def kelime_düzelt(dizi):
nesne = detector.TurkishNLP()
varmı = True
try:
open("words.pkl", "r")
except FileNotFoundError:
varmı = False
if not varmı:
nesne.download()
nesne.create_word_set()
for i in range(len(dizi) - 1):
kelime_kontrol = nesne.list_words(dizi[i])
düzgün_kelime = nesne.auto_correct(kelime_kontrol)
düzgün_kelime_son = " ".join(düzgün_kelime)
dizi[i] = düzgün_kelime_son
return dizi
def _auto_correct(job):
global df
df_str = df["corrected"].astype(str)
obj = detector.TurkishNLP()
#obj.download()
obj.create_word_set()
length = df.shape[0]
for index in range(length):
_print_progress_bar(index,
length,
job=job,
prefix=f"{job} Progress:",
length=50)
if " " in df_str[index]:
words = df_str[index].split()
words = obj.auto_correct(words)
words = " ".join(words)
df["corrected"][index] = words
def _get_spell_checker(self, lang):
if lang is None:
return language_tool_python.LanguageTool(lang)
_exist = lang in self.spell_checkers
if not _exist and lang in ['ru', 'en', 'es', 'fr', 'pt']:
local_lang = lang if lang != 'pt' else 'pt-PT'
self.spell_checkers[lang] = language_tool_python.LanguageTool(
local_lang)
elif not _exist and lang == 'tr':
obj = detector.TurkishNLP()
obj.download()
obj.create_word_set()
self.spell_checkers[lang] = obj
return self.spell_checkers[lang]
classes.append(folderName)
allBlogs = np.array(allBlogs) #Creating rank 1 array
df_allBlogs = pd.DataFrame({'Blog': allBlogs, 'Class': classes}) #Creating data structure with labeled axes.(data, rows and columns)
df_allBlogs = df_allBlogs[['Blog', 'Class']]
print(df_allBlogs)
#NOT: soyle söyle gibi ingilzce karakterleri Türkçe karakterlere çevirmek.
nltk.download('punkt')
tokenizer = nltk.data.load('tokenizers/punkt/PY3/turkish.pickle')
nltk.download('stopwords')
turkishStopWords = set(stopwords.words('turkish'))
stemmer = TurkishStemmer()
#Typos
turkishNLPObject = detector.TurkishNLP()
turkishNLPObject.download()
turkishNLPObject.create_word_set()
number=0
numberTokenized=0
numberTypoAndStopWords=0
numberAllAndStemmed=0
def preprocessBlogs(blog):
#Converting to lowercase characters and removing leading and trailing whitespaces.
blog = blog.lower()
blog = blog.strip()
global number
global numberTokenized
global numberTypoAndStopWords
print("""
TWITTER SENTIMENT ANALYSIS
Coded by FFH
""")
target = input("Enter target name:")
asagi_cek = int(input("Number of page downs:"))
liste = getTweets(target, asagi_cek)
df = tweets_to_df(liste)
df['sentiment'] = np.array(
[analyze_sentiment(tweet) for tweet in df['Tweets']])
pos, neg, notr = 0, 0, 0
for i in df['sentiment']:
if (i == 1):
pos += 1
elif (i == 0):
notr += 1
else:
neg += 1
dialog(pos, neg, notr)
nesne = detector.TurkishNLP()
nesne.download()
nesne.create_word_set()
menu()
import glob
import re
import os
from snowballstemmer import TurkishStemmer
from stop_words import get_stop_words
from sklearn.model_selection import train_test_split
import turkishnlp
from turkishnlp import detector
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.model_selection import cross_val_score
from sklearn.metrics import f1_score
from sklearn.metrics import recall_score
from sklearn.metrics import precision_score
obj = detector.TurkishNLP() # TurkishNLP dosyalarının indirilmesi
# obj.download()
obj.create_word_set()
turkStem = TurkishStemmer()
stop_words = get_stop_words('turkish') # stop_words array
def read_txt(folder_name): # read ve data preprocessing işlemleri
file_list = glob.glob(os.path.join(os.getcwd(), str(folder_name), "*.txt"))
cumle_list = [] # 35, 35,35 dosyanın içeriklerini tutan array
tip_list = [] # p,n,t tutan array 105 tane
for file_path in file_list:
with open(file_path) as f_input:
def addComment(request,id):
title = get_object_or_404(Title, id=id)
comment_control = title.comment.filter(comment_author = request.user).count()
obj = detector.TurkishNLP()
#obj.download()
obj.create_word_set() #veri setini oluşturmak için kullanıyoruz.
if request.method == "POST":
comment_content = obj.list_words(request.POST.get("comment_content"))
comment_author = request.user #sonra bu author'u yorumu yapan kişiye at
if comment_control == 0:
control = obj.is_turkish(comment_content) #türkçe yazım doğruluğu oranını kontrol etmek için.
if control > 0.10:
model = load_model("model.h5")
corrected_words = obj.auto_correct(comment_content) #H2. Burada "list_words" metodunun yaptığı string olarak gelen texti regex yardımıyla kelimelerine ayırmaktır.
corrected_string = " ".join(corrected_words) #H3. Kelimeleri birleştirmek için Python'ın "join" metodu kullanılabilir.
texts = [corrected_string]
tokens = tokenizer.texts_to_sequences(texts)
tokens_pad = pad_sequences(tokens, maxlen=max_tokens)
sentiment = model.predict(tokens_pad)
if (sentiment>=0.85):
sentiment = "Pozitif"
messages.success(request,"Pozitif")
elif (0.40 <= sentiment < 0.85):
sentiment = "Nötr"
messages.success(request,"Nötr")
else:
sentiment = "Negatif"
messages.success(request,"Negatif")
newComment = Comment(comment_author = comment_author, comment_content = corrected_string, sentiment = sentiment )
newComment.title = title
newComment.save()
total_comments = Comment.objects.filter(comment_author = comment_author).count()
positive_count = Comment.objects.filter(comment_author = comment_author, sentiment = "Pozitif").count()
negative_count = Comment.objects.filter(comment_author = comment_author, sentiment = "Negatif").count()
notr_count = Comment.objects.filter(comment_author = comment_author, sentiment = "Nötr").count()
positive_count_title = Comment.objects.filter(title = title, sentiment = "Pozitif").count()
negative_count_title = Comment.objects.filter(title = title, sentiment = "Negatif").count()
notr_count_title = Comment.objects.filter(title = title, sentiment = "Nötr").count()
if SentimentTotalSystem.objects.filter(title = title).exists():
for y in SentimentTotalSystem.objects.filter(title = title):
y.positive_count = positive_count_title
y.negative_count = negative_count_title
y.notr_count = notr_count_title
y.save()
else:
new_sentiment_total = SentimentTotalSystem(title = title, positive_count= positive_count_title, negative_count = negative_count_title, notr_count = notr_count_title)
new_sentiment_total.save()
if PersonalAwardSystem.objects.filter(user = comment_author).exists():
for x in PersonalAwardSystem.objects.filter(user = comment_author):
x.total_comment = total_comments
x.positive_count = positive_count
x.negative_count = negative_count
x.notr_count = notr_count
if x.total_comment>=5:
x.is_gold = True
x.is_silver = False
x.is_bronze = False
elif x.total_comment>=3:
x.is_gold = False
x.is_silver = True
x.is_bronze = False
elif x.total_comment>=1:
x.is_gold = False
x.is_silver = False
x.is_bronze = True
x.save()
else:
new_total = PersonalAwardSystem(user = comment_author, total_comment = total_comments, positive_count = positive_count, negative_count = negative_count, notr_count = notr_count)
if total_comments>=5:
new_total.is_gold = True
new_total.is_silver = False
new_total.is_bronze = False
elif total_comments>=3:
new_total.is_gold = False
new_total.is_silver = True
new_total.is_bronze = False
elif total_comments>=1:
new_total.is_gold = False
new_total.is_silver = False
new_total.is_bronze = True
new_total.save()
else:
messages.success(request,"Yorumunuz Yazım Hatalarından Dolayı Göderilemedi. Lütfen Yorumunuzu Tekrar Belirtiniz!")
else:
messages.success(request,"Yorum Bulunmaktadır Yorum Yapamazsınız")
return redirect("/title/titles/" + str(id))
# Kelime oyununun basit konsol versiyonudur. Fonksiyonlar değişiklik gösterebilir.
# 1 kere çalıştırdıktan sonra obj.download() satırını siliniz
from turkishnlp import detector
obj = detector.TurkishNLP()
obj.download()
obj.create_word_set()
my_array = []
i = 0
toplampuan = 0
baslangicKelimesi = "başarı"
print("\nBu oyun verilen kelimenin son harfi ile başlayan bir kelime yazan kullanıcıya puan kazandırmayı hedefler. \n"
"Başlagıç kelimesi -başarı-\n"
"kelime giriniz...")
def puan_kazandir():
bonus = 0
global toplampuan
kelimeUzunlugu = len(kelime)
puan = kelimeUzunlugu * 4
if(obj.is_vowel_harmonic(kelime)):
print("%10 büyük ünlü uyumu bonusu ! ")