．笔记．

模型评估2

数据分离

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.4)

print(X_train.shape, X_test.shape, y_train.shape, y_test.shape) 

1. 数据分离：

   from sklearn.model_selection import train_test_split

   X_train, X_test, y_train, y_test = train_test_split(X,y,test_size = 0.4)

2. 定义一个k的范围：k_range = list(range(1,26))

3. 定义变量存储多个数据：score_train = []

4. 将单个数据存储在范围变量中：score_train.append(accuracy_score(y_train, y_train_pred)) 

5. 定义一个循环：for k in k_range：

6. 以线的形式绘制一个对比图：

   import matplotlib.pyplot as plt 

   %matplotlib inline

   plt.plot(k_range,score_test)

   plt.xlabel('K(Knn model)')

   plt.ylabel('test_accuracy')

7. 当k=1的时候，模型是最复杂的

#在一定范围内寻求最优解

k_range = list(range(1,26))

#print(k_range)

scores_train = []

scores_test = []

for k in k_range:

    knn = KNeighborsClassifier(n_neighbors=k)

    knn.fit(X_train,y_train)

    y_train_pred = knn.predict(X_train)

    y_test_pred = knn.predict(X_test)

    scores_train.append(accuracy_score(y_train,y_train_pred)) 

    scores_test.append(accuracy_score(y_test,y_test_pred))

for k in k_range:

    print(k,scores_train[k-1])

数据分离

from sklearn.model_selection import train_test_split

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.5)

import matplotlib.pyplot as plt

#在该界面展示

%matplotlib inline

plt.plot(k_range,score_train)

plt.xlabe('K(KNN mode)')

plt.ylable('Training Accuracy')

K越小复杂度越高，所以K=1时训练集的准确率是1