gistfile1.txt

#Fit a linear regression line to model IncomePerCapita 'y' as a function of
#PercentCollegeGrad 'x' from the states.csv data set.

### Imports ###
import numpy as np
import pandas as pd
from pandas import Series, DataFrame
import os
os.chdir('/home/edward/workspace/school/datavis')
os.getcwd()
from scipy import stats
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
from numpy.random import randn


### Data Reading & Cleaning ###
states_df = pd.read_csv('./datafiles/states.csv')


### Linear Regression ###
#sns.lmplot(x='PercentCollegeGrad', y='IncomePerCapita', data=states_df)
y = states_df.IncomePerCapita
x = states_df.PercentCollegeGrad
x = sm.add_constant(x)
est = sm.OLS(y, x)
est = est.fit()
est.summary()
est.params



def find_resid(row, b0=est.params[0], b1=est.params[1]):
    return row['IncomePerCapita'] - (b0 + b1*row['PercentCollegeGrad'])

states_df['Residual'] = states_df.apply(find_resid, axis=1)



### Sorting & Printing ###
states_df_sorted = states_df.sort(['Residual'], ascending=False)
print(states_df_sorted['Name'])