starting to fill README.md, and packages update

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

diff --git a/predictops/learn/preprocessing.py b/predictops/learn/preprocessing.py
index 833e48316bffa1c51affc6885210b71f61b2c1d1..5400d1d39f1135ce5e2abcfec2541201cf5d8ed6 100644 (file)
--- a/predictops/learn/preprocessing.py
+++ b/predictops/learn/preprocessing.py
@@ -1,3 +1,5 @@
+from configparser import ConfigParser
+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


@@ -18,19 +20,22 @@ 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 = []


@@ -43,6 +48,33 @@ class Preprocessing:
                                                       for u in [*dict_features.values()]]))
 
 
                                                       for u in [*dict_features.values()]]))
 
 

+    @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):
         '''
         Add datetime keys in the dated feature dictionary that are missing. The
     def _fill_dict(self):
         '''
         Add datetime keys in the dated feature dictionary that are missing. The


@@ -94,14 +126,22 @@ class Preprocessing:
             self._dataframe = pd.DataFrame.from_dict(self.full_dict,
                                                      orient='index')
             logger.info("Filling NaN values in the feature dataframe")
             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')
+
+            if self._config['PREPROCESSING']['fill_method'] == 'propagate':
+                self._dataframe = self._dataframe.fillna(method='ffill')
+            elif self._config['PREPROCESSING']['fill_method'] == 'linear':
+                self._dataframe = self._dataframe.interpolate()
+            elif self._config['PREPROCESSING']['fill_method'] == 'spline':
+                self._dataframe = self._dataframe.interpolate(method='spline',
+                                                              order=self._config['PREPROCESSING'].getint('order'))

             self._dataframe = self._dataframe.fillna(method='bfill')
             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
 
             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