multivars_linear_aggression.py

import pandas as pd
import numpy as np
import statsmodels.api as sm
from sys import exit


# try whatever you want
listX = ['day_week', 'fog', 'rain', 'weekday']

df = pd.read_csv('../improved_data_set/turnstile_weather_v2.csv', index_col=0)
dk = pd.DataFrame(df.groupby(listX)['ENTRIESn_hourly'].mean().reset_index())

X = dk[listX]
y = dk['ENTRIESn_hourly']

X = sm.add_constant(X)
est = sm.OLS(y, X).fit()

print est.summary()