In [1]:

    

import pandas as pd
%matplotlib inline


    

In [2]:

    

import matplotlib.pyplot as plt
import statsmodels.formula.api as smf


    

In [3]:

    

df = pd.read_csv("heights_weights_genders.csv")


    

In [4]:

    

df.head()


    

    
Out[4]:






  

    

      

      
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
    
  

In [93]:

    

lm = smf.ols(formula="Weight ~ Height + Gender",data=df).fit()


    

In [94]:

    

lm.params


    

    
Out[94]:





Intercept        -244.923503
Gender[T.Male]     19.377711
Height              5.976941
dtype: float64

In [106]:

    

def guess_weight(height, gender):
    for item in df['Weight']:
        intercept = -244.923503
        male = 19.377711
        if gender == 'Male':
            weight = height * 5.97 + intercept + male
        else:
            weight = height * 5.97 + intercept
    return round(weight)


    

In [107]:

    

guess_weight(70, 'Male')


    

    
Out[107]:





192

In [108]:

    

guess_weight(70, 'Female')


    

    
Out[108]:





173