Predicting Energy Efficiency

In [1]:

    

%matplotlib inline

import os
import requests
import pandas as pd 
import matplotlib.pyplot as plt

from pandas.tools.plotting import scatter_matrix

from sklearn import cross_validation as cv
from sklearn.cross_validation import train_test_split as tts

from sklearn.linear_model import Ridge
from sklearn.linear_model import RandomizedLasso
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor

from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error as mse


    

In [ ]:

    

ENERGY = "http://archive.ics.uci.edu/ml/machine-learning-databases/00242/ENB2012_data.xlsx"


    

In [ ]:

    

def download_data(url, path='data'):
    if not os.path.exists(path):
        os.mkdir(path)

    response = requests.get(url)
    name = os.path.basename(url)
    with open(os.path.join(path, name), 'w') as f:
        f.write(response.content)


    

In [ ]:

    

download_data(ENERGY)


    

In [ ]:

    

energy   = pd.read_excel('data/ENB2012_data.xlsx', sep=",")


    

In [ ]:

    

energy.head()


    

In [ ]:

    

energy.columns = ['compactness','surface_area','wall_area','roof_area','height',\
                  'orientation','glazing_area','distribution','heating_load','cooling_load']


    

In [ ]:

    

energy.describe()


    

In [ ]:

    

scatter_matrix(energy, alpha=0.2, figsize=(18,18), diagonal='kde')
plt.show()


    

In [ ]:

    

energy_features = energy.ix[:,0:8]
energy_labels = energy.ix[:,8:]


    

In [ ]:

    

model = RandomizedLasso(alpha=0.1)
model.fit(energy_features, energy_labels["heating_load"])
names = list(energy_features)

print "Features sorted by their score:"
print sorted(zip(map(lambda x: round(x, 4), model.scores_), 
                 names), reverse=True)


    

In [ ]:

    

model = RandomizedLasso(alpha=0.1)
model.fit(energy_features, energy_labels["cooling_load"])
names = list(energy_features)

print "Features sorted by their score:"
print sorted(zip(map(lambda x: round(x, 4), model.scores_), 
                 names), reverse=True)


    

In [ ]:

    

heat_labels = energy.ix[:,8]


    

In [ ]:

    

splits = cv.train_test_split(energy_features, heat_labels, test_size=0.2)
X_train, X_test, y_train, y_test = splits


    

In [ ]:

    

model = Ridge(alpha=0.1)
model.fit(X_train, y_train)

expected = y_test
predicted = model.predict(X_test)

print "Ridge Regression model"
print "Mean Squared Error: %0.3f" % mse(expected, predicted)
print "Coefficient of Determination: %0.3f" % r2_score(expected, predicted)


    

In [ ]:

    

model = LinearRegression()
model.fit(X_train, y_train)

expected = y_test
predicted = model.predict(X_test)

print "Linear Regression model"
print "Mean Squared Error: %0.3f" % mse(expected, predicted)
print "Coefficient of Determination: %0.3f" % r2_score(expected, predicted)


    

In [ ]:

    

model = RandomForestRegressor()
model.fit(X_train, y_train)

expected = y_test
predicted = model.predict(X_test)

print "Random Forest model"
print "Mean squared error = %0.3f" % mse(expected, predicted)
print "R2 score = %0.3f" % r2_score(expected, predicted)