4. Correlation

import matplotlib.pyplot as plt

from pandas import DataFrame

import seaborn as sn

Data = {'A': [45,37,42,35,39],

        'B': [38,31,26,28,33],

        'C': [10,15,17,21,12]}

df = DataFrame(Data,columns=['A','B','C'])

corrMatrix = df.corr()

print("Correlation: ")

print(corrMatrix)

sn.heatmap(corrMatrix, annot=True)

plt.show()

Correlation:

A B C

A 1.000000 0.518457 -0.701886

B 0.518457 1.000000 -0.860941

C -0.701886 -0.860941 1.000000

import pandas as pd

df = pd.read_csv("p3_data2.tsv", "\t")

print(df.head())

ID Advertising costs Part-time Labour costs

0 1 362438 8763

1 2 51725 9258

2 3 236472 9897

3 4 232080 5005

4 5 262733 9918

df2 = df.drop(["ID"], axis=1) # the axis=1 parameter indicates that we are dropping a column.

print("Correlation")

print(df2.corr())

Correlation

Advertising costs Part-time Labour costs

Advertising costs 1.000000 -0.014986

Part-time Labour costs -0.014986 1.000000