def main(argv):
if len(argv) < 2:
print("call: counterparts_huber1992.py data_path")
exit(1)
cr = CorpusReaderWordlist(os.path.join(argv[1], "csv"))
o = OrthographyParser(os.path.join(argv[1], "orthography_profiles", "huber1992.txt"))
ngrams_by_language_count = list()
ngrams_set = set()
for i, wordlistdata_id in enumerate(cr.wordlistdata_ids_for_bibtex_key('huber1992')):
#counterparts = cr.counterpartsForWordlistdataId(wordlistdata_id)
#print wordlistdata_id
language_bookname = cr.get_language_bookname_for_wordlistdata_id(wordlistdata_id)
language_code = cr.get_language_code_for_wordlistdata_id(wordlistdata_id)
counterpart_graphemes = (o.parse_string_to_graphemes(counterpart) \
for counterpart in cr.counterparts_for_wordlistdata_id(wordlistdata_id))
matrix = qlc.ngram.words_ngrams_matrix_for_graphemes_list(counterpart_graphemes, 2)
sum = numpy.sum(matrix.matrix, 0)
#print("Sum length: {0}".format(len(sum)))
#print("Column length: {0}".format(len(columns)))
if len(sum.nonzero()[0]) != matrix.number_of_columns:
print("Error: ")
print("{0} != {1}".format(len(sum.nonzero()[0]), len(columns)))
print(language_bookname)
ngrams_by_language_count.append(collections.defaultdict(int))
for j, c in enumerate(matrix.column_names):
ngrams_set.add(c)
ngrams_by_language_count[i][c] = sum[j]
ngrams_list = sorted(list(ngrams_set))
matrix = qlc.matrix.Matrix(ngrams_by_language_count, ngrams_list)
# matrix = numpy.zeros( ( len(ngrams_by_language_count), len(ngrams_list) ) )
for i in range(matrix.number_of_rows):
for j, ngram in enumerate(ngrams_list):
matrix.matrix[i][j] = ngrams_by_language_count[i][ngram]
print(matrix.matrix)
def main(argv):
if len(argv) < 2:
print("call: concepts_with_counterparts.py data_path [(bibtex_key|component)]")
exit(1)
cr = CorpusReaderWordlist(argv[1])
print("Data loaded", file=sys.stderr)
dictdata_ids = []
if len(argv) == 3:
wordlistdata_ids = cr.wordlistdata_ids_for_bibtex_key(argv[2])
if len(wordlistdata_ids) == 0:
wordlistdata_ids = cr.wordlistdata_ids_for_component(argv[2])
if len(wordlistdata_ids) == 0:
print("did not find any dictionary data for the bibtex_key or component {0}.".format(argv[2]), file=sys.stderr)
sys.exit(1)
else:
wordlistdata_ids = cr.wordlistdata_string_ids
bibtex_keys = collections.defaultdict(list)
for wid in wordlistdata_ids:
wordlistdata_string = cr.wordlistdata_string_ids[wid]
bibtex_key = wordlistdata_string.split("_")[0]
bibtex_keys[bibtex_key].append(wid)
for bibtex_key in bibtex_keys:
print("Writing data for wordlistdata bibtex key {0}".format(bibtex_key), file=sys.stderr)
output = codecs.open("concepts_with_counterparts_%s.txt" % bibtex_key, "w", "utf-8")
output.write("COUNTERPART\tCONCEPT\tLANGUAGE_BOOKNAME\tLANGUAGE_CODE\tBIBTEX_KEY\n")
for wordlistdata_id in bibtex_keys[bibtex_key]:
#heads_with_translations = cr.heads_with_translations_for_dictdata_id(dictdata_id)
language_bookname = cr.get_language_bookname_for_wordlistdata_id(wordlistdata_id)
language_code = cr.get_language_code_for_wordlistdata_id(wordlistdata_id)
for concept, counterpart in cr.data(wordlistdata_id):
output.write("{0}\t{1}\t{2}\t{3}\t{4}\n".format(counterpart, concept, language_bookname, language_code, bibtex_key))
output.close()
if os.path.getsize("concepts_with_counterparts_%s.txt" % bibtex_key) == 0:
os.remove("concepts_with_counterparts_%s.txt" % bibtex_key)
