def test_myTFIDF():
txtdict = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s' % 'afterProccess_test') # 0.6s
data, txtName, wordName = dict2Array(txtdict, dtype=int)
tfidf2 = myTFIDF_array(data, itc=True)
tfidf1 = myTFIDF(txtdict, itc=True)
# myTFIDF_dict 比 myTFIDF_array 快
dd = dict2Array(tfidf1)[0]
cc = dd - tfidf2
fdd = numpy.abs(cc)
print(sum(sum(fdd))) # 误差在1e-15*n 浮点运算 精度下降
def test_myTC():
txt_dict = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s' %
'afterProccess') # 0.6s
tfidf_dict = myTFIDF(txt_dict, itc=True)
tfidf_array, txtName, wordName = dict2Array(tfidf_dict)
tc_dict = myTC_dict(tfidf_dict, rtype=list)
tc_array = myTC_array(tfidf_array)
# myTC_array 比 myTC_dict 快
# print(sum(tc_dict - tc_array))
# 可以借助dataInfo内的函数、查看TC的数据分布
print(fiveNumber(tc_array))
showDistplot(tc_array)
def test_pca_sklearn():
txt_dict = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s' %
'afterProccess_test') # 0.6s
txt_array, txtName, wordName = dict2Array(txt_dict, dtype=int)
testdata = txt_array[:, 1:500]
# newData_dict = doTC_dict(txt_dict, topN=1000)
# testdata, txtName, wordName = dict2Array(newData_dict, dtype=int)
dataMat = numpy.mat(testdata)
print(dataMat.shape)
topNfeat = 50
lowDDataMat, redEigVects = myPCA_R(dataMat, topN=topNfeat)
def test_doTC():
txt_dict = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s' %
'afterProccess')
minTC, topN = 0, 10000
tcData_array, tcWordName = doTC_array(txt_dict, minTC, topN)
tcData_dict = doTC_dict(txt_dict, minTC, topN)
tcData_dict_array, txtName, tcWordName_dict_array = dict2Array(tcData_dict,
dtype=int)
# doTC_dict 比 doTC_array 快
for j in range(len(tcWordName)):
if tcWordName[j] != tcWordName_dict_array[j]:
print("%d tcWordName[i]!=tcWordName_dict_array" % j)
break
print(sum(sum(tcData_dict_array - tcData_array)))
def test_pca():
txt_dict = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s' %
'afterProccess_test') # 0.6s
txt_array, txtName, wordName = dict2Array(txt_dict, dtype=int)
dataMat = numpy.mat(txt_array[:, :1000], dtype=numpy.float64)
topN = 100
newData, U, rdata = myPCA(dataMat, topN=topN, onlyNewData=False)
newData2, U2, rdata2 = myPCA_R(dataMat, topN=topN, onlyNewData=False)
newData3, U3, rdata3 = pca_sklearn(dataMat, topN=topN, onlyNewData=False)
# showDiff(newData, newData2)
# dd = getDiff(dataMat, newData, U)
# rdata = newData * U.T + numpy.mean(dataMat, axis=0)
# print(dd,rdata.max())
print(getDiff(dataMat, rdata))
print(getDiff(dataMat, rdata2))
print(getDiff(dataMat, rdata3))
def test_selectData():
txt_dict = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s' %
'afterProccess') # 0.6s
txt_array, txtName, wordName = dict2Array(txt_dict)
newWid = random.sample(range(0, len(wordName)), 300)
newWid.sort()
newWordname = [wordName[i] for i in newWid]
sfdata = selectData_dict(txt_dict, newWordname)
sfdata2 = selectData_array(txt_array, newWordname, oldWordName=wordName)
sfdata22 = selectData_array(txt_array,
newWordname,
oldWordName=wordName,
orderchange=False)
# 当newWordname顺序改变时即orderchange=True
# selectData_dict 比 selectFeature_array快
sfdata1 = dict2Array(sfdata)[0]
print(sum(sum(sfdata1 - sfdata2)))
def test_selectFeature():
txt_dict = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s' %
'afterProccess_test')
tfidf_dict = myTFIDF(txt_dict, itc=True)
tfidf_array, txtName, wordName = dict2Array(tfidf_dict)
tc_array = myTC_array(tfidf_array)
minTC, topN = 0, 100
tc = tc_array
wordAndIdx = list(zip(wordName, tc))
wordAndIdx.sort(key=lambda x: x[1], reverse=True) # 按tc排序
newWordName = [wordAndIdx[i][0] for i in range(topN)]
newWordName.sort()
idx = tc.argsort()
idx = idx[:-topN - 1:-1]
idx.sort()
newWordName2 = [wordName[i] for i in idx]
for j in range(len(newWordName2)):
if newWordName2[j] != newWordName[j]:
print("%d tcWordName[i]!=tcWordName_dict_array" % j)
break
def do_treecluster_images():
"""特征维度对各层次聚类的影响"""
outDir = '/Users/brobear/PycharmProjects/TextClusteringAnalysis/txt2'
txt_dict = getWordCount(outDir)
xx = range(100, 1000, 100)
xx = [300, 600]
for topN in xx:
data, textNames = TC(txt_dict, topN=topN)[:2]
# # 不降维
# tfidf_dict = myTFIDF(txt_dict, itc=False)
# data, textNames, wordName = dict2Array(tfidf_dict)
# method 's': 最小距离法 'm': 最大距离法 'c': 重心法 'a': 类平均法
# dist e 欧式距离 u 余弦距离
tree = treecluster(data=data, method='m', dist='e')
# tree2 = treecluster(data=data, method='s', dist='e')
# tree3 = treecluster(data=data, method='a', dist='e')
# tree4 = treecluster(data=data, method='c', dist='e')
args = range(2, 50)
# args = list(range(2, 15, 3)) + [21, 27, 30, 40, 50, 60, 70, 80, 100, 150, 250]
d = [[], [], [], [], []] # 轮廓系数
ksize = [[], [], [], [], []] # 最大类的大小
for k in args:
clusterid = tree.cut(nclusters=k)
d[0].append(silhouette_score(data, clusterid, metric='euclidean'))
ksize[0].append(max(size_of_cluster(clusterid)))
clustering = AgglomerativeClustering(linkage='ward', n_clusters=k) # ['ward','complete','average']
clustering.fit(data)
d[1].append(silhouette_score(data, clustering.labels_, metric='euclidean'))
ksize[1].append(max(size_of_cluster(clustering.labels_)))
# clusterid2 = tree2.cut(nclusters=k)
# d[2].append(silhouette_score(data, clusterid2, metric='euclidean'))
# ksize[2].append(max(size_of_cluster(clusterid2)))
# clusterid3 = tree3.cut(nclusters=k)
# d[3].append(silhouette_score(data, clusterid3, metric='euclidean'))
# ksize[3].append(max(size_of_cluster(clusterid3)))
# clusterid4 = tree4.cut(nclusters=k)
# d[4].append(silhouette_score(data, clusterid4, metric='euclidean'))
# ksize[4].append(max(size_of_cluster(clusterid4)))
# d[2].append(hierarchical(data, k, 'complete'))#m,e
# d[3].append(hierarchical(data, k, 'average'))#a,e
# 用subplot()方法绘制多幅图形
plt.figure(figsize=(6, 6))
# 创建第一个画板
plt.figure(1)
# 将第一个画板划分为2行1列组成的区块，并获取到第一块区域
ax1 = plt.subplot(211)
realN = 0
# 在第一个子区域中绘图
for di in d:
if len(di) > 1:
plt.plot(args, di, marker='o')
realN += 1
# plt.legend(xx)
plt.legend(range(realN))
plt.xlabel = 'k'
plt.ylabel = 'silhouette'
# plt.ylim(-1, 1)
# 选中第二个子区域，并绘图
ax2 = plt.subplot(212)
for di in ksize:
if len(di) > 1:
plt.plot(args, di, marker='o')
plt.legend(range(realN))
plt.xlabel = 'k'
plt.ylabel = 'MAXcluster'
# plt.ylim(0, 2000)
ax1.set_title('feature number=%d by TC' % topN)
ax2.set_title("max size of clusters")
plt.savefig('./treecluster_images/feature number=%d by TC 1<k<50' % topN)
plt.show()
txt_dict = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s' %
'afterProccess')
minTC, topN = 0, 10000
tcData_array, tcWordName = doTC_array(txt_dict, minTC, topN)
tcData_dict = doTC_dict(txt_dict, minTC, topN)
tcData_dict_array, txtName, tcWordName_dict_array = dict2Array(tcData_dict,
dtype=int)
# doTC_dict 比 doTC_array 快
for j in range(len(tcWordName)):
if tcWordName[j] != tcWordName_dict_array[j]:
print("%d tcWordName[i]!=tcWordName_dict_array" % j)
break
print(sum(sum(tcData_dict_array - tcData_array)))
if __name__ == '__main__':
txt_dict = getWordCount(
'/Users/brobear/PycharmProjects/TextClusteringAnalysis/txt2')
tfidf_dict = myTFIDF(txt_dict, itc=True)
tfidf_array, txtName, wordName = dict2Array(tfidf_dict)
# 计算各词的单词权值
tc_array = myTC_array(tfidf_array)
showDistplot(tc_array)
tc_array.sort()
tc_array = tc_array[::-1]
from matplotlib import pyplot as plt
plt.plot(range(len(tc_array)), tc_array)
plt.ylim(0, 200)
plt.show()
clusterLabel[i] = minIndex
if minIndex in clusterLabel_map:
clusterLabel_map[minIndex].append(i)
else:
clusterLabel_map[minIndex] = [i]
# 更新中心
for i in range(k):
Cent[i, :] = numpy.mean(data[clusterLabel_map[i], :], axis=0)
print(iter)
return clusterLabel
if __name__ == '__main__':
outDir = '/Users/brobear/PycharmProjects/TextClusteringAnalysis/txt2'
txt_dict = getWordCount(outDir)
tfidf_dict = myTFIDF(txt_dict, itc=False)
data, textNames, wordName = dict2Array(tfidf_dict)
# 降维
topN = 1200
data, textNames = PCA(txt_dict, topN=topN, itc=False)[:2]
# 确定特征维数
for x in [i * 0.1 for i in range(1, 10)]:
data, textNames = PCA(txt_dict, topN=x, itc=False)[:2]
print(x, data.shape)
# 结果：0.1 74 0.2 204 0.3 357 0.4 519 0.5 684 0.6 851 0.7 1022 0.8 1198 0.9 1387
# [74, 204, 357, 519, 684, 851, 1022, 1198, 1387]
#
#
# # 肘方法看k值
# kList = range(5, 40, 1)
@log("Feature_useTime")
def PCA(txt_dict, topN=None, itc=False): # 137s
tfidf_dict = myTFIDF(txt_dict, itc=itc)
tfidf_array, txtName, wordName = dict2Array(tfidf_dict)
newData_mat = pca_sklearn(tfidf_array, topN=topN)
return newData_mat, txtName
@log("Feature_useTime")
def TC_PCA(txt_dict, minTC=0, topN=None, itc=False): # 45s
newData_dict = doTC_dict(txt_dict, minTC=minTC)
tfidf_dict = myTFIDF(newData_dict, itc=itc)
tfidf_array, txtName, wordName = dict2Array(tfidf_dict)
newData_mat = pca_sklearn(tfidf_array, topN=topN)
return newData_mat, txtName
if __name__ == '__main__':
txt_dict = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s' % 'afterProccess') # 0.6s
topN = 1800
# newData_mat, txtName, wordName = TC(txt_dict, topN)
# newData_mat2, txtName2 = PCA(txt_dict, topN=topN)
newData_mat3, txtName3 = TC_PCA(txt_dict, minTC=0, topN=topN)
# numpy.savetxt('data_TC_1800', newData_mat, delimiter=",")
# numpy.savetxt('data_PCA_1800', newData_mat2, delimiter=",")
numpy.savetxt('data_TC_PCA_1800', newData_mat3, delimiter=",")
# TEST
# txt_dict_test = getWordCount('/Users/brobear/OneDrive/data-whitepaper/data/%s_test' % 'afterProccess')
# newData_mat3, txtName3, wordName3 = TC(txt_dict_test, topN)
# numpy.savetxt('data_test', newData_mat3, delimiter=",")
