MyBlog

import matplotlib.pyplot as plt
import sklearn
import mglearn

from sklearn.datasets import load_breast_cancer
cancer = load_breast_cancer()
print("cancer.keys(): n{}".format(cancer.keys()))

'''输出
cancer.keys(): 
dict_keys(['data', 'target', 'target_names', 'DESCR', 'feature_names', 'filename'])
'''

print("Shape of cancer data: {}".format(cancer.data.shape)) 
# 输出：569个数据点 每个数据点有30个特征
# Shape of cancer data: (569, 30)

print("Sample counts per class:n{}".format(
    {n: v for n, v in zip(cancer.target_names, np.bincount(cancer.target))}))

# Sample counts per class:
# {'malignant': 212, 'benign': 357}
# 恶性212个，良性357个

'''备注
zip: 打包成元组
bincount: 对应索引在数组中出现的次数

例如：
x = np.array([7, 6, 2, 1, 4])
np.bincount(x)
输出：array([0, 1, 1, 0, 1, 0, 1, 1])
'''

mglearn.plots.plot_knn_regression(n_neighbors=1)

mglearn.plots.plot_knn_regression(n_neighbors=3)

from sklearn.neighbors import KNeighborsRegressor

X, y = mglearn.datasets.make_wave(n_samples=40)

#将wave数据集分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

#模型实例化，并将邻居个数设为3
reg = KNeighborsRegressor(n_neighbors=3)
#拟合模型
reg.fit(X_train, y_train)

print("Test set predictions:n{}".format(reg.predict(X_test)))

print("R^2: ", reg.score(X_test, y_test))

# 输出为0.83 表示拟合相对较好

fig, axes = plt.subplots(1, 3, figsize=(15, 4))
# 创建100个数据点，在-3和3之间均匀分布
line = np.linspace(-3, 3, 1000).reshape(-1, 1)# reshap()是数组对象中的方法，用于改变数组的形状。变为1列，行数自动计算
for n_neighbors, ax in zip([1, 3, 9], axes):
    # 利用1个、3个或9个邻居分别进行预测
    reg = KNeighborsRegressor(n_neighbors=n_neighbors)
    reg.fit(X_train, y_train)
    ax.plot(line, reg.predict(line))
    ax.plot(X_train, y_train, '^', c=mglearn.cm2(0), markersize=8)
    ax.plot(X_test, y_test, 'v', c=mglearn.cm2(1), markersize=8)
    ax.set_title(
        "{} neighborsn train score: {:.2f} test score: {:.2f}".format(
        n_neighbors, reg.score(X_train, y_train),reg.score(X_test, y_test)))
    ax.set_xlabel("Feature")
    ax.set_ylabel("Target")
axes[0].legend(["Model predictions", "Training data/target", "Test data/target"], loc="best")