“机器学习”系列之Logistic Regression (逻辑回归)

import numpy as npimport matplotlib.pyplot as plt

x = np.arange(-5.0 , 5.0 , 0.02)
y = 1 / (1 + np.exp(-x))
plt.xlabel('x')
plt.ylabel('y = Sigmoid(x)')
plt.title('Sigmoid')
plt.plot(x , y)
plt.show()

from math import expimport numpy as npimport pandas as pdimport matplotlib.pyplot as plt
%matplotlib inlinefrom sklearn.datasets import load_irisfrom sklearn.model_selection import train_test_split

# datadef create_data():
    iris = load_iris()
    df = pd.DataFrame(iris.data, columns=iris.feature_names)
    df['label'] = iris.target
    df.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']
    data = np.array(df.iloc[:100, [0,1,-1]])    # print(data)
    return data[:,:2], data[:,-1]

X, y = create_data()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

import math

class LogisticReressionClassifier:
    def __init__(self, max_iter=200, learning_rate=0.02):
        self.max_iter = max_iter
        self.learning_rate = learning_rate    
    # sigmoid激活函数
    def sigmoid(self, x):
        return 1 / (1 + exp(-x))    def data_matrix(self, X):
        data_mat = []        for d in X:
            data_mat.append([1.0, *d])        return data_mat    def fit(self, X, y):
        # label = np.mat(y)
        data_mat = self.data_matrix(X) # m*n
        self.weights = np.zeros((len(data_mat[0]),1), dtype=np.float32)        for iter_ in range(self.max_iter):            for i in range(len(X)):
                result = self.sigmoid(np.dot(data_mat[i], self.weights))
                error = y[i] - result 
                self.weights += self.learning_rate * error * np.transpose([data_mat[i]])        print('LogisticRegression Model(learning_rate={},max_iter={})'.format(self.learning_rate, self.max_iter))    # def f(self, x):
    #     return -(self.weights[0] + self.weights[1] * x) / self.weights[2]

    def score(self, X_test, y_test):
        right = 0
        X_test = self.data_matrix(X_test)        for x, y in zip(X_test, y_test):
            result = np.dot(x, self.weights)            if (result > 0 and y == 1) or (result < 0 and y == 0):
                right += 1
        return right / len(X_test)

lr_clf = LogisticReressionClassifier()
lr_clf.fit(X_train, y_train)

lr_clf.score(X_test, y_test)

x_ponits = np.arange(4, 8)
y_ = -(lr_clf.weights[1]*x_ponits + lr_clf.weights[0])/lr_clf.weights[2]
plt.plot(x_ponits, y_)#lr_clf.show_graph()plt.scatter(X[:50,0],X[:50,1], label='0')
plt.scatter(X[50:,0],X[50:,1], label='1')
plt.legend()

from sklearn.linear_model import LogisticRegression

clf = LogisticRegression(max_iter=200)

clf.fit(X_train, y_train)

clf.score(X_test, y_test)

print(clf.coef_, clf.intercept_)

x_ponits = np.arange(4, 8)
y_ = -(clf.coef_[0][0]*x_ponits + clf.intercept_)/clf.coef_[0][1]
plt.plot(x_ponits, y_)

plt.plot(X[:50, 0], X[:50, 1], 'bo', color='blue', label='0')
plt.plot(X[50:, 0], X[50:, 1], 'bo', color='orange', label='1')
plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend()