# 判断机器学习算法的性能/train_test_split(使用鸢尾花数据集)

## 通过kNN算法举例/numpy.random.permutation()

Posted by Waldo on March 10, 2018

# 封装model_selection

``````import numpy as np

def train_test_split(X, y, test_ratio=0.2, seed=None):
"""将数据 X 和 y 按照test_ratio分割成X_train, X_test, y_train, y_test"""
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_ration 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, X_test, y_train, y_test
``````

# 通过自己写的kNN算法得出模型准确率

``````import numpy as np
from math import sqrt
from collections import Counter

class KNNClassifier:

def __init__(self, k):
"""初始化kNN分类器"""
assert k >= 1, "k must be valid"
self.k = k
self._X_train = None
self._y_train = None

def fit(self, X_train, y_train):
"""根据训练数据集X_train和y_train训练kNN分类器"""
assert X_train.shape[0] == y_train.shape[0], \
"the size of X_train must be equal to the size of y_train"
assert self.k <= X_train.shape[0], \
"the size of X_train must be at least k."

self._X_train = X_train
self._y_train = y_train
return self

def predict(self, X_predict):
"""给定待预测数据集X_predict，返回表示X_predict的结果向量"""
assert self._X_train is not None and self._y_train is not None, \
"must fit before predict!"
assert X_predict.shape[1] == self._X_train.shape[1], \
"the feature number of X_predict must be equal to X_train"

y_predict = [self._predict(x) for x in X_predict]
return np.array(y_predict)

def _predict(self, x):
"""给定单个待预测数据x，返回x的预测结果值"""
assert x.shape[0] == self._X_train.shape[1], \
"the feature number of x must be equal to X_train"

distances = [sqrt(np.sum((x_train - x) ** 2))
for x_train in self._X_train]
nearest = np.argsort(distances)

topK_y = [self._y_train[i] for i in nearest[:self.k]]