Polynomial Regression using scipy

polynomialRegression.py

import csv
datafile = open('home_data.csv', 'r')
datareader = csv.reader(datafile,delimiter=',')
data = []
for row in datareader:
    data.append(row) 

print data[0]
print data[0][5]
print data[0][3]
print data[0][2]

import numpy as np
import matplotlib.pyplot as plt

from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import make_pipeline
from sklearn import datasets, linear_model

features = []
label = []

xfeatures = []

data.pop(0)

for row in data:
	features.append([float(row[5])/1000, row[3]])
	label.append(row[2])
	xfeatures.append(float(row[5])/1000)

x = np.array(features)
y = np.array(label)

xf = np.array(xfeatures)

x = np.array(x,dtype=float)
y = np.array(y,dtype=float)

xf = np.array(xf,dtype=float)

poly = PolynomialFeatures(3)
X_ = poly.fit_transform(x)

import statsmodels.formula.api as sm
import scipy, scipy.stats

result = sm.OLS( y, X_ ).fit()

print "Regression summary"
print result.summary()

print "Regression coefficients"
print result.params

print "Regression pvalues"
print result.pvalues

from scipy import stats

slope, intercept, r_value, p_value, std_err = stats.linregress(xf,y)

print "For linear regression between sq_ft living and price"
print "slope: ", slope
print "intercept: ", intercept
print "p_value: ", p_value
print "r_value: ", r_value
print "std_err: ", std_err