In [18]:

    

import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt # package for doing plotting (necessary for adding the line)
from sklearn.linear_model import LinearRegression # package for doing linear regression (there are others)
import numpy as np # necessary for working with the data and getting it properly shaped


    

In [3]:

    

df = pd.read_excel("data/height_weight.xlsx")


    

In [32]:

    

df.plot(kind="scatter",x="height",y="weight") # do a scatter plot of the data


    

    
Out[32]:





<matplotlib.axes.AxesSubplot at 0x108e44490>






    

In [4]:

    

df.corr() # calculate r (coefficent of correlation)


    

    
Out[4]:






  

    

      

      
height
      
weight
    
  
  

    

      
height
      
1.000000
      
0.877785
    
    

      
weight
      
0.877785
      
1.000000
    
  

In [44]:

    

data = np.asarray(df[['weight','height']]) #convert the dataframe to a nparray
x, y = data[:, 1:], data[:, 0] #assign the values to variables and reshape the data


    

In [59]:

    

data


    

    
Out[59]:





array([[  50.5,   51.3],
       [  77. ,   56.3],
       [  84. ,   56.5],
       [  83. ,   57.3],
       [  85. ,   57.5],
       [  99.5,   59. ],
       [  84.5,   59.8],
       [  84. ,   62.5],
       [ 112.5,   62.5],
       [ 102.5,   62.8],
       [ 102.5,   63.5],
       [  90. ,   64.3],
       [ 128. ,   64.8],
       [  98. ,   65.3],
       [ 112. ,   66.5],
       [ 112. ,   66.5],
       [ 133. ,   67. ],
       [ 112.5,   69. ],
       [ 150. ,   72. ]])

In [37]:

    

lr = LinearRegression() # create a LinearRegression object


    

In [60]:

    

type(lr)


    

    
Out[60]:





sklearn.linear_model.base.LinearRegression

In [45]:

    

lr.fit(x,y) #fit the data to the values


    

    
Out[45]:





LinearRegression(copy_X=True, fit_intercept=True, normalize=False)

In [49]:

    

m = lr.coef_[0] # the slope of our regression line


    

In [50]:

    

m


    

    
Out[50]:





3.8990302687839535

In [51]:

    

b = lr.intercept_ # the y-intercept (value when x = 0)


    

In [53]:

    

b


    

    
Out[53]:





-143.02691843935344

In [52]:

    

# plot the linear regression line on the scatter plot
df.plot(kind="scatter",x="height",y="weight")
plt.plot(df['height'],m*df['height']+b,'-')


    

    
Out[52]:





[<matplotlib.lines.Line2D at 0x108f14550>]






    

In [54]:

    

# simple function to predict values based on coefficients
def pred_weight(height):
    return (3.8990302687839535*height) + (-143.02691843935344)


    

In [55]:

    

pred_weight(70) #test the function


    

    
Out[55]:





129.9052003755233

In [57]:

    

# predict for a given value
lr.predict(70)


    

    
Out[57]:





129.90520037552329

In [58]:

    

# calculate the R-squared (coefficient of determination)
lr.score(x,y)


    

    
Out[58]:





0.77050684271597392

In [61]:

    

df2 = pd.read_csv("data/heights_weights_genders.csv")


    

In [62]:

    

df2.plot(kind="scatter",x="Height",y="Weight")


    

    
Out[62]:





<matplotlib.axes.AxesSubplot at 0x1090e2350>






    

In [63]:

    

df.describe()


    

    
Out[63]:






  

    

      

      
height
      
weight
    
  
  

    

      
count
      
19.000000
      
19.000000
    
    

      
mean
      
62.336842
      
100.026316
    
    

      
std
      
5.127075
      
22.773933
    
    

      
min
      
51.300000
      
50.500000
    
    

      
25%
      
58.250000
      
84.250000
    
    

      
50%
      
62.800000
      
99.500000
    
    

      
75%
      
65.900000
      
112.250000
    
    

      
max
      
72.000000
      
150.000000
    
  

In [ ]:

    

# create the linear regression line and predict the weight for your height. How close is it?