4.3训练数据集、测试数据集

4.3训练数据集、测试数据集

1.判断机器学习算法的性能

image.png

测试我们的算法

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

iris = datasets.load_iris()

x = iris.data
y = iris.target

train_test_split

将原始数据集拆分成两部分，一部分是训练数据集，一部分是测试数据集。

# 先对原始数据进行随机化，但是因为x.y对应的关系，所以随机化处理是对应关系应该保持一致。
# 随机化方法：可以先把X.y合成一个矩阵然后随机取出一部分数据；另一种方法是先对y进行随机化
# 形成15个索引的随机序列
shuffle_indexes = np.random.permutation(len(X)
# 查看序列
shuffle_indexes
# 指定选取测试数据集的比例
test_ratio = 0.2
test_size = int(len(X) * test_ratio)
# 获得测试数据集索引
test_indexes = shuffle_indexes[:test_size]
# 获得训练数据集索引
train_indexes = shuffle_indexes[test_size:]

# 获取测试和训练数据
X_train = X[train_indexes]
y_train = y[train_indexes]

X_test = X[test_indexes]
y_test = y[test_indexes]

创建model_selection.py文件

# 分割原始数据集为测试数据集和训练数据集

import numpy as np

def train_test_split(X, y, test_ratio=0.2, seed=None):
    assert X.shape[0] == y.shape[0], \
        "the size of X must be equal to the size of y"
    assert 0.0 <= test_ratio <= 1.0, \
        "test_ratio must be valid"

    if seed:
        np.random.seed(seed)

    shuffled_indexes = np.random.permutation(len(X))

    test_size = int(len(X * test_ratio))
    test_indexes = shuffled_indexes[:test_size]
    train_indexes = shuffled_indexes[test_size:]

    X_train = X[train_indexes]
    y_train = y[train_indexes]

    X_test = X[test_indexes]
    y_test = y[test_indexes]

    return X_train, y_train, X_test, y_test

测试使用我们的算法

from playML.model_selection import train_test_split
X_train, y_train, X_test, y_test = train_test_split(X, y)

from playML.kNN2 import KNNClassifier
my_knn_clf = KNNClassifier(k=3)
my_knn_clf.fit(X_train, y_train)
y_predict = my_knn_clf.predict(X_test)
# 得出预测结果
y_predict
# 检验预测结果和实际结果
sum(y_predict == y_test)
# 计算预测准确率
sum(y_predict == y_test)/len(y_test)

sklearn中的train_test_split

from sklearn.model_selection import train_test_split
# random_state设置随机种子
X_train, y_train, X_test, y_test = train_test_split(X, y, test_size=0.2, random_state=666)