polyreg.py

# -*- coding: utf-8 -*-
"""PolyReg.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/13CkobJpabwBk1hNDR3wlik8S9NEWOLI2
"""

# Commented out IPython magic to ensure Python compatibility.
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import pylab as pl
# %matplotlib inline

!wget -O FuelConsumption.csv https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/FuelConsumptionCo2.csv

df = pd.read_csv("FuelConsumption.csv")
df.head()

regrdata = df[['ENGINESIZE', 'CYLINDERS', 'FUELCONSUMPTION_COMB', 'CO2EMISSIONS']]
regrdata.head(9)

plt.scatter(regrdata.ENGINESIZE, regrdata.CO2EMISSIONS, color = 'blue')
plt.xlabel = "Engine size"
plt.ylabel = 'Emissions'
plt.show()

tra  = np.random.rand(len(df)) < 0.8
train = regrdata[tra]
test = regrdata[~tra]
test.head()

from sklearn.preprocessing import PolynomialFeatures
from sklearn import linear_model

train_x = np.asanyarray(train[['ENGINESIZE']])
train_y = np.asanyarray(train[['CO2EMISSIONS']])
test_x = np.asanyarray(test[['ENGINESIZE']])
test_y = np.asanyarray(test[['CO2EMISSIONS']])
polyreg = PolynomialFeatures(degree=3)
trainxpol = polyreg.fit_transform(train_x)
trainxpol

lin = linear_model.LinearRegression()
train_y_ = lin.fit(trainxpol, train_y)
print('Coefficients:',  lin.coef_)
print("Intercepts",  lin.intercept_)

plt.scatter(train.ENGINESIZE, train.CO2EMISSIONS,  color='blue')
XX = np.arange(0.0, 10.0, 0.1)
yy = lin.intercept_[0]+ lin.coef_[0][1]*XX+ lin.coef_[0][2]*np.power(XX, 2) + lin.coef_[0][3]*np.power(XX,3)
plt.plot(XX, yy, )

from sklearn.metrics import r2_score

test_x_poly = polyreg.fit_transform(test_x)
test_y_ = lin.predict(test_x_poly)

print("Mean absolute error: %.2f" % np.mean(np.absolute(test_y_ - test_y)))
print("Residual sum of squares (MSE): %.2f" % np.mean((test_y_ - test_y) ** 2))
print("R2-score: %.2f" % r2_score(test_y_ , test_y) )