Downloads · 30 days
0
engine-predictive-maintenance-model
debasishdas1985/engine-predictive-maintenance-model
engine-predictive-maintenance-model is a tabular classification model from debasishdas1985. Use it for the tabular classification task on the model card, and read the license before you ship it in a product. It is set up for scikit-learn. The card lists the license as mit.
Binary classifier predicting whether an engine requires maintenance (enginecondition = 1) based on six sensor readings (RPM, lub-oil pressure/temp, fuel pressure, coolant pressure/temp).
Access
Public
Updated May 31, 2026
Repo size
1.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.joblib1.3 MB · 100%
At a glance
- Task
- Tabular Classification
- Library
- scikit-learn
- License
- mit
- Access
- Public
- Created
- May 16, 2026
- Updated
- May 31, 2026
- SHA
- 1f9c4224
Model card
From the Hugging Face model README
Engine Predictive Maintenance — XGBoost Classifier
Binary classifier predicting whether an engine requires maintenance (engine_condition = 1)
based on six sensor readings (RPM, lub-oil pressure/temp, fuel pressure,
coolant pressure/temp).
Usage
import joblib, pandas as pd
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="debasishdas1985/engine-predictive-maintenance-model", filename="best_engine_model.joblib")
model = joblib.load(path)
sample = pd.DataFrame([{
"engine_rpm": 700, "lub_oil_pressure": 2.5, "fuel_pressure": 11.8,
"coolant_pressure": 3.2, "lub_oil_temp": 84.1, "coolant_temp": 81.6,
}])
print(model.predict(sample), model.predict_proba(sample))
Best hyperparameters
{'colsample_bytree': 1.0, 'learning_rate': 0.1, 'max_depth': 7, 'n_estimators': 200, 'subsample': 0.8}
Test metrics
| metric | value |
|---|---|
| accuracy | 0.6330 |
| precision | 0.7323 |
| recall | 0.6585 |
| f1-score | 0.6935 |
| ROC-AUC | 0.6792 |
- Task
- Tabular Classification
- Library
- scikit-learn
- License
- mit
- Created
- May 16, 2026
- Updated
- May 31, 2026