Cacher is the code snippet organizer for pro developers

#learning_curve学习曲线描述样本大小与测试精度和训练精度之间的关系
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.learning_curve import learning_curve
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline

df = pd.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data', header=None)
#将数据分成训练集和测试集
from sklearn.preprocessing import LabelEncoder
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
#print(le.transform(['M', 'B']))
#将数据分成训练集和测试集
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=1)
pipe_lr = Pipeline([
        ('scl', StandardScaler()),
        ('clf', LogisticRegression(penalty='l2', random_state=0))])
        
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)
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(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='validation 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([0.9, 1.0])
plt.show()

#validation_curve描述描述准确率与模型参数之间的关系，对应测试精度可以找到测试精度最高的时候的参数值
#验证曲线和学习曲线的区别是，横轴为某个超参数的一系列值，由此来看不同参数设置下模型的准确率，而不是不同训练集大小下的准确率。
#从验证曲线上可以看到随着超参数设置的改变，模型可能从欠拟合到合适再到过拟合的过程，进而选择一个合适的设置，来提高模型的性能。
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.learning_curve import learning_curve
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.learning_curve import validation_curve
df = pd.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data', header=None)
#将数据分成训练集和测试集
from sklearn.preprocessing import LabelEncoder
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
#print(le.transform(['M', 'B']))
#将数据分成训练集和测试集
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=1)

param_range = [0.001, 0.01, 0.1, 1.0, 10.0, 100.0]
pipe_lr = Pipeline([
        ('scl', StandardScaler()),
        ('clf', LogisticRegression(penalty='l2', random_state=0))])
train_scores, test_scores = validation_curve(estimator=pipe_lr,
                              X=X_train,
                              y=y_train,
                              param_name='clf__C',  #这个param_name对于一个sklearn模型是固定名称的
                              param_range=param_range,
                              cv=10)
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='validation 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([0.92, 1.0])
plt.show()