rowdata?=?{
????"電影名稱":?['功夫熊貓',?'葉問3',?'倫敦陷落',?'代理情人',?'新步步驚心',?'諜影重重',?'功夫熊貓',?'美人魚',?'寶貝當(dāng)家'],
????"搞笑鏡頭":?[39,3,2,9,8,5,39,21,45],
????"擁抱鏡頭":?[0,2,3,38,34,2,0,17,2],
????"打斗鏡頭":?[31,65,55,2,17,57,31,5,9],
????"電影類型":?["喜劇片",?"動作片",?"動作片",?"愛情片",?"愛情片",?"動作片",?"喜劇片",?"喜劇片",?"喜劇片"]
}

new_data?=?[24,67]
dist?=?list((((movie_data.iloc[:6,1:3]-new_data)**2).sum(1))**0.5)

k?=?4
dist_l?=?pd.DataFrame({'dist':?dist,?'labels':?(movie_data.iloc[:6,?3])})?
dr?=?dist_l.sort_values(by='dist')[:k]

re?=?dr.loc[:,'labels'].value_counts()
re.index[0]

result?=?[]
result.append(re.index[0])
result

#?導(dǎo)入數(shù)據(jù)集
datingTest?=?pd.read_table('datingTestSet.txt',header=None)
datingTest.head()

#?分析數(shù)據(jù)
%matplotlib?inline
import?matplotlib?as?mpl
import?matplotlib.pyplot?as?plt

#把不同標簽用顏色區(qū)分
Colors?=?[]
for?i?in?range(datingTest.shape[0]):
????m?=?datingTest.iloc[i,-1]??#?標簽
????if?m=='didntLike':
????????Colors.append('black')
????if?m=='smallDoses':
????????Colors.append('orange')
????if?m=='largeDoses':
????????Colors.append('red')

#繪制兩兩特征之間的散點圖
plt.rcParams['font.sans-serif']=['Simhei']?#圖中字體設(shè)置為黑體
pl=plt.figure(figsize=(12,8))??#?建立一個畫布

fig1=pl.add_subplot(221)??#?建立兩行兩列畫布，放在第一個里面
plt.scatter(datingTest.iloc[:,1],datingTest.iloc[:,2],marker='.',c=Colors)
plt.xlabel('玩游戲視頻所占時間比')
plt.ylabel('每周消費冰淇淋公升數(shù)')

fig2=pl.add_subplot(222)
plt.scatter(datingTest.iloc[:,0],datingTest.iloc[:,1],marker='.',c=Colors)
plt.xlabel('每年飛行?？屠锍?)
plt.ylabel('玩游戲視頻所占時間比')

fig3=pl.add_subplot(223)
plt.scatter(datingTest.iloc[:,0],datingTest.iloc[:,2],marker='.',c=Colors)
plt.xlabel('每年飛行常客里程')
plt.ylabel('每周消費冰淇淋公升數(shù)')
plt.show()


#?數(shù)據(jù)歸一化
def?minmax(dataSet):
????minDf?=?dataSet.min()
????maxDf?=?dataSet.max()
????normSet?=?(dataSet?-?minDf?)/(maxDf?-?minDf)
????return?normSet

datingT?=?pd.concat([minmax(datingTest.iloc[:,?:3]),?datingTest.iloc[:,3]],?axis=1)
datingT.head()

#?切分訓(xùn)練集和測試集
def?randSplit(dataSet,rate=0.9):
????n?=?dataSet.shape[0]?
????m?=?int(n*rate)
????train?=?dataSet.iloc[:m,:]
????test?=?dataSet.iloc[m:,:]
????test.index?=?range(test.shape[0])
????return?train,test

train,test?=?randSplit(datingT)


#?分類器針對約會網(wǎng)站的測試代碼
def?datingClass(train,test,k):
????n?=?train.shape[1]?-?1??#?將標簽列減掉
????m?=?test.shape[0]??#?行數(shù)
????result?=?[]
????for?i?in?range(m):
????????dist?=?list((((train.iloc[:,?:n]?-?test.iloc[i,?:n])?**?2).sum(1))**5)
????????dist_l?=?pd.DataFrame({'dist':?dist,?'labels':?(train.iloc[:,?n])})
????????dr?=?dist_l.sort_values(by?=?'dist')[:?k]
????????re?=?dr.loc[:,?'labels'].value_counts()
????????result.append(re.index[0])
????result?=?pd.Series(result)??
????test['predict']?=?result??#?增加一列
????acc?=?(test.iloc[:,-1]==test.iloc[:,-2]).mean()
????print(f'模型預(yù)測準確率為{acc}')
????return?test


datingClass(train,test,5)??#?95%

import?os


#得到標記好的訓(xùn)練集
def?get_train():
????path?=?'digits/trainingDigits'
????trainingFileList?=?os.listdir(path)
????train?=?pd.DataFrame()
????img?=?[]??#?第一列原來的圖像轉(zhuǎn)換為圖片里面0和1，一行
????labels?=?[]??#?第二列原來的標簽
????for?i?in?range(len(trainingFileList)):
????????filename?=?trainingFileList[i]
????????txt?=?pd.read_csv(f'digits/trainingDigits/{filename}',?header?=?None)?#32行
????????num?=?''
????????#?將32行轉(zhuǎn)變?yōu)?行
????????for?i?in?range(txt.shape[0]):
????????????num?+=?txt.iloc[i,:]
????????img.append(num[0])
????????filelable?=?filename.split('_')[0]
????????labels.append(filelable)
????train['img']?=?img
????train['labels']?=?labels
????return?train
????
train?=?get_train()???



#?得到標記好的測試集
def?get_test():
????path?=?'digits/testDigits'
????testFileList?=?os.listdir(path)
????test?=?pd.DataFrame()
????img?=?[]??#?第一列原來的圖像轉(zhuǎn)換為圖片里面0和1，一行
????labels?=?[]??#?第二列原來的標簽
????for?i?in?range(len(testFileList)):
????????filename?=?testFileList[i]
????????txt?=?pd.read_csv(f'digits/testDigits/{filename}',?header?=?None)?#32行
????????num?=?''
????????#?將32行轉(zhuǎn)變?yōu)?行
????????for?i?in?range(txt.shape[0]):
????????????num?+=?txt.iloc[i,:]
????????img.append(num[0])
????????filelable?=?filename.split('_')[0]
????????labels.append(filelable)
????test['img']?=?img
????test['labels']?=?labels
????return?test

test?=?get_test()

#?分類器針對手寫數(shù)字的測試代碼
from?Levenshtein?import?hamming

def?handwritingClass(train,?test,?k):
????n?=?train.shape[0]
????m?=?test.shape[0]
????result?=?[]
????for?i?in?range(m):
????????dist?=?[]
????????for?j?in?range(n):
????????????d?=?str(hamming(train.iloc[j,0],?test.iloc[i,0]))
????????????dist.append(d)
????????dist_l?=?pd.DataFrame({'dist':dist,?'labels':(train.iloc[:,1])})
????????dr?=?dist_l.sort_values(by='dist')[:k]
????????re?=?dr.loc[:,'labels'].value_counts()
????????result.append(re.index[0])
????result?=?pd.Series(result)
????test['predict']?=?result
????acc?=?(test.iloc[:,-1]?==?test.iloc[:,-2]).mean()
????print(f'模型預(yù)測準確率為{acc}')
????return?test

handwritingClass(train,?test,?3)??#?97.8%