学习曲线，调试模型

# -*- coding: utf-8 -*-
'''''
Created on 2018年1月18日
@author: Jason.F
@summary: 判别过拟合和欠拟合
学习曲线Learning Curve：评估样本量和指标的关系
验证曲线validation Curve：评估参数和指标的关系
'''
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
import matplotlib.pyplot as plt
from sklearn.model_selection import learning_curve
import numpy as np
from sklearn.model_selection import validation_curve

# 导入数据
df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data',
                 header=None)
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)  # 类标整数化
print (le.transform(['M', 'B']))
# 划分训练集合测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=1)
# 标准化、模型训练串联
pipe_lr = Pipeline([('scl', StandardScaler()), ('clf', LogisticRegression(random_state=1, penalty='l2'))])

# case1：学习曲线
# 构建学习曲线评估器，train_sizes：控制用于生成学习曲线的样本的绝对或相对数量
train_sizes, train_scores, test_scores = learning_curve(estimator=pipe_lr, X=X_train, y=y_train,
                                                        train_sizes=np.linspace(0.1, 1.0, 10), cv=10, n_jobs=1)
# 统计结果
train_mean = np.mean(train_scores, axis=1)
train_std = np.std(train_scores, axis=1)
test_mean = np.mean(test_scores, axis=1)
test_std = np.std(test_scores, axis=1)
# 绘制效果
plt.plot(train_sizes, train_mean, color='blue', marker='o', markersize=5, label='training accuracy')
plt.fill_between(train_sizes, train_mean + train_std, train_mean - train_std, alpha=0.15, color='blue')
plt.plot(train_sizes, test_mean, color='green', linestyle='--', marker='s', markersize=5, label='test accuracy')
plt.fill_between(train_sizes, test_mean + test_std, test_mean - test_std, alpha=0.15, color='green')
plt.grid()
plt.xlabel('Number of training samples')
plt.ylabel('Accuracy')
plt.legend(loc='lower right')
plt.ylim([0.8, 1.0])
plt.show()

# case2：验证曲线
param_range = [0.001, 0.01, 0.1, 1.0, 10.0, 100.0]
# 10折，验证正则化参数C
train_scores, test_scores = validation_curve(estimator=pipe_lr, X=X_train, y=y_train, param_name='clf__C',
                                             param_range=param_range, cv=10)
# 统计结果
train_mean = np.mean(train_scores, axis=1)
train_std = np.std(train_scores, axis=1)
test_mean = np.mean(test_scores, axis=1)
test_std = np.std(test_scores, axis=1)
plt.plot(param_range, train_mean, color='blue', marker='o', markersize=5, label='training accuracy')
plt.fill_between(param_range, train_mean + train_std, train_mean - train_std, alpha=0.15, color='blue')
plt.plot(param_range, test_mean, color='green', linestyle='--', marker='s', markersize=5, label='test accuracy')
plt.fill_between(param_range, test_mean + test_std, test_mean - test_std, alpha=0.15, color='green')
plt.grid()
plt.xscale('log')
plt.xlabel('Parameter C')
plt.ylabel('Accuracy')
plt.legend(loc='lower right')
plt.ylim([0.8, 1.0])
plt.show()