In [3]:

    

import pandas as pd
%matplotlib inline


    

In [4]:

    

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


    

In [5]:

    

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


    

In [6]:

    

df.head()


    

    
Out[6]:






  

    

      

      
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 [22]:

    

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


    

In [23]:

    

lm.params


    

    
Out[23]:





Intercept   -350.737192
Height         7.717288
dtype: float64

In [29]:

    

def guess_weight(height):
    for item in df['Weight']:
        intercept = -350.737
        weight = height * 7.7 + intercept
    return round(weight)


    

In [30]:

    

guess_weight(70)


    

    
Out[30]:





188