The Realm of Supervised Learning

Preprocessing data using different techniques

Getting ready

import numpy as np
from sklearn import preprocessing 

data = np.array([[3, -1.5, 2, -5.4], [0, 4, -0.3, 2.1], [1, 3.3, -1.9, -4.3]]) ~~~~

How to do it…

# Mean removal
data_standardized = preprocessing.scale(data)
print "\nMean =", data_standardized.mean(axis=0)
print "Std deviation =", data_standardized.std(axis=0)

• python preprocessor.py

Mean = [ 5.55111512e-17 -1.11022302e-16 -7.40148683e-17 -7.40148683e-17]

Std deviation = [ 1. 1. 1. 1.]

# Scaling 
data_scaler = preprocessing.MinMaxScaler(feature_range=(0.1))
data_scaled = data_scaler.fit_transform(data)
print "\nMin max scaled data =", data_scaled 

# Normalization
data_normalized = preprocessing.normalize(data, norm='l1')
print "\nL1 normalized data =", data_normalized

# Binarization
data_binarized = preprocessing.Binarizer(threshold=1.4).transform(data)
print "\nBinarized data =", data_binarized

>

# One Hot Encoding
encoder = preprocessing.OneHotEncoder()
encoder.fit([[0, 2, 1, 12], [1, 3, 5, 3], [2, 3, 2, 12],[1, 2, 4, 3]])
encoded_vector = encoder.transform([[2, 3, 5, 3]]).toarray()
print "\nEncoded vector =", encoded_vector

Label encoding

How to do it…

from sklearn import preprocessing
label_encoder = preprocessing.LabelEncoder()
input_classes = ['audi', 'ford', 'audi', 'toyota', 'ford', 'bmw']
label_encoder.fit(input_classes)
print "\nClass mapping:"
for i, item in enumerate(label_encoder.classes_): print item, '-->', i

>

labels =