

In [1]:

    
import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt # package for doing plotting (necessary for adding the line)
import statsmodels.formula.api as smf # package we'll be using for linear regression

Assignment 1

Use the data from heights_weights_genders.csv to create a simple predictor that takes in a person's height and guesses their weight based on a model using all the data, regardless of gender. Find the weights and use those in your function (i.e. don't generate a model each time)



In [2]:

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



In [11]:

    
df.head()



In [4]:

    
lm = smf.ols(formula="Weight~Height",data=df).fit() #notice the formula regresses Y on X (Y~X)



In [5]:

    
lm.params #get the parameters from the model fit









    Out[5]:





Intercept   -350.737192
Height         7.717288
dtype: float64



In [6]:

    
intercept, slope = lm.params



In [8]:

    
df.plot(kind="scatter",x="Height",y="Weight")
plt.plot(df["Height"],slope*df["Height"]+intercept,"-",color="red") #we create the best fit line from the values in the fit model









    Out[8]:





[<matplotlib.lines.Line2D at 0x10769cbe0>]



In [49]:

    
def weight_predictor(height):
    return slope*height + intercept



In [50]:

    
weight_predictor(73.847017)









    Out[50]:





219.16147979082859



In [ ]:

	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