python多分類預測模版，輸出支持度，多種分類器，str的csv轉float

預測結果為1到11中的1個

首先加載數據，訓練數據，訓練標簽，預測數據，預測標簽：

if __name__=="__main__":  
    
    importTrainContentdata()
    importTestContentdata()
    importTrainlabeldata()
    importTestlabeldata()

traindata = []
testdata = []
trainlabel = []
testlabel = []

def importTrainContentdata():
    file = 'F:/goverment/myfinalcode/train_big.csv'
    fo=open(file) 
    ls=[]
    for line in fo:
        line=line.replace("\t",",")
        line=line.replace("\n",",")
        line=line.replace("\"",",")
        ls.append(line.split(","))
    for i in ls:
        li=[]
        for j in i:
            if j == '':
                continue
            li.append(float(j))
        traindata.append(li)

def importTestContentdata():
    file = 'F:/goverment/myfinalcode/test_big.csv'
    fo=open(file) 
    ls=[]
    for line in fo:
        line=line.replace("\t",",")
        line=line.replace("\n",",")
        line=line.replace("\"",",")
        ls.append(line.split(","))
    for i in ls:
        li=[]
        for j in i:
            if j == '':
                continue
            li.append(float(j))
        testdata.append(li)   

#導入類別的訓練和測試數據
def importTrainlabeldata():
    file = 'F:/goverment/myfinalcode/train_big_label.xls'
    wb = xlrd.open_workbook(file)
    ws = wb.sheet_by_name("Sheet1")
    for r in range(ws.nrows):
        col = []
        for c in range(1):
            col.append(ws.cell(r, c).value)
        trainlabel.append(col)
        
def importTestlabeldata():
    file = 'F:/goverment/myfinalcode/test_big_label.xls'
    wb = xlrd.open_workbook(file)
    ws = wb.sheet_by_name("Sheet1")
    for r in range(ws.nrows):
        col = []
        for c in range(1):
            col.append(ws.cell(r, c).value)
        testlabel.append(col)

其中訓練數據，預測數據是csv文件格式，而且是str，要轉為float並一排排放入lis，然后將所有lis放入traindata或testdata中，但csv中是以","隔開的，所以要將"\t"等都轉為","，需要利用

ls.append(line.split(","))放入ls中，但仍然是str型的，我又另外轉化成了float，后來發
現不轉化也是可以的，可能它后來會在即轉化吧。

之后運用多種分類器，調參數參考
http://scikit-learn.org/stable/supervised_learning.html#supervised-learning
 然后選出盡量好的分類器，提高准確率

 '''
    #19%
    from sklearn import neighbors
    knn=neighbors.KNeighborsClassifier(n_neighbors=75, leaf_size=51, weights='distance',p=2)
    knn.fit(traindata, trainlabel)
    predict=knn.predict(testdata)
    '''

    '''
    #這個不行
    from sklearn.neural_network import MLPClassifier
    import numpy as np
    traindata = np.array(traindata)#TypeError: cannot perform reduce with flexible type
    traindata = traindata.astype(float)
    
    trainlabel = np.array(trainlabel)
    trainlabel = trainlabel.astype(float)
    
    testdata=np.array(testdata)
    testdata = testdata.astype(float)
    model=MLPClassifier(activation='relu', alpha=1e-05, batch_size='auto',
       beta_1=0.9, beta_2=0.999, early_stopping=False,
       epsilon=1e-08, hidden_layer_sizes=(5, 2), learning_rate='constant',
       learning_rate_init=0.001, max_iter=200, momentum=0.9,
       nesterovs_momentum=True, power_t=0.5, random_state=1, shuffle=True,
       solver='lbfgs', tol=0.0001, validation_fraction=0.1, verbose=False,
       warm_start=False)
    model.fit(traindata, trainlabel)
    predict = model.predict(testdata)
    '''
  
    
    '''
    #19%
    from sklearn.tree import DecisionTreeClassifier
    model=DecisionTreeClassifier(class_weight='balanced',max_features=68,splitter='best',random_state=5)
    model.fit(traindata, trainlabel)
    predict = model.predict(testdata)

    
    這個不行
    from sklearn.naive_bayes import MultinomialNB
    clf = MultinomialNB(alpha=0.052).fit(traindata, trainlabel)  
    #clf.fit(traindata, trainlabel)  
    predict=clf.predict(testdata)
    '''
    
    '''17%
    from sklearn.svm import SVC
    clf = SVC(C=150,kernel='rbf', degree=51, gamma='auto',coef0=0.0,shrinking=False,probability=False,tol=0.001,cache_size=300, class_weight=None,verbose=False,max_iter=-1,decision_function_shape=None,random_state=None)
    clf.fit(traindata, trainlabel)
    predict=clf.predict(testdata)
    '''
    
    '''0.5%
    from sklearn.naive_bayes import GaussianNB
    import numpy as np
    gnb = GaussianNB()
    traindata = np.array(traindata)#TypeError: cannot perform reduce with flexible type
    traindata = traindata.astype(float)   
    trainlabel = np.array(trainlabel)
    trainlabel = trainlabel.astype(float)
    testdata=np.array(testdata)
    testdata = testdata.astype(float)
    predict = gnb.fit(traindata, trainlabel).predict(testdata)
    '''
    
    '''16%
    from sklearn.naive_bayes import BernoulliNB
    import numpy as np
    gnb = BernoulliNB()
    traindata = np.array(traindata)#TypeError: cannot perform reduce with flexible type
    traindata = traindata.astype(float)
    
    trainlabel = np.array(trainlabel)
    trainlabel = trainlabel.astype(float)
    
    testdata=np.array(testdata)
    testdata = testdata.astype(float)
    predict = gnb.fit(traindata, trainlabel).predict(testdata)
    '''
    
    from sklearn.ensemble import RandomForestClassifier
    forest = RandomForestClassifier(n_estimators=500,random_state=5, warm_start=False, min_impurity_decrease=0.0,min_samples_split=15)  # 生成隨機森林多分類器
    
    predict = forest.fit(traindata, trainlabel).predict(testdata)

輸出准確率，我還把預測結果輸出到txt中，方便分析。

 

s=len(predict)
    
    f=open('F:/goverment/myfinalcode/predict.txt', 'w')
    for i in range(s):
       f.write(str(predict[i]))
       f.write('\n')
    f.write("寫好了")
    f.close()
    
    
    
    k=0
    print(s)
    
    for i in range(s):
        if testlabel[i] == predict[i]:
            k=k+1
    print("精度為:",k*1.0/s)

 

 

 

接下來是輸出所有標簽的支持度

    print('我要開始輸出支持度啦')
    attribute_proba=forest.predict_proba(testdata)
    #print(forest.predict_proba(testdata))#輸出各個標簽的概率
    print(type(attribute_proba))
    
    
    import xlwt
    myexcel = xlwt.Workbook()
    sheet = myexcel.add_sheet('sheet')
    si=-1
    sj=-1
    for i in attribute_proba:
        si=si+1
        for j in i:
            sj=sj+1
            sheet.write(si,sj,str(j))
        sj=-1
    myexcel.save("attribute_proba_small.xls") 

運行結果如下：

但是這樣還不夠，我還要輸出前3個的預測結果的編號和支持度。
我開了個類attri，key用來放編號，weight則放支持度。
之后對每一條記錄的所有的預測概率（支持度）遍歷3次。每次找出概率最大的一個，挑出后把編號和
概率存好，並把這個值變為0，再尋找挑出最大的一個，循環3次。存好后輸出到excel

    '''接下來輸出每組概率最大的四個的編號'''
    class attri:
        def __init__(self):
            self.key=0
            self.weight=0.0
    label=[]
    for i in attribute_proba:
        lis=[]
        k=0
        while k<3:
            k=k+1
            p=1
            mm=0
            sj=-1
            for j in i:
                sj=sj+1
                if j>mm:
                    mm=j
                    p=sj
            i[p]=0#難道是從1開始？我一開始寫了i【p-1】但debug時發現不對
            a=attri()
            a.key=p
            a.weight=mm
            lis.append(a)
        label.append(lis)
    print('挑幾個輸出') 
    import xlwt
    myexcel = xlwt.Workbook()
    sheet = myexcel.add_sheet('sheet')
    si=-2
    sj=-1
    for i in label:
        si=si+2
        for j in i:
            sj=sj+1
            sheet.write(si,sj,str(j.key))
            sheet.write(si+1,sj,str(j.weight))
        sj=-1
    myexcel.save("proba_big.xls")

運行結果如下：

 

自學得真辛苦啊，這些都是我的學習成果，准確還是可以在提高的，對你有幫助的話，點個贊吧，嘿嘿。