def scanfolder():
biglist = []
for category in os.listdir('./dict'):
print("Category: " + category)
documents = os.listdir('./dict/' + category)[:900]
stripped_documents = [Utils.testStripping('./dict/' + category + '/' + doc) for doc in documents]
for strip_doc in stripped_documents:
biglist.extend(strip_doc)
# Remove duplicates
biglist = list(set(biglist))
bigdict = {}
for word in biglist:
bigdict[word] = 0
with open( "./mainDict.json", "w" ) as outfile:
json.dump(bigdict, outfile, indent=4, separators=(',', ': '))
return
os.chdir("dict")
for name in glob.glob('*/*'):
bigdict.extend(Utils.testStripping(name))
#print(bigdict)
print(' Current length : ',len(bigdict))
print(' Removing dupes : ')
finalList = list(set(bigdict))
print(' New size : ', len(finalList))
# Make dict
d = {}
# Save to disk as dict
for item in finalList:
d[item] = 0
with open( "..\\mainDict.json", "w" ) as outfile:
json.dump(d, outfile)
print ("Total length : ",len(d))
def sp_getTextDocument(path):
words = Utils.testStripping(path)
result = {}
for word in words:
try:
result[word]
result[word] = result['word'] + 1
except:
result[word] = 1
return result
def getExampleArticlesFromSubCat(subcat):
# Ex: subcat = dict/rec.autos
# Pick n-learning articles from subset.
lst = os.listdir(subcat)
lst = lst[:numberOfLearningArticlesInSubset]
# Open each file and add it to a list of wooooords.
subsetWords = []
for fname in lst:
subsetWords.extend(Utils.testStripping(subcat + "/" + fname))
# Many words we got, time to do some counting.
print("Subset word count: ", len(subsetWords))
return subsetWords
def getTextDocument(path):
return Utils.testStripping(path)