Upload 6 files

Dockerfile.py

@@ -0,0 +1,20 @@
+# Use a lightweight Python version
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from your computer to the container
+COPY . /app
+
+# Install the required libraries
+RUN pip install flask pandas scikit-learn nltk joblib
+
+# Download NLTK data inside the container so it doesn't fail
+RUN python -m nltk.downloader stopwords wordnet punkt punkt_tab
+
+# Expose Port 5000 so we can access the app
+EXPOSE 5000
+
+# Command to run the app when the container starts
+CMD ["python", "app.py"]

Readme.md

@@ -0,0 +1,18 @@
+# Sentiment Analysis API 🚀
+
+## Project Overview
+This is a containerized Flask API that predicts the sentiment (Positive/Negative) of consumer reviews using a Logistic Regression model trained on scraped e-commerce data.
+
+## 📂 Project Structure
+- `app.py`: Main Flask application code.
+- `Dockerfile`: Configuration to build the Docker image.
+- `requirements.txt`: List of dependencies.
+- `sentiment_model.pkl`: The trained ML model.
+- `tfidf_vectorizer.pkl`: The TF-IDF vectorizer.
+
+## 🛠️ How to Run (Docker)
+
+### 1. Build the Image
+Run this command in the terminal inside the project folder:
+```bash
+docker build -t sentiment-app .

app.py

@@ -0,0 +1,77 @@
+from flask import Flask, request, jsonify
+import joblib
+import string
+import nltk
+import os
+
+# Initialize App
+app = Flask(__name__)
+
+# --- ROBUST NLTK SETUP ---
+# Set NLTK data path to a local folder to avoid permission issues
+nltk_data_dir = os.path.join(os.getcwd(), 'nltk_data')
+nltk.data.path.append(nltk_data_dir)
+
+def download_nltk_resources():
+    resources = ['stopwords', 'wordnet', 'punkt', 'punkt_tab']
+    for res in resources:
+        try:
+            nltk.data.find(f'corpora/{res}')
+        except LookupError:
+            try:
+                nltk.data.find(f'tokenizers/{res}')
+            except LookupError:
+                print(f"Downloading {res}...")
+                nltk.download(res, download_dir=nltk_data_dir, quiet=True)
+
+download_nltk_resources()
+from nltk.stem import WordNetLemmatizer
+from nltk.corpus import stopwords
+# -------------------------
+
+# Load Model
+print("Loading model...")
+try:
+    model = joblib.load('sentiment_model.pkl')
+    vectorizer = joblib.load('tfidf_vectorizer.pkl')
+    print("Model loaded successfully.")
+except Exception as e:
+    print(f"CRITICAL ERROR: Could not load model files. {e}")
+    model = None
+
+lemmatizer = WordNetLemmatizer()
+stop_words = set(stopwords.words('english'))
+
+def preprocess_text(text):
+    if not isinstance(text, str): return ""
+    text = text.lower()
+    text = text.translate(str.maketrans('', '', string.punctuation))
+    tokens = nltk.word_tokenize(text)
+    clean_tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in stop_words]
+    return " ".join(clean_tokens)
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    if model is None:
+        return jsonify({'error': 'Model not loaded properly.'}), 500
+        
+    try:
+        data = request.get_json()
+        if not data or 'review_text' not in data:
+            return jsonify({'error': 'No review_text provided'}), 400
+            
+        text = data['review_text']
+        clean_text = preprocess_text(text)
+        vectorized_text = vectorizer.transform([clean_text])
+        prediction = model.predict(vectorized_text)[0]
+        
+        return jsonify({
+            'review': text, 
+            'sentiment': "Positive" if prediction == 1 else "Negative"
+        })
+    except Exception as e:
+        print(f"Prediction Error: {e}")
+        return jsonify({'error': str(e)}), 500
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000)

requirements.txt

@@ -0,0 +1,5 @@
+flask
+pandas
+scikit-learn
+nltk
+joblib

sentiment_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205d99a64d43df3e22cf9f02a2f9afe65c05ba67f7ebc87ef0b8fbdf406414ef
+size 80731

tfidf_vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac38e1855742e25a57a1a19aa77356ec818c797263e863330f87b3ff9e0ed0d0
+size 415129