Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+IMDB[[:space:]]Dataset.csv filter=lfs diff=lfs merge=lfs -text

IMDB Dataset.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc447764f82be365fa9c2beef4e8df89d3919e3da95f5088004797d79695aa2
+size 66212309

huggingface_deploy.py

@@ -0,0 +1,380 @@
+import os
+import json
+import joblib
+from transformers import pipeline
+import torch
+
+def create_huggingface_config():
+    """Create Hugging Face model card and configuration"""
+    
+    # Create model card
+    model_card = """---
+language: en
+tags:
+- sentiment-analysis
+- text-classification
+- nltk
+- scikit-learn
+license: mit
+---
+
+# IMDb Sentiment Analysis Model
+
+This model analyzes the sentiment of IMDb movie reviews to classify them as positive or negative.
+
+## Model Details
+
+- **Model Type**: Ensemble of Logistic Regression and Naive Bayes
+- **Vectorizer**: TF-IDF with 5000 features
+- **Accuracy**: 
+  - Logistic Regression: ~88.47%
+  - Naive Bayes: ~85.2%
+
+## Usage
+
+```python
+from transformers import pipeline
+
+# Load the model
+classifier = pipeline("text-classification", model="your-username/imdb-sentiment")
+
+# Make predictions
+result = classifier("This movie was absolutely fantastic!")
+print(result)
+```
+
+## Training Data
+
+The model was trained on the IMDb dataset containing 50,000 movie reviews with binary sentiment labels.
+
+## Preprocessing
+
+1. Text lowercase conversion
+2. Special character removal
+3. Tokenization using NLTK
+4. Stopword removal
+5. Lemmatization using WordNet
+
+## Model Architecture
+
+- **Feature Extraction**: TF-IDF Vectorizer (5000 features)
+- **Classification**: 
+  - Logistic Regression with L2 regularization
+  - Multinomial Naive Bayes
+
+## Performance
+
+- **Logistic Regression**: 88.47% accuracy
+- **Naive Bayes**: 85.2% accuracy
+- **Ensemble**: Improved robustness and confidence
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@misc{imdb-sentiment-analysis,
+  author = {Your Name},
+  title = {IMDb Sentiment Analysis Model},
+  year = {2024},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/your-username/imdb-sentiment}
+}
+```
+"""
+    
+    with open("README.md", "w") as f:
+        f.write(model_card)
+    
+    # Create .gitattributes
+    gitattributes = """*.pkl filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text
+"""
+    
+    with open(".gitattributes", "w") as f:
+        f.write(gitattributes)
+    
+    print("Created Hugging Face configuration files")
+
+def create_kaggle_notebook():
+    """Create a Kaggle notebook for model deployment"""
+    
+    notebook_code = '''{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# IMDb Sentiment Analysis Model Deployment\\n",
+    "\\n",
+    "This notebook demonstrates how to use the trained sentiment analysis model for IMDb reviews.\\n",
+    "\\n",
+    "## Model Details\\n",
+    "- **Logistic Regression Accuracy**: ~88.47%\\n",
+    "- **Naive Bayes Accuracy**: ~85.2%\\n",
+    "- **Vectorizer**: TF-IDF with 5000 features\\n",
+    "- **Preprocessing**: Lowercase, tokenization, stopword removal, lemmatization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Install required packages\\n",
+    "!pip install nltk scikit-learn joblib pandas numpy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import joblib\\n",
+    "import json\\n",
+    "import re\\n",
+    "import nltk\\n",
+    "from nltk.corpus import stopwords\\n",
+    "from nltk.tokenize import word_tokenize\\n",
+    "from nltk.stem import WordNetLemmatizer\\n",
+    "import pandas as pd\\n",
+    "import numpy as np\\n",
+    "\\n",
+    "# Download NLTK resources\\n",
+    "nltk.download('punkt')\\n",
+    "nltk.download('stopwords')\\n",
+    "nltk.download('wordnet')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class SentimentAnalyzer:\\n",
+    "    def __init__(self, model_dir=\\"saved_models\\"):\\n",
+    "        # Load models\\n",
+    "        self.vectorizer = joblib.load(f\\"{model_dir}/tfidf_vectorizer.pkl\\")\\n",
+    "        self.lr_model = joblib.load(f\\"{model_dir}/logistic_regression_model.pkl\\")\\n",
+    "        self.nb_model = joblib.load(f\\"{model_dir}/naive_bayes_model.pkl\\")\\n",
+    "        \\n",
+    "        # Load metadata\\n",
+    "        with open(f\\"{model_dir}/model_metadata.json\\", \\"r\\") as f:\\n",
+    "            self.metadata = json.load(f)\\n",
+    "    \\n",
+    "    def preprocess_text(self, text):\\n",
+    "        # Lowercase\\n",
+    "        text = text.lower()\\n",
+    "        # Remove special characters and digits\\n",
+    "        text = re.sub(r\\"[^a-zA-Z\\\\s]\\", \\"\\", text)\\n",
+    "        # Tokenize\\n",
+    "        tokens = word_tokenize(text)\\n",
+    "        # Remove stopwords\\n",
+    "        stop_words = set(stopwords.words(\\"english\\"))\\n",
+    "        tokens = [word for word in tokens if word not in stop_words]\\n",
+    "        # Lemmatize\\n",
+    "        lemmatizer = WordNetLemmatizer()\\n",
+    "        tokens = [lemmatizer.lemmatize(word) for word in tokens]\\n",
+    "        # Join tokens back to string\\n",
+    "        return \\" \\".join(tokens)\\n",
+    "    \\n",
+    "    def predict(self, text, model_type=\\"both\\"):\\n",
+    "        # Preprocess text\\n",
+    "        cleaned_text = self.preprocess_text(text)\\n",
+    "        \\n",
+    "        # Vectorize\\n",
+    "        text_vector = self.vectorizer.transform([cleaned_text])\\n",
+    "        \\n",
+    "        results = {}\\n",
+    "        \\n",
+    "        if model_type in [\\"lr\\", \\"both\\"]:\\n",
+    "            lr_pred = self.lr_model.predict(text_vector)[0]\\n",
+    "            lr_prob = self.lr_model.predict_proba(text_vector)[0]\\n",
+    "            results[\\"logistic_regression\\"] = {\\n",
+    "                \\"prediction\\": \\"positive\\" if lr_pred == 1 else \\"negative\\",\\n",
+    "                \\"confidence\\": float(max(lr_prob)),\\n",
+    "                \\"probabilities\\": {\\n",
+    "                    \\"negative\\": float(lr_prob[0]),\\n",
+    "                    \\"positive\\": float(lr_prob[1])\\n",
+    "                }\\n",
+    "            }\\n",
+    "        \\n",
+    "        if model_type in [\\"nb\\", \\"both\\"]:\\n",
+    "            nb_pred = self.nb_model.predict(text_vector)[0]\\n",
+    "            nb_prob = self.nb_model.predict_proba(text_vector)[0]\\n",
+    "            results[\\"naive_bayes\\"] = {\\n",
+    "                \\"prediction\\": \\"positive\\" if nb_pred == 1 else \\"negative\\",\\n",
+    "                \\"confidence\\": float(max(nb_prob)),\\n",
+    "                \\"probabilities\\": {\\n",
+    "                    \\"negative\\": float(nb_prob[0]),\\n",
+    "                    \\"positive\\": float(nb_prob[1])\\n",
+    "                }\\n",
+    "            }\\n",
+    "        \\n",
+    "        return results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize analyzer\\n",
+    "analyzer = SentimentAnalyzer()\\n",
+    "\\n",
+    "print(\\"Model loaded successfully!\\")\\n",
+    "print(f\\"Logistic Regression Accuracy: {analyzer.metadata['lr_accuracy']:.2%}\\")\\n",
+    "print(f\\"Naive Bayes Accuracy: {analyzer.metadata['nb_accuracy']:.2%}\\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Test with sample reviews\\n",
+    "test_reviews = [\\n",
+    "    \\"This movie was absolutely fantastic! I loved every minute of it.\\",\\n",
+    "    \\"Terrible film, waste of time. Don\\"t watch it.\\",\\n",
+    "    \\"It was okay, nothing special but not bad either.\\",\\n",
+    "    \\"Amazing performance by the actors, great storyline!\\",\\n",
+    "    \\"Boring and predictable plot, poor acting.\\"\\n",
+    "]\\n",
+    "\\n",
+    "for review in test_reviews:\\n",
+    "    print(f\\"\\nReview: {review}\\")\\n",
+    "    results = analyzer.predict(review)\\n",
+    "    for model, result in results.items():\\n",
+    "        print(f\\"{model}: {result['prediction']} (confidence: {result['confidence']:.2f})\\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Interactive prediction\\n",
+    "def predict_sentiment(review):\\n",
+    "    results = analyzer.predict(review)\\n",
+    "    print(f\\"Review: {review}\\")\\n",
+    "    print(\\"Results:\\")\\n",
+    "    for model, result in results.items():\\n",
+    "        print(f\\"  {model}: {result['prediction']} (confidence: {result['confidence']:.2%})\\")\\n",
+    "    return results\\n",
+    "\\n",
+    "# Example usage\\n",
+    "# predict_sentiment(\\"Your review here\\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}'''
+    
+    with open("kaggle_notebook.ipynb", "w") as f:
+        f.write(notebook_code)
+    
+    print("Created Kaggle notebook")
+
+def create_dockerfile():
+    """Create Dockerfile for containerized deployment"""
+    
+    dockerfile = '''FROM python:3.9-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \\
+    gcc \\
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements and install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Download NLTK data
+RUN python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords'); nltk.download('wordnet')"
+
+# Copy model files
+COPY saved_models/ ./saved_models/
+COPY inference.py .
+COPY streamlit_deployment.py .
+
+# Expose port
+EXPOSE 8501
+
+# Run Streamlit app
+CMD ["streamlit", "run", "streamlit_deployment.py", "--server.port=8501", "--server.address=0.0.0.0"]'''
+    
+    with open("Dockerfile", "w") as f:
+        f.write(dockerfile)
+    
+    print("Created Dockerfile")
+
+def create_docker_compose():
+    """Create docker-compose.yml for easy deployment"""
+    
+    compose = '''version: '3.8'
+
+services:
+  sentiment-analysis:
+    build: .
+    ports:
+      - "8501:8501"
+    volumes:
+      - ./saved_models:/app/saved_models
+    environment:
+      - STREAMLIT_SERVER_PORT=8501
+      - STREAMLIT_SERVER_ADDRESS=0.0.0.0'''
+    
+    with open("docker-compose.yml", "w") as f:
+        f.write(compose)
+    
+    print("Created docker-compose.yml")
+
+if __name__ == "__main__":
+    print("Creating deployment configurations...")
+    
+    # Check if models exist
+    if not os.path.exists("saved_models"):
+        print("❌ Models not found! Please run 'python train_and_save_model.py' first.")
+        exit(1)
+    
+    # Create deployment files
+    create_huggingface_config()
+    create_kaggle_notebook()
+    create_dockerfile()
+    create_docker_compose()
+    
+    print("\n✅ Deployment files created!")
+    print("\n📋 Next steps:")
+    print("1. For Hugging Face: Upload the entire directory to HF Hub")
+    print("2. For Kaggle: Upload kaggle_notebook.ipynb to Kaggle")
+    print("3. For Docker: Run 'docker-compose up'")
+    print("4. For Streamlit Cloud: Push to GitHub and connect to Streamlit Cloud") 

saved_models/logistic_regression_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca354003e9bd826f219453b1236120370d116d198233804f7b3bb5456673f1a
+size 40863

saved_models/model_metadata.json

@@ -0,0 +1,5016 @@
+{
+  "vectorizer_features": [
+    "aaron",
+    "abandoned",
+    "abc",
+    "ability",
+    "able",
+    "aboutbr",
+    "abrupt",
+    "absence",
+    "absent",
+    "absolute",
+    "absolutely",
+    "absurd",
+    "absurdity",
+    "abuse",
+    "abused",
+    "abusive",
+    "abysmal",
+    "academy",
+    "accent",
+    "accept",
+    "acceptable",
+    "accepted",
+    "access",
+    "accident",
+    "accidentally",
+    "acclaimed",
+    "accompanied",
+    "accomplished",
+    "according",
+    "account",
+    "accuracy",
+    "accurate",
+    "accurately",
+    "accused",
+    "achieve",
+    "achieved",
+    "achievement",
+    "acid",
+    "across",
+    "act",
+    "acted",
+    "acting",
+    "action",
+    "active",
+    "activity",
+    "actor",
+    "actress",
+    "actual",
+    "actually",
+    "ad",
+    "adam",
+    "adaptation",
+    "adapted",
+    "add",
+    "added",
+    "addict",
+    "addiction",
+    "adding",
+    "addition",
+    "additional",
+    "address",
+    "adequate",
+    "admire",
+    "admit",
+    "admittedly",
+    "adolescent",
+    "adopted",
+    "adorable",
+    "adult",
+    "advance",
+    "advanced",
+    "advantage",
+    "adventure",
+    "advertising",
+    "advice",
+    "advise",
+    "affair",
+    "affect",
+    "affected",
+    "affection",
+    "afford",
+    "aforementioned",
+    "afraid",
+    "africa",
+    "african",
+    "afternoon",
+    "afterwards",
+    "againbr",
+    "age",
+    "aged",
+    "agency",
+    "agenda",
+    "agent",
+    "aging",
+    "ago",
+    "agree",
+    "agreed",
+    "agrees",
+    "ah",
+    "ahead",
+    "aid",
+    "aim",
+    "aimed",
+    "aint",
+    "air",
+    "aired",
+    "airplane",
+    "airport",
+    "aka",
+    "al",
+    "ala",
+    "alan",
+    "albeit",
+    "albert",
+    "album",
+    "alcohol",
+    "alcoholic",
+    "alert",
+    "alex",
+    "alexander",
+    "alfred",
+    "ali",
+    "alice",
+    "alien",
+    "alike",
+    "alive",
+    "allbr",
+    "allen",
+    "alley",
+    "allow",
+    "allowed",
+    "allowing",
+    "allows",
+    "alltime",
+    "ally",
+    "almost",
+    "alone",
+    "along",
+    "alongside",
+    "already",
+    "alright",
+    "also",
+    "alternate",
+    "alternative",
+    "although",
+    "altman",
+    "altogether",
+    "always",
+    "amanda",
+    "amateur",
+    "amateurish",
+    "amazed",
+    "amazing",
+    "amazingly",
+    "ambiguous",
+    "ambition",
+    "ambitious",
+    "america",
+    "american",
+    "among",
+    "amongst",
+    "amount",
+    "amused",
+    "amusing",
+    "amy",
+    "analysis",
+    "ancient",
+    "anderson",
+    "andor",
+    "andre",
+    "andrew",
+    "andy",
+    "angel",
+    "angela",
+    "angeles",
+    "anger",
+    "angle",
+    "angry",
+    "animal",
+    "animated",
+    "animation",
+    "anime",
+    "ann",
+    "anna",
+    "anne",
+    "annie",
+    "annoyed",
+    "annoying",
+    "another",
+    "answer",
+    "ant",
+    "anthony",
+    "antic",
+    "antonio",
+    "anybody",
+    "anymore",
+    "anyone",
+    "anyones",
+    "anything",
+    "anyway",
+    "anywaybr",
+    "anyways",
+    "anywhere",
+    "apart",
+    "apartment",
+    "ape",
+    "apocalypse",
+    "appalling",
+    "apparent",
+    "apparently",
+    "appeal",
+    "appealing",
+    "appear",
+    "appearance",
+    "appeared",
+    "appearing",
+    "appears",
+    "appreciate",
+    "appreciated",
+    "appreciation",
+    "approach",
+    "appropriate",
+    "appropriately",
+    "april",
+    "arab",
+    "arc",
+    "area",
+    "arent",
+    "argento",
+    "arguably",
+    "argue",
+    "argument",
+    "arm",
+    "armed",
+    "army",
+    "arnold",
+    "around",
+    "arrested",
+    "arrival",
+    "arrive",
+    "arrived",
+    "arrives",
+    "arrogant",
+    "art",
+    "arthur",
+    "artificial",
+    "artist",
+    "artistic",
+    "as",
+    "ashamed",
+    "asian",
+    "aside",
+    "ask",
+    "asked",
+    "asking",
+    "asks",
+    "asleep",
+    "aspect",
+    "assassin",
+    "assassination",
+    "assault",
+    "assigned",
+    "assistant",
+    "associate",
+    "associated",
+    "assume",
+    "assumed",
+    "assuming",
+    "astaire",
+    "astonishing",
+    "astronaut",
+    "asylum",
+    "atlantis",
+    "atmosphere",
+    "atmospheric",
+    "atrocious",
+    "atrocity",
+    "attached",
+    "attack",
+    "attacked",
+    "attempt",
+    "attempted",
+    "attempting",
+    "attention",
+    "attitude",
+    "attorney",
+    "attracted",
+    "attraction",
+    "attractive",
+    "audience",
+    "audio",
+    "audition",
+    "aunt",
+    "aussie",
+    "austen",
+    "austin",
+    "australia",
+    "australian",
+    "authentic",
+    "author",
+    "authority",
+    "available",
+    "average",
+    "avoid",
+    "avoided",
+    "awake",
+    "award",
+    "aware",
+    "away",
+    "awaybr",
+    "awe",
+    "awesome",
+    "awful",
+    "awfully",
+    "awhile",
+    "awkward",
+    "babe",
+    "baby",
+    "back",
+    "backdrop",
+    "background",
+    "bad",
+    "badbr",
+    "baddie",
+    "badly",
+    "bag",
+    "baker",
+    "balance",
+    "baldwin",
+    "ball",
+    "ballet",
+    "bam",
+    "banal",
+    "band",
+    "bang",
+    "bank",
+    "banned",
+    "bar",
+    "barbara",
+    "bare",
+    "barely",
+    "bargain",
+    "barker",
+    "barney",
+    "barrel",
+    "barry",
+    "barrymore",
+    "base",
+    "baseball",
+    "based",
+    "basement",
+    "basic",
+    "basically",
+    "basis",
+    "bat",
+    "bates",
+    "bath",
+    "bathroom",
+    "batman",
+    "battle",
+    "bay",
+    "bbc",
+    "beach",
+    "bean",
+    "bear",
+    "beast",
+    "beat",
+    "beaten",
+    "beating",
+    "beautiful",
+    "beautifully",
+    "beauty",
+    "bebr",
+    "became",
+    "become",
+    "becomes",
+    "becoming",
+    "bed",
+    "bedroom",
+    "beer",
+    "began",
+    "begin",
+    "beginning",
+    "behave",
+    "behavior",
+    "behaviour",
+    "behind",
+    "being",
+    "bela",
+    "belief",
+    "believable",
+    "believe",
+    "believed",
+    "believing",
+    "bell",
+    "belong",
+    "belongs",
+    "beloved",
+    "belt",
+    "ben",
+    "beneath",
+    "benefit",
+    "bergman",
+    "berlin",
+    "bernard",
+    "besides",
+    "best",
+    "bet",
+    "betrayal",
+    "bette",
+    "better",
+    "betterbr",
+    "bettie",
+    "betty",
+    "beverly",
+    "beware",
+    "beyond",
+    "biased",
+    "bible",
+    "big",
+    "bigger",
+    "biggest",
+    "bike",
+    "bill",
+    "billy",
+    "bin",
+    "biography",
+    "bird",
+    "birth",
+    "birthday",
+    "bit",
+    "bite",
+    "bitter",
+    "bizarre",
+    "black",
+    "blade",
+    "blah",
+    "blair",
+    "blake",
+    "blame",
+    "bland",
+    "blank",
+    "blast",
+    "blatant",
+    "bleak",
+    "blend",
+    "blew",
+    "blind",
+    "blob",
+    "block",
+    "blockbuster",
+    "blond",
+    "blonde",
+    "blood",
+    "bloody",
+    "blow",
+    "blowing",
+    "blown",
+    "blue",
+    "bmovie",
+    "bo",
+    "board",
+    "boast",
+    "boat",
+    "bob",
+    "bobby",
+    "body",
+    "bogart",
+    "bold",
+    "boll",
+    "bollywood",
+    "bomb",
+    "bond",
+    "bone",
+    "bonus",
+    "boob",
+    "book",
+    "boom",
+    "boot",
+    "border",
+    "bore",
+    "bored",
+    "boredom",
+    "boring",
+    "boris",
+    "born",
+    "borrowed",
+    "bos",
+    "bother",
+    "bothered",
+    "bottle",
+    "bottom",
+    "bought",
+    "bound",
+    "bourne",
+    "box",
+    "boxing",
+    "boy",
+    "boyfriend",
+    "br",
+    "brad",
+    "brady",
+    "brain",
+    "branagh",
+    "brand",
+    "brando",
+    "brave",
+    "bravo",
+    "brazil",
+    "break",
+    "breaking",
+    "breast",
+    "breath",
+    "breathtaking",
+    "brian",
+    "bride",
+    "bridge",
+    "brief",
+    "briefly",
+    "bright",
+    "brilliance",
+    "brilliant",
+    "brilliantly",
+    "bring",
+    "bringing",
+    "brings",
+    "britain",
+    "british",
+    "broad",
+    "broadcast",
+    "broadway",
+    "broke",
+    "broken",
+    "bronson",
+    "brook",
+    "brooklyn",
+    "brother",
+    "brought",
+    "brown",
+    "bruce",
+    "bruno",
+    "brutal",
+    "brutality",
+    "brutally",
+    "buck",
+    "bud",
+    "buddy",
+    "budget",
+    "buff",
+    "bug",
+    "build",
+    "building",
+    "built",
+    "bull",
+    "bullet",
+    "bullock",
+    "bully",
+    "bumbling",
+    "bunch",
+    "bunny",
+    "buried",
+    "burn",
+    "burned",
+    "burning",
+    "burst",
+    "burt",
+    "burton",
+    "bus",
+    "bush",
+    "business",
+    "businessman",
+    "buster",
+    "busy",
+    "butcher",
+    "butler",
+    "butt",
+    "button",
+    "buy",
+    "buying",
+    "cabin",
+    "cable",
+    "cage",
+    "cagney",
+    "caine",
+    "cake",
+    "california",
+    "call",
+    "called",
+    "calling",
+    "calm",
+    "came",
+    "cameo",
+    "camera",
+    "camerawork",
+    "cameron",
+    "camp",
+    "campaign",
+    "campbell",
+    "campy",
+    "canada",
+    "canadian",
+    "cancer",
+    "candidate",
+    "candy",
+    "cannibal",
+    "cannon",
+    "cant",
+    "capable",
+    "capital",
+    "captain",
+    "captivating",
+    "capture",
+    "captured",
+    "capturing",
+    "car",
+    "card",
+    "cardboard",
+    "care",
+    "cared",
+    "career",
+    "careful",
+    "carefully",
+    "caricature",
+    "caring",
+    "carl",
+    "carlos",
+    "carmen",
+    "carol",
+    "carpenter",
+    "carradine",
+    "carrey",
+    "carrie",
+    "carried",
+    "carry",
+    "carrying",
+    "carter",
+    "cartoon",
+    "cary",
+    "case",
+    "cash",
+    "cassavetes",
+    "cast",
+    "casting",
+    "castle",
+    "casual",
+    "cat",
+    "catch",
+    "catching",
+    "catchy",
+    "category",
+    "catherine",
+    "catholic",
+    "caught",
+    "cause",
+    "caused",
+    "causing",
+    "cave",
+    "cd",
+    "celebrity",
+    "cell",
+    "celluloid",
+    "cent",
+    "center",
+    "central",
+    "centre",
+    "century",
+    "certain",
+    "certainly",
+    "cg",
+    "cgi",
+    "chain",
+    "chainsaw",
+    "chair",
+    "challenge",
+    "challenged",
+    "challenging",
+    "champion",
+    "championship",
+    "chan",
+    "chance",
+    "change",
+    "changed",
+    "changing",
+    "channel",
+    "chaos",
+    "chaplin",
+    "chapter",
+    "character",
+    "characterbr",
+    "characteristic",
+    "characterization",
+    "charactersbr",
+    "charge",
+    "charisma",
+    "charismatic",
+    "charles",
+    "charlie",
+    "charlotte",
+    "charm",
+    "charming",
+    "chase",
+    "chased",
+    "chasing",
+    "che",
+    "cheap",
+    "cheat",
+    "cheated",
+    "cheating",
+    "check",
+    "checked",
+    "checking",
+    "cheek",
+    "cheer",
+    "cheese",
+    "cheesy",
+    "chemistry",
+    "chess",
+    "chest",
+    "chicago",
+    "chick",
+    "chicken",
+    "chief",
+    "child",
+    "childhood",
+    "childish",
+    "childrens",
+    "chill",
+    "chilling",
+    "china",
+    "chinese",
+    "chip",
+    "choice",
+    "choose",
+    "chooses",
+    "chop",
+    "choppy",
+    "choreographed",
+    "choreography",
+    "chorus",
+    "chose",
+    "chosen",
+    "chris",
+    "christ",
+    "christian",
+    "christie",
+    "christina",
+    "christmas",
+    "christopher",
+    "chuck",
+    "chuckle",
+    "church",
+    "cia",
+    "cigarette",
+    "cinderella",
+    "cinema",
+    "cinematic",
+    "cinematographer",
+    "cinematography",
+    "circle",
+    "circumstance",
+    "circus",
+    "citizen",
+    "city",
+    "civil",
+    "civilian",
+    "civilization",
+    "claim",
+    "claimed",
+    "claire",
+    "clark",
+    "class",
+    "classic",
+    "classical",
+    "claude",
+    "clean",
+    "clear",
+    "clearly",
+    "clerk",
+    "clever",
+    "cleverly",
+    "clich",
+    "clichd",
+    "cliche",
+    "clichs",
+    "client",
+    "cliff",
+    "climactic",
+    "climax",
+    "climb",
+    "clint",
+    "clip",
+    "clone",
+    "close",
+    "closed",
+    "closely",
+    "closer",
+    "closest",
+    "closet",
+    "closeup",
+    "closing",
+    "clothes",
+    "clothing",
+    "cloud",
+    "clown",
+    "club",
+    "clue",
+    "clueless",
+    "clumsy",
+    "co",
+    "coach",
+    "coast",
+    "coat",
+    "code",
+    "coffee",
+    "coherent",
+    "coincidence",
+    "cold",
+    "cole",
+    "colin",
+    "colleague",
+    "collect",
+    "collection",
+    "college",
+    "colonel",
+    "color",
+    "colorful",
+    "colour",
+    "columbo",
+    "combat",
+    "combination",
+    "combine",
+    "combined",
+    "come",
+    "comedian",
+    "comedic",
+    "comedy",
+    "comfort",
+    "comfortable",
+    "comic",
+    "comical",
+    "coming",
+    "command",
+    "commander",
+    "comment",
+    "commentary",
+    "commented",
+    "commercial",
+    "commit",
+    "committed",
+    "common",
+    "communist",
+    "community",
+    "companion",
+    "company",
+    "compare",
+    "compared",
+    "comparing",
+    "comparison",
+    "compassion",
+    "compelled",
+    "compelling",
+    "competent",
+    "competition",
+    "complain",
+    "complaining",
+    "complaint",
+    "complete",
+    "completed",
+    "completely",
+    "complex",
+    "complexity",
+    "complicated",
+    "compliment",
+    "composed",
+    "composer",
+    "composition",
+    "computer",
+    "con",
+    "conan",
+    "conceived",
+    "concentrate",
+    "concept",
+    "concern",
+    "concerned",
+    "concerning",
+    "concert",
+    "conclusion",
+    "condition",
+    "confess",
+    "confidence",
+    "conflict",
+    "confrontation",
+    "confused",
+    "confusing",
+    "confusion",
+    "connect",
+    "connected",
+    "connection",
+    "connery",
+    "conrad",
+    "conscience",
+    "consequence",
+    "conservative",
+    "consider",
+    "considerable",
+    "considered",
+    "considering",
+    "consistent",
+    "consistently",
+    "consists",
+    "conspiracy",
+    "constant",
+    "constantly",
+    "constructed",
+    "construction",
+    "contact",
+    "contain",
+    "contained",
+    "containing",
+    "contains",
+    "contemporary",
+    "content",
+    "contest",
+    "contestant",
+    "context",
+    "continue",
+    "continued",
+    "continues",
+    "continuity",
+    "contract",
+    "contrary",
+    "contrast",
+    "contribution",
+    "contrived",
+    "control",
+    "controlled",
+    "controversial",
+    "convention",
+    "conventional",
+    "conversation",
+    "convey",
+    "convict",
+    "conviction",
+    "convince",
+    "convinced",
+    "convincing",
+    "convincingly",
+    "convoluted",
+    "cook",
+    "cool",
+    "cooper",
+    "cop",
+    "cope",
+    "copy",
+    "core",
+    "corner",
+    "corny",
+    "corporate",
+    "corporation",
+    "corps",
+    "corpse",
+    "correct",
+    "correctly",
+    "corrupt",
+    "corruption",
+    "cost",
+    "costar",
+    "costume",
+    "couch",
+    "could",
+    "couldnt",
+    "couldve",
+    "count",
+    "counterpart",
+    "countless",
+    "country",
+    "countryside",
+    "couple",
+    "courage",
+    "course",
+    "court",
+    "cousin",
+    "cover",
+    "covered",
+    "cow",
+    "cowboy",
+    "cox",
+    "crack",
+    "craft",
+    "crafted",
+    "craig",
+    "crap",
+    "crappy",
+    "crash",
+    "craven",
+    "crawford",
+    "crazy",
+    "cream",
+    "create",
+    "created",
+    "creates",
+    "creating",
+    "creation",
+    "creative",
+    "creativity",
+    "creator",
+    "creature",
+    "credibility",
+    "credible",
+    "credit",
+    "credited",
+    "creep",
+    "creepy",
+    "crew",
+    "cried",
+    "crime",
+    "criminal",
+    "cringe",
+    "crisis",
+    "crisp",
+    "critic",
+    "critical",
+    "criticism",
+    "critter",
+    "crocodile",
+    "crook",
+    "cross",
+    "crossing",
+    "crowd",
+    "crucial",
+    "crude",
+    "cruel",
+    "cruelty",
+    "cruise",
+    "crush",
+    "cry",
+    "crystal",
+    "cuba",
+    "cube",
+    "cue",
+    "cult",
+    "cultural",
+    "culture",
+    "cup",
+    "cure",
+    "curiosity",
+    "curious",
+    "current",
+    "currently",
+    "curse",
+    "curtis",
+    "cusack",
+    "custer",
+    "cut",
+    "cute",
+    "cutting",
+    "cyborg",
+    "cynical",
+    "da",
+    "dad",
+    "daddy",
+    "daily",
+    "dalton",
+    "damage",
+    "dame",
+    "damme",
+    "damn",
+    "damned",
+    "dan",
+    "dance",
+    "dancer",
+    "dancing",
+    "dane",
+    "danger",
+    "dangerous",
+    "daniel",
+    "danny",
+    "dare",
+    "daring",
+    "dark",
+    "darker",
+    "darkness",
+    "darn",
+    "date",
+    "dated",
+    "dating",
+    "daughter",
+    "dave",
+    "david",
+    "davis",
+    "davy",
+    "dawn",
+    "dawson",
+    "day",
+    "daybr",
+    "de",
+    "dead",
+    "deadly",
+    "deaf",
+    "deal",
+    "dealer",
+    "dealing",
+    "dealt",
+    "dean",
+    "dear",
+    "death",
+    "debate",
+    "debut",
+    "decade",
+    "decent",
+    "decide",
+    "decided",
+    "decides",
+    "decision",
+    "dedicated",
+    "dee",
+    "deed",
+    "deep",
+    "deeper",
+    "deeply",
+    "defeat",
+    "defend",
+    "defense",
+    "defined",
+    "definite",
+    "definitely",
+    "definition",
+    "degree",
+    "deliberately",
+    "delicate",
+    "delight",
+    "delightful",
+    "deliver",
+    "delivered",
+    "delivering",
+    "delivers",
+    "delivery",
+    "demand",
+    "demented",
+    "demise",
+    "demon",
+    "demonstrates",
+    "dennis",
+    "dentist",
+    "denzel",
+    "department",
+    "depicted",
+    "depicting",
+    "depiction",
+    "depicts",
+    "depressed",
+    "depressing",
+    "depression",
+    "depth",
+    "deranged",
+    "derek",
+    "derivative",
+    "descent",
+    "describe",
+    "described",
+    "describes",
+    "describing",
+    "description",
+    "desert",
+    "deserted",
+    "deserve",
+    "deserved",
+    "deserves",
+    "design",
+    "designed",
+    "designer",
+    "desire",
+    "desired",
+    "despair",
+    "desperate",
+    "desperately",
+    "desperation",
+    "despite",
+    "destiny",
+    "destroy",
+    "destroyed",
+    "destroying",
+    "destroys",
+    "destruction",
+    "detail",
+    "detailed",
+    "detective",
+    "determined",
+    "develop",
+    "developed",
+    "developing",
+    "development",
+    "develops",
+    "device",
+    "devil",
+    "devoid",
+    "devoted",
+    "dialog",
+    "dialogue",
+    "diamond",
+    "diana",
+    "diane",
+    "dick",
+    "dickens",
+    "didnt",
+    "die",
+    "died",
+    "diehard",
+    "difference",
+    "different",
+    "differently",
+    "difficult",
+    "difficulty",
+    "dig",
+    "digital",
+    "dignity",
+    "dilemma",
+    "dimension",
+    "dimensional",
+    "dinner",
+    "dinosaur",
+    "dire",
+    "direct",
+    "directed",
+    "directing",
+    "direction",
+    "directly",
+    "director",
+    "directorial",
+    "directs",
+    "dirt",
+    "dirty",
+    "disagree",
+    "disappear",
+    "disappeared",
+    "disappears",
+    "disappoint",
+    "disappointed",
+    "disappointing",
+    "disappointment",
+    "disaster",
+    "disbelief",
+    "disc",
+    "discover",
+    "discovered",
+    "discovering",
+    "discovers",
+    "discovery",
+    "discus",
+    "discussion",
+    "disease",
+    "disguise",
+    "disgusting",
+    "disjointed",
+    "dislike",
+    "disliked",
+    "disney",
+    "display",
+    "displayed",
+    "distance",
+    "distant",
+    "distinct",
+    "distracting",
+    "distribution",
+    "disturbed",
+    "disturbing",
+    "divine",
+    "divorce",
+    "doc",
+    "doctor",
+    "document",
+    "documentary",
+    "doesnt",
+    "dog",
+    "doll",
+    "dollar",
+    "domestic",
+    "donald",
+    "done",
+    "donna",
+    "dont",
+    "doom",
+    "doomed",
+    "door",
+    "dorothy",
+    "double",
+    "doubt",
+    "doug",
+    "douglas",
+    "downhill",
+    "downright",
+    "dozen",
+    "dr",
+    "dracula",
+    "drag",
+    "dragged",
+    "dragon",
+    "drake",
+    "drama",
+    "dramatic",
+    "draw",
+    "drawing",
+    "drawn",
+    "dreadful",
+    "dream",
+    "dreary",
+    "dress",
+    "dressed",
+    "drew",
+    "drink",
+    "drinking",
+    "drive",
+    "drivel",
+    "driven",
+    "driver",
+    "driving",
+    "drop",
+    "dropped",
+    "drove",
+    "drug",
+    "drunk",
+    "drunken",
+    "dry",
+    "dubbed",
+    "dubbing",
+    "duck",
+    "dud",
+    "dude",
+    "due",
+    "duke",
+    "dull",
+    "dumb",
+    "dump",
+    "duo",
+    "dust",
+    "dutch",
+    "duty",
+    "dvd",
+    "dy",
+    "dying",
+    "dylan",
+    "dynamic",
+    "dysfunctional",
+    "eager",
+    "ear",
+    "earl",
+    "earlier",
+    "early",
+    "earned",
+    "earth",
+    "ease",
+    "easier",
+    "easily",
+    "east",
+    "eastern",
+    "eastwood",
+    "easy",
+    "eat",
+    "eaten",
+    "eating",
+    "eats",
+    "eccentric",
+    "echo",
+    "ed",
+    "eddie",
+    "edgar",
+    "edge",
+    "edgy",
+    "edited",
+    "editing",
+    "edition",
+    "editor",
+    "education",
+    "educational",
+    "edward",
+    "eerie",
+    "effect",
+    "effective",
+    "effectively",
+    "effort",
+    "eg",
+    "egg",
+    "ego",
+    "egyptian",
+    "eight",
+    "eighty",
+    "either",
+    "eitherbr",
+    "el",
+    "elaborate",
+    "elderly",
+    "electric",
+    "elegant",
+    "element",
+    "elephant",
+    "elevator",
+    "elizabeth",
+    "ellen",
+    "else",
+    "elsewhere",
+    "elvis",
+    "em",
+    "embarrassed",
+    "embarrassing",
+    "embarrassment",
+    "embrace",
+    "emily",
+    "emma",
+    "emotion",
+    "emotional",
+    "emotionally",
+    "empathy",
+    "emperor",
+    "emphasis",
+    "empire",
+    "employee",
+    "empty",
+    "encounter",
+    "encourage",
+    "end",
+    "endbr",
+    "endearing",
+    "ended",
+    "ending",
+    "endless",
+    "endure",
+    "enemy",
+    "energy",
+    "engage",
+    "engaged",
+    "engaging",
+    "england",
+    "english",
+    "enjoy",
+    "enjoyable",
+    "enjoyed",
+    "enjoying",
+    "enjoyment",
+    "enjoys",
+    "enormous",
+    "enough",
+    "ensemble",
+    "ensues",
+    "enter",
+    "enterprise",
+    "enters",
+    "entertain",
+    "entertained",
+    "entertaining",
+    "entertainment",
+    "enthusiasm",
+    "entire",
+    "entirely",
+    "entitled",
+    "entry",
+    "environment",
+    "epic",
+    "episode",
+    "equal",
+    "equally",
+    "equipment",
+    "equivalent",
+    "era",
+    "eric",
+    "erika",
+    "ernest",
+    "erotic",
+    "error",
+    "escape",
+    "escaped",
+    "especially",
+    "essence",
+    "essential",
+    "essentially",
+    "established",
+    "estate",
+    "et",
+    "etc",
+    "etcbr",
+    "eugene",
+    "europe",
+    "european",
+    "eva",
+    "eve",
+    "even",
+    "evening",
+    "event",
+    "eventually",
+    "ever",
+    "every",
+    "everybody",
+    "everyday",
+    "everyone",
+    "everyones",
+    "everything",
+    "everywhere",
+    "evidence",
+    "evident",
+    "evil",
+    "evolution",
+    "ex",
+    "exact",
+    "exactly",
+    "exaggerated",
+    "example",
+    "excellent",
+    "except",
+    "exception",
+    "exceptional",
+    "exceptionally",
+    "excess",
+    "excessive",
+    "exchange",
+    "excited",
+    "excitement",
+    "exciting",
+    "excuse",
+    "executed",
+    "execution",
+    "executive",
+    "exercise",
+    "exist",
+    "existed",
+    "existence",
+    "exists",
+    "exorcist",
+    "exotic",
+    "expect",
+    "expectation",
+    "expected",
+    "expecting",
+    "expensive",
+    "experience",
+    "experienced",
+    "experiment",
+    "experimental",
+    "expert",
+    "explain",
+    "explained",
+    "explaining",
+    "explains",
+    "explanation",
+    "explicit",
+    "exploit",
+    "exploitation",
+    "exploration",
+    "explore",
+    "explored",
+    "explores",
+    "exploring",
+    "explosion",
+    "explosive",
+    "expose",
+    "exposed",
+    "exposition",
+    "exposure",
+    "express",
+    "expressed",
+    "expression",
+    "extended",
+    "extent",
+    "exterior",
+    "extra",
+    "extraordinary",
+    "extreme",
+    "extremely",
+    "eye",
+    "fabulous",
+    "face",
+    "faced",
+    "facial",
+    "facing",
+    "fact",
+    "factor",
+    "factory",
+    "fade",
+    "fail",
+    "failed",
+    "failing",
+    "fails",
+    "failure",
+    "fair",
+    "fairly",
+    "fairy",
+    "faith",
+    "faithful",
+    "fake",
+    "falk",
+    "fall",
+    "fallen",
+    "falling",
+    "false",
+    "fame",
+    "familiar",
+    "family",
+    "famous",
+    "fan",
+    "fanatic",
+    "fancy",
+    "fantastic",
+    "fantasy",
+    "far",
+    "farce",
+    "fare",
+    "farm",
+    "farmer",
+    "fascinated",
+    "fascinating",
+    "fascination",
+    "fashion",
+    "fashioned",
+    "fast",
+    "faster",
+    "fat",
+    "fatal",
+    "fate",
+    "father",
+    "fault",
+    "favor",
+    "favorite",
+    "favour",
+    "favourite",
+    "fay",
+    "fbi",
+    "fear",
+    "feast",
+    "feat",
+    "feature",
+    "featured",
+    "featuring",
+    "fed",
+    "feed",
+    "feel",
+    "feelgood",
+    "feeling",
+    "felix",
+    "fell",
+    "fellow",
+    "felt",
+    "female",
+    "feminist",
+    "femme",
+    "fest",
+    "festival",
+    "fever",
+    "fi",
+    "fiance",
+    "fiction",
+    "fictional",
+    "field",
+    "fifteen",
+    "fifth",
+    "fifty",
+    "fight",
+    "fighter",
+    "fighting",
+    "figure",
+    "figured",
+    "file",
+    "fill",
+    "filled",
+    "filler",
+    "filling",
+    "film",
+    "filmbr",
+    "filmed",
+    "filming",
+    "filmmaker",
+    "filmmaking",
+    "filmsbr",
+    "final",
+    "finale",
+    "finally",
+    "financial",
+    "find",
+    "finding",
+    "fine",
+    "finest",
+    "finger",
+    "finish",
+    "finished",
+    "fire",
+    "fired",
+    "firm",
+    "firmly",
+    "first",
+    "firstly",
+    "fish",
+    "fisher",
+    "fist",
+    "fit",
+    "fitting",
+    "five",
+    "fix",
+    "flair",
+    "flame",
+    "flash",
+    "flashback",
+    "flat",
+    "flaw",
+    "flawed",
+    "flawless",
+    "flesh",
+    "flick",
+    "flight",
+    "floating",
+    "floor",
+    "flop",
+    "florida",
+    "flow",
+    "flower",
+    "fly",
+    "flying",
+    "flynn",
+    "focus",
+    "focused",
+    "focusing",
+    "folk",
+    "follow",
+    "followed",
+    "following",
+    "follows",
+    "fond",
+    "fonda",
+    "food",
+    "fool",
+    "fooled",
+    "foot",
+    "footage",
+    "football",
+    "forbidden",
+    "force",
+    "forced",
+    "forcing",
+    "ford",
+    "foreign",
+    "forest",
+    "forever",
+    "forget",
+    "forgettable",
+    "forgive",
+    "forgot",
+    "forgotten",
+    "form",
+    "format",
+    "former",
+    "formula",
+    "formulaic",
+    "forth",
+    "fortunately",
+    "fortune",
+    "forty",
+    "forward",
+    "foster",
+    "fought",
+    "foul",
+    "found",
+    "four",
+    "fourth",
+    "fox",
+    "foxx",
+    "frame",
+    "france",
+    "franchise",
+    "francis",
+    "francisco",
+    "franco",
+    "frank",
+    "frankenstein",
+    "frankie",
+    "frankly",
+    "freak",
+    "fred",
+    "freddy",
+    "free",
+    "freedom",
+    "freeman",
+    "french",
+    "frequent",
+    "frequently",
+    "fresh",
+    "friday",
+    "friend",
+    "friendly",
+    "friendship",
+    "frightened",
+    "frightening",
+    "front",
+    "frost",
+    "frustrated",
+    "frustrating",
+    "frustration",
+    "fu",
+    "fulci",
+    "full",
+    "fully",
+    "fun",
+    "funbr",
+    "function",
+    "funeral",
+    "funnier",
+    "funniest",
+    "funny",
+    "funnybr",
+    "furthermore",
+    "future",
+    "futuristic",
+    "fx",
+    "gabriel",
+    "gadget",
+    "gag",
+    "gain",
+    "gal",
+    "game",
+    "gang",
+    "gangster",
+    "gap",
+    "garbage",
+    "garbo",
+    "garden",
+    "garfield",
+    "gary",
+    "gas",
+    "gate",
+    "gather",
+    "gave",
+    "gay",
+    "geek",
+    "gem",
+    "gender",
+    "gene",
+    "general",
+    "generally",
+    "generated",
+    "generation",
+    "generic",
+    "generous",
+    "genius",
+    "genre",
+    "gentle",
+    "gentleman",
+    "genuine",
+    "genuinely",
+    "george",
+    "gere",
+    "german",
+    "germany",
+    "gesture",
+    "get",
+    "getting",
+    "ghost",
+    "giallo",
+    "giant",
+    "gift",
+    "gifted",
+    "gimmick",
+    "girl",
+    "girlfriend",
+    "give",
+    "given",
+    "giving",
+    "glad",
+    "glance",
+    "glass",
+    "glenn",
+    "glimpse",
+    "global",
+    "globe",
+    "gloria",
+    "glorious",
+    "glory",
+    "glover",
+    "go",
+    "goal",
+    "god",
+    "godfather",
+    "godzilla",
+    "going",
+    "gold",
+    "golden",
+    "golf",
+    "gon",
+    "gone",
+    "good",
+    "goodbr",
+    "goodbye",
+    "goodness",
+    "goofy",
+    "gordon",
+    "gore",
+    "gorgeous",
+    "gory",
+    "got",
+    "gothic",
+    "gotten",
+    "government",
+    "grab",
+    "grace",
+    "grade",
+    "gradually",
+    "graham",
+    "grainy",
+    "grand",
+    "grandfather",
+    "grandmother",
+    "grant",
+    "granted",
+    "graphic",
+    "grasp",
+    "gratuitous",
+    "grave",
+    "gray",
+    "great",
+    "greater",
+    "greatest",
+    "greatly",
+    "greatness",
+    "greed",
+    "greedy",
+    "greek",
+    "green",
+    "greg",
+    "gregory",
+    "grew",
+    "grey",
+    "griffith",
+    "grim",
+    "grip",
+    "gripping",
+    "gritty",
+    "gross",
+    "grotesque",
+    "ground",
+    "group",
+    "grow",
+    "growing",
+    "grown",
+    "grows",
+    "grudge",
+    "gruesome",
+    "gu",
+    "guarantee",
+    "guard",
+    "guess",
+    "guessed",
+    "guessing",
+    "guest",
+    "guide",
+    "guilt",
+    "guilty",
+    "guitar",
+    "gun",
+    "gut",
+    "guy",
+    "gypsy",
+    "ha",
+    "habit",
+    "hack",
+    "hackneyed",
+    "hadnt",
+    "hair",
+    "hal",
+    "half",
+    "halfway",
+    "hall",
+    "halloween",
+    "ham",
+    "hamilton",
+    "hamlet",
+    "hammer",
+    "han",
+    "hand",
+    "handed",
+    "handful",
+    "handle",
+    "handled",
+    "handsome",
+    "hang",
+    "hanging",
+    "hank",
+    "happen",
+    "happened",
+    "happening",
+    "happens",
+    "happily",
+    "happiness",
+    "happy",
+    "hard",
+    "hardcore",
+    "harder",
+    "hardly",
+    "hardy",
+    "harm",
+    "harmless",
+    "harold",
+    "harris",
+    "harrison",
+    "harry",
+    "harsh",
+    "hart",
+    "hartley",
+    "harvey",
+    "hasnt",
+    "hat",
+    "hate",
+    "hated",
+    "hatred",
+    "haunt",
+    "haunted",
+    "haunting",
+    "havent",
+    "hawk",
+    "hbo",
+    "he",
+    "head",
+    "headed",
+    "heading",
+    "health",
+    "hear",
+    "heard",
+    "hearing",
+    "hears",
+    "heart",
+    "heartbreaking",
+    "heartfelt",
+    "heartwarming",
+    "heat",
+    "heaven",
+    "heavily",
+    "heavy",
+    "heck",
+    "hed",
+    "heel",
+    "height",
+    "heist",
+    "held",
+    "helen",
+    "helicopter",
+    "hell",
+    "hello",
+    "help",
+    "helped",
+    "helping",
+    "hence",
+    "henchman",
+    "henry",
+    "herbr",
+    "here",
+    "herebr",
+    "hero",
+    "heroic",
+    "heroine",
+    "hey",
+    "hidden",
+    "hide",
+    "hideous",
+    "hiding",
+    "high",
+    "higher",
+    "highest",
+    "highlight",
+    "highly",
+    "hilarious",
+    "hilariously",
+    "hill",
+    "himbr",
+    "hindi",
+    "hint",
+    "hip",
+    "hippie",
+    "hippy",
+    "hire",
+    "hired",
+    "historical",
+    "historically",
+    "history",
+    "hit",
+    "hitch",
+    "hitchcock",
+    "hitler",
+    "hitman",
+    "hitting",
+    "hoffman",
+    "hogan",
+    "hokey",
+    "hold",
+    "holding",
+    "hole",
+    "holiday",
+    "hollow",
+    "holly",
+    "hollywood",
+    "holmes",
+    "holocaust",
+    "holy",
+    "homage",
+    "home",
+    "homeless",
+    "homer",
+    "homosexual",
+    "honest",
+    "honestly",
+    "honesty",
+    "hong",
+    "honor",
+    "hood",
+    "hook",
+    "hooked",
+    "hooker",
+    "hope",
+    "hoped",
+    "hopefully",
+    "hopeless",
+    "hopelessly",
+    "hoping",
+    "hopper",
+    "horrendous",
+    "horrible",
+    "horribly",
+    "horrid",
+    "horrific",
+    "horrifying",
+    "horror",
+    "horse",
+    "hospital",
+    "host",
+    "hostage",
+    "hot",
+    "hotel",
+    "hour",
+    "house",
+    "household",
+    "housewife",
+    "howard",
+    "however",
+    "hudson",
+    "huge",
+    "hugh",
+    "hughes",
+    "huh",
+    "human",
+    "humanity",
+    "humble",
+    "humor",
+    "humorous",
+    "humour",
+    "hundred",
+    "hung",
+    "hungry",
+    "hunt",
+    "hunter",
+    "hunting",
+    "hurt",
+    "husband",
+    "huston",
+    "hype",
+    "hysterical",
+    "ian",
+    "ice",
+    "icon",
+    "id",
+    "idea",
+    "ideal",
+    "identify",
+    "identity",
+    "idiot",
+    "idiotic",
+    "ie",
+    "ignorance",
+    "ignorant",
+    "ignore",
+    "ignored",
+    "ii",
+    "iii",
+    "ill",
+    "illegal",
+    "illness",
+    "illogical",
+    "im",
+    "image",
+    "imagery",
+    "imagination",
+    "imaginative",
+    "imagine",
+    "imagined",
+    "imdb",
+    "imitation",
+    "immediate",
+    "immediately",
+    "immensely",
+    "immigrant",
+    "impact",
+    "implausible",
+    "importance",
+    "important",
+    "importantly",
+    "impossible",
+    "impress",
+    "impressed",
+    "impression",
+    "impressive",
+    "improve",
+    "improved",
+    "improvement",
+    "inability",
+    "inaccurate",
+    "inane",
+    "inappropriate",
+    "inbr",
+    "incident",
+    "incidentally",
+    "include",
+    "included",
+    "includes",
+    "including",
+    "incoherent",
+    "incompetent",
+    "incomprehensible",
+    "inconsistent",
+    "increasingly",
+    "incredible",
+    "incredibly",
+    "indeed",
+    "independent",
+    "india",
+    "indian",
+    "indie",
+    "individual",
+    "industry",
+    "inept",
+    "inevitable",
+    "inevitably",
+    "inexplicably",
+    "infamous",
+    "inferior",
+    "influence",
+    "influenced",
+    "information",
+    "ingredient",
+    "initial",
+    "initially",
+    "injured",
+    "injury",
+    "inmate",
+    "inner",
+    "innocence",
+    "innocent",
+    "innovative",
+    "insane",
+    "insanity",
+    "inside",
+    "insight",
+    "inspector",
+    "inspiration",
+    "inspire",
+    "inspired",
+    "inspiring",
+    "installment",
+    "instance",
+    "instant",
+    "instantly",
+    "instead",
+    "instinct",
+    "institution",
+    "insult",
+    "insulting",
+    "integrity",
+    "intellectual",
+    "intelligence",
+    "intelligent",
+    "intended",
+    "intense",
+    "intensity",
+    "intent",
+    "intention",
+    "intentionally",
+    "interaction",
+    "interest",
+    "interested",
+    "interesting",
+    "interestingly",
+    "interior",
+    "international",
+    "internet",
+    "interpretation",
+    "interview",
+    "intimate",
+    "intrigue",
+    "intrigued",
+    "intriguing",
+    "introduce",
+    "introduced",
+    "introduces",
+    "introduction",
+    "invasion",
+    "invented",
+    "inventive",
+    "investigate",
+    "investigating",
+    "investigation",
+    "invisible",
+    "invite",
+    "invited",
+    "involve",
+    "involved",
+    "involvement",
+    "involves",
+    "involving",
+    "iq",
+    "iraq",
+    "ireland",
+    "irene",
+    "irish",
+    "iron",
+    "ironic",
+    "ironically",
+    "irony",
+    "irrelevant",
+    "irritating",
+    "isbr",
+    "island",
+    "isnt",
+    "isolated",
+    "issue",
+    "italian",
+    "italy",
+    "itbr",
+    "item",
+    "itll",
+    "ive",
+    "jack",
+    "jackass",
+    "jacket",
+    "jackie",
+    "jackson",
+    "jail",
+    "jake",
+    "james",
+    "jamie",
+    "jane",
+    "japan",
+    "japanese",
+    "jason",
+    "jaw",
+    "jay",
+    "jazz",
+    "jealous",
+    "jealousy",
+    "jean",
+    "jeff",
+    "jeffrey",
+    "jennifer",
+    "jenny",
+    "jeremy",
+    "jerk",
+    "jerry",
+    "jesse",
+    "jessica",
+    "jesus",
+    "jet",
+    "jew",
+    "jewel",
+    "jewish",
+    "jim",
+    "jimmy",
+    "joan",
+    "job",
+    "joe",
+    "joel",
+    "joey",
+    "john",
+    "johnny",
+    "johnson",
+    "join",
+    "joined",
+    "joke",
+    "jon",
+    "jonathan",
+    "jones",
+    "jordan",
+    "joseph",
+    "josh",
+    "journalist",
+    "journey",
+    "joy",
+    "jr",
+    "judge",
+    "judging",
+    "judgment",
+    "judy",
+    "julia",
+    "julian",
+    "julie",
+    "juliet",
+    "july",
+    "jump",
+    "jumped",
+    "jumping",
+    "june",
+    "jungle",
+    "junior",
+    "junk",
+    "justice",
+    "justify",
+    "justin",
+    "juvenile",
+    "kane",
+    "karate",
+    "karen",
+    "karloff",
+    "kate",
+    "kathy",
+    "keaton",
+    "keep",
+    "keeping",
+    "keith",
+    "kelly",
+    "ken",
+    "kennedy",
+    "kenneth",
+    "kept",
+    "kevin",
+    "key",
+    "khan",
+    "kick",
+    "kicked",
+    "kicking",
+    "kid",
+    "kidding",
+    "kidnapped",
+    "kill",
+    "killed",
+    "killer",
+    "killing",
+    "kim",
+    "kind",
+    "kinda",
+    "king",
+    "kingdom",
+    "kirk",
+    "kiss",
+    "kissing",
+    "kitchen",
+    "kitty",
+    "knew",
+    "knife",
+    "knight",
+    "knock",
+    "knocked",
+    "know",
+    "knowing",
+    "knowledge",
+    "known",
+    "kong",
+    "korean",
+    "kramer",
+    "kubrick",
+    "kudos",
+    "kung",
+    "kurt",
+    "kyle",
+    "la",
+    "lab",
+    "label",
+    "labor",
+    "lack",
+    "lacked",
+    "lacking",
+    "lackluster",
+    "lady",
+    "laid",
+    "lake",
+    "lame",
+    "lance",
+    "land",
+    "landing",
+    "landscape",
+    "lane",
+    "language",
+    "large",
+    "largely",
+    "larger",
+    "larry",
+    "last",
+    "lasted",
+    "late",
+    "lately",
+    "later",
+    "latest",
+    "latin",
+    "latter",
+    "laugh",
+    "laughable",
+    "laughably",
+    "laughed",
+    "laughing",
+    "laughter",
+    "laura",
+    "laurel",
+    "lauren",
+    "law",
+    "lawrence",
+    "lawyer",
+    "lay",
+    "layer",
+    "lazy",
+    "le",
+    "lead",
+    "leader",
+    "leading",
+    "leaf",
+    "league",
+    "leap",
+    "learn",
+    "learned",
+    "learning",
+    "learns",
+    "least",
+    "leave",
+    "leaving",
+    "led",
+    "lee",
+    "left",
+    "leg",
+    "legacy",
+    "legal",
+    "legend",
+    "legendary",
+    "leigh",
+    "lemmon",
+    "length",
+    "lengthy",
+    "leo",
+    "leonard",
+    "lesbian",
+    "leslie",
+    "less",
+    "lesser",
+    "lesson",
+    "let",
+    "letter",
+    "letting",
+    "level",
+    "lewis",
+    "li",
+    "liberal",
+    "liberty",
+    "library",
+    "lie",
+    "life",
+    "lifebr",
+    "lifeless",
+    "lifestyle",
+    "lifetime",
+    "lift",
+    "lifted",
+    "light",
+    "lighthearted",
+    "lighting",
+    "likable",
+    "like",
+    "liked",
+    "likely",
+    "likewise",
+    "liking",
+    "lily",
+    "limit",
+    "limited",
+    "lincoln",
+    "linda",
+    "line",
+    "liner",
+    "link",
+    "lion",
+    "lip",
+    "lisa",
+    "list",
+    "listed",
+    "listen",
+    "listening",
+    "lit",
+    "literally",
+    "literary",
+    "literature",
+    "little",
+    "live",
+    "lived",
+    "lively",
+    "living",
+    "lloyd",
+    "load",
+    "loaded",
+    "local",
+    "located",
+    "location",
+    "lock",
+    "locked",
+    "logic",
+    "logical",
+    "lol",
+    "london",
+    "lone",
+    "loneliness",
+    "lonely",
+    "long",
+    "longer",
+    "look",
+    "looked",
+    "looking",
+    "loose",
+    "loosely",
+    "lord",
+    "los",
+    "lose",
+    "loser",
+    "loses",
+    "losing",
+    "loss",
+    "lost",
+    "lot",
+    "lou",
+    "loud",
+    "louis",
+    "lousy",
+    "lovable",
+    "love",
+    "loved",
+    "lovely",
+    "lover",
+    "loving",
+    "low",
+    "lowbudget",
+    "lower",
+    "lowest",
+    "loyal",
+    "loyalty",
+    "lucas",
+    "luck",
+    "luckily",
+    "lucky",
+    "lucy",
+    "ludicrous",
+    "lugosi",
+    "luke",
+    "lust",
+    "lying",
+    "lynch",
+    "lyric",
+    "macbeth",
+    "machine",
+    "macy",
+    "mad",
+    "made",
+    "madebr",
+    "madefortv",
+    "madness",
+    "madonna",
+    "mafia",
+    "magazine",
+    "maggie",
+    "magic",
+    "magical",
+    "magnificent",
+    "maid",
+    "mail",
+    "main",
+    "mainly",
+    "mainstream",
+    "maintain",
+    "major",
+    "majority",
+    "make",
+    "maker",
+    "makeup",
+    "making",
+    "male",
+    "man",
+    "manage",
+    "managed",
+    "manager",
+    "manages",
+    "manhattan",
+    "maniac",
+    "manipulative",
+    "mankind",
+    "mann",
+    "manner",
+    "mansion",
+    "many",
+    "map",
+    "mar",
+    "march",
+    "margaret",
+    "maria",
+    "marie",
+    "marine",
+    "mario",
+    "marion",
+    "mark",
+    "market",
+    "marketing",
+    "marriage",
+    "married",
+    "marry",
+    "marshall",
+    "martha",
+    "martial",
+    "martin",
+    "marty",
+    "marvel",
+    "marvelous",
+    "mary",
+    "mask",
+    "mason",
+    "mass",
+    "massacre",
+    "massive",
+    "master",
+    "masterful",
+    "masterpiece",
+    "match",
+    "mate",
+    "material",
+    "matrix",
+    "matt",
+    "matter",
+    "matthau",
+    "matthew",
+    "mature",
+    "max",
+    "may",
+    "maybe",
+    "mayhem",
+    "mayor",
+    "meal",
+    "mean",
+    "meaning",
+    "meaningful",
+    "meaningless",
+    "meant",
+    "meanwhile",
+    "measure",
+    "meat",
+    "mebr",
+    "medical",
+    "mediocre",
+    "medium",
+    "meet",
+    "meeting",
+    "meg",
+    "mel",
+    "melodrama",
+    "melodramatic",
+    "member",
+    "memorable",
+    "memory",
+    "men",
+    "menace",
+    "menacing",
+    "mental",
+    "mentally",
+    "mention",
+    "mentioned",
+    "mentioning",
+    "mere",
+    "merely",
+    "merit",
+    "meryl",
+    "mess",
+    "message",
+    "messed",
+    "met",
+    "metal",
+    "metaphor",
+    "method",
+    "mexican",
+    "mexico",
+    "mgm",
+    "michael",
+    "michelle",
+    "mickey",
+    "mid",
+    "middle",
+    "middleaged",
+    "midnight",
+    "might",
+    "mighty",
+    "mike",
+    "mild",
+    "mildly",
+    "mile",
+    "military",
+    "milk",
+    "mill",
+    "miller",
+    "million",
+    "milo",
+    "min",
+    "mind",
+    "mindless",
+    "mine",
+    "mini",
+    "minimal",
+    "minimum",
+    "miniseries",
+    "minister",
+    "minor",
+    "minority",
+    "minus",
+    "minute",
+    "minutesbr",
+    "miracle",
+    "mirror",
+    "miscast",
+    "miserable",
+    "miserably",
+    "misery",
+    "misleading",
+    "miss",
+    "missed",
+    "missile",
+    "missing",
+    "mission",
+    "mistake",
+    "mistaken",
+    "mistress",
+    "mitchell",
+    "mitchum",
+    "mix",
+    "mixed",
+    "mixture",
+    "mm",
+    "mob",
+    "mobster",
+    "mode",
+    "model",
+    "modern",
+    "modest",
+    "molly",
+    "mom",
+    "moment",
+    "money",
+    "monk",
+    "monkey",
+    "monologue",
+    "monster",
+    "montage",
+    "montgomery",
+    "month",
+    "monty",
+    "mood",
+    "moody",
+    "moon",
+    "moore",
+    "moral",
+    "morality",
+    "morebr",
+    "moreover",
+    "morgan",
+    "mormon",
+    "morning",
+    "moron",
+    "moronic",
+    "morris",
+    "mostly",
+    "mother",
+    "motif",
+    "motion",
+    "motivation",
+    "motorcycle",
+    "mountain",
+    "mouse",
+    "mouth",
+    "move",
+    "moved",
+    "movement",
+    "movie",
+    "moviebr",
+    "moviegoer",
+    "moviesbr",
+    "moving",
+    "mr",
+    "mstk",
+    "mtv",
+    "much",
+    "muchbr",
+    "muddled",
+    "multiple",
+    "mummy",
+    "mundane",
+    "muppet",
+    "muppets",
+    "murder",
+    "murdered",
+    "murderer",
+    "murdering",
+    "murderous",
+    "murphy",
+    "murray",
+    "museum",
+    "music",
+    "musical",
+    "musician",
+    "muslim",
+    "must",
+    "mustsee",
+    "mutant",
+    "mute",
+    "myers",
+    "mysterious",
+    "mystery",
+    "myth",
+    "na",
+    "nail",
+    "naive",
+    "naked",
+    "name",
+    "named",
+    "namely",
+    "nancy",
+    "narration",
+    "narrative",
+    "narrator",
+    "nasty",
+    "natalie",
+    "nation",
+    "national",
+    "native",
+    "natural",
+    "naturally",
+    "nature",
+    "navy",
+    "nazi",
+    "nbc",
+    "nd",
+    "near",
+    "nearby",
+    "nearly",
+    "neat",
+    "necessarily",
+    "necessary",
+    "neck",
+    "ned",
+    "need",
+    "needed",
+    "needless",
+    "negative",
+    "neighbor",
+    "neighborhood",
+    "neil",
+    "neither",
+    "nelson",
+    "nemesis",
+    "nephew",
+    "nerd",
+    "nerve",
+    "nervous",
+    "net",
+    "network",
+    "never",
+    "nevertheless",
+    "new",
+    "newcomer",
+    "newly",
+    "newman",
+    "news",
+    "newspaper",
+    "next",
+    "nice",
+    "nicely",
+    "nicholas",
+    "nicholson",
+    "nick",
+    "nicole",
+    "niece",
+    "night",
+    "nightclub",
+    "nightmare",
+    "nine",
+    "ninety",
+    "ninja",
+    "niro",
+    "noble",
+    "nobody",
+    "nod",
+    "noir",
+    "noise",
+    "nominated",
+    "nomination",
+    "non",
+    "none",
+    "nonetheless",
+    "nonexistent",
+    "nonsense",
+    "nonsensical",
+    "nonstop",
+    "noone",
+    "normal",
+    "normally",
+    "norman",
+    "norris",
+    "north",
+    "northern",
+    "nose",
+    "nostalgia",
+    "nostalgic",
+    "notable",
+    "notably",
+    "notbr",
+    "notch",
+    "note",
+    "noted",
+    "nothing",
+    "notice",
+    "noticed",
+    "notion",
+    "notorious",
+    "novel",
+    "nowadays",
+    "nowbr",
+    "nowhere",
+    "nuance",
+    "nuclear",
+    "nude",
+    "nudity",
+    "number",
+    "numerous",
+    "nun",
+    "nurse",
+    "nut",
+    "nyc",
+    "object",
+    "objective",
+    "obligatory",
+    "obnoxious",
+    "obscure",
+    "observation",
+    "obsessed",
+    "obsession",
+    "obvious",
+    "obviously",
+    "occasion",
+    "occasional",
+    "occasionally",
+    "occur",
+    "occurred",
+    "occurs",
+    "ocean",
+    "odd",
+    "oddly",
+    "odds",
+    "odyssey",
+    "offbr",
+    "offended",
+    "offensive",
+    "offer",
+    "offered",
+    "offering",
+    "office",
+    "officer",
+    "official",
+    "often",
+    "oh",
+    "oil",
+    "ok",
+    "okay",
+    "old",
+    "older",
+    "oliver",
+    "olivia",
+    "olivier",
+    "onbr",
+    "one",
+    "onebr",
+    "onedimensional",
+    "oneliners",
+    "online",
+    "onscreen",
+    "onto",
+    "open",
+    "opened",
+    "opening",
+    "opera",
+    "operation",
+    "opinion",
+    "opportunity",
+    "opposed",
+    "opposite",
+    "option",
+    "orange",
+    "order",
+    "ordered",
+    "ordinary",
+    "origin",
+    "original",
+    "originality",
+    "originally",
+    "oscar",
+    "otherbr",
+    "others",
+    "otherwise",
+    "ought",
+    "outbr",
+    "outcome",
+    "outer",
+    "outfit",
+    "outing",
+    "outrageous",
+    "outside",
+    "outstanding",
+    "overacting",
+    "overall",
+    "overcome",
+    "overdone",
+    "overlong",
+    "overlook",
+    "overlooked",
+    "overly",
+    "overrated",
+    "overthetop",
+    "overwhelming",
+    "owen",
+    "owned",
+    "owner",
+    "owns",
+    "oz",
+    "pace",
+    "paced",
+    "pacing",
+    "pacino",
+    "pack",
+    "package",
+    "packed",
+    "page",
+    "paid",
+    "pain",
+    "painful",
+    "painfully",
+    "paint",
+    "painted",
+    "painter",
+    "painting",
+    "pair",
+    "pal",
+    "pale",
+    "pan",
+    "panic",
+    "pant",
+    "paper",
+    "par",
+    "parade",
+    "paradise",
+    "parallel",
+    "paranoia",
+    "parent",
+    "paris",
+    "park",
+    "parker",
+    "parody",
+    "part",
+    "particular",
+    "particularly",
+    "partly",
+    "partner",
+    "party",
+    "pas",
+    "pass",
+    "passable",
+    "passage",
+    "passed",
+    "passenger",
+    "passing",
+    "passion",
+    "passionate",
+    "past",
+    "pat",
+    "path",
+    "pathetic",
+    "patience",
+    "patient",
+    "patricia",
+    "patrick",
+    "pattern",
+    "paul",
+    "pause",
+    "pay",
+    "paying",
+    "peace",
+    "peak",
+    "pearl",
+    "penguin",
+    "penn",
+    "penny",
+    "people",
+    "peoplebr",
+    "per",
+    "perception",
+    "perfect",
+    "perfection",
+    "perfectly",
+    "perform",
+    "performance",
+    "performed",
+    "performer",
+    "performing",
+    "performs",
+    "perhaps",
+    "period",
+    "perry",
+    "person",
+    "persona",
+    "personal",
+    "personality",
+    "personally",
+    "perspective",
+    "pet",
+    "pete",
+    "peter",
+    "petty",
+    "pg",
+    "phantom",
+    "phenomenon",
+    "phil",
+    "philip",
+    "phillips",
+    "philosophical",
+    "philosophy",
+    "phone",
+    "phony",
+    "photo",
+    "photograph",
+    "photographed",
+    "photographer",
+    "photography",
+    "phrase",
+    "physical",
+    "physically",
+    "piano",
+    "pick",
+    "picked",
+    "picking",
+    "picture",
+    "pie",
+    "piece",
+    "pig",
+    "pile",
+    "pilot",
+    "pink",
+    "pirate",
+    "pit",
+    "pitch",
+    "pitiful",
+    "pitt",
+    "pity",
+    "place",
+    "placed",
+    "plague",
+    "plain",
+    "plan",
+    "plane",
+    "planet",
+    "planned",
+    "planning",
+    "plant",
+    "plastic",
+    "plausible",
+    "play",
+    "playboy",
+    "played",
+    "player",
+    "playing",
+    "pleasant",
+    "pleasantly",
+    "please",
+    "pleased",
+    "pleasure",
+    "plenty",
+    "plight",
+    "plot",
+    "plotbr",
+    "plus",
+    "poem",
+    "poetic",
+    "poetry",
+    "poignant",
+    "point",
+    "pointed",
+    "pointless",
+    "poison",
+    "police",
+    "policeman",
+    "polish",
+    "polished",
+    "political",
+    "politically",
+    "politician",
+    "politics",
+    "pool",
+    "poor",
+    "poorly",
+    "pop",
+    "popcorn",
+    "popular",
+    "popularity",
+    "population",
+    "porn",
+    "porno",
+    "portion",
+    "portrait",
+    "portray",
+    "portrayal",
+    "portrayed",
+    "portraying",
+    "portrays",
+    "pose",
+    "position",
+    "positive",
+    "positively",
+    "possessed",
+    "possession",
+    "possibility",
+    "possible",
+    "possibly",
+    "post",
+    "posted",
+    "poster",
+    "pot",
+    "potential",
+    "potentially",
+    "pound",
+    "poverty",
+    "powell",
+    "power",
+    "powerful",
+    "practically",
+    "practice",
+    "praise",
+    "prank",
+    "precious",
+    "precisely",
+    "predator",
+    "predecessor",
+    "predictable",
+    "prefer",
+    "pregnant",
+    "prejudice",
+    "premiere",
+    "premise",
+    "prepare",
+    "prepared",
+    "presence",
+    "present",
+    "presentation",
+    "presented",
+    "presenting",
+    "president",
+    "press",
+    "pressure",
+    "presumably",
+    "pretend",
+    "pretending",
+    "pretentious",
+    "pretty",
+    "prevent",
+    "preview",
+    "previous",
+    "previously",
+    "prey",
+    "price",
+    "priceless",
+    "pride",
+    "priest",
+    "primarily",
+    "primary",
+    "prime",
+    "primitive",
+    "prince",
+    "princess",
+    "principal",
+    "principle",
+    "print",
+    "prior",
+    "prison",
+    "prisoner",
+    "private",
+    "prize",
+    "pro",
+    "probably",
+    "problem",
+    "proceeding",
+    "proceeds",
+    "process",
+    "produce",
+    "produced",
+    "producer",
+    "producing",
+    "product",
+    "production",
+    "prof",
+    "profanity",
+    "professional",
+    "professor",
+    "profound",
+    "program",
+    "programme",
+    "progress",
+    "project",
+    "prom",
+    "prominent",
+    "promise",
+    "promised",
+    "promising",
+    "proof",
+    "prop",
+    "propaganda",
+    "proper",
+    "properly",
+    "property",
+    "prostitute",
+    "protagonist",
+    "protect",
+    "proud",
+    "prove",
+    "proved",
+    "provide",
+    "provided",
+    "provides",
+    "providing",
+    "provoking",
+    "psychiatrist",
+    "psychic",
+    "psycho",
+    "psychological",
+    "psychopath",
+    "psychotic",
+    "public",
+    "pull",
+    "pulled",
+    "pulling",
+    "pulp",
+    "pun",
+    "punch",
+    "punishment",
+    "punk",
+    "puppet",
+    "purchase",
+    "purchased",
+    "pure",
+    "purely",
+    "purple",
+    "purpose",
+    "pursuit",
+    "push",
+    "pushed",
+    "pushing",
+    "put",
+    "putting",
+    "puzzle",
+    "quaid",
+    "quality",
+    "quarter",
+    "queen",
+    "quest",
+    "question",
+    "questionable",
+    "quick",
+    "quickly",
+    "quiet",
+    "quietly",
+    "quinn",
+    "quirky",
+    "quit",
+    "quite",
+    "quote",
+    "rabbit",
+    "race",
+    "rachel",
+    "racial",
+    "racism",
+    "racist",
+    "radio",
+    "rage",
+    "rain",
+    "raise",
+    "raised",
+    "raising",
+    "ralph",
+    "ran",
+    "random",
+    "randomly",
+    "randy",
+    "range",
+    "ranger",
+    "rank",
+    "rap",
+    "rape",
+    "raped",
+    "rare",
+    "rarely",
+    "rat",
+    "rate",
+    "rated",
+    "rather",
+    "rating",
+    "raw",
+    "ray",
+    "raymond",
+    "rd",
+    "reach",
+    "reached",
+    "reaching",
+    "react",
+    "reaction",
+    "read",
+    "reader",
+    "reading",
+    "ready",
+    "real",
+    "realise",
+    "realised",
+    "realism",
+    "realistic",
+    "reality",
+    "realize",
+    "realized",
+    "realizes",
+    "realizing",
+    "reallife",
+    "really",
+    "realm",
+    "reason",
+    "reasonable",
+    "reasonably",
+    "rebel",
+    "recall",
+    "receive",
+    "received",
+    "receives",
+    "recent",
+    "recently",
+    "recognition",
+    "recognize",
+    "recognized",
+    "recommend",
+    "recommendation",
+    "recommended",
+    "record",
+    "recorded",
+    "recording",
+    "recycled",
+    "red",
+    "redeeming",
+    "redemption",
+    "redneck",
+    "reduced",
+    "reed",
+    "reef",
+    "reel",
+    "refer",
+    "reference",
+    "referred",
+    "reflect",
+    "reflection",
+    "refreshing",
+    "refuse",
+    "refused",
+    "regard",
+    "regarded",
+    "regarding",
+    "regardless",
+    "region",
+    "regret",
+    "regular",
+    "reign",
+    "reject",
+    "rejected",
+    "relate",
+    "related",
+    "relation",
+    "relationship",
+    "relative",
+    "relatively",
+    "relax",
+    "release",
+    "released",
+    "relevant",
+    "relief",
+    "relies",
+    "religion",
+    "religious",
+    "rely",
+    "remade",
+    "remain",
+    "remained",
+    "remaining",
+    "remains",
+    "remake",
+    "remark",
+    "remarkable",
+    "remarkably",
+    "remember",
+    "remembered",
+    "remind",
+    "reminded",
+    "reminds",
+    "reminiscent",
+    "remote",
+    "remotely",
+    "remove",
+    "removed",
+    "rendered",
+    "rendition",
+    "rent",
+    "rental",
+    "rented",
+    "renting",
+    "repeat",
+    "repeated",
+    "repeatedly",
+    "repeating",
+    "repetitive",
+    "replace",
+    "replaced",
+    "reply",
+    "report",
+    "reporter",
+    "represent",
+    "representation",
+    "represented",
+    "represents",
+    "reputation",
+    "require",
+    "required",
+    "requires",
+    "rerun",
+    "rescue",
+    "research",
+    "resemblance",
+    "resemble",
+    "resembles",
+    "resident",
+    "resist",
+    "resolution",
+    "resort",
+    "resource",
+    "respect",
+    "respectable",
+    "respected",
+    "respective",
+    "response",
+    "responsibility",
+    "responsible",
+    "rest",
+    "restaurant",
+    "restored",
+    "result",
+    "resulting",
+    "retarded",
+    "retired",
+    "return",
+    "returned",
+    "returning",
+    "reunion",
+    "reveal",
+    "revealed",
+    "revealing",
+    "reveals",
+    "revelation",
+    "revenge",
+    "review",
+    "reviewer",
+    "revolution",
+    "revolutionary",
+    "revolves",
+    "reward",
+    "rex",
+    "reynolds",
+    "rhythm",
+    "rich",
+    "richard",
+    "richards",
+    "rick",
+    "rid",
+    "ride",
+    "rider",
+    "ridiculous",
+    "ridiculously",
+    "riding",
+    "rifle",
+    "right",
+    "rightbr",
+    "ring",
+    "riot",
+    "rip",
+    "ripoff",
+    "ripped",
+    "rise",
+    "rising",
+    "risk",
+    "rita",
+    "ritter",
+    "ritual",
+    "rival",
+    "river",
+    "riveting",
+    "road",
+    "rob",
+    "robber",
+    "robbery",
+    "robbins",
+    "robert",
+    "robin",
+    "robinson",
+    "robot",
+    "rochester",
+    "rock",
+    "rocket",
+    "rocky",
+    "rod",
+    "roger",
+    "rogers",
+    "role",
+    "roll",
+    "rolled",
+    "rolling",
+    "roman",
+    "romance",
+    "romantic",
+    "rome",
+    "romp",
+    "ron",
+    "ronald",
+    "roof",
+    "room",
+    "roommate",
+    "root",
+    "rope",
+    "rose",
+    "ross",
+    "rotten",
+    "rough",
+    "round",
+    "route",
+    "routine",
+    "row",
+    "roy",
+    "royal",
+    "rubber",
+    "rubbish",
+    "ruby",
+    "rude",
+    "ruin",
+    "ruined",
+    "rule",
+    "run",
+    "runner",
+    "running",
+    "rupert",
+    "rural",
+    "rush",
+    "rushed",
+    "russell",
+    "russia",
+    "russian",
+    "ruth",
+    "ruthless",
+    "ryan",
+    "sacrifice",
+    "sad",
+    "sadistic",
+    "sadly",
+    "sadness",
+    "safe",
+    "safety",
+    "saga",
+    "said",
+    "sailor",
+    "saint",
+    "sake",
+    "sale",
+    "sally",
+    "salman",
+    "sam",
+    "samuel",
+    "samurai",
+    "san",
+    "sand",
+    "sandler",
+    "sandra",
+    "santa",
+    "sappy",
+    "sarah",
+    "sarandon",
+    "sat",
+    "satan",
+    "satire",
+    "satisfied",
+    "satisfy",
+    "satisfying",
+    "saturday",
+    "savage",
+    "save",
+    "saved",
+    "saving",
+    "saw",
+    "say",
+    "saying",
+    "sbr",
+    "scale",
+    "scare",
+    "scarecrow",
+    "scared",
+    "scarlett",
+    "scary",
+    "scenario",
+    "scene",
+    "scenebr",
+    "scenery",
+    "scenesbr",
+    "scheme",
+    "school",
+    "science",
+    "scientific",
+    "scientist",
+    "scifi",
+    "scope",
+    "score",
+    "scott",
+    "scottish",
+    "scratch",
+    "scream",
+    "screaming",
+    "screen",
+    "screenbr",
+    "screening",
+    "screenplay",
+    "screenwriter",
+    "screw",
+    "script",
+    "scripted",
+    "scriptwriter",
+    "sea",
+    "seagal",
+    "sean",
+    "search",
+    "searching",
+    "season",
+    "seat",
+    "second",
+    "secondary",
+    "secondly",
+    "secret",
+    "secretary",
+    "secretly",
+    "section",
+    "security",
+    "see",
+    "seed",
+    "seeing",
+    "seek",
+    "seeking",
+    "seem",
+    "seemed",
+    "seemingly",
+    "seems",
+    "seen",
+    "seenbr",
+    "segment",
+    "seldom",
+    "selection",
+    "self",
+    "selfish",
+    "sell",
+    "seller",
+    "selling",
+    "send",
+    "sending",
+    "sends",
+    "sens",
+    "sense",
+    "senseless",
+    "sensibility",
+    "sensitive",
+    "sent",
+    "sentence",
+    "sentiment",
+    "sentimental",
+    "separate",
+    "sequel",
+    "sequence",
+    "serf",
+    "sergeant",
+    "serial",
+    "series",
+    "seriesbr",
+    "serious",
+    "seriously",
+    "servant",
+    "serve",
+    "served",
+    "service",
+    "serving",
+    "session",
+    "set",
+    "setting",
+    "settle",
+    "setup",
+    "seven",
+    "seventy",
+    "several",
+    "severe",
+    "severely",
+    "sex",
+    "sexual",
+    "sexuality",
+    "sexually",
+    "sexy",
+    "shade",
+    "shadow",
+    "shake",
+    "shakespeare",
+    "shall",
+    "shallow",
+    "shame",
+    "shape",
+    "share",
+    "shared",
+    "shark",
+    "sharp",
+    "shaw",
+    "shed",
+    "sheen",
+    "sheer",
+    "shelf",
+    "shell",
+    "sheriff",
+    "shes",
+    "shift",
+    "shine",
+    "shining",
+    "ship",
+    "shirley",
+    "shirt",
+    "shock",
+    "shocked",
+    "shocking",
+    "shoddy",
+    "shoe",
+    "shoot",
+    "shooting",
+    "shootout",
+    "shop",
+    "shore",
+    "short",
+    "shortcoming",
+    "shortly",
+    "shot",
+    "shoulder",
+    "shouldnt",
+    "shouldve",
+    "shout",
+    "shouting",
+    "show",
+    "showbr",
+    "showcase",
+    "showdown",
+    "showed",
+    "shower",
+    "showing",
+    "shown",
+    "shut",
+    "shy",
+    "sibling",
+    "sick",
+    "side",
+    "sidekick",
+    "sidney",
+    "sight",
+    "sign",
+    "signed",
+    "significance",
+    "significant",
+    "silence",
+    "silent",
+    "silliness",
+    "silly",
+    "silver",
+    "similar",
+    "similarity",
+    "similarly",
+    "simmons",
+    "simon",
+    "simple",
+    "simplicity",
+    "simplistic",
+    "simply",
+    "simpson",
+    "simultaneously",
+    "sin",
+    "sinatra",
+    "since",
+    "sincere",
+    "sing",
+    "singer",
+    "singing",
+    "single",
+    "sings",
+    "sinister",
+    "sink",
+    "sir",
+    "sister",
+    "sit",
+    "sitcom",
+    "site",
+    "sits",
+    "sitting",
+    "situation",
+    "six",
+    "sixty",
+    "size",
+    "skeleton",
+    "sketch",
+    "skill",
+    "skin",
+    "skip",
+    "skit",
+    "skull",
+    "sky",
+    "slap",
+    "slapstick",
+    "slasher",
+    "slaughter",
+    "slave",
+    "sleaze",
+    "sleazy",
+    "sleep",
+    "sleeping",
+    "slice",
+    "slick",
+    "slight",
+    "slightest",
+    "slightly",
+    "slip",
+    "sloppy",
+    "slow",
+    "slowly",
+    "small",
+    "smaller",
+    "smart",
+    "smell",
+    "smile",
+    "smiling",
+    "smith",
+    "smoke",
+    "smoking",
+    "smooth",
+    "snake",
+    "sneak",
+    "snipe",
+    "snow",
+    "snowman",
+    "soap",
+    "socalled",
+    "soccer",
+    "social",
+    "society",
+    "soft",
+    "softcore",
+    "sold",
+    "soldier",
+    "sole",
+    "solely",
+    "solid",
+    "solo",
+    "solution",
+    "solve",
+    "somebody",
+    "someday",
+    "somehow",
+    "someone",
+    "something",
+    "sometime",
+    "sometimes",
+    "somewhat",
+    "somewhere",
+    "son",
+    "song",
+    "soon",
+    "sophisticated",
+    "soprano",
+    "sorry",
+    "sort",
+    "soul",
+    "sound",
+    "sounded",
+    "sounding",
+    "soundtrack",
+    "source",
+    "south",
+    "southern",
+    "soviet",
+    "space",
+    "spaceship",
+    "spacey",
+    "spade",
+    "spaghetti",
+    "spain",
+    "span",
+    "spanish",
+    "spare",
+    "spark",
+    "speak",
+    "speaking",
+    "speaks",
+    "special",
+    "specially",
+    "specie",
+    "specific",
+    "specifically",
+    "spectacle",
+    "spectacular",
+    "speech",
+    "speed",
+    "spell",
+    "spend",
+    "spending",
+    "spends",
+    "spent",
+    "spider",
+    "spielberg",
+    "spike",
+    "spin",
+    "spiral",
+    "spirit",
+    "spirited",
+    "spiritual",
+    "spite",
+    "splatter",
+    "splendid",
+    "split",
+    "spock",
+    "spoil",
+    "spoiled",
+    "spoiler",
+    "spoilersbr",
+    "spoke",
+    "spoken",
+    "spoof",
+    "spooky",
+    "sport",
+    "spot",
+    "spread",
+    "spring",
+    "spy",
+    "squad",
+    "square",
+    "st",
+    "stab",
+    "staff",
+    "stage",
+    "staged",
+    "stake",
+    "stale",
+    "stan",
+    "stand",
+    "standard",
+    "standing",
+    "standout",
+    "standup",
+    "stanley",
+    "stanwyck",
+    "star",
+    "stare",
+    "staring",
+    "stark",
+    "starred",
+    "starring",
+    "start",
+    "started",
+    "starting",
+    "state",
+    "stated",
+    "statement",
+    "static",
+    "station",
+    "statue",
+    "status",
+    "stay",
+    "stayed",
+    "staying",
+    "steal",
+    "stealing",
+    "steel",
+    "stellar",
+    "step",
+    "stephen",
+    "stereotype",
+    "stereotypical",
+    "steve",
+    "steven",
+    "stevens",
+    "stewart",
+    "stick",
+    "stiff",
+    "still",
+    "stiller",
+    "stilted",
+    "stink",
+    "stinker",
+    "stock",
+    "stole",
+    "stolen",
+    "stomach",
+    "stone",
+    "stood",
+    "stooge",
+    "stop",
+    "stopped",
+    "store",
+    "storm",
+    "story",
+    "storybr",
+    "storyline",
+    "storytelling",
+    "straight",
+    "straightforward",
+    "stranded",
+    "strange",
+    "strangely",
+    "stranger",
+    "streep",
+    "street",
+    "streisand",
+    "strength",
+    "stress",
+    "stretch",
+    "strictly",
+    "strike",
+    "striking",
+    "string",
+    "strip",
+    "stroke",
+    "strong",
+    "stronger",
+    "strongest",
+    "strongly",
+    "struck",
+    "structure",
+    "struggle",
+    "struggling",
+    "stuart",
+    "stuck",
+    "student",
+    "studio",
+    "study",
+    "studying",
+    "stuff",
+    "stumble",
+    "stumbled",
+    "stunned",
+    "stunning",
+    "stunt",
+    "stupid",
+    "stupidity",
+    "style",
+    "stylish",
+    "sub",
+    "subject",
+    "subjected",
+    "subpar",
+    "subplot",
+    "subplots",
+    "subsequent",
+    "substance",
+    "subtitle",
+    "subtle",
+    "subtlety",
+    "succeed",
+    "succeeded",
+    "succeeds",
+    "success",
+    "successful",
+    "successfully",
+    "suck",
+    "sucked",
+    "sudden",
+    "suddenly",
+    "sue",
+    "suffer",
+    "suffered",
+    "suffering",
+    "suffers",
+    "suffice",
+    "suggest",
+    "suggested",
+    "suggestion",
+    "suggests",
+    "suicide",
+    "suit",
+    "suitable",
+    "suited",
+    "sullivan",
+    "sum",
+    "summary",
+    "summer",
+    "sun",
+    "sunday",
+    "sung",
+    "sunny",
+    "sunshine",
+    "super",
+    "superb",
+    "superbly",
+    "superficial",
+    "superhero",
+    "superior",
+    "superman",
+    "supernatural",
+    "supply",
+    "support",
+    "supported",
+    "supporting",
+    "suppose",
+    "supposed",
+    "supposedly",
+    "sure",
+    "surely",
+    "surface",
+    "surfing",
+    "surgery",
+    "surprise",
+    "surprised",
+    "surprising",
+    "surprisingly",
+    "surreal",
+    "surround",
+    "surrounded",
+    "surrounding",
+    "survival",
+    "survive",
+    "survived",
+    "surviving",
+    "survivor",
+    "susan",
+    "suspect",
+    "suspend",
+    "suspense",
+    "suspenseful",
+    "suspension",
+    "suspicion",
+    "suspicious",
+    "sutherland",
+    "swear",
+    "swedish",
+    "sweet",
+    "swim",
+    "swimming",
+    "swing",
+    "switch",
+    "sword",
+    "symbol",
+    "symbolic",
+    "symbolism",
+    "sympathetic",
+    "sympathy",
+    "synopsis",
+    "system",
+    "ta",
+    "table",
+    "tacky",
+    "tactic",
+    "tad",
+    "tag",
+    "tail",
+    "take",
+    "taken",
+    "taking",
+    "tale",
+    "talent",
+    "talented",
+    "talk",
+    "talked",
+    "talking",
+    "tall",
+    "tame",
+    "tank",
+    "tap",
+    "tape",
+    "tarantino",
+    "target",
+    "tarzan",
+    "task",
+    "taste",
+    "tasteless",
+    "taught",
+    "taxi",
+    "taylor",
+    "tea",
+    "teach",
+    "teacher",
+    "teaching",
+    "team",
+    "tear",
+    "technical",
+    "technically",
+    "technique",
+    "technology",
+    "ted",
+    "tedious",
+    "teen",
+    "teenage",
+    "teenager",
+    "teeth",
+    "television",
+    "tell",
+    "telling",
+    "temple",
+    "ten",
+    "tend",
+    "tendency",
+    "tender",
+    "tends",
+    "tense",
+    "tension",
+    "term",
+    "terrible",
+    "terribly",
+    "terrific",
+    "terrifying",
+    "territory",
+    "terror",
+    "terrorist",
+    "terry",
+    "test",
+    "testament",
+    "texas",
+    "text",
+    "th",
+    "thank",
+    "thankfully",
+    "thanks",
+    "thatbr",
+    "thats",
+    "theater",
+    "theatre",
+    "theatrical",
+    "thembr",
+    "theme",
+    "theory",
+    "there",
+    "therebr",
+    "therefore",
+    "theyd",
+    "theyll",
+    "theyre",
+    "theyve",
+    "thick",
+    "thief",
+    "thin",
+    "thing",
+    "thingbr",
+    "think",
+    "thinking",
+    "third",
+    "thirty",
+    "thisbr",
+    "thomas",
+    "thompson",
+    "thoroughly",
+    "though",
+    "thought",
+    "thoughtful",
+    "thoughtprovoking",
+    "thousand",
+    "thread",
+    "threat",
+    "threatening",
+    "threatens",
+    "three",
+    "threw",
+    "thrill",
+    "thriller",
+    "thrilling",
+    "throat",
+    "throughout",
+    "throw",
+    "throwing",
+    "thrown",
+    "thru",
+    "thug",
+    "thumb",
+    "thus",
+    "ticket",
+    "tie",
+    "tied",
+    "tiger",
+    "tight",
+    "till",
+    "tim",
+    "time",
+    "timebr",
+    "timeless",
+    "timesbr",
+    "timing",
+    "timothy",
+    "tiny",
+    "tip",
+    "tired",
+    "tiresome",
+    "titanic",
+    "title",
+    "titled",
+    "tobr",
+    "today",
+    "todd",
+    "together",
+    "toilet",
+    "told",
+    "tom",
+    "tomato",
+    "tommy",
+    "tomorrow",
+    "ton",
+    "tone",
+    "tongue",
+    "tonight",
+    "tony",
+    "toobr",
+    "took",
+    "tool",
+    "top",
+    "topic",
+    "topless",
+    "topnotch",
+    "torn",
+    "torture",
+    "tortured",
+    "total",
+    "totally",
+    "touch",
+    "touched",
+    "touching",
+    "tough",
+    "tour",
+    "tourist",
+    "toward",
+    "towards",
+    "tower",
+    "town",
+    "toy",
+    "trace",
+    "track",
+    "tracking",
+    "tracy",
+    "trade",
+    "trademark",
+    "tradition",
+    "traditional",
+    "traffic",
+    "tragedy",
+    "tragic",
+    "trail",
+    "trailer",
+    "train",
+    "trained",
+    "training",
+    "trait",
+    "tramp",
+    "transfer",
+    "transformation",
+    "transformed",
+    "transition",
+    "translation",
+    "trap",
+    "trapped",
+    "trash",
+    "trashy",
+    "travel",
+    "traveling",
+    "travesty",
+    "treasure",
+    "treat",
+    "treated",
+    "treatment",
+    "tree",
+    "trek",
+    "tremendous",
+    "trend",
+    "trial",
+    "triangle",
+    "tribe",
+    "tribute",
+    "trick",
+    "tried",
+    "trilogy",
+    "trio",
+    "trip",
+    "tripe",
+    "trite",
+    "triumph",
+    "troma",
+    "troop",
+    "trouble",
+    "troubled",
+    "truck",
+    "true",
+    "truly",
+    "trust",
+    "truth",
+    "try",
+    "trying",
+    "tube",
+    "tune",
+    "tunnel",
+    "turkey",
+    "turkish",
+    "turn",
+    "turned",
+    "turner",
+    "turning",
+    "tv",
+    "twelve",
+    "twenty",
+    "twice",
+    "twilight",
+    "twin",
+    "twist",
+    "twisted",
+    "two",
+    "tyler",
+    "type",
+    "typical",
+    "typically",
+    "ugly",
+    "uk",
+    "ultimate",
+    "ultimately",
+    "unable",
+    "unaware",
+    "unbearable",
+    "unbelievable",
+    "unbelievably",
+    "uncle",
+    "uncomfortable",
+    "unconvincing",
+    "undead",
+    "underground",
+    "underlying",
+    "underneath",
+    "underrated",
+    "understand",
+    "understandable",
+    "understanding",
+    "understated",
+    "understood",
+    "underwater",
+    "underworld",
+    "undoubtedly",
+    "uneven",
+    "unexpected",
+    "unexpectedly",
+    "unfair",
+    "unfold",
+    "unfolds",
+    "unforgettable",
+    "unfortunate",
+    "unfortunately",
+    "unfunny",
+    "unhappy",
+    "uniform",
+    "uninspired",
+    "unintentional",
+    "unintentionally",
+    "uninteresting",
+    "union",
+    "unique",
+    "unit",
+    "united",
+    "universal",
+    "universe",
+    "university",
+    "unknown",
+    "unless",
+    "unlikable",
+    "unlike",
+    "unlikeable",
+    "unlikely",
+    "unnecessary",
+    "unoriginal",
+    "unpleasant",
+    "unpredictable",
+    "unreal",
+    "unrealistic",
+    "unseen",
+    "unsettling",
+    "unusual",
+    "unwatchable",
+    "upbr",
+    "uplifting",
+    "upon",
+    "upper",
+    "ups",
+    "upset",
+    "urban",
+    "urge",
+    "us",
+    "usa",
+    "use",
+    "used",
+    "useful",
+    "useless",
+    "user",
+    "using",
+    "usual",
+    "usually",
+    "utter",
+    "utterly",
+    "uwe",
+    "vacation",
+    "vague",
+    "vaguely",
+    "valentine",
+    "valley",
+    "valuable",
+    "value",
+    "vampire",
+    "van",
+    "variation",
+    "variety",
+    "various",
+    "vast",
+    "vega",
+    "vehicle",
+    "vein",
+    "velvet",
+    "vengeance",
+    "venice",
+    "venture",
+    "version",
+    "versus",
+    "veteran",
+    "vhs",
+    "via",
+    "vice",
+    "vicious",
+    "victim",
+    "victor",
+    "victoria",
+    "victory",
+    "video",
+    "vietnam",
+    "view",
+    "viewed",
+    "viewer",
+    "viewing",
+    "viewpoint",
+    "village",
+    "villain",
+    "vince",
+    "vincent",
+    "violence",
+    "violent",
+    "virgin",
+    "virginia",
+    "virtual",
+    "virtually",
+    "virus",
+    "visible",
+    "vision",
+    "visit",
+    "visiting",
+    "visual",
+    "visually",
+    "visuals",
+    "vivid",
+    "vocal",
+    "voice",
+    "voiced",
+    "voiceover",
+    "voight",
+    "volume",
+    "von",
+    "vote",
+    "voyage",
+    "vulnerable",
+    "wacky",
+    "wagner",
+    "wagon",
+    "wait",
+    "waited",
+    "waiting",
+    "wake",
+    "walk",
+    "walked",
+    "walken",
+    "walker",
+    "walking",
+    "wall",
+    "wallace",
+    "walter",
+    "wan",
+    "wandering",
+    "wannabe",
+    "want",
+    "wanted",
+    "wanting",
+    "war",
+    "ward",
+    "wardrobe",
+    "warm",
+    "warmth",
+    "warn",
+    "warned",
+    "warner",
+    "warning",
+    "warren",
+    "warrior",
+    "wasbr",
+    "washington",
+    "wasnt",
+    "waste",
+    "wasted",
+    "wasting",
+    "watch",
+    "watchable",
+    "watchbr",
+    "watched",
+    "watching",
+    "water",
+    "watson",
+    "wave",
+    "wax",
+    "way",
+    "waybr",
+    "wayne",
+    "weak",
+    "weakest",
+    "weakness",
+    "wealth",
+    "wealthy",
+    "weapon",
+    "wear",
+    "wearing",
+    "weather",
+    "web",
+    "website",
+    "wed",
+    "wedding",
+    "week",
+    "weekend",
+    "weight",
+    "weird",
+    "welcome",
+    "well",
+    "wellbr",
+    "welles",
+    "wellknown",
+    "went",
+    "werent",
+    "werewolf",
+    "wes",
+    "west",
+    "western",
+    "wet",
+    "weve",
+    "whale",
+    "whatever",
+    "whats",
+    "whatsoever",
+    "wheel",
+    "whenever",
+    "whereas",
+    "wheres",
+    "whether",
+    "whilst",
+    "white",
+    "who",
+    "whoever",
+    "whole",
+    "wholly",
+    "whore",
+    "whose",
+    "wicked",
+    "wide",
+    "widely",
+    "widescreen",
+    "widmark",
+    "widow",
+    "wife",
+    "wig",
+    "wild",
+    "wilder",
+    "wildly",
+    "william",
+    "williams",
+    "willie",
+    "willing",
+    "willis",
+    "wilson",
+    "win",
+    "wind",
+    "window",
+    "wine",
+    "wing",
+    "winner",
+    "winning",
+    "winter",
+    "wire",
+    "wisdom",
+    "wise",
+    "wish",
+    "wished",
+    "wishing",
+    "wit",
+    "witch",
+    "withbr",
+    "within",
+    "without",
+    "witness",
+    "witnessed",
+    "witty",
+    "wizard",
+    "wolf",
+    "woman",
+    "womens",
+    "wonder",
+    "wondered",
+    "wonderful",
+    "wonderfully",
+    "wondering",
+    "wong",
+    "wont",
+    "woo",
+    "wood",
+    "wooden",
+    "woody",
+    "word",
+    "wore",
+    "work",
+    "workbr",
+    "worked",
+    "worker",
+    "working",
+    "world",
+    "worldbr",
+    "worn",
+    "worried",
+    "worry",
+    "worse",
+    "worst",
+    "worth",
+    "worthless",
+    "worthwhile",
+    "worthy",
+    "would",
+    "wouldbe",
+    "wouldnt",
+    "wouldve",
+    "wound",
+    "wounded",
+    "wow",
+    "wrap",
+    "wrapped",
+    "wreck",
+    "wrestling",
+    "write",
+    "writer",
+    "writerdirector",
+    "writes",
+    "writing",
+    "written",
+    "wrong",
+    "wrongbr",
+    "wrote",
+    "ww",
+    "wwii",
+    "ya",
+    "yard",
+    "yeah",
+    "year",
+    "yearold",
+    "yearsbr",
+    "yell",
+    "yelling",
+    "yellow",
+    "yes",
+    "yesterday",
+    "yet",
+    "york",
+    "youbr",
+    "youd",
+    "youll",
+    "young",
+    "younger",
+    "youre",
+    "youth",
+    "youve",
+    "zero",
+    "zombie",
+    "zone"
+  ],
+  "max_features": 5000,
+  "lr_accuracy": 0.8847,
+  "nb_accuracy": 0.852,
+  "training_samples": 40000,
+  "test_samples": 10000,
+  "preprocessing_steps": [
+    "lowercase",
+    "remove_special_chars",
+    "tokenization",
+    "stopword_removal",
+    "lemmatization"
+  ]
+}

saved_models/naive_bayes_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65976fbe5f21a55075052bf62de3fb4e5e9d21c4bb8b8e1fd068a8c966698af
+size 160791

saved_models/tfidf_vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed2a0971c34fdaf9405735f42068e7c219cf0c87acc564f1a8da43d928b4fe6
+size 183223

sentiment_analysis.py

@@ -0,0 +1,161 @@
+import pandas as pd
+import nltk
+import re
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+import matplotlib.pyplot as plt
+import seaborn as sns
+import streamlit as st
+from collections import Counter
+
+# Download NLTK resources (run once)
+try:
+    nltk.download('punkt')
+    nltk.download('stopwords')
+    nltk.download('wordnet')
+    nltk.download('punkt_tab')
+except Exception as e:
+    print(f"Warning: Could not download NLTK data: {e}")
+    print("Please run: import nltk; nltk.download('all') in Python console")
+
+# 1. Text Preprocessing Function
+def preprocess_text(text):
+    # Lowercase
+    text = text.lower()
+    # Remove special characters and digits
+    text = re.sub(r'[^a-zA-Z\s]', '', text)
+    # Tokenize
+    tokens = word_tokenize(text)
+    # Remove stopwords
+    stop_words = set(stopwords.words('english'))
+    tokens = [word for word in tokens if word not in stop_words]
+    # Lemmatize
+    lemmatizer = WordNetLemmatizer()
+    tokens = [lemmatizer.lemmatize(word) for word in tokens]
+    # Join tokens back to string
+    return ' '.join(tokens)
+
+# 2. Load and Preprocess Dataset
+def load_and_preprocess_data(file_path="IMDB Dataset.csv"):
+    try:
+        df = pd.read_csv(file_path)
+    except FileNotFoundError:
+        print(f"Error: Could not find file '{file_path}'")
+        print("Please make sure the CSV file is in the same directory as this script.")
+        return None
+    # Apply preprocessing to reviews
+    df['cleaned_review'] = df['review'].apply(preprocess_text)
+    # Convert sentiment to binary (1 for positive, 0 for negative)
+    df['sentiment'] = df['sentiment'].replace({'positive': 1, 'negative': 0})
+    return df
+
+# 3. Train and Evaluate Models
+def train_and_evaluate(df):
+    # Convert text to TF-IDF features
+    vectorizer = TfidfVectorizer(max_features=5000)
+    X = vectorizer.fit_transform(df['cleaned_review'])
+    y = df['sentiment']
+    
+    # Split data
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    
+    # Logistic Regression
+    lr_model = LogisticRegression(max_iter=1000)
+    lr_model.fit(X_train, y_train)
+    lr_predictions = lr_model.predict(X_test)
+    lr_accuracy = accuracy_score(y_test, lr_predictions)
+    print("Logistic Regression Accuracy:", lr_accuracy)
+    print("Logistic Regression Classification Report:\n", classification_report(y_test, lr_predictions))
+    
+    # Naive Bayes
+    nb_model = MultinomialNB()
+    nb_model.fit(X_train, y_train)
+    nb_predictions = nb_model.predict(X_test)
+    nb_accuracy = accuracy_score(y_test, nb_predictions)
+    print("Naive Bayes Accuracy:", nb_accuracy)
+    print("Naive Bayes Classification Report:\n", classification_report(y_test, nb_predictions))
+    
+    return vectorizer, lr_model, nb_model, X_test, y_test
+
+# 4. Visualize Frequent Words
+def visualize_frequent_words(df):
+    # Separate positive and negative reviews
+    positive_reviews = df[df['sentiment'] == 1]['cleaned_review']
+    negative_reviews = df[df['sentiment'] == 0]['cleaned_review']
+    
+    # Count words
+    positive_words = ' '.join(positive_reviews).split()
+    negative_words = ' '.join(negative_reviews).split()
+    
+    # Get top 10 words
+    positive_freq = Counter(positive_words).most_common(10)
+    negative_freq = Counter(negative_words).most_common(10)
+    
+    # Plot
+    plt.figure(figsize=(12, 5))
+    
+    plt.subplot(1, 2, 1)
+    sns.barplot(x=[count for word, count in positive_freq], y=[word for word, count in positive_freq])
+    plt.title('Top 10 Positive Words')
+    
+    plt.subplot(1, 2, 2)
+    sns.barplot(x=[count for word, count in negative_freq], y=[word for word, count in negative_freq])
+    plt.title('Top 10 Negative Words')
+    
+    plt.tight_layout()
+    plt.savefig('word_frequency.png')
+    plt.close()
+
+# 5. Streamlit App for Model Deployment
+def run_streamlit_app(vectorizer, lr_model, nb_model):
+    st.title("IMDb Review Sentiment Analysis")
+    st.write("Enter a movie review to predict its sentiment (positive or negative).")
+    
+    # Text input
+    user_input = st.text_area("Enter your review:", "")
+    
+    if st.button("Predict Sentiment"):
+        if user_input:
+            # Preprocess input
+            cleaned_input = preprocess_text(user_input)
+            input_vector = vectorizer.transform([cleaned_input])
+            
+            # Predict with both models
+            lr_prediction = lr_model.predict(input_vector)[0]
+            lr_prob = lr_model.predict_proba(input_vector)[0]
+            nb_prediction = nb_model.predict(input_vector)[0]
+            nb_prob = nb_model.predict_proba(input_vector)[0]
+            
+            # Display results
+            st.write("### Logistic Regression Prediction")
+            st.write(f"Sentiment: {'Positive' if lr_prediction == 1 else 'Negative'}")
+            st.write(f"Confidence: {max(lr_prob):.2f}")
+            
+            st.write("### Naive Bayes Prediction")
+            st.write(f"Sentiment: {'Positive' if nb_prediction == 1 else 'Negative'}")
+            st.write(f"Confidence: {max(nb_prob):.2f}")
+        else:
+            st.write("Please enter a review.")
+
+# Main execution
+if __name__ == "__main__":
+    file_path = "IMDB Dataset.csv"
+    df = load_and_preprocess_data(file_path)
+    
+    if df is not None:
+        # Train and evaluate models
+        vectorizer, lr_model, nb_model, X_test, y_test = train_and_evaluate(df)
+        
+        # Visualize frequent words
+        visualize_frequent_words(df)
+        
+        # Run Streamlit app
+        run_streamlit_app(vectorizer, lr_model, nb_model)
+    else:
+        print("Exiting due to data loading error.")

streamlit_app.py

@@ -0,0 +1,141 @@
+import pandas as pd
+import nltk
+import re
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+import matplotlib.pyplot as plt
+import seaborn as sns
+import streamlit as st
+from collections import Counter
+import pickle
+import os
+
+# Download NLTK resources
+try:
+    nltk.download('punkt')
+    nltk.download('stopwords')
+    nltk.download('wordnet')
+    nltk.download('punkt_tab')
+except Exception as e:
+    st.error(f"Could not download NLTK data: {e}")
+
+# Text Preprocessing Function
+def preprocess_text(text):
+    # Lowercase
+    text = text.lower()
+    # Remove special characters and digits
+    text = re.sub(r'[^a-zA-Z\s]', '', text)
+    # Tokenize
+    tokens = word_tokenize(text)
+    # Remove stopwords
+    stop_words = set(stopwords.words('english'))
+    tokens = [word for word in tokens if word not in stop_words]
+    # Lemmatize
+    lemmatizer = WordNetLemmatizer()
+    tokens = [lemmatizer.lemmatize(word) for word in tokens]
+    # Join tokens back to string
+    return ' '.join(tokens)
+
+# Load and Preprocess Dataset
+def load_and_preprocess_data(file_path="IMDB Dataset.csv"):
+    try:
+        df = pd.read_csv(file_path)
+        # Apply preprocessing to reviews
+        df['cleaned_review'] = df['review'].apply(preprocess_text)
+        # Convert sentiment to binary (1 for positive, 0 for negative)
+        df['sentiment'] = df['sentiment'].replace({'positive': 1, 'negative': 0})
+        return df
+    except FileNotFoundError:
+        st.error(f"Could not find file '{file_path}'")
+        return None
+
+# Train Models
+def train_models(df):
+    # Convert text to TF-IDF features
+    vectorizer = TfidfVectorizer(max_features=5000)
+    X = vectorizer.fit_transform(df['cleaned_review'])
+    y = df['sentiment']
+    
+    # Split data
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    
+    # Logistic Regression
+    lr_model = LogisticRegression(max_iter=1000)
+    lr_model.fit(X_train, y_train)
+    lr_predictions = lr_model.predict(X_test)
+    lr_accuracy = accuracy_score(y_test, lr_predictions)
+    
+    # Naive Bayes
+    nb_model = MultinomialNB()
+    nb_model.fit(X_train, y_train)
+    nb_predictions = nb_model.predict(X_test)
+    nb_accuracy = accuracy_score(y_test, nb_predictions)
+    
+    return vectorizer, lr_model, nb_model, lr_accuracy, nb_accuracy
+
+# Streamlit App
+def main():
+    st.title("IMDb Review Sentiment Analysis")
+    st.write("This app analyzes movie reviews to predict whether they are positive or negative.")
+    
+    # Load data and train models
+    with st.spinner("Loading data and training models..."):
+        df = load_and_preprocess_data()
+        if df is not None:
+            vectorizer, lr_model, nb_model, lr_accuracy, nb_accuracy = train_models(df)
+            st.success("Models trained successfully!")
+            
+            # Display model accuracies
+            col1, col2 = st.columns(2)
+            with col1:
+                st.metric("Logistic Regression Accuracy", f"{lr_accuracy:.2%}")
+            with col2:
+                st.metric("Naive Bayes Accuracy", f"{nb_accuracy:.2%}")
+            
+            # Text input for prediction
+            st.subheader("Predict Sentiment")
+            user_input = st.text_area("Enter a movie review:", height=150)
+            
+            if st.button("Predict Sentiment"):
+                if user_input:
+                    # Preprocess input
+                    cleaned_input = preprocess_text(user_input)
+                    input_vector = vectorizer.transform([cleaned_input])
+                    
+                    # Predict with both models
+                    lr_prediction = lr_model.predict(input_vector)[0]
+                    lr_prob = lr_model.predict_proba(input_vector)[0]
+                    nb_prediction = nb_model.predict(input_vector)[0]
+                    nb_prob = nb_model.predict_proba(input_vector)[0]
+                    
+                    # Display results
+                    col1, col2 = st.columns(2)
+                    
+                    with col1:
+                        st.subheader("Logistic Regression")
+                        if lr_prediction == 1:
+                            st.success("Positive Sentiment")
+                        else:
+                            st.error("Negative Sentiment")
+                        st.write(f"Confidence: {max(lr_prob):.2%}")
+                    
+                    with col2:
+                        st.subheader("Naive Bayes")
+                        if nb_prediction == 1:
+                            st.success("Positive Sentiment")
+                        else:
+                            st.error("Negative Sentiment")
+                        st.write(f"Confidence: {max(nb_prob):.2%}")
+                else:
+                    st.warning("Please enter a review.")
+        else:
+            st.error("Failed to load data. Please check if 'IMDB Dataset.csv' is in the same directory.")
+
+if __name__ == "__main__":
+    main() 

train_and_save_model.py

@@ -0,0 +1,316 @@
+import pandas as pd
+import nltk
+import re
+import pickle
+import joblib
+import json
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+import matplotlib.pyplot as plt
+import seaborn as sns
+from collections import Counter
+import os
+
+# Download NLTK resources
+try:
+    nltk.download('punkt')
+    nltk.download('stopwords')
+    nltk.download('wordnet')
+    nltk.download('punkt_tab')
+except Exception as e:
+    print(f"Warning: Could not download NLTK data: {e}")
+
+# Text Preprocessing Function
+def preprocess_text(text):
+    # Lowercase
+    text = text.lower()
+    # Remove special characters and digits
+    text = re.sub(r'[^a-zA-Z\s]', '', text)
+    # Tokenize
+    tokens = word_tokenize(text)
+    # Remove stopwords
+    stop_words = set(stopwords.words('english'))
+    tokens = [word for word in tokens if word not in stop_words]
+    # Lemmatize
+    lemmatizer = WordNetLemmatizer()
+    tokens = [lemmatizer.lemmatize(word) for word in tokens]
+    # Join tokens back to string
+    return ' '.join(tokens)
+
+# Load and Preprocess Dataset
+def load_and_preprocess_data(file_path="IMDB Dataset.csv"):
+    try:
+        df = pd.read_csv(file_path)
+        print(f"Loaded {len(df)} reviews")
+        # Apply preprocessing to reviews
+        print("Preprocessing reviews...")
+        df['cleaned_review'] = df['review'].apply(preprocess_text)
+        # Convert sentiment to binary (1 for positive, 0 for negative)
+        df['sentiment'] = df['sentiment'].replace({'positive': 1, 'negative': 0})
+        return df
+    except FileNotFoundError:
+        print(f"Error: Could not find file '{file_path}'")
+        return None
+
+# Train Models and Save
+def train_and_save_models(df, model_dir="saved_models"):
+    # Create model directory
+    os.makedirs(model_dir, exist_ok=True)
+    
+    # Convert text to TF-IDF features
+    print("Vectorizing text data...")
+    vectorizer = TfidfVectorizer(max_features=5000)
+    X = vectorizer.fit_transform(df['cleaned_review'])
+    y = df['sentiment']
+    
+    # Split data
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    
+    # Train Logistic Regression
+    print("Training Logistic Regression...")
+    lr_model = LogisticRegression(max_iter=1000, random_state=42)
+    lr_model.fit(X_train, y_train)
+    lr_predictions = lr_model.predict(X_test)
+    lr_accuracy = accuracy_score(y_test, lr_predictions)
+    
+    # Train Naive Bayes
+    print("Training Naive Bayes...")
+    nb_model = MultinomialNB()
+    nb_model.fit(X_train, y_train)
+    nb_predictions = nb_model.predict(X_test)
+    nb_accuracy = accuracy_score(y_test, nb_predictions)
+    
+    # Save models
+    print("Saving models...")
+    
+    # Save vectorizer
+    joblib.dump(vectorizer, os.path.join(model_dir, 'tfidf_vectorizer.pkl'))
+    
+    # Save Logistic Regression model
+    joblib.dump(lr_model, os.path.join(model_dir, 'logistic_regression_model.pkl'))
+    
+    # Save Naive Bayes model
+    joblib.dump(nb_model, os.path.join(model_dir, 'naive_bayes_model.pkl'))
+    
+    # Save model metadata
+    metadata = {
+        'vectorizer_features': vectorizer.get_feature_names_out().tolist(),
+        'max_features': 5000,
+        'lr_accuracy': float(lr_accuracy),
+        'nb_accuracy': float(nb_accuracy),
+        'training_samples': X_train.shape[0],
+        'test_samples': X_test.shape[0],
+        'preprocessing_steps': [
+            'lowercase',
+            'remove_special_chars',
+            'tokenization',
+            'stopword_removal',
+            'lemmatization'
+        ]
+    }
+    
+    with open(os.path.join(model_dir, 'model_metadata.json'), 'w') as f:
+        json.dump(metadata, f, indent=2)
+    
+    # Print results
+    print("\n" + "="*50)
+    print("MODEL TRAINING RESULTS")
+    print("="*50)
+    print(f"Logistic Regression Accuracy: {lr_accuracy:.4f}")
+    print(f"Naive Bayes Accuracy: {nb_accuracy:.4f}")
+    print(f"Models saved to: {model_dir}/")
+    print("="*50)
+    
+    return vectorizer, lr_model, nb_model, lr_accuracy, nb_accuracy
+
+# Create inference script
+def create_inference_script():
+    inference_code = '''import joblib
+import json
+import re
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+
+# Download NLTK resources
+try:
+    nltk.download('punkt')
+    nltk.download('stopwords')
+    nltk.download('wordnet')
+except:
+    pass
+
+class SentimentAnalyzer:
+    def __init__(self, model_dir="saved_models"):
+        # Load models
+        self.vectorizer = joblib.load(f"{model_dir}/tfidf_vectorizer.pkl")
+        self.lr_model = joblib.load(f"{model_dir}/logistic_regression_model.pkl")
+        self.nb_model = joblib.load(f"{model_dir}/naive_bayes_model.pkl")
+        
+        # Load metadata
+        with open(f"{model_dir}/model_metadata.json", 'r') as f:
+            self.metadata = json.load(f)
+    
+    def preprocess_text(self, text):
+        # Lowercase
+        text = text.lower()
+        # Remove special characters and digits
+        text = re.sub(r'[^a-zA-Z\\s]', '', text)
+        # Tokenize
+        tokens = word_tokenize(text)
+        # Remove stopwords
+        stop_words = set(stopwords.words('english'))
+        tokens = [word for word in tokens if word not in stop_words]
+        # Lemmatize
+        lemmatizer = WordNetLemmatizer()
+        tokens = [lemmatizer.lemmatize(word) for word in tokens]
+        # Join tokens back to string
+        return ' '.join(tokens)
+    
+    def predict(self, text, model_type='both'):
+        # Preprocess text
+        cleaned_text = self.preprocess_text(text)
+        
+        # Vectorize
+        text_vector = self.vectorizer.transform([cleaned_text])
+        
+        results = {}
+        
+        if model_type in ['lr', 'both']:
+            lr_pred = self.lr_model.predict(text_vector)[0]
+            lr_prob = self.lr_model.predict_proba(text_vector)[0]
+            results['logistic_regression'] = {
+                'prediction': 'positive' if lr_pred == 1 else 'negative',
+                'confidence': float(max(lr_prob)),
+                'probabilities': {
+                    'negative': float(lr_prob[0]),
+                    'positive': float(lr_prob[1])
+                }
+            }
+        
+        if model_type in ['nb', 'both']:
+            nb_pred = self.nb_model.predict(text_vector)[0]
+            nb_prob = self.nb_model.predict_proba(text_vector)[0]
+            results['naive_bayes'] = {
+                'prediction': 'positive' if nb_pred == 1 else 'negative',
+                'confidence': float(max(nb_prob)),
+                'probabilities': {
+                    'negative': float(nb_prob[0]),
+                    'positive': float(nb_prob[1])
+                }
+            }
+        
+        return results
+
+# Example usage
+if __name__ == "__main__":
+    analyzer = SentimentAnalyzer()
+    
+    # Test with sample reviews
+    test_reviews = [
+        "This movie was absolutely fantastic! I loved every minute of it.",
+        "Terrible film, waste of time. Don't watch it.",
+        "It was okay, nothing special but not bad either."
+    ]
+    
+    for review in test_reviews:
+        print(f"\\nReview: {review}")
+        results = analyzer.predict(review)
+        for model, result in results.items():
+            print(f"{model}: {result['prediction']} (confidence: {result['confidence']:.2f})")
+'''
+    
+    with open('inference.py', 'w') as f:
+        f.write(inference_code)
+    
+    print("Created inference.py for model deployment")
+
+# Create requirements.txt
+def create_requirements():
+    requirements = '''pandas>=1.3.0
+nltk>=3.6
+scikit-learn>=1.0.0
+joblib>=1.1.0
+numpy>=1.21.0
+streamlit>=1.0.0
+matplotlib>=3.5.0
+seaborn>=0.11.0'''
+    
+    with open('requirements.txt', 'w') as f:
+        f.write(requirements)
+    
+    print("Created requirements.txt")
+
+# Create README
+def create_readme():
+    readme = '''# IMDb Sentiment Analysis Model
+
+This repository contains a trained sentiment analysis model for IMDb movie reviews.
+
+## Model Performance
+- Logistic Regression: ~88.47% accuracy
+- Naive Bayes: ~85.2% accuracy
+
+## Files
+- `saved_models/`: Directory containing trained models
+- `inference.py`: Script for making predictions
+- `train_and_save_model.py`: Script to train and save models
+- `requirements.txt`: Python dependencies
+
+## Usage
+
+### Load and Use the Model
+```python
+from inference import SentimentAnalyzer
+
+# Initialize analyzer
+analyzer = SentimentAnalyzer()
+
+# Make prediction
+result = analyzer.predict("This movie was amazing!")
+print(result)
+```
+
+### Deploy on Streamlit
+```bash
+streamlit run streamlit_deployment.py
+```
+
+## Model Details
+- **Vectorizer**: TF-IDF with 5000 features
+- **Preprocessing**: Lowercase, special char removal, tokenization, stopword removal, lemmatization
+- **Models**: Logistic Regression and Naive Bayes
+'''
+    
+    with open('README.md', 'w') as f:
+        f.write(readme)
+    
+    print("Created README.md")
+
+if __name__ == "__main__":
+    print("Training and saving sentiment analysis models...")
+    
+    # Load data
+    df = load_and_preprocess_data()
+    
+    if df is not None:
+        # Train and save models
+        train_and_save_models(df)
+        
+        # Create deployment files
+        create_inference_script()
+        create_requirements()
+        create_readme()
+        
+        print("\n✅ Model training and saving completed!")
+        print("📁 Models saved in 'saved_models/' directory")
+        print("🚀 Ready for deployment on Hugging Face, Kaggle, or other platforms")
+    else:
+        print("❌ Failed to load data. Please check if 'IMDB Dataset.csv' exists.")