def make_files():
# Set analyses variable for creation of further resources
# If it does not already exist, it will be created by importing modules from Reassign_POS above
# If it is deleted by the code above, it will be recreated
if path.exists("SG. Combined Data.xlsx"):
analyses = list_xlsx("SG. Combined Data", "Sheet 1")
else:
print(create_data_combo())
analyses = list_xlsx("SG. Combined Data", "Sheet 1")
# Create 'Clean_GlossDict.pkl' and 'Clean_WordDict.pkl'
print(create_clean_glossdict())
print(create_clean_worddict())
# Create 'A1 List.pkl', 'A2 List.pkl', 'A3 List.pkl', 'Active_Passive List.pkl',
# 'Relative Options List.pkl', and 'Translations List.pkl'
print(save_sorted_tags(sort_tag_levels(list_tag_levels(analyses))))
# Create 'All POS Combos Used.pkl' and 'POS_taglist.pkl'
print(save_all_pos_combos_list(analyses))
print(create_pos_taglist())
# Create 'Gloss_List.pkl' and 'Words_List.pkl'
print(create_glosslist(analyses))
print(create_wordlist(analyses))
# Create 'SG POS-tagged combined.pkl' and 'SG POS-tagged separated.pkl'
print(save_poslist(True))
print(save_poslist(False))
# Create 'sga_dipsgg-ud-test1.conllu' and 'sga_dipsgg-ud-test2.conllu'
print(compile_SGG(open_obj("SG POS-tagged combined.pkl"), True))
print(compile_SGG(open_obj("SG POS-tagged separated.pkl"), False))
return ""
def create_clean_worddict():
sgData = list_xlsx("SG. Combined Data", "Sheet 1")
wordlist = list()
for i in sgData:
thisword = i[2]
if thisword:
if thisword not in wordlist:
wordlist.append(thisword)
worddict = {}
for i in wordlist:
worddict[i] = clean_word(i)
save_obj("Clean_WordDict", worddict)
return "Created file: 'Clean_WordDict.pkl'"
def create_clean_glossdict():
sgData = list_xlsx("SG. Combined Data", "Sheet 1")
glosslist = list()
lastgloss = ""
for i in sgData:
thisgloss = i[10]
if thisgloss != lastgloss:
glosslist.append(thisgloss)
lastgloss = thisgloss
glossdict = {}
for i in glosslist:
glossdict[i] = clean_gloss(i)
save_obj("Clean_GlossDict", glossdict)
return "Created file: 'Clean_GlossDict.pkl'"
Match tokenisation of OI material in gloss-lists to words
Implement appropriate spacing in gloss-lists based on tokenisation
Sequence gloss-lists
"""
from Clean_ExcelLists import create_data_combo
from Pickle import open_obj
from OpenXlsx import list_xlsx
from Clean_Glosses import clean_gloss, clean_word, clean_lemma
from Reassign_POS import clean_analysis, clean_onetag, create_glosslist, create_wordlist
try:
analyses = list_xlsx("SG. Combined Data", "Sheet 1")
except FileNotFoundError:
print(create_data_combo())
analyses = list_xlsx("SG. Combined Data", "Sheet 1")
# # Run the functions below to create the following .pkl files from spreadsheet, "SG. Combined Data"
try:
glosslist = open_obj("Gloss_List.pkl")
wordslist = open_obj("Words_List.pkl")
except FileNotFoundError:
print(create_glosslist(analyses))
print(create_wordlist(analyses))
glosslist = open_obj("Gloss_List.pkl")
wordslist = open_obj("Words_List.pkl")
# Map a word-separated gloss from the Hofman corpus to a list of POS-tagged words from the Bauer corpus
for i in somelist:
tempi = []
for j in i:
try:
if math.isnan(j):
tempi.append(False)
else:
tempi.append(j)
except TypeError:
tempi.append(j)
templist.append(tempi)
return templist
# Gets only required fields from gloss spreadsheet, puts them in preferable order, removes replaces NaN instances
glosslist = [gloss_keeplist] + list_xlsx("glosses_full", "glosses",
gloss_droptup)
glosslist = [[g[0], g[1], g[3], g[2], g[5], g[4], g[6]] for g in glosslist]
glosslist = clean_nan(glosslist)
fix_trans_list = list()
for i in glosslist:
if i[4]:
fix_trans_list.append(i)
else:
i[4] = "* no translation available *"
fix_trans_list.append(i)
glosslist = fix_trans_list
# Gets only required fields from analysis spreadsheet, puts them in preferable order, removes replaces NaN instances
wordlist = [word_keeplist] + list_xlsx("glosses_words", "words", word_droptup)
wordlist = [[w[0], w[1], w[8], w[4], w[2], w[3], w[5], w[6], w[7]]
for w in wordlist]
wordlist = clean_nan(wordlist)