def hebrewParshiot():
parshiot = Parshiot.createSplitParshiot()
print("Calculating regular hebrew TD-IDF for ", PARSHA_NAME)
results = TFIDF.parshaIDF(PARSHA_NAME, parshiot)
print(results)
print("20 most common:")
print(results.most_common(20))
def hebrewParshiotWithFreq():
parshiot = Parshiot.createSplitParshiot()
parshiotFreq = Parshiot.processParshiotByFrequency()
print("Calculating hebrew TD-IDF for ", PARSHA_NAME, " based on minimum letter frequency")
results = TFIDF.parshaFreqIDF(PARSHA_NAME, parshiot, parshiotFreq)
print(results)
print("20 most common:")
print(results.most_common(20))
def hebrewParshiotTop():
parshiot = Parshiot.createSplitParshiot()
print("Calculating regular hebrew TD-IDF for ", PARSHA_NAME)
results = TFIDF.parshaIDF(PARSHA_NAME, parshiot)
print(results)
print(len(results))
percent = int(len(results)/2)
print("top 50% of results: ", percent)
print(results.most_common(percent))
r = results.most_common(percent)
l = [i[0] for i in r]
print(l)
def hebrewFreqParshiot():
parshiot = Parshiot.processParshiotByFrequency()
parshaResults = {}
with open(subDir + 'strippedHebTFIDFparshaResults.csv',
mode='w',
encoding='utf-8') as csv_file:
fieldnames = ['parsha', 'most relevant words']
writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
writer.writeheader()
for parsha in parshiot.keys():
parshaResults[parsha] = TFIDF.parshaIDF(parsha,
parshiot).most_common(20)
writer.writerow({
'parsha':
parsha,
'most relevant words': [a[0] for a in parshaResults[parsha]]
})
def TFIDFOutput(lang='heb'):
parshiot = Parshiot.createSplitParshiot(lang)
parshaResults = {}
with open(subDir + lang + 'TFIDFParshaResults' + '.csv',
mode='w',
encoding='utf-8') as csv_file:
fieldnames = ['parsha', 'most relevant words']
writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
writer.writeheader()
for parsha in parshiot.keys():
parshaResults[parsha] = TFIDF.parshaIDF(parsha,
parshiot).most_common(20)
writer.writerow({
'parsha':
parsha,
'most relevant words': [a[0] for a in parshaResults[parsha]]
})
def englishChapter():
TEXT_NAME = 'JPS-Devarim.txt'
chapterNum = 1
print("Calculating chapter TF-IDF for ", TEXT_NAME, "in chapter ", chapterNum)
print(TFIDF.chapterIDF(chapterNum, TEXT_NAME))