def visualize_nn():
x, y = DataUtil.gen_xor()
nn = NNDist()
nn.add("ReLU", (x.shape[1], 6))
nn.add("ReLU", (6, ))
nn.add("Softmax", (y.shape[1], ))
nn.fit(x, y, epoch=1000, draw_detailed_network=True)
def visualize_nn():
x, y = DataUtil.gen_xor()
nn = NNDist()
nn.add("ReLU", (x.shape[1], 6))
nn.add("ReLU", (6,))
nn.add("Softmax", (y.shape[1],))
nn.fit(x, y, epoch=1000, draw_detailed_network=True)
def main():
nn = NNDist()
epoch = 1000
x, y = DataUtil.gen_xor(100)
nn.add(ReLU((x.shape[1], 24)))
nn.add(CrossEntropy((y.shape[1], )))
nn.fit(x, y, epoch=epoch)
nn.evaluate(x, y)
def main():
nn = NNDist()
epoch = 1000
x, y = DataUtil.gen_xor(100)
nn.add(ReLU((x.shape[1], 24)))
nn.add(CrossEntropy((y.shape[1],)))
nn.fit(x, y, epoch=epoch)
nn.evaluate(x, y)
def main():
nn = NNDist()
save = False
load = False
lr = 0.001
lb = 0.001
epoch = 1000
timing = Timing(enabled=True)
timing_level = 1
x, y = DataUtil.gen_xor()
if not load:
nn.add("ReLU", (x.shape[1], 2))
nn.add("ReLU", (3, ))
nn.add("ReLU", (3, ))
nn.add("CrossEntropy", (y.shape[1], ))
nn.optimizer = "Adam"
nn.preview()
nn.feed_timing(timing)
nn.fit(x,
y,
lr=lr,
lb=lb,
verbose=1,
epoch=epoch,
batch_size=128,
train_only=True,
draw_detailed_network=True)
if save:
nn.save()
nn.draw_results()
nn.visualize2d()
else:
nn.load()
nn.preview()
nn.evaluate(x, y)
timing.show_timing_log(timing_level)
def main(visualize=True):
# x, y = DataUtil.get_dataset("balloon1.0(en)", "../_Data/balloon1.0(en).txt")
x, y = DataUtil.get_dataset(
"test", "/Users/lily/Documents/MachineLearning-master/_Data/test.txt")
fit_time = time.time()
tree = CartTree(whether_continuous=[False] * 4)
tree.fit(x, y, train_only=True)
fit_time = time.time() - fit_time
if visualize:
tree.view()
estimate_time = time.time()
tree.evaluate(x, y)
estimate_time = time.time() - estimate_time
print("Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(fit_time, estimate_time,
fit_time + estimate_time))
if visualize:
tree.visualize()
train_num = 6000
(x_train, y_train), (x_test, y_test), *_ = DataUtil.get_dataset(
"mushroom",
"/Users/lily/Documents/MachineLearning-master/_Data/mushroom.txt",
tar_idx=0,
train_num=train_num)
fit_time = time.time()
tree = C45Tree()
tree.fit(x_train, y_train)
fit_time = time.time() - fit_time
if visualize:
tree.view()
estimate_time = time.time()
tree.evaluate(x_train, y_train)
tree.evaluate(x_test, y_test)
estimate_time = time.time() - estimate_time
print("Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(fit_time, estimate_time,
fit_time + estimate_time))
if visualize:
tree.visualize()
x, y = DataUtil.gen_xor(one_hot=False)
fit_time = time.time()
tree = CartTree()
tree.fit(x, y, train_only=True)
fit_time = time.time() - fit_time
if visualize:
tree.view()
estimate_time = time.time()
tree.evaluate(x, y, n_cores=1)
estimate_time = time.time() - estimate_time
print("Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(fit_time, estimate_time,
fit_time + estimate_time))
if visualize:
tree.visualize2d(x, y, dense=1000)
tree.visualize()
wc = [False] * 16
continuous_lst = [0, 5, 9, 11, 12, 13, 14]
for _cl in continuous_lst:
wc[_cl] = True
train_num = 2000
(x_train, y_train), (x_test, y_test), *_ = DataUtil.get_dataset(
"bank1.0",
"/Users/lily/Documents/MachineLearning-master/_Data/bank1.0.txt",
train_num=train_num,
quantize=True)
fit_time = time.time()
tree = CartTree()
tree.fit(x_train, y_train)
fit_time = time.time() - fit_time
if visualize:
tree.view()
estimate_time = time.time()
tree.evaluate(x_test, y_test)
estimate_time = time.time() - estimate_time
print("Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(fit_time, estimate_time,
fit_time + estimate_time))
if visualize:
tree.visualize()
tree.show_timing_log()
def fit(self, x, y, n_hidden=None, use_scipy=None):
if n_hidden is None:
n_hidden = self._params["n_hidden"]
if use_scipy is None:
use_scipy = self._params["use_scipy"]
self._func_cache = self._func(x, y, n_hidden)
if not use_scipy:
line_search = None if self._line_search is None else self._line_search(self._func_cache)
self._opt_cache = self._opt(self._func_cache, line_search)
else:
self._opt_cache = ScipyOpt(self._func_cache)
self._opt_cache.opt()
self._mat1, self._mat2 = self._func_cache.mat1, self._func_cache.mat2
def predict(self, x, get_raw_results=False, **kwargs):
y_raw = np.maximum(0, np.atleast_2d(x).dot(self._mat1)).dot(self._mat2)
y_pred = 1 / (1 + np.exp(-y_raw)) # type: np.ndarray
if get_raw_results:
return y_pred
return np.argmax(y_pred, axis=1)
data, labels = DataUtil.gen_xor()
nn = NN(GradientDescent, Wolfe)
nn.fit(data, labels)
nn.evaluate(data, labels)
nn.visualize2d(data, labels)
# Draw Training Curve
plt.figure()
plt.plot(np.arange(len(nn["opt_cache"].log))+1, nn["opt_cache"].log)
plt.show()
def main():
# _x, _y = DataUtil.get_dataset("balloon1.0(en)", "../_Data/balloon1.0(en).txt")
_x, _y = DataUtil.get_dataset("test", "../_Data/test.txt")
_fit_time = time.time()
_tree = CartTree(whether_continuous=[False] * 4)
_tree.fit(_x, _y, train_only=True)
_fit_time = time.time() - _fit_time
_tree.view()
_estimate_time = time.time()
_tree.estimate(_x, _y)
_estimate_time = time.time() - _estimate_time
print(
"Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
_fit_time, _estimate_time,
_fit_time + _estimate_time
)
)
_tree.visualize()
train_num = 6000
(x_train, y_train), (x_test, y_test), *_ = DataUtil.get_dataset(
"mushroom", "../_Data/mushroom.txt", tar_idx=0, train_num=train_num)
_fit_time = time.time()
_tree = C45Tree()
_tree.fit(x_train, y_train)
_fit_time = time.time() - _fit_time
_tree.view()
_estimate_time = time.time()
_tree.estimate(x_train, y_train)
_tree.estimate(x_test, y_test)
_estimate_time = time.time() - _estimate_time
print(
"Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
_fit_time, _estimate_time,
_fit_time + _estimate_time
)
)
_tree.visualize()
_x, _y = DataUtil.gen_xor(one_hot=False)
_fit_time = time.time()
_tree = CartTree()
_tree.fit(_x, _y, train_only=True)
_fit_time = time.time() - _fit_time
_tree.view()
_estimate_time = time.time()
_tree.estimate(_x, _y)
_estimate_time = time.time() - _estimate_time
print(
"Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
_fit_time, _estimate_time,
_fit_time + _estimate_time
)
)
_tree.visualize2d(_x, _y)
_tree.visualize()
_wc = [False] * 16
_continuous_lst = [0, 5, 9, 11, 12, 13, 14]
for _cl in _continuous_lst:
_wc[_cl] = True
train_num = 2000
(x_train, y_train), (x_test, y_test), *_ = DataUtil.get_dataset(
"bank1.0", "../_Data/bank1.0.txt", train_num=train_num, quantize=True)
_fit_time = time.time()
_tree = CartTree()
_tree.fit(x_train, y_train)
_fit_time = time.time() - _fit_time
_tree.view()
_estimate_time = time.time()
_tree.estimate(x_test, y_test)
_estimate_time = time.time() - _estimate_time
print(
"Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
_fit_time, _estimate_time,
_fit_time + _estimate_time
)
)
_tree.visualize()
_tree.show_timing_log()
def fit(self, x, y, n_hidden=None, use_scipy=None):
if n_hidden is None:
n_hidden = self._params["n_hidden"]
if use_scipy is None:
use_scipy = self._params["use_scipy"]
self._func_cache = self._func(x, y, n_hidden)
if not use_scipy:
line_search = None if self._line_search is None else self._line_search(self._func_cache)
self._opt_cache = self._opt(self._func_cache, line_search)
else:
self._opt_cache = ScipyOpt(self._func_cache)
self._opt_cache.opt()
self._mat1, self._mat2 = self._func_cache.mat1, self._func_cache.mat2
def predict(self, x, get_raw_results=False):
y_raw = np.maximum(0, np.atleast_2d(x).dot(self._mat1)).dot(self._mat2)
y_pred = 1 / (1 + np.exp(-y_raw)) # type: np.ndarray
if get_raw_results:
return y_pred
return np.argmax(y_pred, axis=1)
data, labels = DataUtil.gen_xor()
nn = NN(GradientDescent, Wolfe)
nn.fit(data, labels)
nn.evaluate(data, labels)
nn.visualize2d(data, labels)
# Draw Training Curve
plt.figure()
plt.plot(np.arange(len(nn["opt_cache"].log))+1, nn["opt_cache"].log)
plt.show()
def main(visualize=True):
# x, y = DataUtil.get_dataset("balloon1.0(en)", "../_Data/balloon1.0(en).txt")
x, y = DataUtil.get_dataset("test", "../_Data/test.txt")
fit_time = time.time()
tree = CartTree(whether_continuous=[False] * 4)
tree.fit(x, y, train_only=True)
fit_time = time.time() - fit_time
if visualize:
tree.view()
estimate_time = time.time()
tree.evaluate(x, y)
estimate_time = time.time() - estimate_time
print(
"Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
fit_time, estimate_time,
fit_time + estimate_time
)
)
if visualize:
tree.visualize()
train_num = 6000
(x_train, y_train), (x_test, y_test), *_ = DataUtil.get_dataset(
"mushroom", "../_Data/mushroom.txt", tar_idx=0, n_train=train_num)
fit_time = time.time()
tree = C45Tree()
tree.fit(x_train, y_train)
fit_time = time.time() - fit_time
if visualize:
tree.view()
estimate_time = time.time()
tree.evaluate(x_train, y_train)
tree.evaluate(x_test, y_test)
estimate_time = time.time() - estimate_time
print(
"Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
fit_time, estimate_time,
fit_time + estimate_time
)
)
if visualize:
tree.visualize()
x, y = DataUtil.gen_xor(one_hot=False)
fit_time = time.time()
tree = CartTree()
tree.fit(x, y, train_only=True)
fit_time = time.time() - fit_time
if visualize:
tree.view()
estimate_time = time.time()
tree.evaluate(x, y, n_cores=1)
estimate_time = time.time() - estimate_time
print(
"Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
fit_time, estimate_time,
fit_time + estimate_time
)
)
if visualize:
tree.visualize2d(x, y, dense=1000)
tree.visualize()
wc = [False] * 16
continuous_lst = [0, 5, 9, 11, 12, 13, 14]
for _cl in continuous_lst:
wc[_cl] = True
train_num = 2000
(x_train, y_train), (x_test, y_test), *_ = DataUtil.get_dataset(
"bank1.0", "../_Data/bank1.0.txt", n_train=train_num, quantize=True)
fit_time = time.time()
tree = CartTree()
tree.fit(x_train, y_train)
fit_time = time.time() - fit_time
if visualize:
tree.view()
estimate_time = time.time()
tree.evaluate(x_test, y_test)
estimate_time = time.time() - estimate_time
print(
"Model building : {:12.6} s\n"
"Estimation : {:12.6} s\n"
"Total : {:12.6} s".format(
fit_time, estimate_time,
fit_time + estimate_time
)
)
if visualize:
tree.visualize()
tree.show_timing_log()