From f5357178353432c5431fc0fd875b9928a326e4c7 Mon Sep 17 00:00:00 2001 From: Christophe Guyeux Date: Tue, 18 Feb 2020 10:33:55 +0100 Subject: [PATCH] Standardization and one hot encoding --- main.py | 8 +-- predictops/learn/preprocessing.py | 110 +++++++++++++++++++++--------- requirements.txt | 2 + 3 files changed, 80 insertions(+), 40 deletions(-) diff --git a/main.py b/main.py index 969054c..d1d7f9c 100644 --- a/main.py +++ b/main.py @@ -5,7 +5,6 @@ from logging import getLogger from logging.config import fileConfig from pathlib import Path -import geopandas as gpd fileConfig((Path.cwd() / 'config') / 'logging.cfg') logger = getLogger() @@ -23,14 +22,11 @@ if __name__ == '__main__': print(process.dataframe.head(n=20)) print(process.dataframe.tail(n=20)) - #target = toarea(stream_file = Path.cwd() / 'data' / 'targets' / 'sdis25' / 'interventions.csv') - - - exit() + '''target = toarea(stream_file = Path.cwd() / 'data' / 'targets' / 'sdis25' / 'interventions.csv') depts = gpd.read_file( Path.cwd() / 'data' / 'targets' / 'departments' / "departements-20180101.shp") Doubs = depts.loc[depts['nom'] == 'Doubs'].iloc[0] ToArea(area=Doubs.geometry, csv_file = Path.cwd() / 'data' / 'targets' / 'sdis25' / 'interventions.csv') - + ''' diff --git a/predictops/learn/preprocessing.py b/predictops/learn/preprocessing.py index 939a7fa..4197b8f 100644 --- a/predictops/learn/preprocessing.py +++ b/predictops/learn/preprocessing.py @@ -6,6 +6,7 @@ from logging import getLogger from logging.config import fileConfig from os import listdir from pathlib import Path +from sklearn import preprocessing import numpy as np import pandas as pd @@ -134,6 +135,75 @@ class Preprocessing: return self._full_dict + def _fill_nan(self): + ''' + Fill NaN values, either by propagation or by interpolation (linear or splines) + ''' + 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]) + + + def _standardize(self): + ''' + Normalizing numerical features + ''' + 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]) + + + def _one_hot_encoding(self): + ''' + 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 + df_out = pd.DataFrame() + for col in 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 + print(self._dataframe.head()) + + @property def dataframe(self): @@ -144,40 +214,12 @@ class Preprocessing: logger.info("Creating feature dataframe from feature dictionary") self._dataframe = pd.DataFrame.from_dict(self.full_dict, orient='index') - 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]) + # Dealing with NaN values + self._fill_nan() + # Normalizing numerical values + self._standardize() + # Dealing with categorical features + self._one_hot_encoding() return self._dataframe diff --git a/requirements.txt b/requirements.txt index 2053469..6249a16 100644 --- a/requirements.txt +++ b/requirements.txt @@ -6,12 +6,14 @@ Fiona==1.8.13 geographiclib==1.50 geopandas==0.6.3 geopy==1.21.0 +joblib==0.14.1 munch==2.5.0 numpy==1.18.1 pandas==1.0.1 pyproj==2.4.2.post1 python-dateutil==2.8.1 pytz==2019.3 +scikit-learn==0.22.1 scipy==1.4.1 Shapely==1.7.0 six==1.14.0 -- 2.39.5