Python master_clean_regex示例

示例#1

文件： generate_cleaned_names_par.py 项目： ChaoOnGitHub/psClean

def clean_wrapper(name_string, dict_list=regex_dicts):
    print name_string
    out = psCleanup.rem_diacritics(name_string)
    out = psCleanup.stdize_case(out)
    out = psCleanup.master_clean_regex([out], dict_list)
    out = out[0].strip()
    return(out)

示例#2

文件： pandas_query_clean_par.py 项目： ChaoOnGitHub/psClean

 def name_clean_wrapper(name_list, clean_regex=name_address_regex, legal_regex=legal_regex):
      name_string = psCleanup.decoder(name_list)
      name_string = psCleanup.remove_diacritics(name_string)
      name_string = psCleanup.stdize_case(name_string)
      name_string = psCleanup.master_clean_regex(name_string, clean_regex)
      names_ids = psCleanup.get_legal_ids(name_string, legal_regex)
      return names_ids

示例#3

文件： generate_cleaned_names_par.py 项目： zhengpingwan/psClean

def clean_wrapper(name_string, dict_list=regex_dicts):
    print name_string
    out = psCleanup.rem_diacritics(name_string)
    out = psCleanup.stdize_case(out)
    out = psCleanup.master_clean_regex([out], dict_list)
    out = out[0].strip()
    return (out)

示例#4

 def address_clean_wrapper(address_list, clean_regex=name_address_regex):
     address_string = psCleanup.decoder(address_list)
     address_string = psCleanup.remove_diacritics(address_string)
     address_string = psCleanup.stdize_case(address_string)
     address_string = psCleanup.master_clean_regex(address_string,
                                                   clean_regex)
     return address_string

示例#5

文件： clean_raw_text.py 项目： ChaoOnGitHub/psClean

def clean_wrapper(name_dict, dict_list=regex_dicts):
    name_string = psCleanup.decoder(name_dict["person_name"])
    out = psCleanup.rem_diacritics(name_string)
    out = psCleanup.stdize_case(out)
    out = psCleanup.master_clean_regex([out], dict_list)
    out = out[0].strip()
    name_dict["person_name"] = psCleanup.encoder(out)
    return name_dict

示例#6

def clean_wrapper(name_dict, dict_list=regex_dicts):
    name_string = psCleanup.decoder(name_dict['person_name'])
    out = psCleanup.rem_diacritics(name_string)
    out = psCleanup.stdize_case(out)
    out = psCleanup.master_clean_regex([out], dict_list)
    out = out[0].strip()
    name_dict['person_name'] = psCleanup.encoder(out)
    return (name_dict)

示例#7

 def name_clean_wrapper(name_list,
                        clean_regex=name_address_regex,
                        legal_regex=legal_regex):
     name_string = psCleanup.decoder(name_list)
     name_string = psCleanup.remove_diacritics(name_string)
     name_string = psCleanup.stdize_case(name_string)
     name_string = psCleanup.master_clean_regex(name_string, clean_regex)
     names_ids = psCleanup.get_legal_ids(name_string, legal_regex)
     return names_ids

示例#8

文件： pandas_query_clean_par.py 项目： ChaoOnGitHub/psClean

 def address_clean_wrapper(address_list, clean_regex=name_address_regex):
      address_string = psCleanup.decoder(address_list)
      address_string = psCleanup.remove_diacritics(address_string)
      address_string = psCleanup.stdize_case(address_string)
      address_string = psCleanup.master_clean_regex(address_string, clean_regex)
      return address_string