Resolve "release v1.2.0"

Closes #257 (closed)

mlair/run_modules/pre_processing.py

@@ -113,9 +113,47 @@ class PreProcessing(RunEnvironment):
         precision = 4
         path = os.path.join(self.data_store.get("experiment_path"), "latex_report")
         path_config.check_path_and_create(path)
-        set_names = ["train", "val", "test"]
-        df = pd.DataFrame(columns=meta_data + set_names)
-        for set_name in set_names:
+        names_of_set = ["train", "val", "test"]
+        df = self.create_info_df(meta_data, meta_round, names_of_set, precision)
+        column_format = self.create_column_format_for_tex(df)
+        self.save_to_tex(path=path, filename="station_sample_size.tex", column_format=column_format, df=df)
+        self.save_to_md(path=path, filename="station_sample_size.md", df=df)
+        df_nometa = df.drop(meta_data, axis=1)
+        self.save_to_tex(path=path, filename="station_sample_size_short.tex", column_format=column_format, df=df_nometa)
+        self.save_to_md(path=path, filename="station_sample_size_short.md", df=df_nometa)
+        # df_nometa.to_latex(os.path.join(path, "station_sample_size_short.tex"), na_rep='---',
+        #                    column_format=column_format)
+        df_descr = self.create_describe_df(df_nometa)
+        column_format = self.create_column_format_for_tex(df_descr)
+        self.save_to_tex(path=path, filename="station_describe_short.tex", column_format=column_format, df=df_descr)
+        self.save_to_md(path=path, filename="station_describe_short.md", df=df_descr)
+        # df_descr.to_latex(os.path.join(path, "station_describe_short.tex"), na_rep='---', column_format=column_format)
+
+    @staticmethod
+    def create_describe_df(df, percentiles=None, ignore_last_lines: int = 2):
+        if percentiles is None:
+            percentiles = [.05, .1, .25, .5, .75, .9, .95]
+        df_descr = df.iloc[:-ignore_last_lines].astype('float32').describe(
+            percentiles=percentiles).astype('int32')
+        df_descr = pd.concat([df.loc[['# Samples']], df_descr]).T
+        df_descr.rename(columns={"# Samples": "no. samples", "count": "no. stations"}, inplace=True)
+        df_descr_colnames = list(df_descr.columns)
+        df_descr_colnames = [df_descr_colnames[1]] + [df_descr_colnames[0]] + df_descr_colnames[2:]
+        df_descr = df_descr[df_descr_colnames]
+        return df_descr
+
+    @staticmethod
+    def save_to_tex(path, filename, column_format, df, na_rep='---'):
+        df.to_latex(os.path.join(path, filename), na_rep=na_rep, column_format=column_format)
+
+    @staticmethod
+    def save_to_md(path, filename, df, mode="w", encoding='utf-8', tablefmt="github"):
+        df.to_markdown(open(os.path.join(path, filename), mode=mode, encoding=encoding),
+                       tablefmt=tablefmt)
+
+    def create_info_df(self, meta_data, meta_round, names_of_set, precision):
+        df = pd.DataFrame(columns=meta_data + names_of_set)
+        for set_name in names_of_set:
             data = self.data_store.get("data_collection", set_name)
             for station in data:
                 station_name = str(station.id_class)
@@ -128,22 +166,7 @@ class PreProcessing(RunEnvironment):
         df.sort_index(inplace=True)
         df = df.reindex(df.index.drop(["# Stations", "# Samples"]).to_list() + ["# Stations", "# Samples"], )
         df.index.name = 'stat. ID'
-        column_format = self.create_column_format_for_tex(df)
-        df.to_latex(os.path.join(path, "station_sample_size.tex"), na_rep='---', column_format=column_format)
-        df.to_markdown(open(os.path.join(path, "station_sample_size.md"), mode="w", encoding='utf-8'), tablefmt="github")
-        df_nometa = df.drop(meta_data, axis=1)
-        df_nometa.to_latex(os.path.join(path, "station_sample_size_short.tex"), na_rep='---',
-                           column_format=column_format)
-        df_descr = df_nometa.iloc[:-2].astype('float32').describe(
-            percentiles=[.05, .1, .25, .5, .75, .9, .95]).astype('int32')
-        df_descr = pd.concat([df_nometa.loc[['# Samples']], df_descr]).T
-        df_descr.rename(columns={"# Samples": "no. samples", "count": "no. stations"}, inplace=True)
-        df_descr_colnames = list(df_descr.columns)
-        df_descr_colnames = [df_descr_colnames[1]] + [df_descr_colnames[0]] + df_descr_colnames[2:]
-        df_descr = df_descr[df_descr_colnames]
-        column_format = self.create_column_format_for_tex(df_descr)
-        df_descr.to_latex(os.path.join(path, "station_describe_short.tex"), na_rep='---', column_format=column_format)
-
+        return df
 
     @staticmethod
     def create_column_format_for_tex(df: pd.DataFrame) -> str: