分类算法-逻辑回归
逻辑回归是一个最基本的二分类,也能得出概率值,将线性回归的式子作为输入,通过sigmoid函数转化为分类
损失函数 优化
损失函数
均方误差和对数似然损失
逻辑回归API
def logistic():
"""逻辑分类做二分类进行癌症预测(根据属性特征)"""
# 构造列名
column_name = ['Sample code number', 'Clump Thickness', 'Uniformity of Cell Size', 'Uniformity of Cell Shape',
'Marginal Adhesion', 'Single Epithelial Cell Size', 'Bare Nuclei', 'Bland Chromatin',
'Normal Nucleoli', 'Mitoses', 'Class']
# 读取数据
data = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast"
"-cancer-wisconsin.data", names=column_name)
print(data.head(10))
# 进行缺失值处理
data = data.replace(to_replace='?', value=np.nan)
data = data.dropna()
# 进行数据的分割
x_train, x_test, y_train, y_test = train_test_split(data[column_name[1:10]], data[column_name[10]], test_size=0.25)
# 进行标准化处理
std = StandardScaler()
x_train = std.fit_transform(x_train)
x_test = std.transform(x_test)
# 逻辑回归预测
lg = LogisticRegression(C=1.0)
lg.fit(x_train, y_train)
print(lg.coef_)
y_predict = lg.predict(x_test)
print("准确率为:", lg.score(x_test, y_test))
# 召回率recall为真实为x的样本中预测为x的比例
print("召回率为:", classification_report(y_test, y_predict, labels=[2, 4], target_names=['良性', '恶性']))
if __name__ == '__main__':
logistic()