Upload 3 files

README.txt

@@ -0,0 +1,31 @@
+# Queue Prediction Model API
+
+This API predicts the appropriate queue for support tickets based on their title and description.
+
+## API Endpoints
+
+### POST /predict
+
+Predicts the queue for a ticket based on its title and description.
+
+#### Input Format:
+```json
+{
+    "title": "string",
+    "description": "string"
+}
+```
+
+#### Output Format:
+```json
+{
+    "predicted_queue": "string",
+    "confidence": float,
+    "top_3_predictions": [
+        {
+            "queue": "string",
+            "probability": float
+        }
+    ]
+}
+```

app.py

@@ -0,0 +1,91 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import joblib
+import pandas as pd
+from typing import Optional
+import uvicorn
+
+# Load the model and label encoder
+model, label_encoder = joblib.load('queue_prediction_model.joblib')
+
+app = FastAPI(title="Queue Prediction API")
+
+class TicketInput(BaseModel):
+    title: str
+    description: str
+
+class TicketPrediction(BaseModel):
+    predicted_queue: str
+    confidence: float
+    top_3_predictions: list
+
+# Copy your helper functions
+def clean_text(text):
+    if pd.isna(text):
+        return ""
+    text = str(text)
+    text = re.sub(r'\S+@\S+', 'EMAIL', text)
+    text = re.sub(r'\b(?:\d{1,3}\.){3}\d{1,3}\b', 'IP_ADDRESS', text)
+    text = re.sub(r'\d{1,2}/\d{1,2}/\d{4}', 'DATE', text)
+    text = re.sub(r'\b\d+\b', 'NUM', text)
+    text = text.lower()
+    return text
+
+def extract_features(df):
+    # Copy your extract_features function here
+    # (The same function from your original code)
+    pass
+
+@app.post("/predict", response_model=TicketPrediction)
+async def predict(ticket: TicketInput):
+    try:
+        # Create a DataFrame with the input data
+        sample = pd.DataFrame({
+            'Description': [ticket.description],
+            'Title': [ticket.title],
+            'Priority': ['Normal']
+        })
+
+        # Process features
+        sample_processed = extract_features(sample)
+        
+        feature_columns = [
+            'cleaned_description', 'cleaned_title', 'has_ups', 'has_battery',
+            'has_problem', 'has_ip', 'has_serial', 'is_security_related',
+            'is_network_related', 'is_programming_related', 'is_support_related',
+            'description_length', 'title_length', 'word_count', 'is_high_priority'
+        ]
+
+        X = sample_processed[feature_columns]
+
+        # Make prediction
+        prediction = model.predict(X)
+        probabilities = model.predict_proba(X)
+
+        predicted_queue = label_encoder.inverse_transform(prediction)[0]
+        confidence = float(np.max(probabilities[0]))
+
+        # Get top 3 predictions
+        top_3_idx = np.argsort(probabilities[0])[-3:][::-1]
+        top_3_predictions = [
+            {
+                "queue": queue,
+                "probability": float(prob)
+            }
+            for queue, prob in zip(
+                label_encoder.inverse_transform(top_3_idx),
+                probabilities[0][top_3_idx]
+            )
+        ]
+
+        return {
+            "predicted_queue": predicted_queue,
+            "confidence": confidence,
+            "top_3_predictions": top_3_predictions
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,8 @@
+fastapi==0.68.0
+uvicorn==0.15.0
+pydantic==1.8.2
+scikit-learn==0.24.2
+pandas==1.3.3
+numpy==1.21.2
+joblib==1.0.1
+python-multipart==0.0.5