Question

Apply PCA ( Principal Component Analysis ) in python to this data set below  that is a csv file

Then plot it. Thank you I will UPVOTE!

A	B	C	D	E	F	G
2	3	1	1	19	12	0
2	0	0	2	12	1	15
95	2	1	0	1	0	1
4	56	2	0	0	3	1
1	2	2	0	39	0	11
0	0	0	34	1	0	0
5	55	0	0	0	2	1
0	33	3	0	0	12	1
0	5	2	0	18	15	2
0	0	0	19	37	0	0
0	1	0	68	17	2	0

Answer 1

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

data = pd.read_csv(".\\Downloads\\Book1.csv")

data

	A	B	C	D	E	F	G
0	2	3	1	1	19	12	0
1	2	0	0	2	12	1	15
2	95	2	1	0	1	0	1
3	4	56	2	0	0	3	1
4	1	2	2	0	39	0	11
5	0	0	0	34	1	0	0
6	5	55	0	0	0	2	1
7	0	33	3	0	0	12	1
8	0	5	2	0	18	15	2
9	0	0	0	19	37	0	0
10	0	1	0	68	17	2	0

from sklearn.preprocessing import StandardScaler

features = ['A', 'B', 'C', 'D','E','F','G']

x = data.loc[:, features].values

x = StandardScaler().fit_transform(data)

x

array([[-0.2933703 , -0.52600014,  0.        , -0.4944455 ,  0.42515456,
         1.41041204, -0.59732271],
       [-0.2933703 , -0.66598404, -0.95742711, -0.44631364, -0.07849007,
        -0.59735098,  2.48262253],
       [ 3.15625978, -0.57266144,  0.        , -0.54257737, -0.86993163,
        -0.77987489, -0.39199303],
       [-0.21918471,  1.94704889,  0.95742711, -0.54257737, -0.94188086,
        -0.23230316, -0.39199303],
       [-0.3304631 , -0.57266144,  0.95742711, -0.54257737,  1.8641392 ,
        -0.77987489,  1.6613038 ],
       [-0.36755589, -0.66598404, -0.95742711,  1.09390598, -0.86993163,
        -0.77987489, -0.59732271],
       [-0.18209191,  1.90038759, -0.95742711, -0.54257737, -0.94188086,
        -0.41482707, -0.39199303],
       [-0.36755589,  0.87383894,  1.91485422, -0.54257737, -0.94188086,
         1.41041204, -0.39199303],
       [-0.36755589, -0.43267753,  0.95742711, -0.54257737,  0.35320532,
         1.95798377, -0.18666335],
       [-0.36755589, -0.66598404, -0.95742711,  0.37192803,  1.72024074,
        -0.77987489, -0.59732271],
       [-0.36755589, -0.61932274, -0.95742711,  2.73038932,  0.28125609,
        -0.41482707, -0.59732271]])

from sklearn.decomposition import PCA
pca = PCA(n_components=2)
principalComponents = pca.fit_transform(x)
principalDf = pd.DataFrame(data = principalComponents
, columns = ['principal component 1', 'principal component 2'])

principalDf

	principal component 1	principal component 2
0	0.535223	0.707044
1	-1.236728	1.131952
2	0.073237	-1.639883
3	1.898497	-0.795800
4	-0.773920	2.381402
5	-1.238889	-1.292917
6	0.811656	-1.446545
7	2.613050	0.294014
8	1.288402	1.329610
9	-1.799728	0.362192
10	-2.170799	-1.031071

plt.scatter(principalDf['principal component 1'],principalDf['principal component 2'])
plt.xlabel("principal component 1")
plt.ylabel("principal component 2")
plt.show()