from matplotlib import pyplot as plt
​
# 用來正常顯示中文標(biāo)簽
plt.rcParams["font.sans-serif"] = ["SimHei"]
# 電影名稱
names = ["California Man", "He's Not Really into Dudes", "Beautiful Woman",
   "Kevin Longblade", "Robo Slayer 3000", "Amped II", "Unknown"]
# 類型標(biāo)簽
labels = ["Romance", "Romance", "Romance", "Action", "Action", "Action", "Unknown"]
colors = ["darkblue", "red", "green"]
colorDict = {label: color for (label, color) in zip(set(labels), colors)}
print(colorDict)
# 打斗次數(shù)，接吻次數(shù)
X = [3, 8, 1, 111, 99, 88, 18]
Y = [104, 95, 81, 15, 2, 10, 88]
​
plt.title("通過打斗次數(shù)和接吻次數(shù)判斷電影類型", fontsize=18)
plt.xlabel("電影中打斗鏡頭出現(xiàn)的次數(shù)", fontsize=16)
plt.ylabel("電影中接吻鏡頭出現(xiàn)的次數(shù)", fontsize=16)
​
# 繪制數(shù)據(jù)
for i in range(len(X)):
 # 散點圖繪制
 plt.scatter(X[i], Y[i], color=colorDict[labels[i]])
​
# 每個點增加描述信息
for i in range(0, 7):
 plt.text(X[i]+2, Y[i]-1, names[i], fontsize=14)
​
plt.show()

# 自定義實現(xiàn) mytest1.py
import numpy as np
​
# 創(chuàng)建數(shù)據(jù)集
def createDataSet():
 features = np.array([[3, 104], [8, 95], [1, 81], [111, 15],
       [99, 2], [88, 10]])
 labels = ["Romance", "Romance", "Romance", "Action", "Action", "Action"]
 return features, labels
​
def knnClassify(testFeature, trainingSet, labels, k):
 """
 KNN算法實現(xiàn)，采用歐式距離
 :param testFeature: 測試數(shù)據(jù)集，ndarray類型，一維數(shù)組
 :param trainingSet: 訓(xùn)練數(shù)據(jù)集，ndarray類型，二維數(shù)組
 :param labels: 訓(xùn)練集對應(yīng)標(biāo)簽，ndarray類型，一維數(shù)組
 :param k: k值，int類型
 :return: 預(yù)測結(jié)果，類型與標(biāo)簽中元素一致
 """
 dataSetsize = trainingSet.shape[0]
 """
 構(gòu)建一個由dataSet[i] - testFeature的新的數(shù)據(jù)集diffMat
 diffMat中的每個元素都是dataSet中每個特征與testFeature的差值（歐式距離中差）
 """
 testFeatureArray = np.tile(testFeature, (dataSetsize, 1))
 diffMat = testFeatureArray - trainingSet
 # 對每個差值求平方
 sqDiffMat = diffMat ** 2
 # 計算dataSet中每個屬性與testFeature的差的平方的和
 sqDistances = sqDiffMat.sum(axis=1)
 # 計算每個feature與testFeature之間的歐式距離
 distances = sqDistances ** 0.5
​
 """
 排序，按照從小到大的順序記錄distances中各個數(shù)據(jù)的位置
 如distance = [5, 9, 0, 2]
 則sortedStance = [2, 3, 0, 1]
 """
 sortedDistances = distances.argsort()
​
 # 選擇距離最小的k個點
 classCount = {}
 for i in range(k):
  voteiLabel = labels[list(sortedDistances).index(i)]
  classCount[voteiLabel] = classCount.get(voteiLabel, 0) + 1
 # 對k個結(jié)果進(jìn)行統(tǒng)計、排序，選取最終結(jié)果，將字典按照value值從大到小排序
 sortedclassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
 return sortedclassCount[0][0]
​
testFeature = np.array([100, 200])
features, labels = createDataSet()
res = knnClassify(testFeature, features, labels, 3)
print(res)
# 使用python包實現(xiàn) mytest2.py
from sklearn.neighbors import KNeighborsClassifier
from .mytest1 import createDataSet
​
features, labels = createDataSet()
k = 5
clf = KNeighborsClassifier(k_neighbors=k)
clf.fit(features, labels)
​
# 樣本值
my_sample = [[18, 90]]
res = clf.predict(my_sample)
print(res)

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
​
# 數(shù)據(jù)加載
def loadDatingData(file):
 datingData = pd.read_table(file, header=None)
 datingData.columns = ["FlightDistance", "PlaytimePreweek", "IcecreamCostPreweek", "label"]
 datingTrainData = np.array(datingData[["FlightDistance", "PlaytimePreweek", "IcecreamCostPreweek"]])
 datingTrainLabel = np.array(datingData["label"])
 return datingData, datingTrainData, datingTrainLabel
​
# 3D圖顯示數(shù)據(jù)
def dataView3D(datingTrainData, datingTrainLabel):
 plt.figure(1, figsize=(8, 3))
 plt.subplot(111, projection="3d")
 plt.scatter(np.array([datingTrainData[x][0]
       for x in range(len(datingTrainLabel))
       if datingTrainLabel[x] == "smallDoses"]),
    np.array([datingTrainData[x][1]
       for x in range(len(datingTrainLabel))
       if datingTrainLabel[x] == "smallDoses"]),
    np.array([datingTrainData[x][2]
       for x in range(len(datingTrainLabel))
       if datingTrainLabel[x] == "smallDoses"]), c="red")
 plt.scatter(np.array([datingTrainData[x][0]
       for x in range(len(datingTrainLabel))
       if datingTrainLabel[x] == "didntLike"]),
    np.array([datingTrainData[x][1]
       for x in range(len(datingTrainLabel))
       if datingTrainLabel[x] == "didntLike"]),
    np.array([datingTrainData[x][2]
       for x in range(len(datingTrainLabel))
       if datingTrainLabel[x] == "didntLike"]), c="green")
 plt.scatter(np.array([datingTrainData[x][0]
       for x in range(len(datingTrainLabel))
       if datingTrainLabel[x] == "largeDoses"]),
    np.array([datingTrainData[x][1]
       for x in range(len(datingTrainLabel))
       if datingTrainLabel[x] == "largeDoses"]),
    np.array([datingTrainData[x][2]
       for x in range(len(datingTrainLabel))
       if datingTrainLabel[x] == "largeDoses"]), c="blue")
 plt.xlabel("飛行里程數(shù)", fontsize=16)
 plt.ylabel("視頻游戲耗時百分比", fontsize=16)
 plt.clabel("冰淇凌消耗", fontsize=16)
 plt.show()
 
datingData, datingTrainData, datingTrainLabel = loadDatingData(FILEPATH1)
datingView3D(datingTrainData, datingTrainLabel)

# 自定義方法實現(xiàn)
import pandas as pd
import numpy as np
​
# 數(shù)據(jù)加載
def loadDatingData(file):
 datingData = pd.read_table(file, header=None)
 datingData.columns = ["FlightDistance", "PlaytimePreweek", "IcecreamCostPreweek", "label"]
 datingTrainData = np.array(datingData[["FlightDistance", "PlaytimePreweek", "IcecreamCostPreweek"]])
 datingTrainLabel = np.array(datingData["label"])
 return datingData, datingTrainData, datingTrainLabel
​
# 數(shù)據(jù)歸一化
def autoNorm(datingTrainData):
 # 獲取數(shù)據(jù)集每一列的最值
 minValues, maxValues = datingTrainData.min(0), datingTrainData.max(0)
 diffValues = maxValues - minValues
 
 # 定義形狀和datingTrainData相似的最小值矩陣和差值矩陣
 m = datingTrainData.shape(0)
 minValuesData = np.tile(minValues, (m, 1))
 diffValuesData = np.tile(diffValues, (m, 1))
 normValuesData = (datingTrainData-minValuesData)/diffValuesData
 return normValuesData
​
# 核心算法實現(xiàn)
def KNNClassifier(testData, trainData, trainLabel, k):
 m = trainData.shape(0)
 testDataArray = np.tile(testData, (m, 1))
 diffDataArray = (testDataArray - trainData) ** 2
 sumDataArray = diffDataArray.sum(axis=1) ** 0.5
 # 對結(jié)果進(jìn)行排序
 sumDataSortedArray = sumDataArray.argsort()
 
 classCount = {}
 for i in range(k):
  labelName = trainLabel[list(sumDataSortedArray).index(i)]
  classCount[labelName] = classCount.get(labelName, 0)+1
 classCount = sorted(classCount.items(), key=lambda x: x[1], reversed=True)
 return classCount[0][0]
 
​
# 數(shù)據(jù)測試
def datingTest(file):
 datingData, datingTrainData, datingTrainLabel = loadDatingData(file)
 normValuesData = autoNorm(datingTrainData)
 
 
 errorCount = 0
 ratio = 0.10
 total = datingTrainData.shape(0)
 numberTest = int(total * ratio)
 for i in range(numberTest):
  res = KNNClassifier(normValuesData[i], normValuesData[numberTest:m], datingTrainLabel, 5)
  if res != datingTrainLabel[i]:
   errorCount += 1
 print("The total error rate is : {}\n".format(error/float(numberTest)))
​
if __name__ == "__main__":
 FILEPATH = "./datingTestSet1.txt"
 datingTest(FILEPATH)
# python 第三方包實現(xiàn)
import pandas as pd
import numpy as np
from sklearn.neighbors import KNeighborsClassifier
​
if __name__ == "__main__":
 FILEPATH = "./datingTestSet1.txt"
 datingData, datingTrainData, datingTrainLabel = loadDatingData(FILEPATH)
 normValuesData = autoNorm(datingTrainData)
 errorCount = 0
 ratio = 0.10
 total = normValuesData.shape[0]
 numberTest = int(total * ratio)
 
 k = 5
 clf = KNeighborsClassifier(n_neighbors=k)
 clf.fit(normValuesData[numberTest:total], datingTrainLabel[numberTest:total])
 
 for i in range(numberTest):
  res = clf.predict(normValuesData[i].reshape(1, -1))
  if res != datingTrainLabel[i]:
   errorCount += 1
 print("The total error rate is : {}\n".format(errorCount/float(numberTest)))