【手撕代码】逻辑回归

import numpy as np
from sklearn import datasets
import numpy as np
import matplotlib.pyplot as plt

# Import helper functions
from utils import make_diagonal, normalize, train_test_split, accuracy_score
from utils import Plot

def sigmoid(x):
    return 1 / (1 + np.exp(-x))


class LogisticRegression():
    """
        Parameters:
        -----------
        n_iterations: int
        learning_rate: float

    """
    def __init__(self, learning_rate=.1, n_iterations=4000):
        self.learning_rate = learning_rate
        self.n_iterations = n_iterations

    def initialize_weights(self, n_features):
        # 初始化参数
        # 参数范围[-1/sqrt(N), 1/sqrt(N)]
        limit = np.sqrt(1 / n_features)
        w = np.random.uniform(-limit, limit, (n_features, 1))
        b = 0
        self.w = np.insert(w, 0, b, axis=0)

    def fit(self, X, y):
        m_samples, n_features = X.shape
        self.initialize_weights(n_features)
        # 为X增加一列特征x1，x1 = 0
        X = np.insert(X, 0, 1, axis=1)
        y = np.reshape(y, (m_samples, 1))

        # 梯度训练n_iterations轮
        for i in range(self.n_iterations):
            h_x = X.dot(self.w)
            y_pred = sigmoid(h_x)
            w_grad = X.T.dot(y_pred - y)
            self.w = self.w - self.learning_rate * w_grad

    def predict(self, X):
        X = np.insert(X, 0, 1, axis=1)
        h_x = X.dot(self.w)
        y_pred = np.round(sigmoid(h_x))
        return y_pred.astype(int)

def main():
    # Load dataset
    data = datasets.load_iris()
    X = normalize(data.data[data.target != 0])
    y = data.target[data.target != 0]
    y[y == 1] = 0
    y[y == 2] = 1

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, seed=1)

    clf = LogisticRegression()
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)
    y_pred = np.reshape(y_pred, y_test.shape)

    accuracy = accuracy_score(y_test, y_pred)
    print("Accuracy:", accuracy)

    # Reduce dimension to two using PCA and plot the results
    Plot().plot_in_2d(X_test, y_pred, title="Logistic Regression", accuracy=accuracy)


main()