sklearn一些小记录

model的属性model.score(data_train,target_train)#是根据data_train学到的模型预测出来跟训练集原先的target做比较计算得分normalizationfrom sklearn import preprocessingpreprocessing.scale(a)preprocessing.minmax_scale(a,feature_range=(-1,1))#默认是(

cross_validationfrom sklearn.cross_validation import cross_val_scorescores=cross_val_score(KNN,X,Y,cv=5,scoring='accuracy')#这个是交叉验证的调用，对KNN这个模型，XY分别是数据和标签，cv=5是5折交叉验证，scoring='accuracy'是以accuracy作为评分标准 ，回归可以用mean_square_error,但是其所得到的是负数，需要在前面添加一个负号

from sklearn.cross_validation import cross_val_scoreimport matplotlib.pyplot as pltk_range = range(1, 31)k_scores = [] # listfor k in k_range:    knn = KNeighborsClassifier(n_neighbors=k)##    loss = -cross_val_score(knn, X, y, cv=10, scoring='mean_squared_error') # for regression # 注意加负号    scores = cross_val_score(knn, X, y, cv=10, scoring='accuracy') # for classification    k_scores.append(scores.mean())# 把每一次的得分都存进去plt.plot(k_range, k_scores) # 这里就是每个K显示一次K_scoresplt.xlabel('Value of K for KNN')plt.ylabel('Cross-Validated Accuracy')plt.show()