X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/predictops.git/blobdiff_plain/910a056eaa0181df00d21fa836f3c68504051717..d6469a787c80df2c938f21d4ae107b84213e238f:/predictops/learn/preprocessing.py

diff --git a/predictops/learn/preprocessing.py b/predictops/learn/preprocessing.py
index b58ffac..833e483 100644
--- a/predictops/learn/preprocessing.py
+++ b/predictops/learn/preprocessing.py
@@ -10,15 +10,32 @@ fileConfig((Path.cwd() / 'config') / 'logging.cfg')
 logger = getLogger()
 
 class Preprocessing:
+    '''
+    Generate a pandas dataframe from a dictionary of features per datetime, which
+    respects the starting and ending dates of the study, and its precision (the
+    time step) as passed to the constructor. Missing feature values are completed.
+
+     - Missing datetimes are added first with np.NaN feature values,
+     - The dataframe is then constructed based on the filled feature dictionary,
+     - NaN values are then filled with last known values.
+
+    '''
     def __init__(self, dict_features,
                  start, end, timestep,
                  features = None):
+        '''
+        Constructor that defines all needed attributes and collects features.
+        '''
+        logger.info("Entering  NaN values in the feature dataframe")
         self._dict_features = dict_features
         self._start = start
         self._end = end
         self._timestep = timestep
+        self._full_dict = None
         self._dataframe = None
-
+        self._datetimes = []
+        # If features are not provided to the constructor, then we collect
+        # any existing feature in the dictionary
         if features != None:
             self._features = features
         else:
@@ -27,27 +44,62 @@ class Preprocessing:
 
 
     def _fill_dict(self):
+        '''
+        Add datetime keys in the dated feature dictionary that are missing. The
+        features are then set to np.NaN. Add missing features in existing datetimes
+        too.
+        '''
+        logger.info("Adding missing dates and filling missing features with NaN values")
         current = self._start
         while current <= self._end:
+            self._datetimes.append(current)
             if current not in self._dict_features:
-                self._dict_features[current] = {feature:np.NaN for feature in self._features}
+                self._dict_features[current] = {feature:np.NaN
+                                                for feature in self._features}
             else:
-                null_dict = {feature:np.NaN for feature in self._features}
+                null_dict = {feature:np.NaN
+                             for feature in self._features}
                 null_dict.update(self._dict_features[current])
                 self._dict_features[current] = null_dict
             current += self._timestep
+        for k in self._dict_features:
+            null_dict = {feature:np.NaN
+                         for feature in self._features}
+            null_dict.update(self._dict_features[k])
+            self._dict_features[k] = null_dict
+
+        self._full_dict = {k: self._dict_features[k]
+                           for k in sorted(self._dict_features.keys())}
+
 
 
     @property
     def full_dict(self):
-        self._fill_dict()
-        return {k: self._dict_features[k] for k in sorted(self._dict_features.keys())}
+        '''
+        Returns the fully filled dated feature dictionary, ordered by datetimes
+        '''
+        if self._full_dict is None:
+            self._fill_dict()
+        return self._full_dict
+
 
 
     @property
     def dataframe(self):
+        '''
+        Returns the feature dataframe, after creating it if needed.
+        '''
         if self._dataframe is None:
-            self._dataframe = pd.DataFrame.from_dict(self.full_dict, orient='index')
+            logger.info("Creating feature dataframe from feature dictionary")
+            self._dataframe = pd.DataFrame.from_dict(self.full_dict,
+                                                     orient='index')
+            logger.info("Filling NaN values in the feature dataframe")
+            #TODO: add other filling methods like linear interpolation
+            self._dataframe = self._dataframe.fillna(method='ffill')
+            self._dataframe = self._dataframe.fillna(method='bfill')
+            self._dataframe = self._dataframe.drop([k.to_pydatetime()
+                                                   for k in self._dataframe.T
+                                                   if k not in self._datetimes])
         return self._dataframe
 
     @dataframe.setter
@@ -55,5 +107,3 @@ class Preprocessing:
         self._dataframe = df
 
 
-    def fill_na(self):
-        self.dataframe = self.dataframe.fillna(method='ffill')
\ No newline at end of file