def __init__(self, n_estimators, learning_rate, min_samples_split,
min_impurity, max_depth, regression, debug):
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.init_estimate = None
self.regression = regression
self.debug = debug
self.multipliers = []
# Square loss for regression
# Log loss for classification
self.loss = SquareLoss()
if not self.regression:
self.loss = LogisticLoss()
# Initialize regression trees
self.trees = []
for _ in range(n_estimators):
tree = RegressionTree(min_samples_split=self.min_samples_split,
min_impurity=min_impurity,
max_depth=self.max_depth)
self.trees.append(tree)
def __init__(self, n_estimators, learning_rate, min_samples_split,
min_impurity, max_depth, regression, debug):
self.n_estimators = n_estimators # Number of trees
self.learning_rate = learning_rate
self.min_samples_split = min_samples_split # The minimum n of sampels to justify split
self.min_impurity = min_impurity # Minimum variance reduction to continue
self.max_depth = max_depth # Maximum depth for tree
self.init_estimate = None # The initial prediction of y
self.regression = regression
self.debug = debug
# Square loss for regression
# Log loss for classification
self.loss = SquareLoss()
if not self.regression:
self.loss = LogisticLoss()
# Initialize regression trees
self.trees = []
for _ in range(n_estimators):
tree = RegressionTree(min_samples_split=self.min_samples_split,
min_impurity=min_impurity,
max_depth=self.max_depth)
self.trees.append(tree)
def __init__(self,
n_estimators, # int 树的个数
learning_rate, # 梯度下降的学习速率
min_samples_split, # 每棵子树叶子节点中数据的最小数目
min_impurity, # 每棵子树的最小纯度
max_depth, # 每棵子树的最大深度
regression=True # boolean 是否为回归问题
):
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 regression:
self.loss = SquareLoss()
else:
self.loss = SoftmaxLoss()
self.trees = []
for _ in range(self.n_estimators):
tree = 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, max_depth=2,
min_split_samples=2, min_impurity=1e-7, regression=False):
self.n_estimators = n_estimators
self.learning_rate = learning_rate
self.regression = regression
if self.regression:
self.loss = SquareLoss()
else:
self.loss = CrossEntropy()
self.trees = []
for _ in range(n_estimators):
tree = RegressionTree(max_depth=max_depth,
min_split_samples=min_split_samples,
min_impurity=min_impurity)
self.trees.append(tree)
def __init__(self,
n_estimators=20,
learning_rate=0.5,
min_samples_split=20,
min_var_red=1e-4,
max_depth=4):
self.n_estimators = n_estimators # Number of trees
self.learning_rate = learning_rate
self.min_samples_split = min_samples_split
self.min_var_red = min_var_red # Minimum variance reduction to continue
self.max_depth = max_depth # Maximum depth for tree
self.init_estimate = None
# Initialize regression trees
self.trees = []
for _ in range(n_estimators):
self.trees.append(
RegressionTree(min_samples_split=self.min_samples_split,
min_impurity=min_var_red,
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)
# Square loss for regression
# Log loss for classification
self.loss = SquareLoss()
if not self.regression:
self.loss = CrossEntropy()
# Initialize regression trees
self.trees = []
for _ in range(n_estimators):
tree = RegressionTree(min_samples_split=self.min_samples_split,
min_impurity=min_impurity,
max_depth=self.max_depth)
self.trees.append(tree)
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()
from decision_tree import RegressionTree
# Get data from train dataset
my_data = np.genfromtxt('./datasets/Train_Datasets.csv', delimiter=',', skip_header=1, dtype=None, encoding=None)
X = np.zeros(shape=(1, 11))
y = np.zeros(shape=(1, 1))
for data in my_data:
raw = list(data)
data = np.array([raw[:-1]])
target = np.array([raw[-1]])
X = np.vstack((data, X))
y = np.vstack((target, y))
X, y = my_data[:, :-1], my_data[:, -1]
models = RegressionTree()
# X = X[:-1]
# y = y[:-1]
models.fit(X, y)
filename = 'models_version_one.sav'
pickle.dump(models, open(filename, 'wb'))
loaded_model = pickle.load(open(filename, 'rb'))
# Test predict for some input
args = sys.argv[1:]
if len(args) < 4:
args = ['FDT07',5.82,'reg',0,'Fruits and Vegetables',256.633,'OUT049',1999,'Medium','Tier 1','Supermarket Type1']
print(loaded_model.predict(np.array([args])),
2050.664)