From 08bfdfc449fbd24d5e4ea612e611c59fb2291f11 Mon Sep 17 00:00:00 2001 From: Bartlomiej Niton <bartek.niton@gmail.com> Date: Mon, 21 Aug 2017 10:55:59 +0200 Subject: [PATCH] Minor fixes. --- preparator.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/preparator.py b/preparator.py index 26ad0c5..02365ec 100644 --- a/preparator.py +++ b/preparator.py @@ -29,7 +29,7 @@ TITLE2REDIRECT_PATH = os.path.abspath(os.path.join(MAIN_PATH, 'data', 'wikipedia ANNO_PATH = TEST_PATH OUT_PATH = os.path.abspath(os.path.join(MAIN_PATH, 'data', - 'test-20170720.csv')) + 'test-1to5-20170720.csv')) EACH_TEXT_SEPARATELLY = False CONTEXT = 5 @@ -39,8 +39,9 @@ MODEL = os.path.abspath(os.path.join(MAIN_PATH, 'models', 'w2v_allwiki_nkjpfull_%d.model' % W2V_SIZE)) FIRST_SECOND_PERSON = ['pri', 'sec'] -INDICATIVE_PRONS_BASES = ["ten", "ta", "to", "ci", "te", "tamten", "tamta", - "tamto", "tamci", "tamte", "ów", "owa", "owo", "owi", "owe"] +INDICATIVE_PRONS_BASES = [u'ten', u'ta', u'to', u'ci', u'te', u'tamten', u'tamta', + u'tamto', u'tamci', u'tamte', u'ów', u'owa', u'owo', + u'owi', u'owe'] SIEBIE_TAGS = ['siebie'] MASCULINE_TAGS = ['m1', 'm2', 'm3'] @@ -50,7 +51,7 @@ ZERO_TAGS = ['fin', 'praet', 'bedzie', 'impt', 'winien', 'aglt'] POSSIBLE_HEADS = [u'§', u'%', u'*', u'"', u'„', u'&', u'-'] HYPHEN_SIGNS = ['-', '#'] -NEG_PROPORTION = 1 +NEG_PROPORTION = 5 RANDOM_VECTORS = True DEBUG = False @@ -612,7 +613,7 @@ def check_one_way_acronym(acronym, expression): for expr2 in expr1.split(): expr2 = expr2.strip() if expr2: - initials += str(expr2[0]).upper() + initials += expr2[0].upper() if acronym == initials: return 1 return 0 -- libgit2 0.22.2