Correlation-Analysis---Python/Python seaborn correlation at main · MoganaD/Correlation-Analysis---Python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
#1.Mount drive
from google.colab import drive
drive.mount('/content/drive')

#2.load dataset from drive
import pandas as pd
df5= pd.read_csv("/content/drive/My Drive/data5.csv",encoding ='latin1')

..............................................................................
#3.Correlation plot using seaborn package (sns), matplotlib for visualisation

import matplotlib.pyplot as plt
import seaborn as sns

#3.1 with regression
sns.pairplot(df, kind="reg")
plt.show()

# with color and correlation by one variable (ex: ethnicity)
sns.pairplot(df5, kind="scatter", hue="Ethnicity", markers=["o", "s", "D"], palette="Set2")
plt.show()

#3.2 without regression
sns.pairplot(df5, kind="scatter")
plot.show()

.............................................................................
#4.Correlation heatmap

corr = df5.corr()

ax = sns.heatmap(

    corr,

    vmin=-1, vmax=1, center=0,

    cmap=sns.diverging_palette(20, 220, n=200),

    square=True

)

ax.set_xticklabels(

    ax.get_xticklabels(),

    rotation=45,

    horizontalalignment='right'

);