X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/predictops.git/blobdiff_plain/fbeb0a86f1d3efc96263a81981b0a059d93fa4f5..ef7617a10d088cccaa6acd8b45a0db76bd8fb61e:/predictops/learn/preprocessing.py diff --git a/predictops/learn/preprocessing.py b/predictops/learn/preprocessing.py index 187a5b7..106a626 100644 --- a/predictops/learn/preprocessing.py +++ b/predictops/learn/preprocessing.py @@ -171,9 +171,14 @@ class Preprocessing: # Dropping rows that are not related to our datetime window (start/ # step / end) - self._dataframe = self._dataframe.drop([k.to_pydatetime() - for k in self._dataframe.T - if k not in self._datetimes]) + logger.info("Dropping rows that are not related to our datetime window") + self._dataframe['datetime'] =\ + self._dataframe.apply(lambda x: datetime(int(x.year), int(x.month), int(x.dayInMonth), int(x.hour)), axis=1) + self._dataframe['row_ok'] =\ + self._dataframe.apply(lambda x:x.datetime in self._datetimes, axis=1) + self._dataframe = self._dataframe[self._dataframe['row_ok']] + self._dataframe = self._dataframe.drop(['datetime', 'row_ok'], axis=1) + logger.info("Rows dropped") def _add_history(self): @@ -182,15 +187,11 @@ class Preprocessing: ''' logger.info("Integrating previous nb of interventions as features") nb_lines = self._config['HISTORY_KNOWLEDGE'].getint('nb_lines') - print(len(self._dataframe)) - print(self._dataframe.head(4)) for k in range(1,nb_lines+1): name = 'history_'+str(nb_lines-k+1) self._dataframe[name] = [np.NaN]*k + list(self._dict_target.values())[:-k] self._numerical_columns.append(name) self._dataframe = self._dataframe[nb_lines:] - print(self._dataframe.head(4)) - print(len(self._dataframe))