstractPlotClass):
@TimeTrackingWrapper
class PlotStationMap(AbstractPlotClass):
"""
- Plot geographical overview of all used stations as squares. Different data sets can be colorised by its key in the
- input dictionary generators. The key represents the color to plot on the map. Currently, there is only a white
- background, but this can be adjusted by loading locally stored topography data (not implemented yet). The plot is
- saved under plot_path with the name station_map.pdf
+ Plot geographical overview of all used stations as squares.
+
+ Different data sets can be colorised by its key in the input dictionary generators. The key represents the color to
+ plot on the map. Currently, there is only a white background, but this can be adjusted by loading locally stored
+ topography data (not implemented yet). The plot is saved under plot_path with the name station_map.pdf
.. image:: ../../../../../_source/_plots/station_map.png
:width: 400
@@ -196,7 +200,7 @@ class PlotStationMap(AbstractPlotClass):
def __init__(self, generators: Dict, plot_folder: str = "."):
"""
- Sets attributes and create plot
+ Set attributes and create plot.
:param generators: dictionary with the plot color of each data set as key and the generator containing all stations
as value.
@@ -208,9 +212,7 @@ class PlotStationMap(AbstractPlotClass):
self._save()
def _draw_background(self):
- """
- Draw coastline, lakes, ocean, rivers and country borders as background on the map.
- """
+ """Draw coastline, lakes, ocean, rivers and country borders as background on the map."""
self._ax.add_feature(cfeature.COASTLINE.with_scale("50m"), edgecolor='black')
self._ax.add_feature(cfeature.LAKES.with_scale("50m"))
self._ax.add_feature(cfeature.OCEAN.with_scale("50m"))
@@ -219,8 +221,9 @@ class PlotStationMap(AbstractPlotClass):
def _plot_stations(self, generators):
"""
- The actual plot function. Loops over all keys in generators dict and its containing stations and plots a square
- and the stations's position on the map regarding the given color.
+ Loop over all keys in generators dict and its containing stations and plot the stations's position.
+
+ Position is highlighted by a square on the map regarding the given color.
:param generators: dictionary with the plot color of each data set as key and the generator containing all
stations as value.
@@ -236,7 +239,9 @@ class PlotStationMap(AbstractPlotClass):
def _plot(self, generators: Dict):
"""
- Main plot function to create the station map plot. Sets figure and calls all required sub-methods.
+ Create the station map plot.
+
+ Set figure and call all required sub-methods.
:param generators: dictionary with the plot color of each data set as key and the generator containing all
stations as value.
@@ -387,11 +392,12 @@ def plot_conditional_quantiles(stations: list, plot_folder: str = ".", rolling_w
@TimeTrackingWrapper
class PlotClimatologicalSkillScore(AbstractPlotClass):
"""
- Create plot of climatological skill score after Murphy (1988) as box plot over all stations. A forecast time step
- (called "ahead") is separately shown to highlight the differences for each prediction time step. Either each single
- term is plotted (score_only=False) or only the resulting scores CASE I to IV are displayed (score_only=True,
- default). Y-axis is adjusted following the data and not hard coded. The plot is saved under plot_folder path with
- name skill_score_clim_{extra_name_tag}{model_setup}.pdf and resolution of 500dpi.
+ Create plot of climatological skill score after Murphy (1988) as box plot over all stations.
+
+ A forecast time step (called "ahead") is separately shown to highlight the differences for each prediction time
+ step. Either each single term is plotted (score_only=False) or only the resulting scores CASE I to IV are displayed
+ (score_only=True, default). Y-axis is adjusted following the data and not hard coded. The plot is saved under
+ plot_folder path with name skill_score_clim_{extra_name_tag}{model_setup}.pdf and resolution of 500dpi.
.. image:: ../../../../../_source/_plots/skill_score_clim_all_terms_CNN.png
:width: 400
@@ -399,19 +405,17 @@ class PlotClimatologicalSkillScore(AbstractPlotClass):
.. image:: ../../../../../_source/_plots/skill_score_clim_CNN.png
:width: 400
+ :param data: dictionary with station names as keys and 2D xarrays as values, consist on axis ahead and terms.
+ :param plot_folder: path to save the plot (default: current directory)
+ :param score_only: if true plot only scores of CASE I to IV, otherwise plot all single terms (default True)
+ :param extra_name_tag: additional tag that can be included in the plot name (default "")
+ :param model_setup: architecture type to specify plot name (default "CNN")
+
"""
def __init__(self, data: Dict, plot_folder: str = ".", score_only: bool = True, extra_name_tag: str = "",
model_setup: str = ""):
- """
- Sets attributes and create plot
-
- :param data: dictionary with station names as keys and 2D xarrays as values, consist on axis ahead and terms.
- :param plot_folder: path to save the plot (default: current directory)
- :param score_only: if true plot only scores of CASE I to IV, otherwise plot all single terms (default True)
- :param extra_name_tag: additional tag that can be included in the plot name (default "")
- :param model_setup: architecture type to specify plot name (default "CNN")
- """
+ """Initialise."""
super().__init__(plot_folder, f"skill_score_clim_{extra_name_tag}{model_setup}")
self._labels = None
self._data = self._prepare_data(data, score_only)
@@ -420,8 +424,10 @@ class PlotClimatologicalSkillScore(AbstractPlotClass):
def _prepare_data(self, data: Dict, score_only: bool) -> pd.DataFrame:
"""
- Shrink given data, if only scores are relevant. In any case, transform data to a plot friendly format. Also set
- plot labels depending on the lead time dimensions.
+ Shrink given data, if only scores are relevant.
+
+ In any case, transform data to a plot friendly format. Also set plot labels depending on the lead time
+ dimensions.
:param data: dictionary with station names as keys and 2D xarrays as values
:param score_only: if true only scores of CASE I to IV are relevant
@@ -435,7 +441,7 @@ class PlotClimatologicalSkillScore(AbstractPlotClass):
def _label_add(self, score_only: bool):
"""
- Adds the phrase "terms and " if score_only is disabled or empty string (if score_only=True).
+ Add the phrase "terms and " if score_only is disabled or empty string (if score_only=True).
:param score_only: if false all terms are relevant, otherwise only CASE I to IV
:return: additional label
@@ -444,7 +450,7 @@ class PlotClimatologicalSkillScore(AbstractPlotClass):
def _plot(self, score_only):
"""
- Main plot function to plot climatological skill score.
+ Plot climatological skill score.
:param score_only: if true plot only scores of CASE I to IV, otherwise plot all single terms
"""
@@ -463,22 +469,24 @@ class PlotClimatologicalSkillScore(AbstractPlotClass):
@TimeTrackingWrapper
class PlotCompetitiveSkillScore(AbstractPlotClass):
"""
- Create competitive skill score for the given model setup and the reference models ordinary least squared ("ols") and
- the persistence forecast ("persi") for all lead times ("ahead"). The plot is saved under plot_folder with the name
+ Create competitive skill score plot.
+
+ Create this plot for the given model setup and the reference models ordinary least squared ("ols") and the
+ persistence forecast ("persi") for all lead times ("ahead"). The plot is saved under plot_folder with the name
skill_score_competitive_{model_setup}.pdf and resolution of 500dpi.
.. image:: ../../../../../_source/_plots/skill_score_competitive.png
:width: 400
+ :param data: data frame with index=['cnn-persi', 'ols-persi', 'cnn-ols'] and columns "ahead" containing the pre-
+ calculated comparisons for cnn, persistence and ols.
+ :param plot_folder: path to save the plot (default: current directory)
+ :param model_setup: architecture type (default "CNN")
+
"""
def __init__(self, data: pd.DataFrame, plot_folder=".", model_setup="CNN"):
- """
- :param data: data frame with index=['cnn-persi', 'ols-persi', 'cnn-ols'] and columns "ahead" containing the pre-
- calculated comparisons for cnn, persistence and ols.
- :param plot_folder: path to save the plot (default: current directory)
- :param model_setup: architecture type (default "CNN")
- """
+ """Initialise."""
super().__init__(plot_folder, f"skill_score_competitive_{model_setup}")
self._labels = None
self._data = self._prepare_data(data)
@@ -487,7 +495,7 @@ class PlotCompetitiveSkillScore(AbstractPlotClass):
def _prepare_data(self, data: pd.DataFrame) -> pd.DataFrame:
"""
- Reformat given data and create plot labels. Introduces the dimensions stations and comparison
+ Reformat given data and create plot labels and introduce the dimensions stations and comparison.
:param data: data frame with index=['cnn-persi', 'ols-persi', 'cnn-ols'] and columns "ahead" containing the pre-
calculated comparisons for cnn, persistence and ols.
@@ -502,9 +510,7 @@ class PlotCompetitiveSkillScore(AbstractPlotClass):
return data.stack(level=0).reset_index(level=2, drop=True).reset_index(name="data")
def _plot(self):
- """
- Main plot function to plot skill scores of the comparisons cnn-persi, ols-persi and cnn-ols.
- """
+ """Plot skill scores of the comparisons cnn-persi, ols-persi and cnn-ols."""
fig, ax = plt.subplots()
sns.boxplot(x="comparison", y="data", hue="ahead", data=self._data, whis=1., ax=ax, palette="Blues_d",
showmeans=True, meanprops={"markersize": 3, "markeredgecolor": "k"}, flierprops={"marker": "."},
@@ -518,8 +524,10 @@ class PlotCompetitiveSkillScore(AbstractPlotClass):
def _ylim(self) -> Tuple[float, float]:
"""
- Calculate y-axis limits from data. Lower is the minimum of either 0 or data's minimum (reduced by small
- subtrahend) and upper limit is data's maximum (increased by a small addend).
+ Calculate y-axis limits from data.
+
+ Lower limit is the minimum of 0 and data's minimum (reduced by small subtrahend) and upper limit is data's
+ maximum (increased by a small addend).
:return:
"""
@@ -531,11 +539,12 @@ class PlotCompetitiveSkillScore(AbstractPlotClass):
@TimeTrackingWrapper
class PlotBootstrapSkillScore(AbstractPlotClass):
"""
- Create plot of climatological skill score after Murphy (1988) as box plot over all stations. A forecast time step
- (called "ahead") is separately shown to highlight the differences for each prediction time step. Either each single
- term is plotted (score_only=False) or only the resulting scores CASE I to IV are displayed (score_only=True,
- default). Y-axis is adjusted following the data and not hard coded. The plot is saved under plot_folder path with
- name skill_score_clim_{extra_name_tag}{model_setup}.pdf and resolution of 500dpi.
+ Create plot of climatological skill score after Murphy (1988) as box plot over all stations.
+
+ A forecast time step (called "ahead") is separately shown to highlight the differences for each prediction time
+ step. Either each single term is plotted (score_only=False) or only the resulting scores CASE I to IV are displayed
+ (score_only=True, default). Y-axis is adjusted following the data and not hard coded. The plot is saved under
+ plot_folder path with name skill_score_clim_{extra_name_tag}{model_setup}.pdf and resolution of 500dpi.
.. image:: ../../../../../_source/_plots/skill_score_bootstrap.png
:width: 400
@@ -544,7 +553,7 @@ class PlotBootstrapSkillScore(AbstractPlotClass):
def __init__(self, data: Dict, plot_folder: str = ".", model_setup: str = ""):
"""
- Sets attributes and create plot
+ Set attributes and create plot.
:param data: dictionary with station names as keys and 2D xarrays as values, consist on axis ahead and terms.
:param plot_folder: path to save the plot (default: current directory)
@@ -559,8 +568,10 @@ class PlotBootstrapSkillScore(AbstractPlotClass):
def _prepare_data(self, data: Dict) -> pd.DataFrame:
"""
- Shrink given data, if only scores are relevant. In any case, transform data to a plot friendly format. Also set
- plot labels depending on the lead time dimensions.
+ Shrink given data, if only scores are relevant.
+
+ In any case, transform data to a plot friendly format. Also set plot labels depending on the lead time
+ dimensions.
:param data: dictionary with station names as keys and 2D xarrays as values
:return: pre-processed data set
@@ -571,7 +582,7 @@ class PlotBootstrapSkillScore(AbstractPlotClass):
def _label_add(self, score_only: bool):
"""
- Adds the phrase "terms and " if score_only is disabled or empty string (if score_only=True).
+ Add the phrase "terms and " if score_only is disabled or empty string (if score_only=True).
:param score_only: if false all terms are relevant, otherwise only CASE I to IV
:return: additional label
@@ -579,9 +590,7 @@ class PlotBootstrapSkillScore(AbstractPlotClass):
return "" if score_only else "terms and "
def _plot(self):
- """
- Main plot function to plot climatological skill score.
- """
+ """Plot climatological skill score."""
fig, ax = plt.subplots()
sns.boxplot(x=self._x_name, y="data", hue="ahead", data=self._data, ax=ax, whis=1., palette="Blues_d",
showmeans=True, meanprops={"markersize": 1, "markeredgecolor": "k"}, flierprops={"marker": "."})
@@ -594,9 +603,15 @@ class PlotBootstrapSkillScore(AbstractPlotClass):
@TimeTrackingWrapper
class PlotTimeSeries:
+ """
+ Create time series plot.
+
+ Currently, plots are under development and not well designed for any use in public.
+ """
def __init__(self, stations: List, data_path: str, name: str, window_lead_time: int = None, plot_folder: str = ".",
sampling="daily"):
+ """Initialise."""
self._data_path = data_path
self._data_name = name
self._stations = stations
@@ -613,9 +628,11 @@ class PlotTimeSeries:
def _get_window_lead_time(self, window_lead_time: int):
"""
- Extract the lead time from data and arguments. If window_lead_time is not given, extract this information from
- data itself by the number of ahead dimensions. If given, check if data supports the give length. If the number
- of ahead dimensions in data is lower than the given lead time, data's lead time is used.
+ Extract the lead time from data and arguments.
+
+ If window_lead_time is not given, extract this information from data itself by the number of ahead dimensions.
+ If given, check if data supports the give length. If the number of ahead dimensions in data is lower than the
+ given lead time, data's lead time is used.
:param window_lead_time: lead time from arguments to validate
:return: validated lead time, comes either from given argument or from data itself
@@ -702,9 +719,9 @@ class PlotTimeSeries:
return f(data, min), f(data, max)
@staticmethod
- def _create_pdf_pages(plot_folder):
+ def _create_pdf_pages(plot_folder: str):
"""
- Standard save method to store plot locally. The name of this plot is static.
+ Store plot locally.
:param plot_folder: path to save the plot
"""
@@ -716,6 +733,24 @@ class PlotTimeSeries:
@TimeTrackingWrapper
class PlotAvailability(AbstractPlotClass):
"""
+ Create data availablility plot similar to Gantt plot.
+
+ Each entry of given generator, will result in a new line in the plot. Data is summarised for given temporal
+ resolution and checked whether data is available or not for each time step. This is afterwards highlighted as a
+ colored bar or a blank space.
+
+ You can set different colors to highlight subsets for example by providing different generators for the same index
+ using different keys in the input dictionary.
+
+ Note: each bar is surrounded by a small white box to highlight gabs in between. This can result in too long gabs
+ in display, if a gab is only very short. Also this appears on a (fluent) transition from one to another subset.
+
+ Calling this class will create three versions fo the availability plot.
+
+ 1) Data availability for each element
+ 1) Data availability as summary over all elements (is there at least a single elemnt for each time step)
+ 1) Combination of single and overall availability
+
.. image:: ../../../../../_source/_plots/data_availability.png
:width: 400
@@ -729,6 +764,7 @@ class PlotAvailability(AbstractPlotClass):
def __init__(self, generators: Dict[str, DataGenerator], plot_folder: str = ".", sampling="daily",
summary_name="data availability"):
+ """Initialise."""
# create standard Gantt plot for all stations (currently in single pdf file with single page)
super().__init__(plot_folder, "data_availability")
self.sampling = self._get_sampling(sampling)