|
|
|
|
|
--- |
|
|
tags: |
|
|
- autotrain |
|
|
- tabular |
|
|
- regression |
|
|
- tabular-regression |
|
|
datasets: |
|
|
- Notaspy1234/autotrain-data-Autotrain3 |
|
|
--- |
|
|
|
|
|
# Model Trained Using AutoTrain |
|
|
|
|
|
- Problem type: Tabular regression |
|
|
|
|
|
## Validation Metrics |
|
|
|
|
|
- r2: 0.9753017864826334 |
|
|
- mse: 0.3290419495851166 |
|
|
- mae: 0.47130432128906286 |
|
|
- rmse: 0.5736217826975512 |
|
|
- rmsle: 0.057378419858521094 |
|
|
- loss: 0.5736217826975512 |
|
|
|
|
|
## Best Params |
|
|
|
|
|
- learning_rate: 0.022993157585548683 |
|
|
- reg_lambda: 0.0030417803769039035 |
|
|
- reg_alpha: 0.17755049688249555 |
|
|
- subsample: 0.33171622212758833 |
|
|
- colsample_bytree: 0.10545502763287017 |
|
|
- max_depth: 8 |
|
|
- early_stopping_rounds: 387 |
|
|
- n_estimators: 15000 |
|
|
- eval_metric: rmse |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
import json |
|
|
import joblib |
|
|
import pandas as pd |
|
|
|
|
|
model = joblib.load('model.joblib') |
|
|
config = json.load(open('config.json')) |
|
|
|
|
|
features = config['features'] |
|
|
|
|
|
# data = pd.read_csv("data.csv") |
|
|
data = data[features] |
|
|
|
|
|
predictions = model.predict(data) # or model.predict_proba(data) |
|
|
|
|
|
# predictions can be converted to original labels using label_encoders.pkl |
|
|
|
|
|
``` |
|
|
|
