def fit(self, x):
n_sample = x.shape[0]
self.dbw.fit(x)
x_bins = self.dbw.transform(x)
# 初始化模型参数
self.default_y_prob = np.log(0.5 / self.n_components) # 默认p_y
for y_label in range(0, self.n_components):
self.p_x_y[y_label] = {}
self.p_y[y_label] = np.log(1.0 / self.n_components) # 初始p_y设置一样
self.default_x_prob[y_label] = np.log(0.5 / n_sample) # 默认p_x_y
# 初始p_x_y设置一样
for j in range(0, x_bins.shape[1]):
self.p_x_y[y_label][j] = {}
x_j_set = set(x_bins[:, j])
for x_j in x_j_set:
# 随机抽样计算条件概率
sample_x_index = np.random.choice(
n_sample, n_sample // self.n_components)
sample_x_bins = x_bins[sample_x_index]
p_x_y = (np.sum(sample_x_bins[:, j] == x_j) +
1) / (sample_x_bins.shape[0] + len(x_j_set))
self.p_x_y[y_label][j][x_j] = np.log(p_x_y)
# 计算隐变量
W_log = self.get_log_w(x_bins)
W = utils.softmax(W_log)
W_gen = np.exp(W_log)
current_log_loss = np.log(W_gen.sum(axis=1)).sum()
# 迭代训练
current_epoch = 0
for _ in range(0, self.n_iter):
if self.verbose is True:
utils.plot_decision_function(x, self.predict(x), self)
utils.plt.pause(0.1)
utils.plt.clf()
# 更新模型参数
for k in range(0, self.n_components):
self.p_y[k] = np.log(np.sum(W[:, k]) / n_sample)
for j in range(0, x_bins.shape[1]):
x_j_set = set(x_bins[:, j])
for x_j in x_j_set:
self.p_x_y[k][j][x_j] = np.log(
1e-10 +
np.sum(W[:, k] *
(x_bins[:, j] == x_j)) / np.sum(W[:, k]))
# 更新隐变量
W_log = self.get_log_w(x_bins)
W = utils.softmax(W_log)
W_gen = np.exp(W_log)
# 计算log like hold
new_log_loss = np.log(W_gen.sum(axis=1)).sum()
if new_log_loss - current_log_loss > self.tol:
current_log_loss = new_log_loss
current_epoch += 1
else:
print('total epochs:', current_epoch)
break
if self.verbose:
utils.plot_decision_function(x, self.predict(x), self)
utils.plt.show()
def fit(self, x):
n_sample = x.shape[0]
# 初始化模型参数
self.default_y_prob = np.log(0.5 / self.n_components) # 默认p_y
for y_label in range(0, self.n_components):
self.p_x_y[y_label] = {}
self.p_y[y_label] = 1.0 / self.n_components # 初始p_y设置一样
# 初始p_x_y设置一样
for j in range(0, x.shape[1]):
self.p_x_y[y_label][j] = {}
u = np.mean(x[:, j], axis=0) + np.random.random() * (
x[:, j].max() + x[:, j].min()) / 2
sigma = np.std(x[:, j])
self.p_x_y[y_label][j] = [u, sigma]
# 计算隐变量
W = self.get_w(x)
current_log_loss = np.log(W.sum(axis=1)).sum()
W = W / np.sum(W, axis=1, keepdims=True)
# 迭代训练
current_epoch = 0
for _ in range(0, self.n_iter):
if self.verbose is True:
utils.plot_decision_function(x, self.predict(x), self)
utils.plt.pause(0.1)
utils.plt.clf()
# 更新模型参数
for k in range(0, self.n_components):
self.p_y[k] = np.sum(W[:, k]) / n_sample
for j in range(0, x.shape[1]):
x_j = x[:, j]
u = np.sum(x_j * W[:, k]) / np.sum(W[:, k])
sigma = np.sqrt(
np.sum(
(x_j - u) * (x_j - u) * W[:, k]) / np.sum(W[:, k]))
self.p_x_y[k][j] = [u, sigma]
# 更新隐变量
W = self.get_w(x)
new_log_loss = np.log(W.sum(axis=1)).sum()
W = W / np.sum(W, axis=1, keepdims=True)
if new_log_loss - current_log_loss > self.tol:
current_log_loss = new_log_loss
current_epoch += 1
else:
print('total epochs:', current_epoch)
break
if self.verbose:
utils.plot_decision_function(x, self.predict(x), self)
utils.plt.show()
os.chdir('../')
from sklearn.datasets import make_classification
from ml_models import utils
data, target = make_classification(n_samples=100,
n_features=2,
n_classes=2,
n_informative=1,
n_redundant=0,
n_repeated=0,
n_clusters_per_class=1,
class_sep=3.0)
from ml_models.svm import HardMarginSVM, SoftMarginSVM
svm = SoftMarginSVM()
svm.fit(data, target, show_train_process=True)
# 计算F1
from sklearn.metrics import f1_score
print(f1_score(target, svm.predict(data)))
print(np.sum(np.abs(target - svm.predict(data))))
utils.plt.close()
utils.plot_decision_function(data, target, svm, svm.support_vectors)
utils.plt.show()
print('support vector', svm.support_vectors)
from sklearn.datasets import make_classification
from ml_models import utils
from ml_models.linear_model import LogisticRegression
from ml_models.tree import CARTClassifier
from ml_models.svm import SVC
data, target = make_classification(n_samples=100,
n_features=2,
n_classes=2,
n_informative=1,
n_redundant=0,
n_repeated=0,
n_clusters_per_class=1,
class_sep=0.5)
X_train, X_test, y_train, y_test = model_selection.train_test_split(
data, target, test_size=0.1)
from ml_models.ensemble import BaggingClassifier
classifier = BaggingClassifier(base_estimator=CARTClassifier(), n_estimators=3)
classifier.fit(X_train, y_train)
# # 计算F1
from sklearn.metrics import f1_score
print(f1_score(y_test, classifier.predict(X_test)))
print(np.sum(np.abs(y_test - classifier.predict(X_test))))
#
utils.plot_decision_function(X_train, y_train, classifier)
utils.plt.show()
from sklearn.datasets.samples_generator import make_blobs import numpy as np X, y = make_blobs(n_samples=400, centers=4, cluster_std=0.85, random_state=0) X = X[:, ::-1] # 将0,2类归为0类 y = np.where(y == 2, 0, y) # 将1,3类归为1类 y = np.where(y == 3, 1, y) from ml_models.cluster import LVQ kmeans = LVQ(class_label=[0, 0, 1, 1]) kmeans.fit(X, y) from ml_models import utils utils.plot_decision_function(X, y, kmeans) utils.plt.show()
import os
os.chdir('../')
from sklearn.datasets import make_classification
from ml_models import utils
data, target = make_classification(n_samples=100,
n_features=2,
n_classes=2,
n_informative=1,
n_redundant=0,
n_repeated=0,
n_clusters_per_class=1,
class_sep=.3)
from ml_models.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(max_bins=20)
tree.fit(data, target)
tree.prune(alpha=1)
# # 计算F1
from sklearn.metrics import f1_score
print(f1_score(target, tree.predict(data)))
print(np.sum(np.abs(target - tree.predict(data))))
#
utils.plot_decision_function(data, target, tree)
utils.plt.show()
import numpy as np
import os
from sklearn import model_selection
os.chdir('../')
from sklearn.datasets import make_classification
from ml_models import utils
data, target = make_classification(n_samples=100, n_features=2, n_classes=2, n_informative=1, n_redundant=0,
n_repeated=0, n_clusters_per_class=1, class_sep=.3, random_state=44)
X_train, X_test, y_train, y_test = model_selection.train_test_split(data, target, test_size=0.1, random_state=0)
from ml_models.tree import CARTClassifier
tree = CARTClassifier()
tree.fit(X_train, y_train)
tree.prune(5)
# # 计算F1
from sklearn.metrics import f1_score
print(f1_score(y_test, tree.predict(X_test)))
print(np.sum(np.abs(y_test - tree.predict(X_test))))
#
utils.plot_decision_function(X_train, y_train, tree)
utils.plt.show()
from sklearn.datasets.samples_generator import make_blobs X, y = make_blobs(n_samples=400, centers=4, cluster_std=0.85, random_state=0) X = X[:, ::-1] from ml_models.cluster import AGNES agnes = AGNES(k=4) agnes.fit(X) from ml_models import utils utils.plot_decision_function(X, y, agnes) utils.plt.show()
from sklearn.datasets.samples_generator import make_blobs from ml_models import utils X, y = make_blobs(n_samples=400, centers=4, cluster_std=0.85, random_state=0) X = X[:, ::-1] from ml_models.pgm import SemiGaussianNBClassifier nb = SemiGaussianNBClassifier(link_rulers=[(0, 1)]) nb.fit(X, y) print(nb.predict_proba(X).shape) utils.plot_decision_function(X, y, nb) utils.plt.show()
from sklearn.datasets.samples_generator import make_blobs from ml_models import utils X, y = make_blobs(n_samples=400, centers=4, cluster_std=0.85, random_state=0) X = X[:, ::-1] from ml_models.em import GMMClassifier gmm = GMMClassifier(n_iter=100) gmm.fit(X, y) print(gmm.predict(X)) utils.plot_decision_function(X, y, gmm) utils.plt.show()
"""
二分类
"""
from ml_models import utils
from sklearn.datasets import make_classification
data, target = make_classification(n_samples=200, n_features=2, n_classes=2, n_informative=1, n_redundant=0,
n_repeated=0, n_clusters_per_class=1)
# ffm=FFM(batch_size=1, epochs=20, solver='adam',objective='logistic')
# ffm.fit(data,target,show_log=True)
# utils.plot_decision_function(data,target,ffm)
# utils.plt.show()
"""
多分类
"""
from sklearn.datasets.samples_generator import make_blobs
X, y = make_blobs(n_samples=400, centers=4, cluster_std=0.85, random_state=0)
X = X[:, ::-1]
from ml_models.wrapper_models import *
#
ffm = FFM(epochs=10, solver='adam', objective='logistic')
ovo = MultiClassWrapper(ffm, mode='ovo')
ovo.fit(X, y)
utils.plot_decision_function(X, y, ovo)
utils.plt.show()
from sklearn.datasets import make_classification, make_moons
import numpy as np
from ml_models import utils
from ml_models.svm import SVC
X, y = make_classification(n_samples=500, n_features=2,
n_informative=2, n_redundant=0,
n_repeated=0, n_classes=2,
n_clusters_per_class=1, weights=[0.05, 0.95],
class_sep=3, flip_y=0.05, random_state=0)
# X, y = make_moons(noise=0.01)
weights = np.where(y == 0, 50, 1)
svc_with_sample_weight = SVC(kernel='rbf', gamma=2.0)
svc_with_sample_weight.fit(X, y, sample_weight=weights, show_train_process=True)
utils.plot_decision_function(X=X, y=y, clf=svc_with_sample_weight)
