機器學習：如何判斷和解決過擬合和欠擬合

1.利用學習曲線判斷
2.誤差 = 偏差(精確率) + 方差(穩定性)
3.下圖中虛線爲訓練集，實線爲測試集

'''
功能：判別過擬合和欠擬合
學習曲線Learning Curve：評估樣本量和指標的關係
驗證曲線validation Curve：評估參數和指標的關係
'''
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.cross_validation 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.learning_curve import learning_curve
import numpy as np
from sklearn.learning_curve import validation_curve
#導入數據
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)#類標整數化
print (le.transform(['M','B']))
#劃分訓練集合測試集
X_train,X_test,y_train,y_test = train_test_split (X,y,test_size=0.20,random_state=1)
#標準化、模型訓練串聯
pipe_lr=Pipeline([('scl',StandardScaler()),('clf',LogisticRegression(random_state=1,penalty='l2'))])
 
#case1：學習曲線
#構建學習曲線評估器，train_sizes：控制用於生成學習曲線的樣本的絕對或相對數量
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)
#統計結果
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)
#繪製效果
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：驗證曲線
param_range=[0.001,0.01,0.1,1.0,10.0,100.0]
#10折，驗證正則化參數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)
#統計結果
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()