Merge branch 'feature/#260-resample-time-series' into features/#276-i…

…mprove-simple-example

edisgo/edisgo.py

@@ -2037,6 +2037,36 @@ def check_integrity(self):
 
             logging.info("Integrity check finished. Please pay attention to warnings.")
 
+    def resample_timeseries(self, method: str = "ffill", freq: str = "15min"):
+        """
+        Returns timeseries resampled from hourly resolution to 15 minute resolution.
+
+        Parameters
+        ----------
+        method : str, optional
+            Method to choose from to fill missing values when upsampling. Possible
+            options are:
+
+            * 'ffill': propagate last valid observation forward to next valid
+            observation. See
+            https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.ffill.html
+            'ffill' is the Default.
+
+            * 'bfill': use next valid observation to fill gap. See
+            https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.bfill.html
+
+            * 'interpolate': Fill NaN values using an interpolation method. See
+            https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.interpolate.html
+
+        freq : str, optional
+            Frequency that timeseries is resampled to. Can be any frequency up to one
+            hour. Offset aliases can be found here:
+            https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases
+            15 minutes is the default.
+
+        """
+        self.timeseries.resample_timeseries(method=method, freq=freq)
+
 
 def import_edisgo_from_pickle(filename, path=""):
     abs_path = os.path.abspath(path)

edisgo/network/timeseries.py

@@ -2145,6 +2145,82 @@ def _check_if_components_exist(
             return set(component_names) - set(comps_not_in_network)
         return component_names
 
+    def resample_timeseries(self, method: str = "ffill", freq: str = "15min"):
+        """
+        Returns timeseries resampled from hourly resolution to 15 minute resolution.
+
+        Parameters
+        ----------
+        method : str, optional
+            Method to choose from to fill missing values when upsampling. Possible
+            options are:
+
+            * 'ffill': propagate last valid observation forward to next valid
+            observation. See
+            https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.ffill.html
+            'ffill' is the Default.
+
+            * 'bfill': use next valid observation to fill gap. See
+            https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.bfill.html
+
+            * 'interpolate': Fill NaN values using an interpolation method. See
+            https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.interpolate.html
+
+        freq : str, optional
+            Frequency that timeseries is resampled to. Can be any frequency up to one
+            hour. Offset aliases can be found here:
+            https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases
+            15 minutes is the default.
+
+        """
+        attrs = self._attributes
+        df_dict = {}
+        for attr in attrs:
+            df_dict[attr] = getattr(self, attr)
+            new_dates = pd.DatetimeIndex(
+                [
+                    df_dict[attr].index[-1] + pd.DateOffset(hours=1)
+                ]  # ToDo: For downsampling the Offset has to be adjusted
+            )
+            df_dict[attr] = (
+                df_dict[attr]
+                .reindex(df_dict[attr].index.union(new_dates).unique().sort_values())
+                .ffill()
+            )
+        index = pd.date_range(
+            self.timeindex[0],
+            self.timeindex[-1] + pd.Timedelta("1h"),
+            freq=freq,
+            closed="left",
+        )
+        self._timeindex = index
+        if pd.Timedelta(index[1] - index[0]) < pd.Timedelta("1h"):
+            if method == "interpolate":
+                for attr in attrs:
+                    setattr(
+                        self,
+                        attr,
+                        df_dict[attr].resample(freq, closed="left").interpolate(),
+                    )
+            elif method == "ffill":
+                for attr in attrs:
+                    setattr(
+                        self, attr, df_dict[attr].resample(freq, closed="left").ffill()
+                    )
+            else:
+                for attr in attrs:
+                    setattr(
+                        self, attr, df_dict[attr].resample(freq, closed="left").bfill()
+                    )
+        else:
+            for attr in attrs:
+                setattr(
+                    self,
+                    attr,
+                    df_dict[attr].resample(freq).mean(),
+                )
+        print(" ")
+
 
 class TimeSeriesRaw:
     """

tests/network/test_timeseries.py

@@ -2310,6 +2310,26 @@ def test_check_if_components_exist(self):
         assert len(component_names) == 1
         assert "Load_residential_LVGrid_5_3" in component_names
 
+    def test_resample_timeseries(self):
+        # add dummy time series
+        timeindex = pd.date_range("1/1/2011", periods=4, freq="H")
+        self.edisgo.set_timeindex(timeindex)
+        # add example data for active power
+        self.edisgo.set_time_series_active_power_predefined(
+            fluctuating_generators_ts="oedb"
+        )
+        len_timeindex_orig = len(self.edisgo.timeseries.timeindex)
+        mean_value_orig = self.edisgo.timeseries.generators_active_power.mean()
+        self.edisgo.timeseries.resample_timeseries()
+        # check if resampled length of time index is 4 times original length of
+        # timeindex
+        assert len(self.edisgo.timeseries.timeindex) == 4 * len_timeindex_orig
+        # check if mean value of resampled data is the same as mean value of original
+        # data
+        assert (
+            self.edisgo.timeseries.generators_active_power.mean() == mean_value_orig
+        ).unique()
+
 
 class TestTimeSeriesRaw:
     @pytest.fixture(autouse=True)