In [2]:

    

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


    

In [5]:

    

cd ..


    

    




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

In [6]:

    

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


    

In [7]:

    

maledf = df[(df['Gender'] == 'Male')]


    

In [8]:

    

femaledf = df[(df['Gender'] == 'Female')]


    

In [9]:

    

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


    

    
Out[9]:





<matplotlib.axes._subplots.AxesSubplot at 0x183c13b12e8>






    

In [12]:

    

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


    

In [13]:

    

lm.params


    

    
Out[13]:





Intercept   -224.498841
Height         5.961774
dtype: float64

In [15]:

    

intercept, slope = lm.params


    

In [16]:

    

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


    

    
Out[16]:





[<matplotlib.lines.Line2D at 0x183c2b84630>]






    

In [17]:

    

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


    

In [18]:

    

getmaleweight(75)


    

    
Out[18]:





222.63419519661883

In [20]:

    

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


    

In [21]:

    

lm.params


    

    
Out[21]:





Intercept   -246.013266
Height         5.994047
dtype: float64

In [22]:

    

intercept, slope = lm.params


    

In [23]:

    

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


    

    
Out[23]:





[<matplotlib.lines.Line2D at 0x183c28d0518>]






    

In [24]:

    

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


    

In [25]:

    

getfemaleweight(69)


    

    
Out[25]:





167.57595067828643

In [ ]: