feature_names = np.array(X[0])
# Remove the first row because they are feature names
return np.array(X[1:]).astype(np.float32), np.array(y[1:]).astype(np.float32), feature_names
if __name__=='__main__':
# Load the dataset from the input file
X, y, feature_names = load_dataset(sys.argv[1])
X, y = shuffle(X, y, random_state=7)
# Split the data 80/20 (80% for training, 20% for testing)
num_training = int(0.9 * len(X))
X_train, y_train = X[:num_training], y[:num_training]
X_test, y_test = X[num_training:], y[num_training:]
# Fit Random Forest regression model
rf_regressor = RandomForestRegressor(n_estimators=1000, max_depth=10, min_samples_split=1)
rf_regressor.fit(X_train, y_train)
# Evaluate performance of Random Forest regressor
y_pred = rf_regressor.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
evs = explained_variance_score(y_test, y_pred)
print "\n#### Random Forest regressor performance ####"
print "Mean squared error =", round(mse, 2)
print "Explained variance score =", round(evs, 2)
# Plot relative feature importances
plot_feature_importances(rf_regressor.feature_importances_, 'Random Forest regressor', feature_names)
np.float32), feature_names
if __name__ == '__main__':
# Load the dataset from the input file
X, y, feature_names = load_dataset(sys.argv[1])
X, y = shuffle(X, y, random_state=7)
# Split the data 80/20 (80% for training, 20% for testing)
num_training = int(0.9 * len(X))
X_train, y_train = X[:num_training], y[:num_training]
X_test, y_test = X[num_training:], y[num_training:]
# Fit Random Forest regression model
rf_regressor = RandomForestRegressor(n_estimators=1000,
max_depth=10,
min_samples_split=1)
rf_regressor.fit(X_train, y_train)
# Evaluate performance of Random Forest regressor
y_pred = rf_regressor.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
evs = explained_variance_score(y_test, y_pred)
print "\n#### Random Forest regressor performance ####"
print "Mean squared error =", round(mse, 2)
print "Explained variance score =", round(evs, 2)
# Plot relative feature importances
plot_feature_importances(rf_regressor.feature_importances_,
'Random Forest regressor', feature_names)
evs = explained_variance_score(y_test, y_pred_dt)
print("\n#### Decision Tree performance ####")
print("Mean squared error =", round(mse, 2))
print("Explained variance score =", round(evs, 2))
y_pred_ab = ab_regressor.predict(X_test)
mse = mean_squared_error(y_test, y_pred_ab)
evs = explained_variance_score(y_test, y_pred_ab)
print("\n#### AdaBoost performance ####")
print("Mean squared error =", round(mse, 2))
print("Explained variance score =", round(evs, 2))
#relative importance of features
plot_feature_importances(dt_regressor.feature_importances_,
'Decision Tree regressor', housing_data.feature_names)
plot_feature_importances(ab_regressor.feature_importances_,
'AdaBoost regressor', housing_data.feature_names)
def plot_feature_importances(feature_importances, title, feature_names):
# Normalize the importance values
feature_importances = 100.0 * (feature_importances / max(feature_importances))
# Sort the index values and flip them so that they are arranged in decreasing order of importance
index_sorted = np.flipud(np.argsort(feature_importances))
# Center the location of the labels on the X-axis (for display purposes only)
pos = np.arange(index_sorted.shape[0]) + 0.5
# Plot the bar graph
plt.figure()
plt.bar(pos, feature_importances[index_sorted], align='center')
plt.xticks(pos, feature_names[index_sorted])
plt.ylabel('Relative Importance')
plt.title(title)