faodl/agri-soybeans-classifier

pip install transformers torch huggingface_hub pandas joblib scikit-learn xgboost sentence-transformers lightgbm

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

MODEL_ID = "faodl/agri-soybeans-classifier"

texts = [
    "Rice export prices increased after new procurement rules were announced.",
    "The finance ministry released its monthly fuel tax bulletin.",
]

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, subfolder="transformer")
model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID, subfolder="transformer")
threshold = float(getattr(model.config, "threshold", 0.5))

encoded = tokenizer(
    texts,
    truncation=True,
    padding=True,
    max_length=256,
    return_tensors="pt",
)

with torch.no_grad():
    logits = model(**encoded).logits
    probabilities = torch.softmax(logits, dim=-1)[:, 1].tolist()

for text, probability in zip(texts, probabilities):
    label = model.config.id2label[int(probability >= threshold)]
    print({"text": text, "probability_positive": probability, "label": label})

import json
import joblib
from huggingface_hub import hf_hub_download

MODEL_ID = "faodl/agri-soybeans-classifier"
BASELINE = "logistic"

texts = [
    "Maize production forecasts were revised after delayed rains.",
    "The central bank published new exchange rate statistics.",
]

model_path = hf_hub_download(
    repo_id=MODEL_ID,
    repo_type="model",
    filename=f"baselines/{BASELINE}/{BASELINE}_tfidf.joblib",
)
report_path = hf_hub_download(
    repo_id=MODEL_ID,
    repo_type="model",
    filename="report.json",
)

pipeline = joblib.load(model_path)
with open(report_path, encoding="utf-8") as handle:
    report = json.load(handle)

threshold = next(
    result["validation_best_threshold"]["threshold"]
    for result in report["results"]
    if result["model_type"] == f"{BASELINE}_tfidf"
)

probabilities = pipeline.predict_proba(texts)[:, 1]
for text, probability in zip(texts, probabilities):
    label = "RELEVANT" if probability >= threshold else "NOT_RELEVANT"
    print({"text": text, "probability_positive": float(probability), "label": label})

import joblib
from huggingface_hub import hf_hub_download
from sentence_transformers import SentenceTransformer

MODEL_ID = "faodl/agri-soybeans-classifier"
BASELINE = "embedding-logistic"

texts = [
    "Wheat export inspections rose as demand from importers increased.",
    "The sports ministry announced a new stadium renovation plan.",
]

model_path = hf_hub_download(
    repo_id=MODEL_ID,
    repo_type="model",
    filename=f"baselines/{BASELINE}/{BASELINE}.joblib",
)
artifact = joblib.load(model_path)
embedding_model = SentenceTransformer(artifact["embedding_model_name"])
embeddings = embedding_model.encode(
    texts,
    batch_size=artifact.get("embedding_batch_size", 64),
    convert_to_numpy=True,
    normalize_embeddings=artifact.get("normalize_embeddings", True),
)
probabilities = artifact["classifier"].predict_proba(embeddings)[:, 1]
threshold = artifact["validation_best_threshold"]["threshold"]

for text, probability in zip(texts, probabilities):
    label = "RELEVANT" if probability >= threshold else "NOT_RELEVANT"
    print({"text": text, "probability_positive": float(probability), "label": label})