def __init__(self,
data,
labels,
polynomial_degree=0,
sinusoid_degree=0,
normalize_data=True):
"""
1. data preprocess
2. get the number of features
3. initialize
"""
data_processed, features_mean, features_deviation = \
prepare_for_training(data, polynomial_degree=0, sinusoid_degree=0, normalize_data=True)
self.data = data_processed
self.labels = labels
self.features_mean = features_mean
self.features_deviation = features_deviation
self.polynomial_degree = polynomial_degree
self.sinusoid_degree = sinusoid_degree
self.normalize_data = normalize_data
# features: x(1), x(2), x(3)...
num_features = self.data.shape[1]
# Θ matrix
self.theta = np.zeros((num_features, 1))
def __init__(self,
data,
labels,
polynomial_degree=0,
sinusoid_degree=0,
normalize_data=True):
"""
1.对数据进行预处理操作
2.先得到所有的特征个数
3.初始化参数矩阵
"""
(data_processed, features_mean,
features_deviation) = prepare_for_training(data,
polynomial_degree,
sinusoid_degree,
normalize_data=True)
self.data = data_processed
self.labels = labels
self.features_mean = features_mean
self.features_deviation = features_deviation
self.polynomial_degree = polynomial_degree
self.sinusoid_degree = sinusoid_degree
self.normalize_data = normalize_data
num_features = self.data.shape[1]
self.theta = np.zeros((num_features, 1))
def __init__(self,
data,
labels,
polynomial_degree=0,
sinusoid_degree=0,
normalize_data=False):
"""
1.对数据进行预处理操作
2.先得到所有的特征个数
3.初始化参数矩阵
"""
(data_processed, features_mean,
features_deviation) = prepare_for_training(data,
polynomial_degree,
sinusoid_degree,
normalize_data=False)
self.data = data_processed
self.labels = labels
self.unique_labels = np.unique(labels)
self.features_mean = features_mean
self.features_deviation = features_deviation
self.polynomial_degree = polynomial_degree
self.sinusoid_degree = sinusoid_degree
self.normalize_data = normalize_data
num_features = self.data.shape[1]
num_unique_labels = self.unique_labels.shape[0]
# 参数为二维矩阵，行为标签种类数目，列为参数
self.theta = np.zeros((num_unique_labels, num_features))
def __init__(self,
data,
labels,
polynomial_degree=0,
sinusoid_degree=0,
normalize_data=True):
"""
1. data preprocess
2. get the number of features
3. initialize
"""
data_processed, features_mean, features_deviation = \
prepare_for_training(data, polynomial_degree=0, sinusoid_degree=0, normalize_data=True)
self.data = data_processed
self.labels = labels
# multi-class will have unique_labels classes
# thus have
self.unique_labels = np.unique(labels)
self.features_mean = features_mean
self.features_deviation = features_deviation
self.polynomial_degree = polynomial_degree
self.sinusoid_degree = sinusoid_degree
self.normalize_data = normalize_data
# features: x(1), x(2), x(3)...
num_features = self.data.shape[1]
# np.unique(labels).shape: (num_labels,)
num_unique_labels = np.unique(labels).shape[0]
# Θ matrix, since we have multiple classes, the first dimension is num_unique_labels
self.theta = np.zeros((num_unique_labels, num_features))
def predict(self, data):
"""
预测
:param data:
:return:
"""
data_processed = prepare_for_training(data, self.polynomial_degree, self.sinusoid_degree, self.normalize_data)[0]
return np.dot(data_processed, self.theta)
def __init__(self, data, labels, layers, normalize_data=False):
data_processed = prepare_for_training(data,
normalize_data=normalize_data)[0]
self.data = data_processed
self.labels = labels
self.layers = layers #784 25 10
self.normalize_data = normalize_data
self.thetas = MultilayerPerceptron.thetas_init(layers)
def predict(self, data):
"""
predict after training
"""
data_processed = \
prepare_for_training(data, self.polynomial_degree, self.sinusoid_degree, self.normalize_data)[0]
return LinearRegression.make_prediction(data_processed, self.theta)
def loss(self, data):
"""
损失值
:param data:
:return:
"""
data_processed = prepare_for_training(data, self.polynomial_degree, self.sinusoid_degree, self.normalize_data)[0]
return data_processed
def predict(self, data):
data_processed = prepare_for_training(
data, normalize_data=self.normalize_data)[0]
num_examples = data_processed.shape[0]
predictions = MultilayerPerceptron.feedforward_propagation(
data_processed, self.thetas, self.layers)
return np.argmax(predictions, axis=1).reshape((num_examples, 1))
def predict(self,data):
num_examples = data.shape[0]
data_processed = prepare_for_training(data, self.polynomial_degree, self.sinusoid_degree,self.normalize_data)[0]
prob = LogisticRegression.hypothesis(data_processed,self.theta.T)
max_prob_index = np.argmax(prob, axis=1)
class_prediction = np.empty(max_prob_index.shape,dtype=object)
for index,label in enumerate(self.unique_labels):
class_prediction[max_prob_index == index] = label
return class_prediction.reshape((num_examples,1))
def predict(self, data):
"""
用训练的参数模型，与预测得到回归值结果
"""
data_processed = prepare_for_training(
data, self.polynomial_degree, self.sinusoid_degree, self.normalize_data
)[0]
predictions = LinearRegression.hypothesis(data_processed, self.theta)
return predictions
def predict(self, data):
num_examples = data.shape[0]
data_processed, features_mean, features_deviation = prepare_for_training(
data,
self.polynomial_degree,
self.sinusoid_degree,
normalize_data=self.normalize_data)
prob = self.hypothesis(data_processed, self.theta.T)
prob_index = np.argmax(prob, axis=1) # 找出行最大值的位置, 即找出预测概率值的最大值的位置
class_prediction = np.empty(prob_index.shape, dtype=object)
for index, label in enumerate(self.unique_labels):
class_prediction[prob_index == index] = label
return class_prediction.reshape((num_examples, 1))
def predict(self, data):
"""
预测
:param data:
:return:
"""
num_examples = data.shape[0]
data_processed, *_ = prepare_for_training(data, self.polynomial_degree,
self.sinusoid_degree,
self.normalize_data)
predictions = self.hypothesis(data_processed, self.theta.T)
max_prob_index = np.argmax(predictions, axis=1) # 找出概率值最大的所在位置
predict_cls = np.empty(max_prob_index.shape, dtype=object) # 初始化预测标签
for index, label in enumerate(self.unique_labels):
predict_cls[max_prob_index == index] = label
return predict_cls.reshape((num_examples, 1))
def __init__(self, data, labels, polynomial_degree=0, sinusoid_degree=0, normalize_data=True):
"""
1、对数据进行预处理
2、先得到所有的参数个数
3、初始化参数矩阵
:param data:
:param labels:
:param polynomial_degree:
:param sinusoid_degree:
:param normalize_data:
"""
data_processed, features_mean, features_deviation = prepare_for_training(
data, polynomial_degree, sinusoid_degree, normalize_data)
self.data = data_processed
self.labels = labels
self.features_mean = features_mean
self.polynomial_degree = polynomial_degree
self.sinusoid_degree = sinusoid_degree
self.normalize_data = normalize_data
num_features = self.data.shape[1]
self.theta = np.zeros((num_features, 1))
def __init__(self,
data,
labels,
polynomial_degree=0,
sinusoid_degree=0,
normalize_data=False):
data_processed, features_mean, features_deviation = prepare_for_training(
data, polynomial_degree, sinusoid_degree, normalize_data)
self.data = data_processed
self.labels = labels
self.unique_labels = np.unique(
labels) # 标签个数(不重复)--多分类标签个数，如二分类，就是0, 1
self.features_mean = features_mean
self.features_deviation = features_deviation
self.polynomial_degree = polynomial_degree
self.sinusoid_degree = sinusoid_degree
self.normalize_data = normalize_data
num_features = self.data.shape[1]
num_unique_labels = self.unique_labels.shape[0]
self.theta = np.zeros(
(num_unique_labels, num_features
)) # 每个特征对应一个theta, 每个类别对应一组theta值, 以鸢尾花数据为例，theta值是一组3行4列的值
def __init__(self,
data,
labels,
polynomial_degree=0,
sinusoid_degree=0,
normalize_data=False):
data_processed, features_mean, features_deviation = prepare_for_training(
data, polynomial_degree, sinusoid_degree, normalize_data)
self.data = data_processed
self.labels = labels
self.features_mean = features_mean
self.features_deviation = features_deviation
self.polynomial_degree = polynomial_degree
self.sinusoid_degree = sinusoid_degree
self.normalize_data = normalize_data
self.num_examples, self.num_features = self.data.shape
self.unique_labels = np.unique(self.labels) # labels里有多少个不同值(分为几类)
self.num_unique_labels, *_ = self.unique_labels.shape
self.theta = np.zeros(
(self.num_unique_labels, self.num_features)) # 初始化theta
def get_cost(self, data, labels):
data_processed = prepare_for_training(
data, self.polynomial_degree, self.sinusoid_degree, self.normalize_data
)[0]
return self.cost_function(data_processed, labels)
def get_loss(self, data, labels):
data_processed = prepare_for_training(data, self.polynomial_degree,
self.sinusoid_degree,
self.normalize_data)[0]
return self.caluate_loss(data_processed, labels)