minor changes

.gitignore

@@ -1,3 +1,6 @@
 .venv
 healthcare_facilities_reviews.jsonl
-nlp_models.ipynb
+*.ipynb
+__pycache__/
+*.csv
+.ipynb_checkoints/

app.py

@@ -38,7 +38,10 @@ def predict_sentiment(text):
 st.title("Sentiment Analysis with Logistic Regression")
 text_input = st.text_input("Enter your review:")
 if st.button("Predict"):
-    st.write("Knopka")
     prediction = predict_sentiment(text_input)
-    st.write("prediction")
-    st.write("Predicted Sentiment:", prediction)
+    if prediction == 1:
+        st.write("prediction")
+        st.write("Отзыв положительный")
+    elif prediction == 0:
+        st.write("prediction")
+        st.write("Отзыв отрицательный")

preprocessing.py

@@ -1,11 +1,11 @@
 import re
 import string
 
+import nltk
 import pymorphy2
-from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize
 
-stop_words = set(stopwords.words("russian"))
+nltk.download("punkt")
 
 
 def clean_text(text: str) -> str:
@@ -20,7 +20,6 @@ def clean_text(text: str) -> str:
 def lemmize_and_tokenize_text(text: str) -> list[str]:
     morph = pymorphy2.MorphAnalyzer()
     tokens = word_tokenize(text)
-    tokens = [token for token in tokens if token not in stop_words]
     lemmas = [morph.parse(token)[0].normal_form for token in tokens]
     return lemmas