as-cle-bert/carbon-footprint-prediction

Model Trained Using AutoTrain

• Problem type: Tabular regression

Validation Metrics

• r2: 0.9900762497798218
• mse: 10317.805777253338
• mae: 74.54517527770996
• rmse: 101.57660053995377
• rmsle: 0.042811727450114016
• loss: 101.57660053995377

Best Params

• learning_rate: 0.016479102091350954
• reg_lambda: 0.3449233788687026
• reg_alpha: 3.244557908377455e-07
• subsample: 0.5379679408548034
• colsample_bytree: 0.9050706969365716
• max_depth: 4
• early_stopping_rounds: 293
• n_estimators: 7000
• eval_metric: rmse

Usage

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