from huggingface_hub import hf_hub_download
import joblib, numpy as np

repo = "Arko007/agromind-crop-recommendation"
model = joblib.load(hf_hub_download(repo, "crop_predict_model.pkl"))
sc = joblib.load(hf_hub_download(repo, "crop_predict_standscaler.pkl"))
ms = joblib.load(hf_hub_download(repo, "crop_predict_minmaxscaler.pkl"))

features = np.array([[50, 30, 40, 28, 65, 6.5, 200]])
pred = model.predict(sc.transform(ms.transform(features)))

Output

Library: scikit-learn
Format: joblib/pickle (.pkl)
Scalers included: StandardScaler + MinMaxScaler

Integer crop ID (1–22) mapping to: Rice, Maize, Jute, Cotton, Coconut, Papaya, Orange, Apple, Muskmelon, Watermelon, Grapes, Mango, Banana, Pomegranate, Lentil, Blackgram, Mungbean, Mothbeans, Pigeonpeas, Kidneybeans, Chickpea, Coffee.