AroshN/priority_classif_xgb

Vehicle Maintenance Ticket Priority Classifier

Classifies vehicle maintenance issues as Low, Medium, or High priority using an XGBoost model.

REST API

Send a POST request to /predict:

curl -X POST "https://<your-hf-username>-vehicle-priority-classifier.hf.space/predict" \
  -H "Content-Type: application/json" \
  -d '{"issue_text": "Brakes are making a grinding noise"}'

Response:

{"priority": "High"}

UI

Visit /ui for the interactive Gradio interface.

/--- language: - en tags: - xgboost - tabular-classification - priority-prediction - machine-learning license: mit pipeline_tag: tabular-classification

Task Priority Classifier (XGBoost)

Model Description

This model predicts the priority level (e.g., Low, Medium, High) of tasks or tickets based on input attributes such as urgency, category, estimated effort, and deadlines. It was trained using XGBoost.

• Model Type: Gradient Boosted Decision Trees (XGBoost)
• Task: Multi-class / Tabular Classification
• Framework: XGBoost / Scikit-Learn

Intended Uses & Limitations

• Intended Use: Assisting productivity applications, project management tools, or ticketing systems in auto-assigning task priorities.
• Limitations: Performance depends on the distribution of task attributes. Extreme outliers or missing values should be handled prior to inference.

How to Use

You can load and run inference with this model using Python:

import joblib
import pandas as pd
from huggingface_hub import hf_hub_download

# Download model file from Hugging Face Hub (change filename to match your file: model.joblib / model.json / model.pkl)
model_path = hf_hub_download(repo_id="AroshN/priority_classif_xgb", filename="model.joblib")
model = joblib.load(model_path)

# Example sample input
sample_data = pd.DataFrame([{
    "urgency": 3,
    "estimated_hours": 4.5,
    "days_until_due": 2,
    "category": 1
}])

# Predict priority
prediction = model.predict(sample_data)
print(f"Predicted Priority: {prediction[0]}")