sporada/bundesdata_markup_nlp_software
1
0
Fork 0
Code Issues 6 Pull Requests Projects Releases Wiki Activity

Added some documentation.

Browse Source
This commit is contained in:
Stephan Porada
2019-03-03 18:41:12 +01:00
parent 9ef4c51c9d
commit 714f61315b
6 changed files with 1050 additions and 16480 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
bundesdata_markup_nlp/bundesdata_markup.py
View File

@ -85,7 +85,7 @@ def parse_arguments():
parser.add_argument("-fr",
"--fresh_run",
help="Deltes all temporary folders in output folder \
also deletes all paths saved in the config file file \
also deletes all paths saved in the config file \
before starting the markup process. The user has to set\
the paths again with -sp.",
action="store_true",

1
bundesdata_markup_nlp/bundesdata_nlp.py
View File

@ -17,6 +17,7 @@ This script handles the tokenization, lemmatization and ngramm calculation of
the input protocols. Needs some user input specfied int parse_arguments().
"""
def parse_arguments():
"""
Argument Parser

16
bundesdata_markup_nlp/config.ini
View File

@ -31,8 +31,16 @@ date_string = [\d\t ]*Deutscher Bundestag (?:–|—|-|--) \d{1,2} ?\. Wahlperio
multiline_comment = \B\([^\(\)]* ; [^\(\)]*\)\B ; kommentar
[File paths]
output_folder = /home/stephan/Desktop/output
input_folder_xmls = /home/stephan/Desktop/18_Wahlperiode_2013-2017/
new_metadata = /home/stephan/Desktop/output/new_metadata
new_simple_markup = /home/stephan/Desktop/output/simple_xml
output_folder = /home/stephan/Downloads/output
input_folder_xmls = /home/stephan/Downloads/development_data_xml
new_metadata = /home/stephan/Downloads/output/new_metadata
new_simple_markup = /home/stephan/Downloads/output/simple_xml
complex_markup = /home/stephan/Downloads/output/complex_markup
clear_speech_markup = /home/stephan/Downloads/output/clear_speech_markup
tmp_path = /home/stephan/Downloads/nlp_output/lemmatized/tmp
beautiful_xml = /home/stephan/Downloads/output/beautiful_xml
nlp_output = /home/stephan/Downloads/nlp_output
nlp_input = /home/stephan/Downloads/nlp_output/nlp_beuatiful_xml/
nlp_lemmatized_tokenized = /home/stephan/Downloads/nlp_output/lemmatized
nlp_beuatiful_xml = /home/stephan/Downloads/nlp_output/nlp_beuatiful_xml

17375
bundesdata_markup_nlp/logs/bundesdata.log Normal file → Executable file
View File

File diff suppressed because it is too large Load Diff

1
bundesdata_markup_nlp/logs/bundesdata_nlp.log Normal file → Executable file
View File

@ -0,0 +1 @@
2019/03/03 18:31:14 __main__ INFO:Start time of script is: 2019-03-03 18:31:14.664969