error - Githubissues

hi, i'm getting this error. what should i do? thanks. _fixup_main_from_path(data['init_main_from_path']) File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path run_name="mp_main__") File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\runpy.py", line 263, in run_path pkg_name=pkg_name, script_name=fname) File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\runpy.py", line 96, in _run_module_code mod_name, mod_spec, pkg_name, script_name) File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "C:\Users\User\PycharmProjects\BINAP\wordembedding-hebrew-master\create_corpus.py", line 12, in for text in wiki.get_texts(): File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\site-packages\gensim\corpora\wikicorpus.py", line 679, in get_texts pool = multiprocessing.Pool(self.processes, init_to_ignore_interrupt) File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\context.py", line 119, in Pool context=self.get_context()) File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\pool.py", line 175, in init__ self._repopulate_pool() File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\pool.py", line 236, in _repopulate_pool self._wrap_exception) File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\pool.py", line 255, in _repopulate_pool_static w.start() File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\process.py", line 105, in start self._popen = self._Popen(self) File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\popen_spawn_win32.py", line 33, in init prep_data = spawn.get_preparation_data(process_obj._name) File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\spawn.py", line 143, in get_preparation_data _check_not_importing_main() File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\multiprocessing\spawn.py", line 136, in _check_not_importing_main is not going to be frozen to produce an executable.''') RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

This is a fix for that code:

from gensim.corpora import WikiCorpus from gensim import utils

def create_wiki_corpus(input_path, output_file): i = 0

print("Starting to create wiki corpus")
output = open(output_file, 'w', encoding='utf-8')  # Specify the encoding when opening the file
wiki = WikiCorpus(input_path, dictionary={})

for text in get_texts(wiki):
    print(text)
    article = " ".join([t for t in text])  # Use " ".join instead of space.join

    output.write(article + "\n")
    i += 1
    if i % 1000 == 0:
        print("Saved " + str(i) + " articles")

output.close()
print("Finished - Saved " + str(i) + " articles")

def get_texts(wiki): for doc in wiki.getstream(): yield [word for word in utils.to_unicode(doc).lower().split()]

input_file = "hewiki-latest-pages-articles.xml.bz2" output_file = "wiki.he.text"

create_wiki_corpus(input_file, output_file)

liorshk / wordembedding-hebrew

error #5