python起步-2

仅供学习使用

练习9

绘图

身高X，体重Y

身高	体重
152	51
156	53
160	54
164	55
168	57
172	60
176	62
180	65
184	69
188	72

import matplotlib.pyplot as plt
import numpy as np

data = np.array([
    [152, 51],
    [156, 53],
    [160, 54],
    [164, 55],
    [168, 57],
    [172, 60],
    [176, 62],
    [180, 65],
    [184, 69],
    [188, 72]
])

print(data.shape)

x, y = data[:, 0], data[:, 1]
plt.scatter(x, y)
plt.xlabel('height(cm)')
plt.ylabel('weight(kg)')
plt.show()
plt.figure()

(10, 2)

练习10

这部分代码是从网站拷贝下来的
给iris数据集使用KNN分类

from sklearn import datasets
from collections import Counter  # 为了做投票
from sklearn.model_selection import train_test_split
import numpy as np

# 导入iris数据
iris = datasets.load_iris()
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=2003)

import math

def euc_dis(instance1, instance2):
    """
    计算两个样本instance1和instance2之间的欧式距离
    instance1: 第一个样本， array型
    instance2: 第二个样本， array型
    """
    dist = math.sqrt(sum(instance1-instance2)**2)
    return dist

def knn_classify(X, y, testInstance, k):
    """
    给定一个测试数据testInstance, 通过KNN算法来预测它的标签。
    X: 训练数据的特征
    y: 训练数据的标签
    testInstance: 测试数据，这里假定一个测试数据 array型
    k: 选择多少个neighbors?
    """
    distances = [euc_dis(x,testInstance) for x in X]
    kneighbors = np.argsort(distances)[:k]
    count = Counter(y[kneighbors])
    return count.most_common()[0][0]

predictions = [knn_classify(X_train, y_train, data, 3) for data in X_test]
correct = np.count_nonzero((predictions == y_test) == True)
print("Accuracy is: %.3f" % (correct / len(X_test)))

Accuracy is: 0.816