Whiteman data joined with Vehicle data(2008- 2013)

whiteman_vehicledata.py

import pandas as pd
import numpy as np
import statsmodels.formula.api as sm
import matplotlib.pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages


whiteman_pems = pd.read_csv('whiteman_pems.csv')
whiteman_cleaned = whiteman_pems.fillna(0)

model = sm.OLS(whiteman_cleaned['h22'],whiteman_cleaned['VHT'])

fitted = model.fit()

summary_file = open('summary.txt', 'w')
summary_file.write(fitted.summary().as_text())

plt.plot(whiteman_cleaned['VHT'], whiteman_cleaned['h22'], 'ro')
plt.plot(whiteman_cleaned['VHT'], fitted.fittedvalues, 'b')

plt.legend(['Data', 'Fitted model'])
plt.xlabel('Vehicle Hours')
plt.ylabel('H22')
plt.title('H22 dependence on traffic')
pp = PdfPages('whiteman_traffic.pdf')
plt.savefig(pp, format='pdf')
pp.close()