def main():
print ("-- Regression Tree --")
# Load temperature data
data = pd.read_csv('../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()
def __init__(self, n_estimators, learning_rate, min_samples_split,
min_impurity, max_depth, regression):
self.n_estimators = n_estimators
self.learning_rate = learning_rate
self.min_samples_split = min_samples_split
self.min_impurity = min_impurity
self.max_depth = max_depth
self.regression = regression
self.bar = progressbar.ProgressBar(widgets=bar_widgets)
self.loss = SquareLoss() #回归树残差 -(y - y_pred)
if not self.regression: #分类树残差 y - p
self.loss = SotfMaxLoss()
#分类问题也使用回归树，利用残差去学习概率
self.trees = []
for i in range(self.n_estimators):
self.trees.append(
RegressionTree(min_samples_split=self.min_samples_split,
min_impurity=self.min_impurity,
max_depth=self.max_depth))
def __init__(self, n_estimators, learning_rate, min_samples_split,
min_impurity, max_depth, regression):
self.n_estimators = n_estimators
self.learning_rate = learning_rate
self.min_samples_split = min_samples_split
self.min_impurity = min_impurity
self.max_depth = max_depth
self.regression = regression
self.bar = progressbar.ProgressBar(widgets=bar_widgets)
if self.regression:
self.loss = SquareLoss()
else:
self.loss = SotfMaxLoss()
# also use RegressionTree for classification problems, we study the probability
self.trees = [
RegressionTree(min_samples_split=self.min_samples_split,
min_impurity=self.min_impurity,
max_depth=self.max_depth)
for _ in range(self.n_estimators)
]
def main():
print("-- Regression Tree --")
# Load temperature data
data = pd.read_csv('../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()