Upload folder using huggingface_hub

.github/workflows/update_space.yml

@@ -0,0 +1,28 @@
+name: Run Python script
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.9'
+
+    - name: Install Gradio
+      run: python -m pip install gradio
+
+    - name: Log in to Hugging Face
+      run: python -c 'import huggingface_hub; huggingface_hub.login(token="${{ secrets.hf_token }}")'
+
+    - name: Deploy to Spaces
+      run: gradio deploy

.gitignore

@@ -0,0 +1 @@
+__pycache__

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----
+MIIFazCCA1OgAwIBAgIRAIIQz7DSQONZRGPgu2OCiwAwDQYJKoZIhvcNAQELBQAw
+TzELMAkGA1UEBhMCVVMxKTAnBgNVBAoTIEludGVybmV0IFNlY3VyaXR5IFJlc2Vh
+cmNoIEdyb3VwMRUwEwYDVQQDEwxJU1JHIFJvb3QgWDEwHhcNMTUwNjA0MTEwNDM4
+WhcNMzUwNjA0MTEwNDM4WjBPMQswCQYDVQQGEwJVUzEpMCcGA1UEChMgSW50ZXJu
+ZXQgU2VjdXJpdHkgUmVzZWFyY2ggR3JvdXAxFTATBgNVBAMTDElTUkcgUm9vdCBY
+MTCCAiIwDQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAK3oJHP0FDfzm54rVygc
+h77ct984kIxuPOZXoHj3dcKi/vVqbvYATyjb3miGbESTtrFj/RQSa78f0uoxmyF+
+0TM8ukj13Xnfs7j/EvEhmkvBioZxaUpmZmyPfjxwv60pIgbz5MDmgK7iS4+3mX6U
+A5/TR5d8mUgjU+g4rk8Kb4Mu0UlXjIB0ttov0DiNewNwIRt18jA8+o+u3dpjq+sW
+T8KOEUt+zwvo/7V3LvSye0rgTBIlDHCNAymg4VMk7BPZ7hm/ELNKjD+Jo2FR3qyH
+B5T0Y3HsLuJvW5iB4YlcNHlsdu87kGJ55tukmi8mxdAQ4Q7e2RCOFvu396j3x+UC
+B5iPNgiV5+I3lg02dZ77DnKxHZu8A/lJBdiB3QW0KtZB6awBdpUKD9jf1b0SHzUv
+KBds0pjBqAlkd25HN7rOrFleaJ1/ctaJxQZBKT5ZPt0m9STJEadao0xAH0ahmbWn
+OlFuhjuefXKnEgV4We0+UXgVCwOPjdAvBbI+e0ocS3MFEvzG6uBQE3xDk3SzynTn
+jh8BCNAw1FtxNrQHusEwMFxIt4I7mKZ9YIqioymCzLq9gwQbooMDQaHWBfEbwrbw
+qHyGO0aoSCqI3Haadr8faqU9GY/rOPNk3sgrDQoo//fb4hVC1CLQJ13hef4Y53CI
+rU7m2Ys6xt0nUW7/vGT1M0NPAgMBAAGjQjBAMA4GA1UdDwEB/wQEAwIBBjAPBgNV
+HRMBAf8EBTADAQH/MB0GA1UdDgQWBBR5tFnme7bl5AFzgAiIyBpY9umbbjANBgkq
+hkiG9w0BAQsFAAOCAgEAVR9YqbyyqFDQDLHYGmkgJykIrGF1XIpu+ILlaS/V9lZL
+ubhzEFnTIZd+50xx+7LSYK05qAvqFyFWhfFQDlnrzuBZ6brJFe+GnY+EgPbk6ZGQ
+3BebYhtF8GaV0nxvwuo77x/Py9auJ/GpsMiu/X1+mvoiBOv/2X/qkSsisRcOj/KK
+NFtY2PwByVS5uCbMiogziUwthDyC3+6WVwW6LLv3xLfHTjuCvjHIInNzktHCgKQ5
+ORAzI4JMPJ+GslWYHb4phowim57iaztXOoJwTdwJx4nLCgdNbOhdjsnvzqvHu7Ur
+TkXWStAmzOVyyghqpZXjFaH3pO3JLF+l+/+sKAIuvtd7u+Nxe5AW0wdeRlN8NwdC
+jNPElpzVmbUq4JUagEiuTDkHzsxHpFKVK7q4+63SM1N95R1NbdWhscdCb+ZAJzVc
+oyi3B43njTOQ5yOf+1CceWxG1bQVs5ZufpsMljq4Ui0/1lvh+wjChP4kqKOJ2qxq
+4RgqsahDYVvTH9w7jXbyLeiNdd8XM2w9U/t7y0Ff/9yi0GE44Za4rF2LN9d11TPA
+mRGunUHBcnWEvgJBQl9nJEiU0Zsnvgc/ubhPgXRR4Xq37Z0j4r7g1SgEEzwxA57d
+emyPxgcYxn/eR44/KJ4EBs+lVDR3veyJm+kXQ99b21/+jh5Xos1AnX5iItreGCc=
+-----END CERTIFICATE-----

.gradio/flagged/dataset1.csv

@@ -0,0 +1,3 @@
+Upload your review file (CSV or XLSX),Vader,Transformers,Download CSV,Message,Data Preview,timestamp
+.gradio\flagged\Upload your review file CSV or XLSX\0dc80347f848c9c73fcf\IMDB Dataset - Copy.csv,true,true,.gradio\flagged\Download CSV\9b36608063ab4608a7a5\sentiment_analysis_results.csv,,"{""headers"": [""review"", ""sentiment"", ""neg"", ""neu"", ""pos"", ""compound""], ""data"": [[""One of the other reviewers has mentioned that after watching just 1 Oz episode you'll be hooked. They are right, as this is exactly what happened with me.<br /><br />The first thing that struck me about Oz was its brutality and unflinching scenes of violence, which set in right from the word GO. Trust me, this is not a show for the faint hearted or timid. This show pulls no punches with regards to drugs, sex or violence. Its is hardcore, in the classic use of the word.<br /><br />It is called OZ as that is the nickname given to the Oswald Maximum Security State Penitentary. It focuses mainly on Emerald City, an experimental section of the prison where all the cells have glass fronts and face inwards, so privacy is not high on the agenda. Em City is home to many..Aryans, Muslims, gangstas, Latinos, Christians, Italians, Irish and more....so scuffles, death stares, dodgy dealings and shady agreements are never far away.<br /><br />I would say the main appeal of the show is due to the fact that it goes where other shows wouldn't dare. Forget pretty pictures painted for mainstream audiences, forget charm, forget romance...OZ doesn't mess around. The first episode I ever saw struck me as so nasty it was surreal, I couldn't say I was ready for it, but as I watched more, I developed a taste for Oz, and got accustomed to the high levels of graphic violence. Not just violence, but injustice (crooked guards who'll be sold out for a nickel, inmates who'll kill on order and get away with it, well mannered, middle class inmates being turned into prison bitches due to their lack of street skills or prison experience) Watching Oz, you may become comfortable with what is uncomfortable viewing....thats if you can get in touch with your darker side."", ""positive"", 0.203, 0.748, 0.048, -0.9951], [""A wonderful little production. <br /><br />The filming technique is very unassuming- very old-time-BBC fashion and gives a comforting, and sometimes discomforting, sense of realism to the entire piece. <br /><br />The actors are extremely well chosen- Michael Sheen not only \""has got all the polari\"" but he has all the voices down pat too! You can truly see the seamless editing guided by the references to Williams' diary entries, not only is it well worth the watching but it is a terrificly written and performed piece. A masterful production about one of the great master's of comedy and his life. <br /><br />The realism really comes home with the little things: the fantasy of the guard which, rather than use the traditional 'dream' techniques remains solid then disappears. It plays on our knowledge and our senses, particularly with the scenes concerning Orton and Halliwell and the sets (particularly of their flat with Halliwell's murals decorating every surface) are terribly well done."", ""positive"", 0.053, 0.776, 0.172, 0.9641], [""I thought this was a wonderful way to spend time on a too hot summer weekend, sitting in the air conditioned theater and watching a light-hearted comedy. The plot is simplistic, but the dialogue is witty and the characters are likable (even the well bread suspected serial killer). While some may be disappointed when they realize this is not Match Point 2: Risk Addiction, I thought it was proof that Woody Allen is still fully in control of the style many of us have grown to love.<br /><br />This was the most I'd laughed at one of Woody's comedies in years (dare I say a decade?). While I've never been impressed with Scarlet Johanson, in this she managed to tone down her \""sexy\"" image and jumped right into a average, but spirited young woman.<br /><br />This may not be the crown jewel of his career, but it was wittier than \""Devil Wears Prada\"" and more interesting than \""Superman\"" a great comedy to go see with friends."", ""positive"", 0.094, 0.714, 0.192, 0.9605], [""Basically there's a family where a little boy (Jake) thinks there's a zombie in his closet & his parents are fighting all the time.<br /><br />This movie is slower than a soap opera... and suddenly, Jake decides to become Rambo and kill the zombie.<br /><br />OK, first of all when you're going to make a film you must Decide if its a thriller or a drama! As a drama the movie is watchable. Parents are divorcing & arguing like in real life. And then we have Jake with his closet which totally ruins all the film! I expected to see a BOOGEYMAN similar movie, and instead i watched a drama with some meaningless thriller spots.<br /><br />3 out of 10 just for the well playing parents & descent dialogs. As for the shots with Jake: just ignore them."", ""negative"", 0.138, 0.797, 0.065, -0.9213], [""Petter Mattei's \""Love in the Time of Money\"" is a visually stunning film to watch. Mr. Mattei offers us a vivid portrait about human relations. This is a movie that seems to be telling us what money, power and success do to people in the different situations we encounter. <br /><br />This being a variation on the Arthur Schnitzler's play about the same theme, the director transfers the action to the present time New York where all these different characters meet and connect. Each one is connected in one way, or another to the next person, but no one seems to know the previous point of contact. Stylishly, the film has a sophisticated luxurious look. We are taken to see how these people live and the world they live in their own habitat.<br /><br />The only thing one gets out of all these souls in the picture is the different stages of loneliness each one inhabits. A big city is not exactly the best place in which human relations find sincere fulfillment, as one discerns is the case with most of the people we encounter.<br /><br />The acting is good under Mr. Mattei's direction. Steve Buscemi, Rosario Dawson, Carol Kane, Michael Imperioli, Adrian Grenier, and the rest of the talented cast, make these characters come alive.<br /><br />We wish Mr. Mattei good luck and await anxiously for his next work."", ""positive"", 0.052, 0.801, 0.147, 0.9744]], ""metadata"": {""display_value"": null, ""styling"": null}}",2024-11-07 19:35:08.804271
+.gradio\flagged\Upload your review file CSV or XLSX\11262994bbf3b5da5f4d\IMDB Dataset - Copy.csv,false,true,.gradio\flagged\Download CSV\b60237ef4d855c94dac8\sentiment_analysis_results.csv,,"{""headers"": [""review"", ""sentiment"", ""label"", ""score""], ""data"": [[""One of the other reviewers has mentioned that after watching just 1 Oz episode you'll be hooked. They are right, as this is exactly what happened with me.<br /><br />The first thing that struck me about Oz was its brutality and unflinching scenes of violence, which set in right from the word GO. Trust me, this is not a show for the faint hearted or timid. This show pulls no punches with regards to drugs, sex or violence. Its is hardcore, in the classic use of the word.<br /><br />It is called OZ as that is the nickname given to the Oswald Maximum Security State Penitentary. It focuses mainly on Emerald City, an experimental section of the prison where all the cells have glass fronts and face inwards, so privacy is not high on the agenda. Em City is home to many..Aryans, Muslims, gangstas, Latinos, Christians, Italians, Irish and more....so scuffles, death stares, dodgy dealings and shady agreements are never far away.<br /><br />I would say the main appeal of the show is due to the fact that it goes where other shows wouldn't dare. Forget pretty pictures painted for mainstream audiences, forget charm, forget romance...OZ doesn't mess around. The first episode I ever saw struck me as so nasty it was surreal, I couldn't say I was ready for it, but as I watched more, I developed a taste for Oz, and got accustomed to the high levels of graphic violence. Not just violence, but injustice (crooked guards who'll be sold out for a nickel, inmates who'll kill on order and get away with it, well mannered, middle class inmates being turned into prison bitches due to their lack of street skills or prison experience) Watching Oz, you may become comfortable with what is uncomfortable viewing....thats if you can get in touch with your darker side."", ""positive"", ""POSITIVE"", 0.5136224031448364], [""A wonderful little production. <br /><br />The filming technique is very unassuming- very old-time-BBC fashion and gives a comforting, and sometimes discomforting, sense of realism to the entire piece. <br /><br />The actors are extremely well chosen- Michael Sheen not only \""has got all the polari\"" but he has all the voices down pat too! You can truly see the seamless editing guided by the references to Williams' diary entries, not only is it well worth the watching but it is a terrificly written and performed piece. A masterful production about one of the great master's of comedy and his life. <br /><br />The realism really comes home with the little things: the fantasy of the guard which, rather than use the traditional 'dream' techniques remains solid then disappears. It plays on our knowledge and our senses, particularly with the scenes concerning Orton and Halliwell and the sets (particularly of their flat with Halliwell's murals decorating every surface) are terribly well done."", ""positive"", ""POSITIVE"", 0.5018884539604187], [""I thought this was a wonderful way to spend time on a too hot summer weekend, sitting in the air conditioned theater and watching a light-hearted comedy. The plot is simplistic, but the dialogue is witty and the characters are likable (even the well bread suspected serial killer). While some may be disappointed when they realize this is not Match Point 2: Risk Addiction, I thought it was proof that Woody Allen is still fully in control of the style many of us have grown to love.<br /><br />This was the most I'd laughed at one of Woody's comedies in years (dare I say a decade?). While I've never been impressed with Scarlet Johanson, in this she managed to tone down her \""sexy\"" image and jumped right into a average, but spirited young woman.<br /><br />This may not be the crown jewel of his career, but it was wittier than \""Devil Wears Prada\"" and more interesting than \""Superman\"" a great comedy to go see with friends."", ""positive"", ""POSITIVE"", 0.5064340829849243], [""Basically there's a family where a little boy (Jake) thinks there's a zombie in his closet & his parents are fighting all the time.<br /><br />This movie is slower than a soap opera... and suddenly, Jake decides to become Rambo and kill the zombie.<br /><br />OK, first of all when you're going to make a film you must Decide if its a thriller or a drama! As a drama the movie is watchable. Parents are divorcing & arguing like in real life. And then we have Jake with his closet which totally ruins all the film! I expected to see a BOOGEYMAN similar movie, and instead i watched a drama with some meaningless thriller spots.<br /><br />3 out of 10 just for the well playing parents & descent dialogs. As for the shots with Jake: just ignore them."", ""negative"", ""POSITIVE"", 0.5148193836212158], [""Petter Mattei's \""Love in the Time of Money\"" is a visually stunning film to watch. Mr. Mattei offers us a vivid portrait about human relations. This is a movie that seems to be telling us what money, power and success do to people in the different situations we encounter. <br /><br />This being a variation on the Arthur Schnitzler's play about the same theme, the director transfers the action to the present time New York where all these different characters meet and connect. Each one is connected in one way, or another to the next person, but no one seems to know the previous point of contact. Stylishly, the film has a sophisticated luxurious look. We are taken to see how these people live and the world they live in their own habitat.<br /><br />The only thing one gets out of all these souls in the picture is the different stages of loneliness each one inhabits. A big city is not exactly the best place in which human relations find sincere fulfillment, as one discerns is the case with most of the people we encounter.<br /><br />The acting is good under Mr. Mattei's direction. Steve Buscemi, Rosario Dawson, Carol Kane, Michael Imperioli, Adrian Grenier, and the rest of the talented cast, make these characters come alive.<br /><br />We wish Mr. Mattei good luck and await anxiously for his next work."", ""positive"", ""POSITIVE"", 0.5115845203399658]], ""metadata"": {""display_value"": null, ""styling"": null}}",2024-11-07 19:51:20.128949

Datasets/Instruction.md

@@ -0,0 +1,3 @@
+Please install the test Dataset from:
+
+[text](https://www.kaggle.com/datasets/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews)

README.md

@@ -1,12 +1,93 @@
----
-title: BulkSentimentAnalysis
-emoji: 🚀
-colorFrom: yellow
-colorTo: gray
-sdk: gradio
-sdk_version: 5.5.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: BulkSentimentAnalysis
+app_file: app.py
+sdk: gradio
+sdk_version: 5.5.0
+---
+# Bulk Sentiment Analysis for Reviews
+
+This project provides a tool for bulk sentiment analysis of store reviews. Using various sentiment analysis models, including VADER and Hugging Face's Transformers, users can analyze reviews in CSV or Excel format to understand the overall sentiment. Results can be downloaded in CSV format, making it easy to leverage insights for decision-making.
+
+## Features
+
+- **Bulk Upload:** Upload CSV or Excel files of reviews for analysis.
+- **Model Options:** Choose from multiple sentiment analysis models:
+  - **VADER** for rule-based sentiment analysis.
+  - **SpaCy (Static Embeddings)** and **SpaCy (Contextual Embeddings)** for improved flexibility (coming soon).
+  - **Transformers** for deep learning-based sentiment analysis using pretrained models from Hugging Face.
+- **Download Results:** Export analyzed reviews with sentiment scores and labels as a CSV.
+
+## Installation
+
+To get started, clone this repository and install the dependencies.
+
+```bash
+git clone https://github.com/yourusername/bulk-sentiment-analysis
+cd bulk-sentiment-analysis
+pip install -r requirements.txt
+```
+
+Ensure your environment supports GPU processing, especially for Transformer-based models, to handle large datasets more efficiently.
+
+### Dependencies
+
+- Python 3.7+
+- [Streamlit](https://streamlit.io/) for building the user interface
+- [Pandas](https://pandas.pydata.org/) for data handling
+- [NLTK](https://www.nltk.org/) and [VADER](https://github.com/cjhutto/vaderSentiment) for sentiment analysis
+- [SpaCy](https://spacy.io/) (optional, for static and contextual embedding-based analysis)
+- [Transformers](https://huggingface.co/transformers/) by Hugging Face for deep learning sentiment models
+
+To install these, you can run:
+```bash
+pip install streamlit pandas nltk torch transformers spacy
+```
+
+For GPU support, install the appropriate CUDA version of PyTorch, following instructions from the [official PyTorch website](https://pytorch.org/get-started/locally/).
+
+## Usage
+
+1. **Run the Application**
+
+   Launch the Streamlit app with:
+   ```bash
+   streamlit run app.py
+   ```
+
+2. **Upload Your File**
+
+   Upload a CSV or Excel file containing reviews. Make sure there is a column labeled `Review` with the text you want to analyze.
+
+3. **Choose a Model**
+
+   Select one or more sentiment analysis models:
+   - **VADER** for quick, rule-based analysis.
+   - **Transformers** for more accurate, context-based sentiment detection.
+
+4. **Analyze and Download Results**
+
+   After processing, the app will display results in the UI. You can download the full results as a CSV file.
+
+### Example of CSV Output
+
+The output CSV will contain the original reviews alongside new columns with sentiment scores and labels, depending on the models chosen.
+
+## Folder Structure
+
+- **`app.py`**: Main Streamlit application script.
+- **`sentiment_analysis/`**: Contains modular functions for each sentiment analysis model (e.g., `vader_analyzer.py`, `spacy_static.py`, etc.).
+- **`requirements.txt`**: List of required dependencies.
+
+## Future Enhancements
+
+- **Integrate SpaCy models** for static and contextual embedding-based sentiment analysis.
+- **Improved preprocessing** to handle non-English text and non-standard review formats.
+- **Performance optimization** with caching and batch processing for large datasets.
+
+## Contributing
+
+Feel free to open issues or submit pull requests for improvements. All contributions are welcome!
+
+---
+
+This README should give users a clear understanding of what the project does, how to set it up, and how to use it. Let me know if you'd like any more specific instructions or additional sections!

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import pandas as pd
+from sentiment_analysis.vader_analyzer import analyze_sentiment_vader
+from sentiment_analysis.transformers_analyzer import analyze_sentiment_transformers
+
+def analyze_reviews(file, use_vader, use_transformers):
+    # Read the uploaded file
+    if file.name.endswith(".csv"):
+        df = pd.read_csv(file)
+    elif file.name.endswith(".xlsx"):
+        df = pd.read_excel(file)
+    else:
+        return "Please upload a CSV or Excel file."
+
+    # Check the number of entries and truncate if needed
+    if len(df) > 1000:
+        df = df.head(1000)
+        error_message = "The file contains more than 1,000 entries. Only the first 1,000 reviews are processed."
+    else:
+        error_message = "No Errors Found"
+
+    # Ensure the "review" column exists
+    df.columns = df.columns.str.lower()
+    if 'review' not in df.columns:
+        return "Please make sure the file has a 'review' column with review text."
+
+    # Apply selected sentiment analysis models
+    if use_vader:
+        vader_results = analyze_sentiment_vader(df["review"])
+        df = pd.concat([df, vader_results], axis=1)
+
+    if use_transformers:
+        transformers_results = analyze_sentiment_transformers(df["review"])
+        df = pd.concat([df, transformers_results], axis=1)
+
+    # Save the result to a CSV file
+    output_file = "sentiment_analysis_results.csv"
+    df.to_csv(output_file, index=False)
+    
+    return output_file, error_message, df.head()  # Return the output file, error message, and preview
+
+# Define Gradio interface
+interface = gr.Interface(
+    fn=analyze_reviews,
+    inputs=[
+        gr.File(label="Upload your review file (CSV or XLSX)"),
+        gr.Radio(["Vader", "Transformers"], label="Select Sentiment Analysis Model"),
+    ],
+    outputs=[
+        gr.File(label="Download CSV"),
+        gr.Textbox(label="Error Message"),
+        gr.Dataframe(label="Data Preview"),
+    ],
+    title="Bulk Sentiment Analysis for Reviews",
+    description="Upload a file with a 'review' column to analyze sentiment using Vader and Transformers models."
+)
+
+# Launch the Gradio app
+interface.launch(share=True)

notebooks/transformers_sentiment.ipynb

@@ -0,0 +1,226 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import AutoModelForSequenceClassification, AutoTokenizer\n",
+    "import pandas as pd\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0      One of the other reviewers has mentioned that ...\n",
+       "1      A wonderful little production. <br /><br />The...\n",
+       "2      I thought this was a wonderful way to spend ti...\n",
+       "3      Basically there's a family where a little boy ...\n",
+       "4      Petter Mattei's \"Love in the Time of Money\" is...\n",
+       "                             ...                        \n",
+       "495    \"American Nightmare\" is officially tied, in my...\n",
+       "496    First off, I have to say that I loved the book...\n",
+       "497    This movie was extremely boring. I only laughe...\n",
+       "498    I was disgusted by this movie. No it wasn't be...\n",
+       "499    Such a joyous world has been created for us in...\n",
+       "Name: review, Length: 500, dtype: object"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "reviews = pd.read_csv('../Datasets/IMDB Dataset.csv')\n",
+    "reviews = reviews.head(500)[\"review\"]\n",
+    "reviews"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>label</th>\n",
+       "      <th>score</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.508178</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.521151</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.528036</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.517413</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.520384</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>495</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.528022</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>496</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.512645</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>497</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.524352</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>498</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.503319</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>499</th>\n",
+       "      <td>POSITIVE</td>\n",
+       "      <td>0.526241</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>500 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        label     score\n",
+       "0    POSITIVE  0.508178\n",
+       "1    POSITIVE  0.521151\n",
+       "2    POSITIVE  0.528036\n",
+       "3    POSITIVE  0.517413\n",
+       "4    POSITIVE  0.520384\n",
+       "..        ...       ...\n",
+       "495  POSITIVE  0.528022\n",
+       "496  POSITIVE  0.512645\n",
+       "497  POSITIVE  0.524352\n",
+       "498  POSITIVE  0.503319\n",
+       "499  POSITIVE  0.526241\n",
+       "\n",
+       "[500 rows x 2 columns]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Load tokenizer and model\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\"distilbert-base-uncased\")\n",
+    "model = AutoModelForSequenceClassification.from_pretrained(\"distilbert-base-uncased\").to(\"cuda\")\n",
+    "\n",
+    "results = []\n",
+    "for review in reviews:\n",
+    "    # Tokenize with truncation and padding to max length\n",
+    "    tokenized_review = tokenizer(review, return_tensors=\"pt\", truncation=True, padding=\"max_length\", max_length=512).to(\"cuda\")\n",
+    "\n",
+    "    # Get the model's output (logits)\n",
+    "    with torch.no_grad():\n",
+    "        outputs = model(**tokenized_review)\n",
+    "    \n",
+    "    # Convert logits to probabilities\n",
+    "    probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)\n",
+    "    \n",
+    "    # Get the predicted label and score\n",
+    "    score = probabilities.max().item()\n",
+    "    label = \"POSITIVE\" if torch.argmax(probabilities).item() == 1 else \"NEGATIVE\"\n",
+    "    \n",
+    "    # Append the result\n",
+    "    results.append({\"label\": label, \"score\": score})\n",
+    "\n",
+    "# Create DataFrame\n",
+    "sentiment_df = pd.DataFrame(results)\n",
+    "sentiment_df\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "NLP_env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

notebooks/vader_sentiment.ipynb

@@ -0,0 +1,249 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import nltk\n",
+    "from nltk.sentiment.vader import SentimentIntensityAnalyzer\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package vader_lexicon to C:\\Users\\Rikhil\n",
+      "[nltk_data]     Nellimarla\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Package vader_lexicon is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Download VADER lexicon for sentiment analysis\n",
+    "nltk.download('vader_lexicon')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "FileNotFoundError",
+     "evalue": "[Errno 2] No such file or directory: '../Datasets/IMDB Dataset.csv'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[38], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m data \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m../Datasets/IMDB Dataset.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1026\u001b[0m, in \u001b[0;36mread_csv\u001b[1;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[0;32m   1013\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[0;32m   1014\u001b[0m     dialect,\n\u001b[0;32m   1015\u001b[0m     delimiter,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1022\u001b[0m     dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[0;32m   1023\u001b[0m )\n\u001b[0;32m   1024\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[1;32m-> 1026\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _read(filepath_or_buffer, kwds)\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:620\u001b[0m, in \u001b[0;36m_read\u001b[1;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[0;32m    617\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[0;32m    619\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[1;32m--> 620\u001b[0m parser \u001b[38;5;241m=\u001b[39m TextFileReader(filepath_or_buffer, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwds)\n\u001b[0;32m    622\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[0;32m    623\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1620\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[1;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[0;32m   1617\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[0;32m   1619\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m-> 1620\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_engine(f, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mengine)\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1880\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[1;34m(self, f, engine)\u001b[0m\n\u001b[0;32m   1878\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[0;32m   1879\u001b[0m         mode \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m-> 1880\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;241m=\u001b[39m get_handle(\n\u001b[0;32m   1881\u001b[0m     f,\n\u001b[0;32m   1882\u001b[0m     mode,\n\u001b[0;32m   1883\u001b[0m     encoding\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mencoding\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m),\n\u001b[0;32m   1884\u001b[0m     compression\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcompression\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m),\n\u001b[0;32m   1885\u001b[0m     memory_map\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmemory_map\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m),\n\u001b[0;32m   1886\u001b[0m     is_text\u001b[38;5;241m=\u001b[39mis_text,\n\u001b[0;32m   1887\u001b[0m     errors\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mencoding_errors\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstrict\u001b[39m\u001b[38;5;124m\"\u001b[39m),\n\u001b[0;32m   1888\u001b[0m     storage_options\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstorage_options\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m),\n\u001b[0;32m   1889\u001b[0m )\n\u001b[0;32m   1890\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m   1891\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles\u001b[38;5;241m.\u001b[39mhandle\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\common.py:873\u001b[0m, in \u001b[0;36mget_handle\u001b[1;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[0;32m    868\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[0;32m    869\u001b[0m     \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[0;32m    870\u001b[0m     \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[0;32m    871\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mencoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mmode:\n\u001b[0;32m    872\u001b[0m         \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[1;32m--> 873\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(\n\u001b[0;32m    874\u001b[0m             handle,\n\u001b[0;32m    875\u001b[0m             ioargs\u001b[38;5;241m.\u001b[39mmode,\n\u001b[0;32m    876\u001b[0m             encoding\u001b[38;5;241m=\u001b[39mioargs\u001b[38;5;241m.\u001b[39mencoding,\n\u001b[0;32m    877\u001b[0m             errors\u001b[38;5;241m=\u001b[39merrors,\n\u001b[0;32m    878\u001b[0m             newline\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m    879\u001b[0m         )\n\u001b[0;32m    880\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    881\u001b[0m         \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[0;32m    882\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(handle, ioargs\u001b[38;5;241m.\u001b[39mmode)\n",
+      "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '../Datasets/IMDB Dataset.csv'"
+     ]
+    }
+   ],
+   "source": [
+    "data = pd.read_csv('../Datasets/IMDB Dataset.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data=data.head(500)\n",
+    "sia = SentimentIntensityAnalyzer()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[23], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;129;01min\u001b[39;00m data\u001b[38;5;241m.\u001b[39mcolumns:\n\u001b[1;32m----> 2\u001b[0m     data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msentiment_score\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28;01mlambda\u001b[39;00m x: sia\u001b[38;5;241m.\u001b[39mpolarity_scores(x)[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcompound\u001b[39m\u001b[38;5;124m'\u001b[39m])\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m      4\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mColumn \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m not found.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\series.py:4924\u001b[0m, in \u001b[0;36mSeries.apply\u001b[1;34m(self, func, convert_dtype, args, by_row, **kwargs)\u001b[0m\n\u001b[0;32m   4789\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapply\u001b[39m(\n\u001b[0;32m   4790\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   4791\u001b[0m     func: AggFuncType,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   4796\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[0;32m   4797\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m DataFrame \u001b[38;5;241m|\u001b[39m Series:\n\u001b[0;32m   4798\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   4799\u001b[0m \u001b[38;5;124;03m    Invoke function on values of Series.\u001b[39;00m\n\u001b[0;32m   4800\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   4915\u001b[0m \u001b[38;5;124;03m    dtype: float64\u001b[39;00m\n\u001b[0;32m   4916\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m   4917\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m SeriesApply(\n\u001b[0;32m   4918\u001b[0m         \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   4919\u001b[0m         func,\n\u001b[0;32m   4920\u001b[0m         convert_dtype\u001b[38;5;241m=\u001b[39mconvert_dtype,\n\u001b[0;32m   4921\u001b[0m         by_row\u001b[38;5;241m=\u001b[39mby_row,\n\u001b[0;32m   4922\u001b[0m         args\u001b[38;5;241m=\u001b[39margs,\n\u001b[0;32m   4923\u001b[0m         kwargs\u001b[38;5;241m=\u001b[39mkwargs,\n\u001b[1;32m-> 4924\u001b[0m     )\u001b[38;5;241m.\u001b[39mapply()\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\apply.py:1427\u001b[0m, in \u001b[0;36mSeriesApply.apply\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m   1424\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_compat()\n\u001b[0;32m   1426\u001b[0m \u001b[38;5;66;03m# self.func is Callable\u001b[39;00m\n\u001b[1;32m-> 1427\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_standard()\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\apply.py:1507\u001b[0m, in \u001b[0;36mSeriesApply.apply_standard\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m   1501\u001b[0m \u001b[38;5;66;03m# row-wise access\u001b[39;00m\n\u001b[0;32m   1502\u001b[0m \u001b[38;5;66;03m# apply doesn't have a `na_action` keyword and for backward compat reasons\u001b[39;00m\n\u001b[0;32m   1503\u001b[0m \u001b[38;5;66;03m# we need to give `na_action=\"ignore\"` for categorical data.\u001b[39;00m\n\u001b[0;32m   1504\u001b[0m \u001b[38;5;66;03m# TODO: remove the `na_action=\"ignore\"` when that default has been changed in\u001b[39;00m\n\u001b[0;32m   1505\u001b[0m \u001b[38;5;66;03m#  Categorical (GH51645).\u001b[39;00m\n\u001b[0;32m   1506\u001b[0m action \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(obj\u001b[38;5;241m.\u001b[39mdtype, CategoricalDtype) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m-> 1507\u001b[0m mapped \u001b[38;5;241m=\u001b[39m obj\u001b[38;5;241m.\u001b[39m_map_values(\n\u001b[0;32m   1508\u001b[0m     mapper\u001b[38;5;241m=\u001b[39mcurried, na_action\u001b[38;5;241m=\u001b[39maction, convert\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconvert_dtype\n\u001b[0;32m   1509\u001b[0m )\n\u001b[0;32m   1511\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(mapped) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(mapped[\u001b[38;5;241m0\u001b[39m], ABCSeries):\n\u001b[0;32m   1512\u001b[0m     \u001b[38;5;66;03m# GH#43986 Need to do list(mapped) in order to get treated as nested\u001b[39;00m\n\u001b[0;32m   1513\u001b[0m     \u001b[38;5;66;03m#  See also GH#25959 regarding EA support\u001b[39;00m\n\u001b[0;32m   1514\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m obj\u001b[38;5;241m.\u001b[39m_constructor_expanddim(\u001b[38;5;28mlist\u001b[39m(mapped), index\u001b[38;5;241m=\u001b[39mobj\u001b[38;5;241m.\u001b[39mindex)\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\base.py:921\u001b[0m, in \u001b[0;36mIndexOpsMixin._map_values\u001b[1;34m(self, mapper, na_action, convert)\u001b[0m\n\u001b[0;32m    918\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(arr, ExtensionArray):\n\u001b[0;32m    919\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m arr\u001b[38;5;241m.\u001b[39mmap(mapper, na_action\u001b[38;5;241m=\u001b[39mna_action)\n\u001b[1;32m--> 921\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m algorithms\u001b[38;5;241m.\u001b[39mmap_array(arr, mapper, na_action\u001b[38;5;241m=\u001b[39mna_action, convert\u001b[38;5;241m=\u001b[39mconvert)\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\algorithms.py:1743\u001b[0m, in \u001b[0;36mmap_array\u001b[1;34m(arr, mapper, na_action, convert)\u001b[0m\n\u001b[0;32m   1741\u001b[0m values \u001b[38;5;241m=\u001b[39m arr\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mobject\u001b[39m, copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[0;32m   1742\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m na_action \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m-> 1743\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mmap_infer(values, mapper, convert\u001b[38;5;241m=\u001b[39mconvert)\n\u001b[0;32m   1744\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m   1745\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mmap_infer_mask(\n\u001b[0;32m   1746\u001b[0m         values, mapper, mask\u001b[38;5;241m=\u001b[39misna(values)\u001b[38;5;241m.\u001b[39mview(np\u001b[38;5;241m.\u001b[39muint8), convert\u001b[38;5;241m=\u001b[39mconvert\n\u001b[0;32m   1747\u001b[0m     )\n",
+      "File \u001b[1;32mlib.pyx:2972\u001b[0m, in \u001b[0;36mpandas._libs.lib.map_infer\u001b[1;34m()\u001b[0m\n",
+      "Cell \u001b[1;32mIn[23], line 2\u001b[0m, in \u001b[0;36m<lambda>\u001b[1;34m(x)\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;129;01min\u001b[39;00m data\u001b[38;5;241m.\u001b[39mcolumns:\n\u001b[1;32m----> 2\u001b[0m     data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msentiment_score\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28;01mlambda\u001b[39;00m x: sia\u001b[38;5;241m.\u001b[39mpolarity_scores(x)[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcompound\u001b[39m\u001b[38;5;124m'\u001b[39m])\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m      4\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mColumn \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m not found.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\nltk\\sentiment\\vader.py:366\u001b[0m, in \u001b[0;36mSentimentIntensityAnalyzer.polarity_scores\u001b[1;34m(self, text)\u001b[0m\n\u001b[0;32m    355\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    356\u001b[0m \u001b[38;5;124;03mReturn a float for sentiment strength based on the input text.\u001b[39;00m\n\u001b[0;32m    357\u001b[0m \u001b[38;5;124;03mPositive values are positive valence, negative value are negative\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    363\u001b[0m \u001b[38;5;124;03m    matched as if it was a normal word in the sentence.\u001b[39;00m\n\u001b[0;32m    364\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    365\u001b[0m \u001b[38;5;66;03m# text, words_and_emoticons, is_cap_diff = self.preprocess(text)\u001b[39;00m\n\u001b[1;32m--> 366\u001b[0m sentitext \u001b[38;5;241m=\u001b[39m SentiText(\n\u001b[0;32m    367\u001b[0m     text, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconstants\u001b[38;5;241m.\u001b[39mPUNC_LIST, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconstants\u001b[38;5;241m.\u001b[39mREGEX_REMOVE_PUNCTUATION\n\u001b[0;32m    368\u001b[0m )\n\u001b[0;32m    369\u001b[0m sentiments \u001b[38;5;241m=\u001b[39m []\n\u001b[0;32m    370\u001b[0m words_and_emoticons \u001b[38;5;241m=\u001b[39m sentitext\u001b[38;5;241m.\u001b[39mwords_and_emoticons\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\nltk\\sentiment\\vader.py:274\u001b[0m, in \u001b[0;36mSentiText.__init__\u001b[1;34m(self, text, punc_list, regex_remove_punctuation)\u001b[0m\n\u001b[0;32m    272\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mPUNC_LIST \u001b[38;5;241m=\u001b[39m punc_list\n\u001b[0;32m    273\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mREGEX_REMOVE_PUNCTUATION \u001b[38;5;241m=\u001b[39m regex_remove_punctuation\n\u001b[1;32m--> 274\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mwords_and_emoticons \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_words_and_emoticons()\n\u001b[0;32m    275\u001b[0m \u001b[38;5;66;03m# doesn't separate words from\u001b[39;00m\n\u001b[0;32m    276\u001b[0m \u001b[38;5;66;03m# adjacent punctuation (keeps emoticons & contractions)\u001b[39;00m\n\u001b[0;32m    277\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mis_cap_diff \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallcap_differential(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mwords_and_emoticons)\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\nltk\\sentiment\\vader.py:306\u001b[0m, in \u001b[0;36mSentiText._words_and_emoticons\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    300\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    301\u001b[0m \u001b[38;5;124;03mRemoves leading and trailing puncutation\u001b[39;00m\n\u001b[0;32m    302\u001b[0m \u001b[38;5;124;03mLeaves contractions and most emoticons\u001b[39;00m\n\u001b[0;32m    303\u001b[0m \u001b[38;5;124;03m    Does not preserve punc-plus-letter emoticons (e.g. :D)\u001b[39;00m\n\u001b[0;32m    304\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    305\u001b[0m wes \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtext\u001b[38;5;241m.\u001b[39msplit()\n\u001b[1;32m--> 306\u001b[0m words_punc_dict \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_words_plus_punc()\n\u001b[0;32m    307\u001b[0m wes \u001b[38;5;241m=\u001b[39m [we \u001b[38;5;28;01mfor\u001b[39;00m we \u001b[38;5;129;01min\u001b[39;00m wes \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(we) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m]\n\u001b[0;32m    308\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, we \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(wes):\n",
+      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\nltk\\sentiment\\vader.py:293\u001b[0m, in \u001b[0;36mSentiText._words_plus_punc\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    291\u001b[0m words_only \u001b[38;5;241m=\u001b[39m {w \u001b[38;5;28;01mfor\u001b[39;00m w \u001b[38;5;129;01min\u001b[39;00m words_only \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(w) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m}\n\u001b[0;32m    292\u001b[0m \u001b[38;5;66;03m# the product gives ('cat', ',') and (',', 'cat')\u001b[39;00m\n\u001b[1;32m--> 293\u001b[0m punc_before \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(p): p[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m product(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mPUNC_LIST, words_only)}\n\u001b[0;32m    294\u001b[0m punc_after \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(p): p[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m product(words_only, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mPUNC_LIST)}\n\u001b[0;32m    295\u001b[0m words_punc_dict \u001b[38;5;241m=\u001b[39m punc_before\n",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "if 'review' in data.columns:\n",
+    "    data['sentiment_score'] = data['review'].apply(lambda x: sia.polarity_scores(x)['compound'])\n",
+    "else:\n",
+    "    print(\"Column 'review' not found.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This oatmeal is not good. Its mushy, soft, I don't like it. Quaker Oats is the way to go.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(data['sentiment'].value_counts())\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['This', 'oatmeal', 'is', 'not', 'good', '.', 'Its', 'mushy', ',', 'soft']"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize=(8, 6))\n",
+    "sns.countplot(x='sentiment', data=data, palette='Set1')\n",
+    "plt.title('Sentiment Distribution')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[('This', 'DT'),\n",
+       " ('oatmeal', 'NN'),\n",
+       " ('is', 'VBZ'),\n",
+       " ('not', 'RB'),\n",
+       " ('good', 'JJ'),\n",
+       " ('.', '.'),\n",
+       " ('Its', 'PRP$'),\n",
+       " ('mushy', 'NN'),\n",
+       " (',', ','),\n",
+       " ('soft', 'JJ')]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.to_csv('sentiment_analysis_results.csv', index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(S\n",
+      "  This/DT\n",
+      "  oatmeal/NN\n",
+      "  is/VBZ\n",
+      "  not/RB\n",
+      "  good/JJ\n",
+      "  ./.\n",
+      "  Its/PRP$\n",
+      "  mushy/NN\n",
+      "  ,/,\n",
+      "  soft/JJ\n",
+      "  ,/,\n",
+      "  I/PRP\n",
+      "  do/VBP\n",
+      "  n't/RB\n",
+      "  like/VB\n",
+      "  it/PRP\n",
+      "  ./.\n",
+      "  (ORGANIZATION Quaker/NNP Oats/NNPS)\n",
+      "  is/VBZ\n",
+      "  the/DT\n",
+      "  way/NN\n",
+      "  to/TO\n",
+      "  go/VB\n",
+      "  ./.)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(data[['review', 'sentiment_score', 'sentiment']].head())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "NLP_env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,5 @@
+pandas
+torch
+nltk
+streamlit
+transformers

sentiment_analysis/transformers_analyzer.py

@@ -0,0 +1,35 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import pandas as pd
+
+def analyze_sentiment_transformers(reviews):
+    # Set device to "cpu" if CUDA (GPU) is unavailable
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+    # Initialize tokenizer and model
+    tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
+    model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased").to(device)
+
+    results = []
+    for review in reviews:
+        # Tokenize with truncation and padding to max length
+        tokenized_review = tokenizer(review, return_tensors="pt", truncation=True, padding="max_length", max_length=512)
+        tokenized_review = {key: val.to(device) for key, val in tokenized_review.items()}  # Ensure tensors are on the correct device
+
+        # Get the model's output (logits)
+        with torch.no_grad():
+            outputs = model(**tokenized_review)
+        
+        # Convert logits to probabilities
+        probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
+        
+        # Get the predicted label and score
+        score = probabilities.max().item()
+        label = "POSITIVE" if torch.argmax(probabilities).item() == 1 else "NEGATIVE"
+        
+        # Append the result
+        results.append({"label": label, "score": score})
+
+    # Convert results to DataFrame
+    sentiment_df = pd.DataFrame(results)
+    return sentiment_df

sentiment_analysis/vader_analyzer.py

@@ -0,0 +1,18 @@
+import nltk
+from nltk.sentiment.vader import SentimentIntensityAnalyzer
+import pandas as pd
+
+# Download VADER lexicon if not already available
+try:
+    nltk.data.find('sentiment/vader_lexicon.zip')
+except LookupError:
+    nltk.download('vader_lexicon')
+
+def analyze_sentiment_vader(reviews):
+    sia = SentimentIntensityAnalyzer()
+    results = []
+    for review in reviews:
+        score = sia.polarity_scores(review)
+        results.append(score)
+    sentiment_df = pd.DataFrame(results)
+    return sentiment_df

streamlit_app.py

@@ -0,0 +1,48 @@
+import streamlit as st
+import pandas as pd
+from sentiment_analysis.vader_analyzer import analyze_sentiment_vader
+from sentiment_analysis.transformers_analyzer import analyze_sentiment_transformers
+
+st.title("Bulk Sentiment Analysis for Reviews")
+
+# Step 1: File Upload
+uploaded_file = st.file_uploader("Upload your review file", type=["csv", "xlsx"])
+
+if uploaded_file is not None:
+    # Read the file into a DataFrame
+    if uploaded_file.name.endswith('.csv'):
+        df = pd.read_csv(uploaded_file)
+    else:
+        df = pd.read_excel(uploaded_file)
+
+    # Check the number of entries and truncate if needed
+    if len(df) > 1000:
+        df = df.head(1000)
+        st.error("The file contains more than 1,000 entries. Only the first 1,000 reviews are processed.")
+
+    st.write("Data Preview:", df.head())
+
+    # Step 2: Model Selection
+    st.write("Select sentiment analysis models:")
+    use_vader = st.checkbox("Vader")
+    use_transformers = st.checkbox("Transformers")
+
+    # Ensure "review" column exists
+    df.columns = df.columns.str.lower()
+    if 'review' in df.columns:
+        # Step 3: Process reviews with Selected Models
+        if use_vader:
+            vader_results = analyze_sentiment_vader(df["review"])
+            df = pd.concat([df, vader_results], axis=1)
+            st.write("Vader Analysis Results", df.head())
+
+        if use_transformers:
+            transformers_results = analyze_sentiment_transformers(df["review"])
+            df = pd.concat([df, transformers_results], axis=1)
+            st.write("Transformers Analysis Results", df.head())
+
+        # Step 4: Download Results
+        csv = df.to_csv(index=False)
+        st.download_button("Download CSV", csv, "sentiment_analysis_results.csv", "text/csv")
+    else:
+        st.error("Please make sure the file has a 'review' column with review text.")