def _tree_prune(self, tree, X, y):
if not isinstance(tree, TreeNode):
return
Lb = tree.L
Rb = tree.R
self._tree_prune(Lb, X, y)
self._tree_prune(Rb, X, y)
if isinstance(Lb, TreeNode):
pred_no_prone = self.predict(X)
perf_no_prone = mean_error(y, pred_no_prone)
tree.L = Lb.Default
pred_with_prone = self.predict(X)
perf_with_prone = mean_error(y, pred_with_prone)
if perf_with_prone < perf_no_prone:
improve = perf_no_prone - perf_with_prone
logger.info('tree prune, mean error descent %f' % (improve))
else:
tree.L = Lb
if isinstance(Rb, TreeNode):
pred_no_prone = self.predict(X)
perf_no_prone = mean_error(y, pred_no_prone)
tree.R = Rb.Default
pred_with_prone = self.predict(X)
perf_with_prone = mean_error(y, pred_with_prone)
if perf_with_prone < perf_no_prone:
improve = perf_no_prone - perf_with_prone
logger.info('tree prune, mean error descent %f' % (improve))
else:
tree.R = Rb
else:
is_valid = False
nFeat = X.shape[1]
if nFeat == self._nFeat:
is_valid = True
return is_valid
def predict(self, X):
models = self._parameter['trees']
pred = np.zeros(X.shape[0])
for model in models:
pred += np.array(model.predict(X))
return pred
if __name__ == '__main__':
path = os.getcwd() + '/../dataset/winequality-white.csv'
loader = DataLoader(path)
dataset = loader.load(target_col_name='quality')
trainset, testset = dataset.cross_split()
gbdt = GradientBoostingDecisionTree(10)
gbdt.fit(trainset[0], trainset[1])
predict = gbdt.predict(testset[0])
print 'GBDT mean error:', mean_error(testset[1], predict)
dt = DecisionTreeRegressor()
dt.fit(trainset[0], trainset[1])
predict = dt.predict(testset[0])
print 'DecisionTree mean error:', mean_error(testset[1], predict)
if nFeat == self._nFeat:
is_valid = True
return is_valid
def feval(self, parameter, X, y):
y = np.reshape(y, (y.shape[0], 1))
param_list = unroll_parameter(parameter, self._parameter_shape)
W, b = param_list[0], param_list[1]
nSize = X.shape[0]
h = np.dot(X, W) + np.repeat(np.reshape(b, (1, b.shape[0])), X.shape[0], axis=0)
loss = self._lossor.calculate(y, h)
residual = h - y
grad_W = 1. / nSize * np.dot(X.T, residual)
grad_b = 1. / nSize * np.sum(residual)
grad_parameter = roll_parameter([grad_W, grad_b])
return loss, grad_parameter
if __name__ == '__main__':
path = os.getcwd() + '/../dataset/winequality-white.csv'
loader = DataLoader(path)
dataset = loader.load(target_col_name='quality')
trainset, testset = dataset.cross_split()
linear = LinearRegressor(solve_type='numeric', normalize=True, max_iter=2000, batch_size=50,
learning_rate=1e-3,
is_plot_loss=True)
linear.fit(trainset[0], trainset[1])
prediction = linear.predict(testset[0])
performance = mean_error(testset[1], prediction)
print performance
