In [ ]:
#Using the heights_weights_genders.csv, analyze the difference between the height weight correlation in women and men.

In [1]:
import pandas as pd
import numpy as np

In [2]:
df = pd.read_csv("data/heights_weights_genders.csv")

In [5]:
df.head(10)


Out[5]:
Gender Height Weight
0 Male 73.847017 241.893563
1 Male 68.781904 162.310473
2 Male 74.110105 212.740856
3 Male 71.730978 220.042470
4 Male 69.881796 206.349801
5 Male 67.253016 152.212156
6 Male 68.785081 183.927889
7 Male 68.348516 167.971110
8 Male 67.018950 175.929440
9 Male 63.456494 156.399676

In [6]:
df_m = df[df['Gender'].str.contains("Male")]
df_w = df[df['Gender'].str.contains("Female")]

In [11]:
df_m.corr()


Out[11]:
Height Weight
Height 1.000000 0.862979
Weight 0.862979 1.000000

In [12]:
df_w.corr()


Out[12]:
Height Weight
Height 1.000000 0.849609
Weight 0.849609 1.000000

In [ ]: