分類準確度的計算方式:
分類正確的樣本數 / 總樣本數
(新加了score(x_test, y_test)函式,不關心predict的具體值是多少(predict函式在score中呼叫),只關心模型的準確度)
# from sklearn.neighbors import kneighborsclassifier
import numpy as np
from math import sqrt
from collections import counter
from .metrics import accuracy_score
class knnclassifier:
def __init__(self, k):
"""初始化knn分類器"""
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):
"""根據訓練資料集x_train和y_train訓練knn分類器"""
print(x_train.shape[0])
print(y_train.shape[0])
assert x_train.shape[0] == y_train.shape[0]#, \ "the size of x_train must be equal to 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):
"""給定待**資料集x_predict,返回表示x_predict的結果向量"""
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):
"""給定單個待**資料x,返回x的**結果值"""
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]]
votes = counter(topk_y)
return votes.most_common(1)[0][0]
def score(self, x_test, y_test):
"""根據測試集x_test和y_test確定當前模型的準確度"""
y_predit = self.predict(x_test)
return accuracy_score(y_test, y_predit)
from sklearn.model_selection import train_test_split
from sklearn import datasets
# 資料集載入
digits = datasets.load_digits()
x = digits.data
y = digits.target
print(x.shape)
print(y.shape)
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=666)
# knn
from sklearn.neighbors import kneighborsclassifier
knn_classifier = kneighborsclassifier(n_neighbors=3)
knn_classifier.fit(x_train, y_train)
# knn中自帶的準確度計算函式
print(knn_classifier.score(x_test, y_test))
03 分類準確度
在本文中，我們首先會再使用這樣的思路用我們的 knn 演算法在另外乙個更大一些的資料集上進行測試。與此同時，我們進一步來封裝 accuracy，同時也學習 sklearn 中分類的準確度相應的呼叫方式。最後，我們真正使用我們的測試資料集測試出的模型的結果來看，所謂的模型選擇是怎麼回事？在這個過程中，...
3 邏輯回歸 分類準確度
準確的有 0,0 1,1 其餘的都是 錯誤的點 from sklearn.metrics import confusion matrix 引入混淆矩陣 confusion matrix y test,y predict from sklearn.metrics import precision sc...
筆記 KNN之分類準確度
分類準確度 以sklearn中的手寫數字datasets.load digits為例，其是8 8的圖形，具有64個特徵值，類別由0到9 我們挑選出666這個圖形，將其視覺化 x digits.data some digit x 666 some digit image some digit.resh...