Add logreg

.gitignore

@@ -1 +1,3 @@
 .venv
+healthcare_facilities_reviews.jsonl
+nlp_models.ipynb

app.py

@@ -0,0 +1,44 @@
+import pickle
+
+import streamlit as st
+
+from preprocessing import data_preprocessing
+
+# Load preprocessing steps
+with open("vectorizer.pkl", "rb") as f:
+    vectorizer = pickle.load(f)
+
+# Load trained model
+with open("logreg_model.pkl", "rb") as f:
+    logreg = pickle.load(f)
+
+
+# Define function for preprocessing input text
+def preprocess_text(text):
+    # Apply preprocessing steps (cleaning, tokenization, vectorization)
+    clean_text = data_preprocessing(
+        text
+    )  # Assuming data_preprocessing is your preprocessing function
+    print("Clean text ", clean_text)
+    vectorized_text = vectorizer.transform([" ".join(clean_text)])
+    return vectorized_text
+
+
+# Define function for making predictions
+def predict_sentiment(text):
+    # Preprocess input text
+    processed_text = preprocess_text(text)
+    print(preprocess_text)
+    # Make prediction
+    prediction = logreg.predict(processed_text)
+    return prediction
+
+
+# Streamlit app code
+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)

logreg_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d996382921eccfb01cb81804f5b0ccd5e1ff18939b3d8e63fefadb2b2cc6053
+size 664190

preprocessing.py

@@ -0,0 +1,31 @@
+import re
+import string
+
+import pymorphy2
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+
+stop_words = set(stopwords.words("russian"))
+
+
+def clean_text(text: str) -> str:
+    text = text.lower()
+    text = re.sub(r"\w*(\w)\1{2,}\w*", "", text)
+    text = re.sub(r"\d+\w*", "", text)
+    text = re.sub(r"\[.*?\]", "", text)
+    text = text.translate(str.maketrans("", "", string.punctuation))
+    return text
+
+
+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
+
+
+def data_preprocessing(text: str) -> list[str]:
+    cleaned_text = clean_text(text)
+    lemmized_text = lemmize_and_tokenize_text(cleaned_text)
+    return lemmized_text

requirements.txt

@@ -86,3 +86,202 @@ validators==0.22.0
 watchdog==4.0.0
 wcwidth==0.2.13
 zipp==3.17.0
+absl-py==2.1.0
+aiofiles==23.2.1
+aiogram==3.3.0
+aiohttp==3.9.1
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+antlr4-python3-runtime==4.9.3
+appdirs==1.4.4
+appnope==0.1.4
+asttokens==2.4.1
+astunparse==1.6.3
+attrs==23.2.0
+backcall==0.2.0
+beautifulsoup4==4.12.2
+black==24.2.0
+bleach==6.1.0
+blinker==1.7.0
+cachetools==5.3.2
+category-encoders==2.6.3
+certifi==2023.7.22
+chardet==4.0.0
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpickle==3.0.0
+contourpy==1.2.0
+cycler==0.10.0
+DAWG-Python==0.7.2
+decorator==5.1.1
+defusedxml==0.7.1
+detectron2 @ git+https://github.com/facebookresearch/detectron2.git@3ff5dd1cff4417af07097064813c9f28d7461d3c
+dm-tree==0.1.8
+docopt==0.6.2
+executing==2.0.1
+fastjsonschema==2.19.1
+filelock==3.13.1
+flatbuffers==23.5.26
+fonttools==4.47.2
+frozendict==2.4.0
+frozenlist==1.4.1
+fsspec==2024.2.0
+fvcore==0.1.5.post20221221
+gast==0.5.4
+gitdb==4.0.11
+GitPython==3.1.41
+google-pasta==0.2.0
+grpcio==1.62.0
+h5py==3.10.0
+html5lib==1.1
+hydra-core==1.3.2
+idna==2.10
+imageio==2.33.1
+importlib-metadata==7.0.1
+importlib-resources==6.1.1
+iopath==0.1.9
+ipython==8.12.3
+iso8601==2.1.0
+jedi==0.19.1
+Jinja2==3.1.3
+joblib==1.3.2
+jsonschema==4.20.0
+jsonschema-specifications==2023.12.1
+jupyter_client==8.6.0
+jupyter_core==5.7.1
+jupyterlab_pygments==0.3.0
+kaggle==1.6.6
+keras==3.0.5
+kiwisolver==1.4.5
+lazy_loader==0.3
+learn==1.0.0
+libclang==16.0.6
+llvmlite==0.42.0
+lxml==5.1.0
+magic-filter==1.0.12
+Markdown==3.5.2
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.8.2
+matplotlib-inline==0.1.6
+mdurl==0.1.2
+mistune==3.0.2
+ml-dtypes==0.3.2
+mplcyberpunk==0.7.1
+mpmath==1.3.0
+multidict==6.0.4
+multitasking==0.0.11
+mypy-extensions==1.0.0
+namex==0.0.7
+nbclient==0.9.0
+nbconvert==7.14.2
+nbformat==5.9.2
+networkx==3.2.1
+nltk==3.8.1
+numba==0.59.0
+numpy==1.26.3
+omegaconf==2.3.0
+opencv-python==4.9.0.80
+opencv-python-headless==4.8.0.74
+opt-einsum==3.3.0
+packaging==23.2
+pandas==2.1.4
+pandocfilters==1.5.0
+parso==0.8.3
+pathspec==0.12.1
+patsy==0.5.6
+peewee==3.17.0
+pexpect==4.9.0
+pickleshare==0.7.5
+pillow==10.2.0
+pipreqs==0.5.0
+platformdirs==4.1.0
+portalocker==2.8.2
+prompt-toolkit==3.0.43
+protobuf==4.25.2
+psutil==5.9.8
+ptyprocess==0.7.0
+pure-eval==0.2.2
+py-cpuinfo==9.0.0
+pyarrow==14.0.2
+pycocotools==2.0.7
+pydantic==2.5.3
+pydantic_core==2.14.6
+pydeck==0.8.1b0
+pyfiglet==0.7
+Pygments==2.17.2
+pymorphy2==0.9.1
+pymorphy2-dicts-ru==2.4.417127.4579844
+pynndescent==0.5.11
+pyparsing==3.1.1
+python-dateutil==2.8.2
+python-dotenv==1.0.1
+python-magic==0.4.27
+python-slugify==8.0.4
+pytz==2023.3.post1
+PyYAML==6.0.1
+pyzmq==25.1.2
+referencing==0.32.1
+regex==2023.12.25
+requests==2.31.0
+requests-toolbelt==1.0.0
+rich==13.7.0
+roboflow==1.1.21
+rpds-py==0.17.1
+schedule==1.2.1
+scikit-base==0.7.2
+scikit-image==0.22.0
+scikit-learn==1.4.0
+scipy==1.12.0
+seaborn==0.13.1
+setuptools==69.0.3
+six==1.16.0
+sktime==0.26.0
+smmap==5.0.1
+soupsieve==2.5
+stack-data==0.6.3
+statsmodels==0.14.1
+streamlit==1.30.0
+supervision==0.18.0
+sweetviz==2.3.1
+sympy==1.12
+tabulate==0.9.0
+tenacity==8.2.3
+tensorboard==2.16.2
+tensorboard-data-server==0.7.2
+tensorflow==2.16.0rc0
+termcolor==2.4.0
+text-unidecode==1.3
+thop==0.1.1.post2209072238
+threadpoolctl==3.2.0
+tifffile==2024.1.30
+tinycss2==1.2.1
+toml==0.10.2
+toolz==0.12.0
+torch==2.2.0
+torchaudio==2.2.0
+torchutils==0.0.4
+torchvision==0.17.0
+tornado==6.4
+tqdm==4.66.1
+traitlets==5.14.1
+twitchio==2.8.2
+typing_extensions==4.9.0
+tzdata==2023.4
+tzlocal==5.2
+ultralytics==8.1.19
+urllib3==2.1.0
+validators==0.22.0
+wcwidth==0.2.13
+webencodings==0.5.1
+Werkzeug==3.0.1
+wheel==0.42.0
+wrapt==1.16.0
+xlrd==2.0.1
+yacs==0.1.8
+yarg==0.1.9
+yarl==1.9.4
+yellowbrick==1.5
+yfinance==0.2.35
+zipp==3.17.0

vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f39240cedb8d7c29f44d666699030a8d088be200a8a7228efc5a2ec90293f6e
+size 3379321