Скачать или смотреть Machine Learning | Standard Scaler to scale features | Feature Scaling | Standard Scaler | ML - P22

Machine Learning | Standard Scaler to scale features | Feature Scaling | Scale Features | Standard Scaler | ML - P22
Table of Content
0:00 Introduction
00:17 Import numpy
00:17 Import preprocessing from Sklearn
00:21 Create array using numpy
00:26 Create an object of StandardScaler
00:40 Fit the object of StandardScaler with the array X
00:44 Transform the object of StandardScaler after performing Fit()
01:04 How to fit_transform the StandardScaler object
01:21 Formula for StandardScaler transformation
02:04 Apply StandardScaler on 3X3 array
02:07 Define 3X3 array
02:18 Create object of StandardScaler and apply fit_transform()
02:21 Check the array after the StandardScaler transformation
02:32 Verification of the transformed matrix
02:45 Find the mean of a column of a matrix using numpy
03:03 Mathematically verify the values in the matrix after the transformation
03:12 How to get the Standard Deviation of the column using numpy
03:40 Apply StandardScaler on the dataset imported as pandas dataframe
03:44 Import pandas library
03:48 create pandas dataframe from imported .csv file
03:57 Check the content of the dataframe using dataframe.info()
04:13 Create object of StandardScaler and apply fit_transform()
04:38 Features Extraction
05:01 Print the transformed features

Github Link - https://github.com/technologycult/Pyt...

Feature Scalaing - Standard Scalar - Topics to be covered

(Xi - Xmean) / (standard Deviation of that feature)

Code Starts here
==============

from sklearn import preprocessing
import numpy as np

x = np.array([[-400],
[-100],
[0],
[100],
[400]])

standardscaler = preprocessing.StandardScaler()

x_scaler = standardscaler.fit_transform(x)

print(x_scaler)

x1 = np.array([[1,2,3],
[4,5,6],
[7,8,9]])

standardscaler1 = preprocessing.StandardScaler()

x_scaler1 = standardscaler1.fit_transform(x1)

import pandas as pd

dataset = pd.read_csv('Age-Salary.csv')

features = dataset.iloc[:,[2,3]].values

standardscaler2 = preprocessing.StandardScaler()

x_scaler2 = standardscaler2.fit_transform(features)

print(x_scaler2)

Applying it to 3X3 Matrix

x1 = np.array([[1,2,3],
[4,5,6],
[7,8,9]])

standardscaler1 = preprocessing.StandardScaler().fit(x1)

x_scaler1 = standardscaler1.transform(x1)

print(x_scaler1)

Appying ti to a Pandas Dataset

import pandas as pd

dataset = pd.read_csv('Age-Salary.csv')

features = dataset.iloc[:,[2,3]].values

standardscaler_as = preprocessing.MinMaxScaler().fit(features)

features_scale = standardscaler_as.transform(features)