Python for Machine Learning - Part 17 | One Hot Encoding | Dummy Encoding | Preprocessing

In this Video we will worl with One Hot Encoding: import pandas as pd import numpy as np df = pd.read_csv('Datapreprocessing.csv') # Get the rows that contains NULL (NaN) df.isnull().sum() # Fill the NaN values for Occupation, Emplyment Status and Employement Type col = ['Occupation','Employment Status','Employement Type'] df[col] = df[col].fillna(df.mode().iloc[0]) features = df.iloc[:,:-1].values features1 = df.iloc[:,:-1].values labels = df.iloc[:,-1].values from sklearn.preprocessing import Imputer, OneHotEncoder imputer = Imputer(missing_values='NaN',strategy='mean',axis=0) # 2 step transformation # Fit and Tranform imputer.fit(features[:,[1,6]]) features[:,[1,6]] = imputer.fit_transform(features[:,[1,6]]) features1[:,[1,6]] = imputer.fit_transform(features1[:,[1,6]]) #------------------------------- L A B E L E N C O D I N G ------------------# from sklearn.preprocessing import LabelEncoder encode = LabelEncoder() features[:,0] = encode.fit_transform(features[:,0]) features[:,2] = encode.fit_transform(features[:,2]) features[:,3] = encode.fit_transform(features[:,3]) features[:,4] = encode.fit_transform(features[:,4]) features[:,5] = encode.fit_transform(features[:,5]) features1[:,0] = encode.fit_transform(features1[:,0]) features1[:,2] = encode.fit_transform(features1[:,2]) features1[:,3] = encode.fit_transform(features1[:,3]) features1[:,4] = encode.fit_transform(features1[:,4]) features1[:,5] = encode.fit_transform(features1[:,5]) df1 = pd.DataFrame(features) #--------------------------- ONE HOT ENCODING --------------------------------# hotencode = OneHotEncoder(categorical_features=[0]) features = hotencode.fit_transform(features).toarray() hotencode = OneHotEncoder(categorical_features=[7]) features = hotencode.fit_transform(features).toarray() hotencode = OneHotEncoder(categorical_features=[9]) features = hotencode.fit_transform(features).toarray() hotencode = OneHotEncoder(categorical_features=[11]) features = hotencode.fit_transform(features).toarray() hotencode = OneHotEncoder(categorical_features=[13]) features = hotencode.fit_transform(features).toarray() #-- hotencode = OneHotEncoder(categorical_features=[0]) features1 = hotencode.fit_transform(features1).toarray() hotencode = OneHotEncoder(categorical_features=[2]) features1 = hotencode.fit_transform(features1).toarray() hotencode = OneHotEncoder(categorical_features=[3]) features1 = hotencode.fit_transform(features1).toarray() hotencode = OneHotEncoder(categorical_features=[4]) features1 = hotencode.fit_transform(features1).toarray() hotencode = OneHotEncoder(categorical_features=[5]) features1 = hotencode.fit_transform(features1).toarray()