In [1]:

    

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import statsmodels.formula.api as smf


    

In [2]:

    

cd C:\Users\Harsha Devulapalli\Desktop\algorithms\class5


    

    




C:\Users\Harsha Devulapalli\Desktop\algorithms\class5

In [28]:

    

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


    

In [29]:

    

df.plot(kind="scatter",x="Height",y="Weight")


    

    
Out[29]:





<matplotlib.axes._subplots.AxesSubplot at 0x1fbce6eb0f0>






    

In [30]:

    

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


    

In [39]:

    

lm.params


    

    
Out[39]:





Intercept   -350.737192
Height         7.717288
dtype: float64

In [32]:

    

intercept, slope = lm.params


    

In [33]:

    

df.plot(kind="scatter",x="Height",y="Weight")
plt.plot(df["Height"],slope*df["Height"]+intercept,"-",color="red")


    

    
Out[33]:





[<matplotlib.lines.Line2D at 0x1fbce6f2c18>]






    

In [36]:

    

def getweight(height):
    weight = slope*height+intercept
    return weight


    

In [38]:

    

getweight(69)


    

    
Out[38]:





181.75565540205253

In [ ]: