Add model files and API implementation

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 combined_data.csv filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,74 @@
 ---
 license: mit
+tags:
+- text-classification
+- tensorflow
+- news-classification
+pipeline_tag: text-classification
+widget:
+  - text: "Enter your news headline here"
+datasets:
+- custom_news_dataset
+model-index:
+- name: news-source-classifier
+  results:
+  - task: 
+      type: text-classification
+      name: News Source Classification
+    metrics:
+      - type: accuracy
+        value: 0.82
+        name: Test Accuracy
 ---
+
+# News Source Classifier
+
+This model classifies news headlines as either Fox News or NBC News using an LSTM neural network.
+
+## Model Description
+
+- **Model Architecture**: LSTM Neural Network
+- **Input**: News headlines (text)
+- **Output**: Binary classification (Fox News vs NBC)
+- **Training Data**: Large collection of headlines from both news sources
+- **Performance**: Achieves approximately 82% accuracy on the test set
+
+## Usage
+
+You can use this model directly with a FastAPI endpoint:
+
+```python
+import requests
+
+# Make a prediction
+response = requests.post(
+    "https://your-app-url/predict",
+    json={"text": "Your news headline here"}
+)
+print(response.json())
+```
+
+Or use it locally:
+
+```python
+from transformers import pipeline
+
+classifier = pipeline("text-classification", model="your-username/news-source-classifier")
+result = classifier("Your news headline here")
+print(result)
+```
+
+## Limitations and Bias
+
+This model has been trained on news headlines from specific sources and time periods, which may introduce certain biases. Users should be aware of these limitations when using the model.
+
+## Training
+
+The model was trained using:
+- TensorFlow 2.13.0
+- LSTM architecture
+- Binary cross-entropy loss
+- Adam optimizer
+
+## License
+This project is licensed under the MIT License.

app.py

@@ -0,0 +1,57 @@
+import tensorflow as tf
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.text import tokenizer_from_json
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+import json
+import pickle
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+
+app = FastAPI(title="News Source Classifier")
+
+try:
+    model = load_model('news_classifier.h5')
+    
+    with open('tokenizer.json') as f:
+        tokenizer_data = json.load(f)
+        tokenizer = tokenizer_from_json(tokenizer_data)
+        
+    with open('vectorizer.pkl', 'rb') as f:
+        vectorizer = pickle.load(f)
+except Exception as e:
+    print(f"Error loading model: {str(e)}")
+    raise
+
+class PredictionRequest(BaseModel):
+    text: str
+
+class PredictionResponse(BaseModel):
+    source: str
+    confidence: float
+
+@app.post("/predict", response_model=PredictionResponse)
+async def predict(request: PredictionRequest):
+    try:
+        sequence = tokenizer.texts_to_sequences([request.text])
+        padded = pad_sequences(sequence, maxlen=100)
+
+        prediction = model.predict(padded)
+        confidence = float(np.max(prediction))
+        
+        predicted_class = int(np.argmax(prediction))
+        source = 'foxnews' if predicted_class == 0 else 'nbc'
+        
+        return PredictionResponse(
+            source=source,
+            confidence=confidence
+        )
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/")
+async def root():
+    return {
+        "message": "News Source Classifier API",
+        "usage": "Make a POST request to /predict with a JSON payload containing 'text' field"
+    }

news_classifier.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9258ee4d92199555974374b569634e73ad0d2b059d3b7125f3b75c2144528f4
+size 117315152

requirements.txt

@@ -0,0 +1,8 @@
+tensorflow==2.13.0
+fastapi==0.68.1
+uvicorn==0.15.0
+numpy>=1.19.2
+pydantic==1.8.2
+python-multipart==0.0.5
+scikit-learn>=0.24.2
+joblib>=1.1.0

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f470ba41cfc5aead8a050a1fdb44b35191b4c72de7703db579a668867363cf24
+size 7021963

vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c379aaf596d44439b4330c4f89e3813e734dea7867b4b5fd9065c547161e552
+size 900222