Reducing the computation time and adding holidays features

[predictops.git] / predictops / learn / preprocessing.py

diff --git a/predictops/learn/preprocessing.py b/predictops/learn/preprocessing.py
index 4197b8fed13cb4137e33655753976532e42987a2..885aad3393979b897e3e0d8c40f3378dbba08e5a 100644 (file)
--- a/predictops/learn/preprocessing.py
+++ b/predictops/learn/preprocessing.py
@@ -25,12 +25,12 @@ class Preprocessing:
      - NaN values are then filled with last known values.
     '''
 
      - NaN values are then filled with last known values.
     '''
 

-    def __init__(self, config_file = None, dict_features = None, features = None):
+    def __init__(self, config_file = None,
+                 dict_features = None, dict_target = None):

         '''
         Constructor that defines all needed attributes and collects features.
         '''
         '''
         Constructor that defines all needed attributes and collects features.
         '''

-        self._config = ConfigParser()
-        self._config.read(config_file)
+        self._config = config_file

 
         self._start = datetime.strptime(self._config['DATETIME']['start'],
                                         '%m/%d/%Y %H:%M:%S')
 
         self._start = datetime.strptime(self._config['DATETIME']['start'],
                                         '%m/%d/%Y %H:%M:%S')


@@ -39,32 +39,31 @@ class Preprocessing:
         self._timestep = timedelta(hours =
                                    self._config['DATETIME'].getfloat('hourStep'))
         self._dict_features = dict_features
         self._timestep = timedelta(hours =
                                    self._config['DATETIME'].getfloat('hourStep'))
         self._dict_features = dict_features

+        self._dict_target = dict_target
+

         self._full_dict = None
         self._dataframe = None
         self._datetimes = []
         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:
-            self._features = set(chain.from_iterable([tuple(u.keys())
+
+        self._features = set(chain.from_iterable([tuple(u.keys())

                                                       for u in [*dict_features.values()]]))
                                                       for u in [*dict_features.values()]]))

-        feature_files = Path.cwd() / 'config' / 'features'
-        self._features = {feat : {'numerical': False} for feat in self._features}
-        for feature_file in listdir(feature_files):
-            if feature_file.endswith('csv'):
-                with open(feature_files / feature_file , "r") as f:
-                    reader = DictReader(f, delimiter=',')
-                    typed_names = {row['name']: row['type'] for row in reader}
-                for feature in self._features:
-                    if feature.split('_')[0] in typed_names:
-                        self._features[feature]['type'] = int(typed_names[feature.split('_')[0]])
-            elif feature_file.endswith('cfg'):
+
+        #feature_files = Path.cwd() / 'config' / 'features'
+        self._features = {feat : {'numerical': False, 'categorical': False}
+                          for feat in self._features}
+
+        for feature in self._config['FEATURES']:
+            if self._config['FEATURES'][feature]:
+                feature_file = self._config['FEATURE_CONFIG'][feature]

                 config = ConfigParser()
                 config = ConfigParser()

-                config.read(feature_files / feature_file)
+                config.read(feature_file)

                 for section in config:
                     if config.has_option(section, 'numerical'):
                         self._features[section]['numerical'] = config[section].getboolean('numerical')
                 for section in config:
                     if config.has_option(section, 'numerical'):
                         self._features[section]['numerical'] = config[section].getboolean('numerical')

+                        self._features[section]['categorical'] = config[section].getboolean('categorical')
+
+        self._numerical_columns = [k for k in self._features if self._features[k]['numerical']]
+        self._categorical_columns = [k for k in self._features if self._features[k]['categorical']]

 
 
 
 
 
 


@@ -141,27 +140,23 @@ class Preprocessing:
         '''
         logger.info("Filling NaN numerical values in the feature dataframe")
         # We interpolate (linearly or with splines) only numerical columns
         '''
         logger.info("Filling NaN numerical values in the feature dataframe")
         # We interpolate (linearly or with splines) only numerical columns

-        numerical_columns = [k for k in self._features if self._features[k]['type'] == 1
-                   or (self._features[k]['type'] == 3 and self._features[k]['numerical'])]

         # The interpolation
         if self._config['PREPROCESSING']['fill_method'] == 'propagate':
         # The interpolation
         if self._config['PREPROCESSING']['fill_method'] == 'propagate':

-            self._dataframe[numerical_columns] =\
-                self._dataframe[numerical_columns].fillna(method='ffill')
+            self._dataframe[self._numerical_columns] =\
+                self._dataframe[self._numerical_columns].fillna(method='ffill')

         elif self._config['PREPROCESSING']['fill_method'] == 'linear':
         elif self._config['PREPROCESSING']['fill_method'] == 'linear':

-            self._dataframe[numerical_columns] =\
-                self._dataframe[numerical_columns].interpolate()
+            self._dataframe[self._numerical_columns] =\
+                self._dataframe[self._numerical_columns].interpolate()

         elif self._config['PREPROCESSING']['fill_method'] == 'spline':
         elif self._config['PREPROCESSING']['fill_method'] == 'spline':

-            self._dataframe[numerical_columns] =\
-                self._dataframe[numerical_columns].interpolate(method='spline',
+            self._dataframe[self._numerical_columns] =\
+                self._dataframe[self._numerical_columns].interpolate(method='spline',

                      order=self._config['PREPROCESSING'].getint('order'))
 
         # For the categorical columns, NaN values are filled by duplicating
         # the last known value (forward fill method)
         logger.info("Filling NaN categorical values in the feature dataframe")
                      order=self._config['PREPROCESSING'].getint('order'))
 
         # For the categorical columns, NaN values are filled by duplicating
         # the last known value (forward fill method)
         logger.info("Filling NaN categorical values in the feature dataframe")

-        categorical_columns = [k for k in self._features if self._features[k]['type'] == 2
-                   or (self._features[k]['type'] == 3 and not self._features[k]['numerical'])]
-        self._dataframe[categorical_columns] =\
-            self._dataframe[categorical_columns].fillna(method='ffill')
+        self._dataframe[self._categorical_columns] =\
+            self._dataframe[self._categorical_columns].fillna(method='ffill')

 
         # Uncomment this line to fill NaN values at the beginning of the
         # dataframe. This may not be a good idea, especially for features
 
         # Uncomment this line to fill NaN values at the beginning of the
         # dataframe. This may not be a good idea, especially for features


@@ -170,9 +165,27 @@ class Preprocessing:
 
         # Dropping rows that are not related to our datetime window (start/
         # step / end)
 
         # 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")
+        dates = tuple((x.year, x.month, x.day, x.hour) for x in self._datetimes)
+        self._dataframe['row_ok'] =\
+            self._dataframe.apply(lambda x: (int(x.year), int(x.month), int(x.dayInMonth), int(x.hour)) in dates, axis=1)
+        self._dataframe = self._dataframe[self._dataframe['row_ok']]
+        self._dataframe = self._dataframe.drop(['row_ok'], axis=1)
+        logger.info("Rows dropped")
+
+
+    def _add_history(self):
+        '''
+        Integrating previous nb of interventions as features
+        '''
+        logger.info("Integrating previous nb of interventions as features")
+        nb_lines = self._config['HISTORY_KNOWLEDGE'].getint('nb_lines')
+        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:]
+

 
 
     def _standardize(self):
 
 
     def _standardize(self):


@@ -181,9 +194,9 @@ class Preprocessing:
         '''
         logger.info("Standardizing numerical values in the feature dataframe")
         # We operate only on numerical columns
         '''
         logger.info("Standardizing numerical values in the feature dataframe")
         # We operate only on numerical columns

-        numerical_columns = [k for k in self._features if self._features[k]['type'] == 1
-                   or (self._features[k]['type'] == 3 and self._features[k]['numerical'])]
-        self._dataframe[numerical_columns] = preprocessing.scale(self._dataframe[numerical_columns])
+        self._dataframe[self._numerical_columns] =\
+            preprocessing.scale(self._dataframe[self._numerical_columns])
+

 
 
     def _one_hot_encoding(self):
 
 
     def _one_hot_encoding(self):


@@ -191,18 +204,17 @@ class Preprocessing:
         Apply a one hot encoding for category features
         '''
         logger.info("One hot encoding for categorical feature")
         Apply a one hot encoding for category features
         '''
         logger.info("One hot encoding for categorical feature")

-        categorical_columns = [k for k in self._features if self._features[k]['type'] == 2
-                   or (self._features[k]['type'] == 3 and not self._features[k]['numerical'])]

 
 

-        # On fait un codage disjonctif complet des variables qualitatives
+        # We store numerical columns

         df_out = pd.DataFrame()
         df_out = pd.DataFrame()

-        for col in categorical_columns:
+        for col in  self._numerical_columns:
+            df_out[col] = self._dataframe[col]
+        # The one hot encoding
+        for col in self._categorical_columns:

             pd1 = pd.get_dummies(self._dataframe[col],prefix=col)
             for col1 in pd1.columns:
                 df_out[col1] = pd1[col1]
         self._dataframe = df_out
             pd1 = pd.get_dummies(self._dataframe[col],prefix=col)
             for col1 in pd1.columns:
                 df_out[col1] = pd1[col1]
         self._dataframe = df_out

-        print(self._dataframe.head())
-

 
 
     @property
 
 
     @property


@@ -216,6 +228,8 @@ class Preprocessing:
                                                      orient='index')
             # Dealing with NaN values
             self._fill_nan()
                                                      orient='index')
             # Dealing with NaN values
             self._fill_nan()

+            # Adding previous (historical) nb_interventions as features
+            self._add_history()

             # Normalizing numerical values
             self._standardize()
             # Dealing with categorical features
             # Normalizing numerical values
             self._standardize()
             # Dealing with categorical features