Machine Learning with Python | Preprocessing | Label Encoding with user defined Function - P60

''' Topic to be Covered - Label Encoding using Functions ''' import pandas as pd import numpy as np train = pd.read_csv('train.csv') train['Age'].fillna(train['Age'].mean,inplace=True) train.drop(['Cabin'],axis=1,inplace=True) train['Embarked'].fillna(train['Embarked'].mode()[0],inplace=True) print(train.info()) print(train.head()) features = train.iloc[:].values df = pd.DataFrame(features) #------------------------------- L A B E L E N C O D I I N ------------------# # Sex, Embarked, from sklearn.preprocessing import LabelEncoder encode = LabelEncoder() features[:,4] = encode.fit_transform(features[:,4]) features[:,10] = encode.fit_transform(features[:,10]) #features[:,10] = encode.fit_transform(features[:,10]) #features[:,10] = encode.fit_transform(features[:,10]) #features[:,10] = encode.fit_transform(features[:,10]) #features[:,10] = encode.fit_transform(features[:,10]) df = pd.DataFrame(features) ######################################################### from sklearn.preprocessing import LabelEncoder encode = LabelEncoder() features1 = train.iloc[:].values #label_index = [4,10] label_index=[3,4,8,9,10] df2= pd.DataFrame(features1) def label_encode(list1,features1): for i in range(len(label_index)): for j in range(features1.shape[1] + 1): if j == label_index[i]: features1[:,j] = encode.fit_transform(features1[:,j]) label_encode(label_index,features1) df3= pd.DataFrame(features1)