def main():
print("-- Gradient Boosting Classification --")
data = datasets.load_iris()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
clf = GradientBoostingClassifier(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
pca = PCA()
pca.plot_in_2d(X_test,
y_pred,
title="Gradient Boosting",
accuracy=accuracy,
legend_labels=data.target_names)
print("-- Gradient Boosting Regression --")
X, y = datasets.make_regression(n_features=1,
n_samples=150,
bias=0,
noise=5)
X_train, X_test, y_train, y_test = train_test_split(standardize(X),
y,
test_size=0.5)
clf = GradientBoostingRegressor(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.scatter(X_test[:, 0], y_pred, color='green')
plt.title("Gradient Boosting Regression (%.2f MSE)" % mse)
plt.show()
def main():
X, y = datasets.make_regression(n_features=1, n_samples=100, bias=0, noise=5)
X_train, X_test, y_train, y_test = train_test_split(standardize(X), y, test_size=0.3)
clf = RegressionTree()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
# Print the mean squared error
print "Mean Squared Error:", mean_squared_error(y_test, y_pred)
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.scatter(X_test[:, 0], y_pred, color='green')
plt.show()
def main():
print ("-- Gradient Boosting Classification --")
data = datasets.load_iris()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
clf = GradientBoostingClassifier(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print ("Accuracy:", accuracy)
pca = PCA()
pca.plot_in_2d(X_test, y_pred,
title="Gradient Boosting",
accuracy=accuracy,
legend_labels=data.target_names)
print ("-- Gradient Boosting Regression --")
X, y = datasets.make_regression(n_features=1, n_samples=150, bias=0, noise=5)
X_train, X_test, y_train, y_test = train_test_split(standardize(X), y, test_size=0.5)
clf = GradientBoostingRegressor(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print ("Mean Squared Error:", mse)
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.scatter(X_test[:, 0], y_pred, color='green')
plt.title("Gradient Boosting Regression (%.2f MSE)" % mse)
plt.show()
def main():
print("-- Classification Tree --")
data = datasets.load_iris()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.4,
seed=2)
clf = ClassificationTree()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print("Accuracy:", accuracy_score(y_test, y_pred))
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
print("-- Regression Tree --")
X, y = datasets.make_regression(n_features=1,
n_samples=100,
bias=0,
noise=5)
X_train, X_test, y_train, y_test = train_test_split(standardize(X),
y,
test_size=0.3)
clf = RegressionTree()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print("Mean Squared Error:", mean_squared_error(y_test, y_pred))
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.scatter(X_test[:, 0], y_pred, color='green')
plt.show()
def main():
print("-- Regression Tree --")
# Load temperature data
data = pd.read_csv('../datasets/TempLinkoping2016.txt', sep="\t")
time = np.atleast_2d(data["time"].as_matrix()).T
temp = np.atleast_2d(data["temp"].as_matrix()).T
X = standardize(time) # Time. Fraction of the year [0, 1]
y = temp[:, 0] # Temperature. Reduce to one-dim
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
model = RegressionTree()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_pred_line = model.predict(X)
# Color map
cmap = plt.get_cmap('viridis')
mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)
# Plot the results
# Plot the results
m1 = plt.scatter(366 * X_train, y_train, color=cmap(0.9), s=10)
m2 = plt.scatter(366 * X_test, y_test, color=cmap(0.5), s=10)
m3 = plt.scatter(366 * X_test, y_pred, color='black', s=10)
plt.suptitle("Regression Tree")
plt.title("MSE: %.2f" % mse, fontsize=10)
plt.xlabel('Day')
plt.ylabel('Temperature in Celcius')
plt.legend((m1, m2, m3), ("Training data", "Test data", "Prediction"),
loc='lower right')
plt.show()