def main():
parser = argparse.ArgumentParser(description="层次聚类算法Scratch代码命令行参数")
parser.add_argument("--k", type=int, default=3, help="聚类中心")
args = parser.parse_args()
X, y = load_iris(return_X_y=True)
xtrain, _, ytrain, _ = train_test_split(X, y, train_size=0.8, shuffle=True)
model = HierarchicalClusterScratch(args.k)
model.fit(xtrain)
y_pred = model.predict(xtrain)
# 用真实标签绘制散点图
plot_scatter(xtrain, ytrain)
# 用聚类标签绘制散点图
plot_scatter(xtrain, y_pred)
def main():
parser = argparse.ArgumentParser(description="kmeans算法Scratch代码命令行参数")
parser.add_argument("--k", type=int, default=3, help="聚类中心")
parser.add_argument("--max_iter", type=int, default=1000, help="最大迭代次数")
args = parser.parse_args()
X, y = load_iris(return_X_y=True)
xtrain, _, ytrain, _ = train_test_split(X, y, train_size=0.8, shuffle=True)
model = KMeansScratch(args.k, args.max_iter)
model.fit(xtrain)
y_pred = model.predict(xtrain)
# 用真实标签绘制散点图
plot_scatter(xtrain, ytrain)
# 用聚类标签绘制散点图
plot_scatter(xtrain, y_pred)
def main():
parser = argparse.ArgumentParser(description="高斯混合模型算法Scratch代码命令行参数")
parser.add_argument("--k", type=int, default=3, help="聚类中心或高斯模型个数")
parser.add_argument("--max_iter", type=int, default=1000, help="最大迭代次数")
parser.add_argument("--tolerance", type=float, default=1e-6, help="模型收敛阈值")
args = parser.parse_args()
X, y = load_iris(return_X_y=True)
xtrain, _, ytrain, _ = train_test_split(X, y, train_size=0.8, shuffle=True)
model = GMMScratch(args.k, args.max_iter, args.tolerance)
model.fit(xtrain)
y_pred = model.predict(xtrain)
# 用真实标签绘制散点图
plot_scatter(xtrain, ytrain)
# 用聚类标签绘制散点图
plot_scatter(xtrain, y_pred)
import sys
import numpy as np
import math
from util import plot_scatter
data_points_B = np.asarray([[-0.5, 1], [0, 1], [0.25, 0.75], [-0.5, 0.5],
[0.5, 0.5], [-0.5, 0], [0, 0], [0.25, -0.25],
[-0.5, -0.5], [0.5, -0.5], [0.25, -0.75],
[-0.5, -1], [0, -1], [0.25, 0.25], [-0.25, 0]]) * 2
def gaussian_mixture_B(batchsize, std=0.1):
mean = data_points_B[np.random.choice(range(len(data_points_B)),
batchsize)]
return np.random.normal(mean, std**2, (batchsize, 2)).astype(np.float32)
def gaussian_mixture(batchsize, num_cluster=8, scale=2, std=0.2):
rand_indices = np.random.randint(0, num_cluster, size=batchsize)
base_angle = math.pi * 2 / num_cluster
angle = rand_indices * base_angle - math.pi / 2
mean = np.zeros((batchsize, 2), dtype=np.float32)
mean[:, 0] = np.cos(angle) * scale
mean[:, 1] = np.sin(angle) * scale
return np.random.normal(mean, std**2, (batchsize, 2)).astype(np.float32)
if __name__ == '__main__':
plot_scatter(gaussian_mixture(1000), dir='.', color='red')
print('-- begin training --')
with tf.Session() as sess:
saver = tf.train.Saver()
init = tf.global_variables_initializer()
sess.run(init)
for epoch in range(epoch_num):
print('** epoch {} begin **'.format(epoch))
g_obj = 0.0
d_obj = 0.0
# plot p_g
batch_z = np.random.normal(0, 1, [10000, z_dim]).astype(np.float32)
tmp = model.generate(sess, batch_z)
plot_scatter(tmp, 'result', epoch, None)
for step in range(num_one_epoch):
# draw from p_z
batch_z = np.random.normal(0, 1, [batch_size, z_dim]).astype(
np.float32)
# draw from p_data
#batch_inputs = gaussian_mixture(batch_size)
batch_inputs = gaussian_mixture_B(batch_size)
# train discriminator
d_obj += model.training_disc(sess, batch_z, batch_inputs)
# train generator
init = tf.global_variables_initializer()
sess.run(init)
for epoch in range(epoch_num):
print('** epoch {} begin **'.format(epoch))
g_obj = 0.0
d_obj = 0.0
for step in range(num_one_epoch):
# draw from p_z
batch_z = np.random.normal(0, 1, [batch_size, z_dim]).astype(np.float32)
# draw from p_data
batch_inputs = gaussian_mixture(batch_size)
# train discriminator
d_obj += model.training_disc(sess, batch_z, batch_inputs)
# train generator
g_obj += model.training_gen(sess, batch_z)
print('epoch:{}, d_obj = {}, g_obj = {}'.format(epoch,
d_obj/num_one_epoch,
g_obj/num_one_epoch))
# plot p_g
batch_z = np.random.normal(0, 1, [10000, z_dim]).astype(np.float32)
tmp = model.generate(sess, batch_z)
plot_scatter(tmp, 'result', epoch)
saver.save(sess, './model.dump')
print('-- begin training --')
num_one_epoch = 50
with tf.Session() as sess:
saver = tf.train.Saver()
init = tf.global_variables_initializer()
sess.run(init)
for epoch in range(epoch_num):
plotting = []
for i in range(50):
batch_z = np.random.normal(0, 1, [batch_size, z_dim]).astype(
np.float32)
tmp = model.generate(sess, batch_z)
plotting.extend([list(_) for _ in tmp])
plot_scatter(np.asarray(plotting), 'result', epoch)
print('** epoch {} begin **'.format(epoch))
g_obj = 0.0
d_obj = 0.0
for step in range(num_one_epoch):
for i in range(2):
batch_z = np.random.normal(
0, 1, [batch_size, z_dim]).astype(np.float32)
#batch_inputs = gaussian_mixture(batch_size)
batch_inputs = gaussian_mixture_B(batch_size)
model.training_disc(sess, batch_z, batch_inputs)
batch_z = np.random.normal(0, 1, [batch_size, z_dim]).astype(
np.float32)
#batch_inputs = gaussian_mixture(batch_size)
