9-4 实现逻辑回归算法

实现逻辑回归

使用逻辑回归

9-5 决策边界

决策边界

kNN的决策边界

9-4 实现逻辑回归算法

实现逻辑回归

使用逻辑回归

metrics.py

import numpy as np
from math import sqrtdef accuracy_score(y_true, y_predict):"""计算y_true和y_predict之间的准确率"""assert len(y_true) == len(y_predict), \"the size of y_true must be equal to the size of y_predict"return np.sum(y_true == y_predict) / len(y_true)def mean_squared_error(y_true, y_predict):"""计算y_true和y_predict之间的MSE"""assert len(y_true) == len(y_predict), \"the size of y_true must be equal to the size of y_predict"return np.sum((y_true - y_predict)**2) / len(y_true)def root_mean_squared_error(y_true, y_predict):"""计算y_true和y_predict之间的RMSE"""return sqrt(mean_squared_error(y_true, y_predict))def mean_absolute_error(y_true, y_predict):"""计算y_true和y_predict之间的MAE"""assert len(y_true) == len(y_predict), \"the size of y_true must be equal to the size of y_predict"return np.sum(np.absolute(y_true - y_predict)) / len(y_true)def r2_score(y_true, y_predict):"""计算y_true和y_predict之间的R Square"""return 1 - mean_squared_error(y_true, y_predict)/np.var(y_true)

model_selection.py

import numpy as npdef train_test_split(X, y, test_ratio=0.2, seed=None):"""将数据 X 和 y 按照test_ratio分割成X_train, X_test, y_train, y_test"""assert X.shape[0] == y.shape[0], \"the size of X must be equal to the size of y"assert 0.0 <= test_ratio <= 1.0, \"test_ration must be valid"if seed:np.random.seed(seed)shuffled_indexes = np.random.permutation(len(X))test_size = int(len(X) * test_ratio)test_indexes = shuffled_indexes[:test_size]train_indexes = shuffled_indexes[test_size:]X_train = X[train_indexes]y_train = y[train_indexes]X_test = X[test_indexes]y_test = y[test_indexes]return X_train, X_test, y_train, y_test

LogisticRegression.py

import numpy as np
from .metrics import accuracy_scoreclass LogisticRegression:def __init__(self):"""初始化Logistic Regression模型"""self.coef_ = Noneself.intercept_ = Noneself._theta = Nonedef _sigmoid(self, t):return 1. / (1. + np.exp(-t))def fit(self, X_train, y_train, eta=0.01, n_iters=1e4):"""根据训练数据集X_train, y_train, 使用梯度下降法训练Logistic Regression模型"""assert X_train.shape[0] == y_train.shape[0], \"the size of X_train must be equal to the size of y_train"def J(theta, X_b, y):y_hat = self._sigmoid(X_b.dot(theta))try:return - np.sum(y*np.log(y_hat) + (1-y)*np.log(1-y_hat)) / len(y)except:return float('inf')def dJ(theta, X_b, y):return X_b.T.dot(self._sigmoid(X_b.dot(theta)) - y) / len(y)def gradient_descent(X_b, y, initial_theta, eta, n_iters=1e4, epsilon=1e-8):theta = initial_thetacur_iter = 0while cur_iter < n_iters:gradient = dJ(theta, X_b, y)last_theta = thetatheta = theta - eta * gradientif (abs(J(theta, X_b, y) - J(last_theta, X_b, y)) < epsilon):breakcur_iter += 1return thetaX_b = np.hstack([np.ones((len(X_train), 1)), X_train])initial_theta = np.zeros(X_b.shape[1])self._theta = gradient_descent(X_b, y_train, initial_theta, eta, n_iters)self.intercept_ = self._theta[0]self.coef_ = self._theta[1:]return selfdef predict_proba(self, X_predict):"""给定待预测数据集X_predict，返回表示X_predict的结果概率向量"""assert self.intercept_ is not None and self.coef_ is not None, \"must fit before predict!"assert X_predict.shape[1] == len(self.coef_), \"the feature number of X_predict must be equal to X_train"X_b = np.hstack([np.ones((len(X_predict), 1)), X_predict])return self._sigmoid(X_b.dot(self._theta))def predict(self, X_predict):"""给定待预测数据集X_predict，返回表示X_predict的结果向量"""assert self.intercept_ is not None and self.coef_ is not None, \"must fit before predict!"assert X_predict.shape[1] == len(self.coef_), \"the feature number of X_predict must be equal to X_train"proba = self.predict_proba(X_predict)return np.array(proba >= 0.5, dtype='int')def score(self, X_test, y_test):"""根据测试数据集 X_test 和 y_test 确定当前模型的准确度"""y_predict = self.predict(X_test)return accuracy_score(y_test, y_predict)def __repr__(self):return "LogisticRegression()"

LogisticRegression.py是在LinearRegression.py的基础上修改的

LinearRegression.py

import numpy as np
from .metrics import r2_scoreclass LinearRegression:def __init__(self):"""初始化Linear Regression模型"""self.coef_ = Noneself.intercept_ = Noneself._theta = Nonedef fit_normal(self, X_train, y_train):"""根据训练数据集X_train, y_train训练Linear Regression模型"""assert X_train.shape[0] == y_train.shape[0], \"the size of X_train must be equal to the size of y_train"X_b = np.hstack([np.ones((len(X_train), 1)), X_train])self._theta = np.linalg.inv(X_b.T.dot(X_b)).dot(X_b.T).dot(y_train)self.intercept_ = self._theta[0]self.coef_ = self._theta[1:]return selfdef fit_bgd(self, X_train, y_train, eta=0.01, n_iters=1e4):"""根据训练数据集X_train, y_train, 使用梯度下降法训练Linear Regression模型"""assert X_train.shape[0] == y_train.shape[0], \"the size of X_train must be equal to the size of y_train"def J(theta, X_b, y):try:return np.sum((y - X_b.dot(theta)) ** 2) / len(y)except:return float('inf')def dJ(theta, X_b, y):return X_b.T.dot(X_b.dot(theta) - y) * 2. / len(y)def gradient_descent(X_b, y, initial_theta, eta, n_iters=1e4, epsilon=1e-8):theta = initial_thetacur_iter = 0while cur_iter < n_iters:gradient = dJ(theta, X_b, y)last_theta = thetatheta = theta - eta * gradientif (abs(J(theta, X_b, y) - J(last_theta, X_b, y)) < epsilon):breakcur_iter += 1return thetaX_b = np.hstack([np.ones((len(X_train), 1)), X_train])initial_theta = np.zeros(X_b.shape[1])self._theta = gradient_descent(X_b, y_train, initial_theta, eta, n_iters)self.intercept_ = self._theta[0]self.coef_ = self._theta[1:]return selfdef fit_sgd(self, X_train, y_train, n_iters=50, t0=5, t1=50):"""根据训练数据集X_train, y_train, 使用梯度下降法训练Linear Regression模型"""assert X_train.shape[0] == y_train.shape[0], \"the size of X_train must be equal to the size of y_train"assert n_iters >= 1def dJ_sgd(theta, X_b_i, y_i):return X_b_i * (X_b_i.dot(theta) - y_i) * 2.def sgd(X_b, y, initial_theta, n_iters=5, t0=5, t1=50):def learning_rate(t):return t0 / (t + t1)theta = initial_thetam = len(X_b)for i_iter in range(n_iters):indexes = np.random.permutation(m)X_b_new = X_b[indexes,:]y_new = y[indexes]for i in range(m):gradient = dJ_sgd(theta, X_b_new[i], y_new[i])theta = theta - learning_rate(i_iter * m + i) * gradientreturn thetaX_b = np.hstack([np.ones((len(X_train), 1)), X_train])initial_theta = np.random.randn(X_b.shape[1])self._theta = sgd(X_b, y_train, initial_theta, n_iters, t0, t1)self.intercept_ = self._theta[0]self.coef_ = self._theta[1:]return selfdef predict(self, X_predict):"""给定待预测数据集X_predict，返回表示X_predict的结果向量"""assert self.intercept_ is not None and self.coef_ is not None, \"must fit before predict!"assert X_predict.shape[1] == len(self.coef_), \"the feature number of X_predict must be equal to X_train"X_b = np.hstack([np.ones((len(X_predict), 1)), X_predict])return X_b.dot(self._theta)def score(self, X_test, y_test):"""根据测试数据集 X_test 和 y_test 确定当前模型的准确度"""y_predict = self.predict(X_test)return r2_score(y_test, y_predict)def __repr__(self):return "LinearRegression()"

9-5 决策边界

决策边界的公式表示一条直线

y 就是x2

决策边界

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasetsiris = datasets.load_iris()X = iris.data
y = iris.targetX = X[y<2,:2]
y = y[y<2]plt.scatter(X[y==0,0], X[y==0,1], color="red")
plt.scatter(X[y==1,0], X[y==1,1], color="blue")
plt.show()

结果全分类对了，说明其不对的数据在训练数据中，完全能分对测试数据

以上的分类边界都是直线

def plot_decision_boundary(model, axis):x0, x1 = np.meshgrid(np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1, 1),np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1, 1),)X_new = np.c_[x0.ravel(), x1.ravel()]y_predict = model.predict(X_new)zz = y_predict.reshape(x0.shape)from matplotlib.colors import ListedColormapcustom_cmap = ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap)plot_decision_boundary(log_reg, axis=[4, 7.5, 1.5, 4.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

kNN的决策边界

plot_decision_boundary(knn_clf, axis=[4, 7.5, 1.5, 4.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

plot_decision_boundary(knn_clf_all, axis=[4, 8, 1.5, 4.5])
plt.scatter(iris.data[iris.target==0,0], iris.data[iris.target==0,1])
plt.scatter(iris.data[iris.target==1,0], iris.data[iris.target==1,1])
plt.scatter(iris.data[iris.target==2,0], iris.data[iris.target==2,1])
plt.show()

边界不规则，有些边界明显是过拟合的

k越大模型越简单，对应分类边界越规则

knn_clf_all = KNeighborsClassifier(n_neighbors=50)
knn_clf_all.fit(iris.data[:,:2], iris.target)plot_decision_boundary(knn_clf_all, axis=[4, 8, 1.5, 4.5])
plt.scatter(iris.data[iris.target==0,0], iris.data[iris.target==0,1])
plt.scatter(iris.data[iris.target==1,0], iris.data[iris.target==1,1])
plt.scatter(iris.data[iris.target==2,0], iris.data[iris.target==2,1])
plt.show()

第9章逻辑回归学习笔记中相关推荐

人工智能入门算法逻辑回归学习笔记
逻辑回归是一个非常经典的算法,其中也包含了非常多的细节,曾看到一句话:如果面试官问你熟悉哪个机器学习模型,可以说 SVM,但千万别说 LR,因为细节真的太多了. 秉持着精益求精的工匠精神不断对笔记进行 ...
线性回归、逻辑回归学习笔记
学习源代码 import numpy as np import matplotlib.pyplot as plt def true_fun(X): # 这是我们设定的真实函数,即ground trut ...
线性回归、逻辑回归-学习笔记整理
线性回归线性回归(Linear regression)是利用回归方程(函数)对一个或多个自变量(特征值)和因变量(目标值)之间关系进行建模的一种分析方式. 只有一个自变量的情况称为单变量回归,多于一 ...
【逻辑回归学习笔记】
算法描述 1.逻辑回归要做的事就是寻找分界面实现二分类. 2.问题假设:对一堆三角形和正方形分类. 3.数据输入:已知正方形和三角形的坐标和标签. 4.算法过程: 知识储备 1.分类和回归 ①分类的目 ...
天池龙珠训练营逻辑回归学习笔记
1.知识点 "线性回归"试图学得一个线性模型以尽可能准确地预测实值输出标记.线性回归模型一般可简写为 y = w T x + b y = w^{T}x + b y=wTx+b更一般 ...
【机器学习】Logistic回归---学习笔记（重新整理）
Logistic回归学习笔记 Logistic回归学习线路预备知识:建议先去B站学习一下信息量,熵,BL散度,交叉熵的概念. Logistic回归的函数模型损失函数.损失最小化架构对数损失作为损 ...
第三章：zigbee学习笔记之物理层和mac层帧格式分析
本文原地址:https://blog.csdn.net/tainjau/article/details/81634681 IEEE802.15.4工作组致力于无线个人区域网络(wireless per ...
逻辑回归函数学习笔记
继续逻辑回归学习,今日笔记记录. 1.逻辑回归和线性回归的关系:对逻辑回归的概率比取自然对数,则得到的是一个线性函数,推导过程如下. 首先,看逻辑回归的定义其次,计算两个极端y/(1-y),其值为( ...
Elasticsearch7学习笔记(中)
Elasticsearch是实时全文搜索和分析引擎,提供搜集.分析.存储数据三大功能:是一套开放REST和JAVA API等结构提供高效搜索功能,可扩展的分布式系统.它构建于Apache Lucene ...
《C++Primer》第九章-顺序容器-学习笔记(1)-顺序容器定义与操作
<C++Primer>第九章-顺序容器-学习笔记(1) 文章目录 <C++Primer>第九章-顺序容器-学习笔记(1) 摘要顺序容器的定义容器元素的初始化将一个容器初始 ...

第9章逻辑回归学习笔记中

9-4 实现逻辑回归算法

实现逻辑回归

使用逻辑回归

9-5 决策边界

决策边界

kNN的决策边界

第9章逻辑回归学习笔记中相关推荐

最新文章

热门文章

第9章 逻辑回归 学习笔记 中

9-4 实现逻辑回归算法

实现逻辑回归

使用逻辑回归

9-5 决策边界

决策边界

kNN的决策边界

第9章 逻辑回归 学习笔记 中相关推荐

最新文章

热门文章

第9章逻辑回归学习笔记中

第9章逻辑回归学习笔记中相关推荐