SYMBOL INDEX (222 symbols across 30 files)

FILE: 法律文书切分程序及说明文档/split_case.py
  function get_text (line 8) | def get_text(filename):
  function find_line_no (line 35) | def find_line_no(lines, s, flag):  # 根据关键字s在lines中寻找对应的行  flag False 倒序寻找
  function cut_case (line 51) | def cut_case(filename):  # 按规则切分文本
  function write2file_cut (line 153) | def write2file_cut(target_path,item):
  function main (line 201) | def main(source_path,target_path):

FILE: 法律文档—法律条文推荐/MemNN_classifier.py
  function get_each_case_laws (line 22) | def get_each_case_laws(sid,new_all_pieces_count_dict):
  function get_stories (line 32) | def get_stories(s_index,e_index,contents,top_50_law_text,new_all_pieces_...
  function get_vocab (line 47) | def get_vocab(train_stories,test_stories,test_stories2):
  function vectorize_stories (line 52) | def vectorize_stories(data,word_idx,story_maxlen,query_maxlen):
  function Mem_Model (line 67) | def Mem_Model(story_maxlen,query_maxlen,vocab_size):
  function Mem_Model2 (line 106) | def Mem_Model2(story_maxlen,query_maxlen,vocab_size):
  function get_labels_by_probs (line 165) | def get_labels_by_probs(prob_list,k):
  function generate_arrays (line 172) | def generate_arrays(inputs_train,queries_train,answers_train):
  function merge_labels (line 178) | def merge_labels(real_labels,pred_labels):
  function write2file (line 184) | def write2file(filename,flag,epoch,result,hloss,Accuracy):
  function main (line 196) | def main():

FILE: 法律文档—法律条文推荐/baseline_random/eval_functions.py
  function createPRF_me (line 7) | def createPRF_me(real_label,pred_label):  # 计算prf值 写入文件  rate ig 比率
  function get_PRF_subAcc (line 51) | def get_PRF_subAcc(all_case_laebls):
  function get_per_hloss (line 77) | def get_per_hloss(list1,list2):  # 计算单个样本的汉明损失
  function get_hloss (line 87) | def get_hloss(all_case_laebls):  # 计算测试集的hloss
  function get_Accuracy (line 96) | def get_Accuracy(all_case_laebls):
  function main (line 111) | def main():

FILE: 法律文档—法律条文推荐/baseline_random/top10labels.py
  function create_pred_label_top10 (line 9) | def create_pred_label_top10(answers_test):
  function create_pred_label_by_random (line 16) | def create_pred_label_by_random(answers_test):
  function create_all_case_labels (line 23) | def create_all_case_labels(answers_test,pred_labels):
  function main (line 29) | def main():

FILE: 法律文档—法律条文推荐/extract_caipanyiju.py
  function readFromFile (line 14) | def readFromFile(filename):  # 读文件
  function get_info (line 22) | def get_info(contents):  # 提取每个案件的首部 事实信息 和 裁判依据
  function write2file (line 35) | def write2file(fname,res_list):  # 写入文件
  function main (line 42) | def main():

FILE: 法律文档—法律条文推荐/get_all_laws.py
  function merge_laws (line 9) | def merge_laws(laws_list):  # key:xx法xx条   value:包含该法律条文的案件号
  function digit2chinese (line 39) | def digit2chinese(digit):  # 将数字转换为汉字  最多考虑百位
  function remove_punct (line 56) | def remove_punct(piece):  # 法律条文处理
  function merge_same_laws (line 124) | def merge_same_laws(all_pieces_count_dict):  # 合并相同的法律条文
  function get_each_case_laws (line 141) | def get_each_case_laws(sid,new_all_pieces_count_dict):
  function get_nums_by_del_some_pieces (line 150) | def get_nums_by_del_some_pieces(k,new_all_pieces_count_dict):
  function get_counts_of_laws (line 162) | def get_counts_of_laws(new_all_pieces_count_dict):  # 统计xx法出现的情况
  function write2file (line 177) | def write2file(idict,filename):  # 将laws和pieces的字典写入文件
  function main (line 184) | def main():

FILE: 法律文档—法律条文推荐/lstm_classifier_imbalance/Model/embedding.py
  class MySentences (line 5) | class MySentences(object):
    method __init__ (line 6) | def __init__(self,contents):
    method __iter__ (line 8) | def __iter__(self):
  function main (line 15) | def main():

FILE: 法律文档—法律条文推荐/lstm_classifier_imbalance/em_lstm.py
  class Document (line 12) | class Document:
    method __init__ (line 13) | def __init__(self,polarity,words):
  function get_each_case_laws (line 18) | def get_each_case_laws(sid,new_all_pieces_count_dict):
  function make_documents (line 28) | def make_documents(icontent,polarity):  # 生成documents  最大熵分类器的套路
  function make_document_per_case (line 39) | def make_document_per_case(icontent,polarity_list):
  function get_contents_documents (line 52) | def get_contents_documents(id_list,polarity,contents):  # 根据idlist从conte...
  function get_contents_documents_for_test (line 61) | def get_contents_documents_for_test(test_id_list,pos_id_list,neg_id_list...
  function split_case_by_law_1 (line 73) | def split_case_by_law_1(new_all_pieces_count_dict,law):
  function split_case_by_law_2 (line 103) | def split_case_by_law_2(new_all_pieces_count_dict,law):
  function get_trains_tests_order_by_polarity (line 138) | def get_trains_tests_order_by_polarity(law,new_all_pieces_count_dict,con...
  function get_trains_tests_order_by_caseId (line 191) | def get_trains_tests_order_by_caseId(law,new_all_pieces_count_dict,conte...
  function trainAndTestByLstm (line 242) | def trainAndTestByLstm(trains,vals,tests,my_model,result_file,law_index,...
  function main (line 246) | def main():

FILE: 法律文档—法律条文推荐/lstm_classifier_imbalance/eval_functions.py
  function createPRF_me (line 7) | def createPRF_me(real_label,pred_label):  # 计算prf值 写入文件  rate ig 比率
  function get_PRF_subAcc (line 51) | def get_PRF_subAcc(all_case_laebls):
  function get_per_hloss (line 78) | def get_per_hloss(list1,list2):  # 计算单个样本的汉明损失
  function get_hloss (line 88) | def get_hloss(all_case_laebls):  # 计算测试集的hloss
  function get_Accuracy (line 97) | def get_Accuracy(all_case_laebls):
  function main (line 112) | def main():

FILE: 法律文档—法律条文推荐/lstm_classifier_imbalance/get_multi_label_result.py
  function readFromFile (line 12) | def readFromFile(filesname):
  function get_all_case_labels (line 28) | def get_all_case_labels(source_path,k):  # k用于限制预测标签的个数 只保留预测概率最大的k个
  function cut_pred_label (line 58) | def cut_pred_label(all_case_laebls,k):
  function createPRF_me (line 74) | def createPRF_me(real_label,pred_label):  # 计算prf值 写入文件  rate ig 比率
  function main (line 117) | def main():

FILE: 法律文档—法律条文推荐/lstm_classifier_imbalance/lstm_process.py
  class Document (line 30) | class Document:
    method __init__ (line 31) | def __init__(self,polarity,words):
  function createVec (line 35) | def createVec(docs,my_model):  # 生成词向量表示
  function LSTM_model (line 67) | def LSTM_model(X_train,Y_train,X_val,Y_val,X_test,Y_test,test_label):
  function LSTM_model2 (line 134) | def LSTM_model2(X_train,Y_train,X_val,Y_val,X_test,Y_test,test_label):
  function get_documents (line 196) | def get_documents(trains,vals,tests,my_model):  # 从em_lstm.py中接收数据供实验所用 ...
  function createResult (line 219) | def createResult(pred_label,real_label,law_index,lenT,lenV,lenP,lenN,log...
  function make_result_file (line 268) | def make_result_file(best_pred_label,best_pred_prob,real_label,result_fi...
  function lstm_run (line 280) | def lstm_run(trains,vals,tests,my_model,result_file,law_index,lenT,lenV,...

FILE: 法律文档—法律条文推荐/lstm_classifier_imbalance/tongji_case.py
  function get_each_case_laws (line 10) | def get_each_case_laws(sid,new_all_pieces_count_dict):
  function get_pieces_count (line 18) | def get_pieces_count(contents,new_all_pieces_count_dict):
  function get_tests_predAndpred_pieces_count (line 25) | def get_tests_predAndpred_pieces_count(all_case_laebls):
  function tongji_count (line 35) | def tongji_count(count_dict,length):
  function main (line 41) | def main():

FILE: 法律文档—法律条文推荐/maxent_classifier_imbalance/documents.py
  class Document (line 14) | class Document:
    method __init__ (line 15) | def __init__(self,polarity,words):
  function get_each_case_laws (line 20) | def get_each_case_laws(sid,new_all_pieces_count_dict):
  function make_documents (line 32) | def make_documents(icontent,polarity):  # 生成documents  最大熵分类器的套路
  function make_document_per_case (line 43) | def make_document_per_case(icontent,polarity_list):
  function get_contents_documents (line 56) | def get_contents_documents(id_list,polarity,contents):  # 根据idlist从conte...
  function get_contents_documents_for_test (line 65) | def get_contents_documents_for_test(test_id_list,pos_id_list,neg_id_list...
  function split_case_by_law_1 (line 101) | def split_case_by_law_1(new_all_pieces_count_dict,law):
  function split_case_by_law_2 (line 124) | def split_case_by_law_2(new_all_pieces_count_dict,law):
  function trainAndTest (line 146) | def trainAndTest(trains,tests,result_file,law_index,lenTP,lenTN,lenP,len...
  function get_trains_tests_order_by_polarity (line 155) | def get_trains_tests_order_by_polarity(law,new_all_pieces_count_dict,con...
  function get_trains_tests_order_by_caseId (line 204) | def get_trains_tests_order_by_caseId(law,new_all_pieces_count_dict,conte...
  function main (line 239) | def main():

FILE: 法律文档—法律条文推荐/maxent_classifier_imbalance/eval_functions.py
  function createPRF_me (line 7) | def createPRF_me(real_label,pred_label):  # 计算prf值 写入文件  rate ig 比率
  function get_PRF_subAcc (line 51) | def get_PRF_subAcc(all_case_labels):
  function get_per_hloss (line 81) | def get_per_hloss(list1,list2):  # 计算单个样本的汉明损失
  function get_hloss (line 91) | def get_hloss(all_case_labels):  # 计算测试集的hloss
  function get_Accuracy (line 100) | def get_Accuracy(all_case_labels):
  function xiugai_pred (line 119) | def xiugai_pred(all_case_labels):
  function main (line 125) | def main():

FILE: 法律文档—法律条文推荐/maxent_classifier_imbalance/get_multi_label_result.py
  function readFromFile (line 12) | def readFromFile(filesname):
  function get_all_case_labels (line 28) | def get_all_case_labels(source_path,k):  # k用于限制预测标签的个数 只保留预测概率最大的k个
  function cut_pred_label (line 59) | def cut_pred_label(all_case_laebls,k,labelNum):
  function createPRF_me (line 76) | def createPRF_me(real_label,pred_label):  # 计算prf值 写入文件  rate ig 比率
  function main (line 119) | def main():

FILE: 法律文档—法律条文推荐/maxent_classifier_imbalance/maxent.py
  function get_lexcion (line 11) | def get_lexcion(documents): #生成字典
  function getDFWords (line 19) | def getDFWords(documents): #词频 保留出现次数大于5的词汇
  function createFormatText (line 38) | def createFormatText(documents,lexcion,path): #生成mallet工具所需的文本格式
  function file2Bin (line 64) | def file2Bin(FilePath,BinPath): #tests.txt时要加上pipe
  function train (line 78) | def train(trainBinPath,modelPath):
  function classify (line 88) | def classify(modelPath,testBinPath,resultPath):
  function createResult2 (line 98) | def createResult2(resultPath):
  function getPredLabel (line 151) | def getPredLabel(FilePath): # 得到预测的类别和真实的类别
  function createPRF (line 165) | def createPRF(FilePath,seed,log_path='maxent_prf.txt'):  # 计算prf值 写入文件
  function createPRF_me (line 208) | def createPRF_me(pred_label,real_label,law_index,lenTP,lenTN,lenP,lenN,l...
  function getPredProb (line 258) | def getPredProb(FilePath):
  function me_classify (line 280) | def me_classify(trains,tests,result_file='result.txt'):  # 默认为result.txt

FILE: 法律文档—法律条文推荐/maxent_classifier_imbalance/tongji_case.py
  function get_each_case_laws (line 10) | def get_each_case_laws(sid,new_all_pieces_count_dict):
  function get_pieces_count (line 18) | def get_pieces_count(contents,new_all_pieces_count_dict):
  function get_tests_predAndpred_pieces_count (line 25) | def get_tests_predAndpred_pieces_count(all_case_laebls):
  function tongji_count (line 35) | def tongji_count(count_dict,length):
  function main (line 41) | def main():

FILE: 法律文档—法律条文推荐/maxent_classifier_imbalance/word_cut.py
  function cut (line 9) | def cut(contents):  # 分词
  function main (line 17) | def main():

FILE: 法律文档—法律条文推荐/new_model_2/extract_law_text.py
  function readFromFile (line 7) | def readFromFile(filename):  # 读文件
  function cut (line 16) | def cut(contents):  # 分词
  function main (line 24) | def main():

FILE: 法律文档—法律条文推荐/new_model_2/tf-idf.py
  class Document (line 7) | class Document:
    method __init__ (line 8) | def __init__(self,words):
  function getDFWords (line 11) | def getDFWords(documents): #词频 保留出现次数大于3的词汇
  function make_new_documents (line 31) | def make_new_documents(lexcion,documents,contents):
  function make_documents (line 43) | def make_documents(new_contents):
  function tfidf (line 52) | def tfidf(documents):  # 计算tf-idf
  function select_feat_by_tfidf (line 65) | def select_feat_by_tfidf(documents,contents):
  function main (line 76) | def main():

FILE: 法律文档—法律条文推荐/new_model_2/tongji.py
  function get_count (line 4) | def get_count(count,rate):
  function main (line 11) | def main():

FILE: 法律文档—法律条文推荐/tongji_laws.py
  function get_all_yiju (line 10) | def get_all_yiju(filename):  # 得到所有的裁判依据
  function deal_yiju (line 19) | def deal_yiju(yiju):  # 处理法律依据 提取法律条文  xx法xx条
  function write2file (line 46) | def write2file(contents,yiju_list,filename):
  function main (line 58) | def main():

FILE: 法律文档相似度计算程序及文档/cal_similarity.py
  class Document (line 12) | class Document:
    method __init__ (line 13) | def __init__(self,words,filename):
  function get_text (line 17) | def get_text(f_path,filename):
  function extract (line 29) | def extract(lines,filename,key_part=['# 首部']):  # 按关键部分提取文书内容  默认只使用首部
  function tfidf (line 45) | def tfidf(documents):  # 计算tf-idf
  function test_tfidf (line 64) | def test_tfidf(documents,idf_words):  # 计算测试样本的tfidf
  function cosine (line 74) | def cosine(source,target):   # 计算两文本cos距离
  function similar (line 84) | def similar(source,target):  # 计算两个文档的相似度
  function find_max_sim (line 87) | def find_max_sim(test,targets,top_k):  # 寻找和某个文件最相似的k个文件
  function make_documents (line 96) | def make_documents(f_path,filenames,key_part):  # 将文件生成所需格式
  function process (line 109) | def process(test,target,top_k):  # 在target中寻找与test最相似的top_k个文件
  function write2file (line 119) | def write2file(test_file,sim_filenames,saved_file):
  function start (line 127) | def start(train_path,test_path,top_k,key_part,use_model):
  function main (line 164) | def main():

FILE: 法律文档相似度计算程序及文档/cal_similarity2.py
  class Document (line 15) | class Document:
    method __init__ (line 16) | def __init__(self,words,filename):
  function get_text (line 20) | def get_text(f_path,filename):
  function extract (line 33) | def extract(lines,filename,key_part=['# 首部']):  # 按关键部分提取文书内容  默认只使用首部
  function tfidf (line 51) | def tfidf(documents):  # 计算tf-idf
  function cosine (line 66) | def cosine(source,target):   # 计算两文本cos距离
  function similar (line 76) | def similar(source,target):  # 计算两个文档的相似度
  function find_max_sim (line 79) | def find_max_sim(test,targets,top_k):  # 寻找和某个文件最相似的k个文件
  function make_documents (line 88) | def make_documents(f_path,filenames,key_part):  # 将文件生成所需格式
  function process (line 101) | def process(test,target,top_k):  # 在target中寻找与test最相似的top_k个文件
  function write2file (line 111) | def write2file(test_file,sim_filenames,saved_file):
  function start (line 119) | def start(train_path,test_path,top_k,key_part):
  function main (line 142) | def main():

FILE: 法律文档相似度计算程序及文档/jieba_seg.py
  function cut (line 10) | def cut(filename1,filename2): # 对每一个文件seg and pos
  function getFileList (line 18) | def getFileList(source_path,target_path):
  function main (line 27) | def main():

FILE: 法律文档相似度计算程序及文档/train_model.py
  class Document (line 10) | class Document:
    method __init__ (line 11) | def __init__(self,words,filename):
  function get_text (line 15) | def get_text(f_path,filename):
  function extract (line 27) | def extract(lines,filename,key_part=['# 首部']):  # 按关键部分提取文书内容  默认只使用首部
  function make_documents (line 43) | def make_documents(f_path,filenames,key_part):  # 将文件生成所需格式
  function tfidf (line 56) | def tfidf(documents):  # 计算tf-idf
  function start (line 75) | def start(train_path,key_part):
  function main (line 86) | def main():

FILE: 法律文档聚类方法研究及文档/cal_similarity.py
  class Document (line 9) | class Document:
    method __init__ (line 10) | def __init__(self,words,filename):
  function get_text (line 14) | def get_text(f_path,filename):
  function extract (line 26) | def extract(lines,filename,key_part=['# 首部']):  # 按关键部分提取文书内容  默认只使用首部
  function tfidf (line 39) | def tfidf(documents):  # 计算tf-idf
  function cosine (line 52) | def cosine(source,target):   # 计算两文本cos距离
  function similar (line 62) | def similar(source,target):  # 计算两个文档的相似度
  function find_max_sim (line 65) | def find_max_sim(test,targets,top_k):  # 寻找和某个文件最相似的k个文件
  function make_documents (line 74) | def make_documents(f_path,filenames,key_part):  # 将文件生成所需格式
  function process (line 90) | def process(test,target,top_k):  # 在target中寻找与test最相似的top_k个文件
  function write2file (line 100) | def write2file(test_file,sim_filenames,saved_file):
  function start (line 108) | def start(train_path,test_path,top_k,key_part):
  function main (line 129) | def main():

FILE: 法律文档聚类方法研究及文档/cluster_test.py
  class Document (line 6) | class Document:   # 文档类  文件名 词
    method __init__ (line 7) | def __init__(self,words,filename):
  function get_text (line 11) | def get_text(filename):
  function extract (line 23) | def extract(lines,filename,key_part=['# 首部']):  # 按关键部分提取文书内容  默认只使用首部
  function tfidf (line 36) | def tfidf(documents):  # 计算tf-idf
  function cosine (line 49) | def cosine(source,target):
  function similar (line 59) | def similar(source,target):
  function init (line 62) | def init(documents):
  function getDocuments (line 74) | def getDocuments(item):
  function clustering (line 94) | def clustering(documents,k=5):   # 层次聚类
  function make_documents (line 131) | def make_documents(filenames):  # 将文件生成所需格式
  class Item (line 148) | class Item:
    method __init__ (line 149) | def __init__(self,children):
  function main (line 183) | def main():

FILE: 法律文档聚类方法研究及文档/kmeans_cluster.py
  class Document (line 21) | class Document:
    method __init__ (line 22) | def __init__(self,words,filename,text):
  function get_text (line 27) | def get_text(filename):
  function extract (line 40) | def extract(filename,key_part=['# 首部']):  # 按关键部分提取文书内容  默认只使用首部
  function tfidf (line 57) | def tfidf(documents):  # 计算tf-idf
  function get_tfidf (line 70) | def get_tfidf(documents):  # 使用gensim计算得到tfidf
  function create_format_mat (line 86) | def create_format_mat(documents,words):
  function clustering (line 105) | def clustering(docs,n_clusters):  # 聚类 n_clusters 类别数
  function write2file (line 113) | def write2file(item_parts):  # 将结果写入文件
  function cluster_process (line 127) | def cluster_process(filenames,key_part,s,n_clusters=2):
  function main (line 170) | def main():

FILE: 法律文档聚类方法研究及文档/test_tfidf.py
  class Document (line 8) | class Document:   # 文档类  文件名 词
    method __init__ (line 9) | def __init__(self,words,filename):
  function tfidf (line 13) | def tfidf(documents):  # 计算tf-idf
  function get_tfidf (line 26) | def get_tfidf(documents):  # 使用gensim计算得到tfidf