How to rescale features in Python?

Recipe Objective

In a dataset there may be many outliers which effects the performance of the model. We can deal with it by scaling the data. Here we will be using min-max scaler for this.

So this is the recipe on how we can can rescale features in Python.

Explore the Must Know Python Libraries for Data Science and Machine Learning.

Step 1 - Importing Library

from sklearn import preprocessing import numpy as np

We have imported numpy and preprocessing which is needed.

Step 2 - Creating array

We have created a array with values on which we will perform operation. x = np.array([[-500.5], [-100.1], [0], [100.1], [900.9]])

Step 3 - Scaling the array

We have used min-max scaler to scale the data in the array in the range 0 to 1 which we have passed in the parameter. Then we have used fit transform to fit and transform the array according to the min max scaler. minmax_scale = preprocessing.MinMaxScaler(feature_range=(0, 1)) x_scale = minmax_scale.fit_transform(x) print(x) print(x_scale) So the output comes as

[[-500.5]
 [-100.1]
 [   0. ]
 [ 100.1]
 [ 900.9]]

[[0.        ]
 [0.28571429]
 [0.35714286]
 [0.42857143]
 [1.        ]]