逻辑回归实践

#生成200条二分类数据（2个特征）
from sklearn.datasets import make_blobs
X, y = make_blobs(n_samples= 200, n_features= 2, centers = 2, random_state = 8)
print(X)

#数据可视化
import matplotlib.pyplot as plt
%matplotlib inline
plt.scatter(X[:,0],X[:,1], c = y, cmap = plt.cm.spring, edgecolors = 'k')

梯度下降法实现逻辑回归

#添加全1列
import numpy as np
x_ones = np.ones((X.shape[0],1))
X = np.hstack((X,x_ones))
print(X)

#拆分数据
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 8)
#查看数据维度
print(X.shape, X_train.shape, X_test.shape)
print(y.shape, y_train.shape, y_test.shape)

#将因变量转为列向量
y_train = y_train.reshape(-1,1)
y_test = y_test.reshape(-1,1)
print(y_train.shape, y_test.shape)

#初始化theta值
theta = np.ones([X_train.shape[1],1])
#设置步长值
alpha = 0.001
#定义sigmoid函数
def sigmoid(z):
    s = 1.0 / (1 + np.exp(-z))
    return s
num_iters = 10000
for i in range(num_iters):
    h = sigmoid(np.dot(X_train, theta))
    theta = theta - alpha * np.dot(X_train.T, (h - y_train)) / 140
print(theta)

#预测
pred_y = sigmoid(np.dot(X_test, theta))
#预测结果二值化
pred_y[pred_y > 0.5] = 1
pred_y[pred_y <= 0.5] = 0
print("预测准确率：", np.sum(pred_y == y_test) / len(y_test))

逻辑回归——Kaggle糖尿病预测实战

#导入数据
import pandas as pd
data = pd.read_csv("pima-indians-diabetes.data.csv")
data

#分离特征变量和分类变量
X = data.iloc[:, :-1]
y = data.iloc[:, -1]

#特征标准化
mu = X.mean(axis = 0)
std = X.std(axis = 0)
X = (X - mu) / std

#添加全1列
import numpy as np
x_ones = np.ones((X.shape[0],1))
X = np.hstack((X, x_ones))

#拆分训练集和测试集
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 8)
print(X.shape, X_train.shape, X_test.shape)
print(y.shape, y_train.shape, y_test.shape)

#将因变量转为列向量
y_train = y_train.values.reshape(-1,1)
y_test = y_test.values.reshape(-1,1)
print(y_train.shape, y_test.shape)

#初始化theta值
theta = np.ones([X_train.shape[1],1])
theta

#设置步长值
alpha = 0.001
#定义sigmoid函数
def sigmoid(z):
    s = 1.0 / (1 + np.exp(-z))
    return s
num_iters = 10000
for i in range(num_iters):
    h = sigmoid(np.dot(X_train, theta))
    theta = theta - alpha * np.dot(X_train.T, (h - y_train)) / 537
print(theta)

#预测
pred_y = sigmoid(np.dot(X_test, theta))
print(pred_y)

#预测结果二值化
pred_y[pred_y > 0.5] = 1
pred_y[pred_y <= 0.5] = 0
print(pred_y.reshape(1, -1))

print(y_test.reshape(1, -1))

print("预测准确率：", np.sum(pred_y == y_test) / len(y_test))

逻辑回归实现三分类

#导入iris数据集
from sklearn.datasets import load_iris
iris = load_iris()

#分离自变量、因变量
X = iris.data
y = iris.target

#拆分训练集和测试集
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state = 8)

#导入逻辑回归模块
from sklearn.linear_model import LogisticRegression

#"三板斧"
logis = LogisticRegression()
logis.fit(X_train, y_train)

#模型预估
logis.score(X_test, y_test)

from sklearn.metrics import classification_report
print(classification_report(y_test, logis.predict(X_test)))

#等价于选择参数：multi_class = 'multinomial',solver='lbfgs'
logis2 = LogisticRegression(multi_class = 'multinomial',solver='lbfgs')
logis2.fit(X_train, y_train)

logis2.score(X_test, y_test)

#若选择参数：multi_class = 'ovr',solver='lbfgs'
logis3 = LogisticRegression(multi_class = 'ovr',solver='lbfgs')
logis3.fit(X_train, y_train)

logis3.score(X_test, y_test)

原文地址：https://blog.csdn.net/2301_78286654/article/details/137183550

免责声明：本站文章内容转载自网络资源，如本站内容侵犯了原著者的合法权益，可联系本站删除。更多内容请关注自学内容网（zxcms.com）！