Adding a source module to check for redundancy in feature names.

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

diff --git a/predictops/learn/preprocessing.py b/predictops/learn/preprocessing.py
index 833e48316bffa1c51affc6885210b71f61b2c1d1..a878a8215d83e8cd504ff7f345cbd1c15165a7e7 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 os import listdir
 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.
-
     '''
-    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.
         '''
-        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._start = start
-        self._end = end
-        self._timestep = timestep
         self._full_dict = None
         self._dataframe = None
         self._datetimes = []
@@ -41,6 +48,43 @@ class Preprocessing:
         else:
             self._features = set(chain.from_iterable([tuple(u.keys())
                                                       for u in [*dict_features.values()]]))
+        for csv_file in listdir():
+            with open(csv_file, "r") as f:
+                reader = DictReader(f, delimiter=',')
+                dico_features = {{row['name']: row['type']  # qualitative (2) or quantitative (1)
+                                    }
+                                for row in reader if row['name'] in self._features}
+
+        self._features = {feat : None for feat in self._features}
+        print(self._features)
+        exit()
+
+
+    @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):
@@ -94,14 +138,26 @@ class Preprocessing:
             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')
+
+            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'))
+
+            # 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')
+
             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