Refactoring, and categorical / numerical / mixed NaN values are now

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

diff --git a/predictops/learn/preprocessing.py b/predictops/learn/preprocessing.py
index 833e48316bffa1c51affc6885210b71f61b2c1d1..939a7fa30e79d45314adec6f8d526362137e3e9b 100644 (file)
--- a/predictops/learn/preprocessing.py
+++ b/predictops/learn/preprocessing.py
@@ -1,6 +1,10 @@
+from configparser import ConfigParser
+from csv import DictReader
+from datetime import datetime, timedelta

 from itertools import chain
 from logging import getLogger
 from logging.config import fileConfig
 from itertools import chain
 from logging import getLogger
 from logging.config import fileConfig

+from os import listdir

 from pathlib import Path
 
 import numpy as np
 from pathlib import Path
 
 import numpy as np


@@ -18,19 +22,22 @@ class Preprocessing:
      - 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.
      - 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):
+
+    def __init__(self, config_file = None, dict_features = None, features = None):

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

-        logger.info("Entering  NaN values in the feature dataframe")
+        self._config = ConfigParser()
+        self._config.read(config_file)
+
+        self._start = datetime.strptime(self._config['DATETIME']['start'],
+                                        '%m/%d/%Y %H:%M:%S')
+        self._end = datetime.strptime(self._config['DATETIME']['end'],
+                                        '%m/%d/%Y %H:%M:%S')
+        self._timestep = timedelta(hours =
+                                   self._config['DATETIME'].getfloat('hourStep'))

         self._dict_features = dict_features
         self._dict_features = dict_features

-        self._start = start
-        self._end = end
-        self._timestep = timestep

         self._full_dict = None
         self._dataframe = None
         self._datetimes = []
         self._full_dict = None
         self._dataframe = None
         self._datetimes = []


@@ -41,6 +48,50 @@ class Preprocessing:
         else:
             self._features = set(chain.from_iterable([tuple(u.keys())
                                                       for u in [*dict_features.values()]]))
         else:
             self._features = set(chain.from_iterable([tuple(u.keys())
                                                       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'):
+                config = ConfigParser()
+                config.read(feature_files / feature_file)
+                for section in config:
+                    if config.has_option(section, 'numerical'):
+                        self._features[section]['numerical'] = config[section].getboolean('numerical')
+
+
+
+    @property
+    def start(self):
+        return self._start
+
+    @start.setter
+    def start(self, x):
+        self._start = x
+
+
+    @property
+    def end(self):
+        return self._end
+
+    @end.setter
+    def end(self, x):
+        self._end = x
+
+
+    @property
+    def timestep(self):
+        return self._timestep
+
+    @timestep.setter
+    def timestep(self, x):
+        self._timestep = x

 
 
     def _fill_dict(self):
 
 
     def _fill_dict(self):


@@ -93,15 +144,43 @@ class Preprocessing:
             logger.info("Creating feature dataframe from feature dictionary")
             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')
+            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':
+                self._dataframe[numerical_columns] =\
+                    self._dataframe[numerical_columns].fillna(method='ffill')
+            elif self._config['PREPROCESSING']['fill_method'] == 'linear':
+                self._dataframe[numerical_columns] =\
+                    self._dataframe[numerical_columns].interpolate()
+            elif self._config['PREPROCESSING']['fill_method'] == 'spline':
+                self._dataframe[numerical_columns] =\
+                    self._dataframe[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")
+            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')
+
+            # Uncomment this line to fill NaN values at the beginning of the
+            # dataframe. This may not be a good idea, especially for features
+            # that are available only for recent years, e.g., air quality
+            #self._dataframe = self._dataframe.fillna(method='bfill')
+
+            # 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])
         return self._dataframe
 
             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
     def dataframe(self, df):
         self._dataframe = df
     @dataframe.setter
     def dataframe(self, df):
         self._dataframe = df