def ExtractFeatureWords(filename):
result = Reader.readfile(filename)
result_split = Segmentation.SplitCluster(result)
delete_result = Candidate.DeleteRepetition(result_split)
candidate = Candidate.BuildClass(delete_result)
Candidate.CalLenScore(candidate, 2, 15)
Candidate.CalSupScore(candidate, result_split)
Candidate.CalPosScore(candidate, result_split)
for i in range(len(candidate)):
for j in range(len(candidate[i])):
candidate[i][j].CalScore()
candidate_list = Candidate.GenCandidateList(candidate)
sorted_candidate_list = Candidate.CandidateListSort(candidate_list)
# extracted_word = Candidate.CutByRank(sorted_candidate_list,0.5)
# PrintExtractedWord(extracted_word)
extracted_word = Candidate.CutByScore(sorted_candidate_list, 2.9)
# PrintExtractedWord(extracted_word)
# extracted_word = Candidate.CutByRankAndScore(sorted_candidate_list,0.05,2.9)
# PrintExtractedWord(extracted_word)
extracted_result = Candidate.ExtractedWordDeleteRepetition(extracted_word)
# PrintExtractedResult(extracted_result)
# print("")
# print("")
# print("")
# print("")
#
# extracted_word = Candidate.CutByScore(sorted_candidate_list,2.0)
# print("the result of cut by score: ")
# for i in range(len(extracted_word)):
# print("")
# for j in range(len(extracted_word[i])):
# print(extracted_word[i][j])
return extracted_result
def ExtractedWordDeleteRepetition(extracted_word):
"""
得出每个聚类去重后的所有关键词
:param extracted_word: 未去重的每个聚类类别内部的关键词
:return: 去重后提取的关键词
"""
extracted_result = []
for i in range(len(extracted_word)):
for j in range(len(extracted_word[i])):
if extracted_word[i][j][0] not in extracted_result:
extracted_result.append(extracted_word[i][j][0])
return extracted_result
if __name__ == '__main__':
result = Reader.readfile('result38.bin')
result_split = Segmentation.SplitCluster(result)
delete_result = DeleteRepetition(result_split)
candidate = BuildClass(delete_result)
CalLenScore(candidate,2,15)
CalSupScore(candidate,result_split)
CalPosScore(candidate,result_split)
for i in range(len(candidate)):
for j in range(len(candidate[i])):
candidate[i][j].CalScore()
candidate_list = GenCandidateList(candidate)
sorted_candidate_list = CandidateListSort(candidate_list)
for i in range(len(sorted_candidate_list)):
print("")
for j in range(len(sorted_candidate_list[i])):
print(sorted_candidate_list[i][j])
