Views
No views yet
Maheentouqeer1/glycocare-glucose-regression
Version: 1.0portion_grams – from portion estimator (YOLO + MiDaS)pre_meal_glucoseage, weight_kg, diabetes_type, medication_flag, activity_level, time_of_daymaster_food_items.csv:
cal_per_100g, carbs_g_per_100g, protein_g_per_100g, fat_g_per_100g, gi, density_g_per_mlpostprandial_glucose_delta – predicted change in glucose level (mg/dL)meal_training_data.csv (synthetic meal-level data generated using master food metadata)master_food_items.csv (61 Pakistani dishes with nutrition, GI, density, and disease labels)| File | Description |
|---|---|
glucose_regression_model.pkl | Trained RandomForest regression model |
meal_training_data.csv | Training dataset (synthetic) |
master_food_items.csv | Master nutrition + disease metadata |
glucose_predictor.py | Loader and inference script |
1from huggingface_hub import hf_hub_download
2import joblib, pandas as pd
3
4# Load model
5model_path = hf_hub_download(repo_id="Maheentouqeer1/glycocare-glucose-regression", filename="glucose_regression_model.pkl")
6model = joblib.load(model_path)
7
8# Predict glucose change
9sample = {
10 "portion_grams": 300,
11 "pre_meal_glucose": 110,
12 "age": 35,
13 "weight_kg": 70,
14 "diabetes_type": 2,
15 "medication_flag": 1,
16 "activity_level": "moderate",
17 "time_of_day": "lunch",
18 "cal_per_100g": 160,
19 "carbs_g_per_100g": 28,
20 "protein_g_per_100g": 12,
21 "fat_g_per_100g": 5,
22 "gi": 65,
23 "density_g_per_ml": 0.96
24}
25prediction = model.predict(pd.DataFrame([sample]))
26print("Predicted glucose delta:", round(prediction[0], 2), "mg/dL")