def valuate(mincount2,maxcount2,PredictAndAnalyze = PredictAndAnalyze2):
vectorinfo = {}
for ID in ["0000","0001","0002","0003","0004","0005","0006"]:
vectorinfo[ID] = {}
for j in textinfo[ID].keys():
#print j
try:
vectorinfo[ID][j] = createvector(video_id = j, ID = ID,mincount = mincount2,maxcount = maxcount2)
except:
#vectorinfo[ID][j] = np.zeros(len(model[model.vocab.keys()[0]]))
print ID,j
target2 = createtargetarray(maxcount2,100000000,10760.0,34544)
data2 = createtvectorMat(maxcount2,100000000,vectorinfo)
(TfidfTextList, word2freqlist) = makeTfidfTextList(maxcount2,100000000,mincount2,maxcount2)
tfidf = TfidfVectorizer(tokenizer=tokenize)
tfs = tfidf.fit_transform(TfidfTextList.values())
idlist = TfidfTextList.keys()
feature_names = tfidf.get_feature_names()
tfidfvectorinfo = {}
sample = tfs.toarray().shape[0]
print sample, len(feature_names),
for n in range(0,sample):
#print n
tfidfvectorinfo[idlist[n]] = maketfidfvec(n,feature_names = feature_names,tfs = tfs,idlist= idlist,word2freqlist = word2freqlist)
l = {}
for ID in ["0000","0001","0002","0003","0004","0005","0006"]:
l[ID] = vectorinfo[ID].keys()
tfidfdata = createtfidfvectorMat(maxcount2,100000000,tfidfvectorinfo)
print mincount2,maxcount2
print "logreg"
k2 = PredictAndAnalyze(data2,target2,clf_cv =linear_model.LogisticRegression(C=1e1))
print accuracy_score(k2[0],k2[1]),(1.0 - accuracy_score(k2[2],k2[3]))
k22 = PredictAndAnalyze(data = tfidfdata,target = target2,clf_cv =linear_model.LogisticRegression(C=1e1))
print accuracy_score(k22[0],k22[1]),(1.0 - accuracy_score(k22[2],k22[3]))
print "svm"
k0 = PredictAndAnalyze(data = data2,target = target2,clf_cv = svm.SVC(kernel='linear', probability=True))
print accuracy_score(k0[0],k0[1]),(1.0 - accuracy_score(k0[2],k0[3]))
print "LinearSVM"
k1 = PredictAndAnalyze(data = data2,target = target2,clf_cv = svm.LinearSVC())
print accuracy_score(k1[0],k1[1]),(1.0 - accuracy_score(k1[2],k1[3]))
k00 = PredictAndAnalyze(data = tfidfdata,target = target2,clf_cv = svm.LinearSVC())
print accuracy_score(k00[0],k00[1]),(1.0 - accuracy_score(k00[2],k00[3]))
return k2,k0,k1
k0 = PredictAndAnalyze(data2,target2,clf_cv = svm.SVC(kernel='linear', probability=True,class_weight={0:2,1:1}))
k0 = PredictAndAnalyze(data2,target2,clf_cv = svm.SVC(kernel='linear', probability=True))
k1 = PredictAndAnalyze(data2,target2,clf_cv = neighbors.KNeighborsClassifier(n_neighbors=10))
k2 = PredictAndAnalyze(data2,target2,clf_cv =linear_model.LogisticRegression(C=1e1))
l = {}
for ID in ["0000","0001","0002","0003"]:
l[ID] = vectorinfo[ID].keys()
(TfidfTextList, word2freqlist) = makeTfidfTextList(100,100000000)
tfs = tfidf.fit_transform(TfidfTextList.values())
idlist = TfidfTextList.keys()
tfidfvectorinfo = {}
sample = tfs.toarray().shape[0]
for n in range(0,sample):
tfidfvectorinfo[idlist[n]] = maketfidfvec(n,100,100000000)
tfidfdata = createtfidfvectorMat(100,100000000)
k2 = PredictAndAnalyze(data = tfidfdata,target = target2,clf_cv =linear_model.LogisticRegression(C=1e5))
k0 = PredictAndAnalyze(data = tfidfdata,target = target2,clf_cv = svm.SVC(kernel='linear', probability=True))
#コメント数毎で比較
tfidf = TfidfVectorizer(tokenizer=tokenize)
for narray in range(2,10):
target2 = createtargetarray(narray * 100 - 100,narray * 100 + 100,10000,30000)
data2 = createtvectorMat(narray * 100 - 100,narray * 100 + 100)
(TfidfTextList, word2freqlist) = makeTfidfTextList(narray * 100 - 100,narray * 100 + 100)
tfs = tfidf.fit_transform(TfidfTextList.values())
idlist = TfidfTextList.keys()
tfidfvectorinfo = {}