预测结果为1到11中的1个
首先加载数据，训练数据，训练标签，预测数据，预测标签：
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)
#导入类别的训练和测试数据
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)
其中训练数据，预测数据是csv文件格式，而且是str，要转为float并一排排放入lis，然后将所有lis放入traindata或testdata中，但csv中是以","隔开的，所以要将"\t"等都转为","，需要利用
ls.append(line.split(","))放入ls中，但仍然是str型的，我又另外转化成了float，后来发现不转化也是可以的，可能它后来会在即转化吧。
之后运用多种分类器，调参数参考http://scikit-learn.org/stable/supervised_learning.html#supervised-learning 然后选出尽量好的分类器，提高准确率
‘‘‘
#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)
‘‘‘
‘‘‘
#这个不行
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)
这个不行
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) # 生成随机森林多分类器
predict = forest.fit(traindata, trainlabel).predict(testdata)
输出准确率，我还把预测结果输出到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("写好了")
f.close()
k=0
print(s)
for i in range(s):
if testlabel[i] == predict[i]:
k=k+1
print("精度为:",k*1.0/s)
接下来是输出所有标签的支持度
print(‘我要开始输出支持度啦‘)
attribute_proba=forest.predict_proba(testdata)
#print(forest.predict_proba(testdata))#输出各个标签的概率
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")
运行结果如下：
但是这样还不够，我还要输出前3个的预测结果的编号和支持度。我开了个类attri，key用来放编号，weight则放支持度。之后对每一条记录的所有的预测概率（支持度）遍历3次。每次找出概率最大的一个，挑出后把编号和概率存好，并把这个值变为0，再寻找挑出最大的一个，循环3次。存好后输出到excel
‘‘‘接下来输出每组概率最大的四个的编号‘‘‘
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#难道是从1开始？我一开始写了i【p-1】但debug时发现不对
a=attri()
a.key=p
a.weight=mm
lis.append(a)
label.append(lis)
print(‘挑几个输出‘)
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")
运行结果如下：
自学得真辛苦啊，这些都是我的学习成果，准确还是可以在提高的，对你有帮助的话，点个赞吧，嘿嘿。
原文地址：https://www.cnblogs.com/caiyishuai/p/9395039.html
时间： 2024-11-29 06:14:37