Question

Python program to Normalize data for KNN Classifier

data = pd.read_csv('iris.data')

Y=data['status']

X=data[data.columns.difference(['status','name'])]
# split the data in testing and training
train_in,test_in,train_out,test_out=train_test_split(X,Y,train_size=0.8)

knn = KNeighborsClassifier()

1. use sklearn.preprocessing.scalar(), Stan- dardScaler(), MinMaxScaler(), MaxAbsScaler()) to normalize data

Answer 1

import pandas as pd
from sklearn.preprocessing import MinMaxScaler,StandardScaler,MaxAbsScaler

data = pd.read_csv('iris.data')

Y=data['status']

X=data[data.columns.difference(['status','name'])]

# split the data in testing and training

train_in,test_in,train_out,test_out=train_test_split(X,Y,train_size=0.8)

# Normalize feature data using MinMax scaler
scaler = MinMaxScaler()

X_train_scaled = scaler.fit_transform(train_in)
X_test_scaled = scaler.transform(test_in)

# Normalize feature data using StandardScaler
standarad_scaler = StandardScaler()

X_train_scaled = standarad_scaler.fit_transform(train_in)
X_test_scaled = standarad_scaler.transform(test_in)

# Normalize feature data using MaxAbsScaler
max_abs_scaler = MaxAbsScaler()

X_train_scaled = max_abs_scaler.fit_transform(train_in)
X_test_scaled = max_abs_scaler.transform(test_in)


knn = KNeighborsClassifier()