04-Hyper-Parameter-K

来源于Jupyter Notebook

import numpy as np
import matplotlib
import matplotlib.pyplot as plt
from sklearn import datasets

//加载手写数字的数据集
digits = datasets.load_digits()
digits.keys()
print(digits.DESCR)
X = digits.data
X.shape
y = digits.target
y.shape

digits.target_names

y[:100]

X[:10]

some_digit = X[666]

y[666]//结果是0

some_digit_image = some_digit.reshape(8,8)/将some_digit通过reshape的方式转换成8*8 的矩阵
plt.imshow(some_digit_image,cmap = matplotlib.cm.binary)
plt.show()//将8*8的矩阵绘制出来（绘制出来一个0）

//scikit-learn中的accuracy_score（分类准确度）

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=666)

from sklearn.neighbors import KNeighborsClassifier
knn_clf = KNeighborsClassifier(n_neighbors=3)

knn_clf.fit(X_train,y_train)//训练模型

y_predict = knn_clf.predict(X_test)//预测出X_test中样本对应的标签

from sklearn.metrics import accuracy_score
accuracy_score(y_test,y_predict)//最终预测结果的准确率

knn_clf.score(X_test,y_test)//此种方法依然可以获得最终准确率