[refactor] improve test coverage for observations

spatio_temporal_dataset/spatio_temporal_observations/abstract_spatio_temporal_observations.py

@@ -19,6 +19,12 @@ class AbstractSpatioTemporalObservations(object):
         Main attribute of the class is the DataFrame df_maxima
         Index are coordinates index
         Columns are independent observations from the same coordinates index
+
+        For example, if we have spatial coordinates,
+        then all the columns might correspond to annual maxima observations for different years
+
+        If we have a spatio-temporal coordinates,
+        then all the columns might correspond to observations that were made at some spatial coodinate, and for some given year
         """
         assert df_maxima_gev is not None or df_maxima_frech is not None
         assert isinstance(df_maxima_gev, pd.DataFrame) or isinstance(df_maxima_frech, pd.DataFrame)
@@ -27,13 +33,6 @@ class AbstractSpatioTemporalObservations(object):
         self.df_maxima_gev = df_maxima_gev  # type: pd.DataFrame
         self.df_maxima_frech = df_maxima_frech  # type: pd.DataFrame
 
-    @classmethod
-    def from_csv(cls, csv_path: str = None):
-        assert csv_path is not None
-        assert op.exists(csv_path)
-        df = pd.read_csv(csv_path, index_col=0)
-        return cls.from_df(df)
-
     @property
     def _df_maxima(self) -> pd.DataFrame:
         if self.df_maxima_frech is not None:
@@ -70,22 +69,6 @@ class AbstractSpatioTemporalObservations(object):
     def nb_obs(self) -> int:
         return len(self.columns)
 
-    @classmethod
-    def from_df(cls, df):
-        df_maxima_list = []
-        for suffix in [cls.OBSERVATIONS_GEV, cls.OBSERVATIONS_FRECH]:
-            columns_with_suffix = [c for c in df.columns if str(c).endswith(suffix)]
-            if columns_with_suffix:
-                df_maxima = df[columns_with_suffix] if columns_with_suffix else None
-                df_maxima.columns = [c.replace(' ' + suffix, '') for c in df_maxima.columns]
-            else:
-                df_maxima = None
-            df_maxima_list.append(df_maxima)
-        df_maxima_gev, df_maxima_frech = df_maxima_list
-        if df_maxima_gev is not None and df_maxima_frech is not None:
-            assert pd.Index.equals(df_maxima_gev.columns, df_maxima_frech.columns)
-        return cls(df_maxima_gev=df_maxima_gev, df_maxima_frech=df_maxima_frech)
-
     def convert_to_spatio_temporal_index(self, coordinates: AbstractCoordinates):
         assert coordinates.has_spatio_temporal_coordinates
         assert len(coordinates.index) == len(self.index) * self.nb_obs
@@ -130,9 +113,6 @@ class AbstractSpatioTemporalObservations(object):
     def __str__(self) -> str:
         return self._df_maxima.__str__()
 
-    def __len__(self):
-        return self._df_maxima.__len__()
-
     def print_summary(self):
         # Write a summary of observations
         df = self.df_maxima_gev

spatio_temporal_dataset/spatio_temporal_observations/alps_precipitation_observations.py

-import os.path as op
-
-from spatio_temporal_dataset.spatio_temporal_observations.abstract_spatio_temporal_observations import \
-    AbstractSpatioTemporalObservations
-from root_utils import get_full_path
-
-
-class AlpsPrecipitationObservations(AbstractSpatioTemporalObservations):
-    RELATIVE_PATH = r'local/spatio_temporal_datasets/Gilles  - precipitations'
-    FULL_PATH = get_full_path(relative_path=RELATIVE_PATH)
-
-    @classmethod
-    def from_csv(cls, csv_file='max_precip_3j'):
-        csv_path = op.join(cls.FULL_PATH, csv_file + '.csv')
-        return super().from_csv(csv_path)
-
-    @classmethod
-    def transform_gilles_txt_into_csv(cls):
-        filepath = op.join(cls.FULL_PATH, 'original data', 'max_precip_3j.txt')
-        station_to_coordinates = {}
-        # todo: be absolutely sure of the mapping, in the txt file of Gilles we do not have the coordinate
-        # this seems rather dangerous, especially if he loaded
-        # todo: re-do the whole analysis, and extraction myself about the snow
-        with open(filepath, 'r') as f:
-            for l in f:
-                _, station_name, coordinates = l.split('"')
-                coordinates = coordinates.split()
-                print(len(coordinates))
-                assert len(coordinates) == 55
-                station_to_coordinates[station_name] = coordinates
-        # df = pd.DataFrame.from_dict(data=station_to_coordinates, orient='index',
-        #                             columns=[cls.COORDINATE_X, cls.COORDINATE_Y, cls.COORDINATE_Z])
-        # print(df.head())
-        # filepath = op.join(cls.FULL_PATH, 'max_precip_3j.csv')
-        # assert not op.exists(filepath)
-        # df.to_csv(filepath)