Formatted computer + added correct forms of accentuation

.gitignore

@@ -98,3 +98,4 @@ grid_results/
 .idea/
 cnn/word_accetuation/svm/data/
 data_merge.ipynb
+data_merge.py

sloleks_accentuation2.py

@@ -16,7 +16,7 @@ content = data._read_content('data/SlovarIJS_BESEDE_utf8.lex')
 dictionary, max_word, max_num_vowels, vowels, accented_vowels = data._create_dict(content)
 feature_dictionary = data._create_slovene_feature_dictionary()
 syllable_dictionary = data._create_syllables_dictionary(content, vowels)
-accented_vowels = ['ŕ', 'á', 'ä', 'é', 'ë', 'ě', 'í', 'î', 'ó', 'ô', 'ö', 'ú', 'ü']
+accented_vowels = ['ŕ', 'á', 'à', 'é', 'è', 'ê', 'í', 'ì', 'ó', 'ô', 'ò', 'ú', 'ù']
 
 data = Data('l', shuffle_all_inputs=False)
 letter_location_model, syllable_location_model, syllabled_letters_location_model = data.load_location_models(

sloleks_accentuation2_tab2xml.py

@@ -59,7 +59,8 @@ start_timer = time.time()
 print('Copy initialization complete')
 with open("data/new_sloleks/final_sloleks.xml", "ab") as myfile:
     # myfile2 = open('data/new_sloleks/p' + str(iter_index) + '.xml', 'ab')
-    for event, element in etree.iterparse('data/Sloleks_v1.2.xml', tag="LexicalEntry", encoding="UTF-8", remove_blank_text=True):
+    for event, element in etree.iterparse('data/new_sloleks/final_sloleks_read.xml', tag="LexicalEntry", encoding="UTF-8", remove_blank_text=True):
+    # for event, element in etree.iterparse('data/Sloleks_v1.2.xml', tag="LexicalEntry", encoding="UTF-8", remove_blank_text=True):
         # if word_glob_num >= word_limit:
         #     myfile2.close()
         #     myfile2 = open('data/new_sloleks/p' + str(iter_index) + '.xml', 'ab')

sloleks_accetuation2.ipynb

@@ -219,7 +219,6 @@
     {
      "ename": "IndexError",
      "evalue": "index 10 is out of bounds for axis 0 with size 10",
-     "output_type": "error",
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mIndexError\u001b[0m                                Traceback (most recent call last)",
@@ -228,7 +227,8 @@
       "\u001b[0;32m~/Developement/accetuation/prepare_data.py\u001b[0m in \u001b[0;36mget_ensemble_location_predictions\u001b[0;34m(input_words, letter_location_model, syllable_location_model, syllabled_letters_location_model, letter_location_co_model, syllable_location_co_model, syllabled_letters_location_co_model, dictionary, max_word, max_num_vowels, vowels, accented_vowels, feature_dictionary, syllable_dictionary)\u001b[0m\n\u001b[1;32m   1465\u001b[0m         \u001b[0mletter_location_co_predictions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mletter_location_co_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict_generator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgenerator\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m/\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mbatch_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1466\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1467\u001b[0;31m         \u001b[0mletter_location_co_predictions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreverse_predictions\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mletter_location_co_predictions\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput_words\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvowels\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1468\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1469\u001b[0m         \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mData\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m's'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshuffle_all_inputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconvert_multext\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreverse_inputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;32m~/Developement/accetuation/prepare_data.py\u001b[0m in \u001b[0;36mreverse_predictions\u001b[0;34m(self, predictions, words, vowels)\u001b[0m\n\u001b[1;32m   1503\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1504\u001b[0m             \u001b[0;32mfor\u001b[0m \u001b[0mk\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mword_len\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1505\u001b[0;31m                 \u001b[0mnew_predictions\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0mpredictions\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mword_len\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0;36m1\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1506\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1507\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mnew_predictions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mIndexError\u001b[0m: index 10 is out of bounds for axis 0 with size 10"
-     ]
+     ],
+     "output_type": "error"
     }
    ],
    "source": [

text2SAMPA.py

@@ -86,6 +86,7 @@ def create_syllables(word, vowels):
 
 
 def convert_to_SAMPA(word):
+    word = word.lower()
     syllables = create_syllables(word, vowels)
     letters_in_stressed_syllable = [False] * len(word)
     # print(syllables)
@@ -152,6 +153,11 @@ def convert_to_SAMPA(word):
 
     word = list(''.join(word))
 
+    test_word = ''.join(word)
+    test_word = test_word.replace('"', '').replace(':', '')
+    if len(test_word) <= 1:
+        return ''.join(word)
+
     previous_letter_i = -1
     letter_i = 0
     next_letter_i = 1