Delete app/utils/predict_afteruse.py

app/utils/predict_afteruse.py

@@ -1,103 +0,0 @@
-import torch
-from transformers import BertTokenizer, BertForSequenceClassification
-import numpy as np
-import os
-
-HF_TOKEN = os.getenv("HF_TOKEN")
-
-# Load the pre-trained model and tokenizer
-tokenizer = BertTokenizer.from_pretrained("Maulidaaa/bert-safe-multilabel", token=HF_TOKEN)
-model = BertForSequenceClassification.from_pretrained("Maulidaaa/bert-safe-multilabel", token=HF_TOKEN)
-
-model.eval()
-
-# Efek after use (harus sesuai saat training)
-afteruse_labels = [
-    "acne fighting", "acne trigger", "anti aging", "brightening", "moisturizing",
-    "redness reducing", "skin texture", "soothing", "unknown", "whitening"
-]
-
-afteruse_descriptions_en = {
-    "acne fighting": "helps fight acne",
-    "acne trigger": "may trigger acne",
-    "anti aging": "reduces signs of aging",
-    "brightening": "brightens the skin",
-    "moisturizing": "moisturizes the skin",
-    "redness reducing": "reduces redness",
-    "skin texture": "improves skin texture",
-    "soothing": "soothes the skin",
-    "unknown": "has unknown effects",
-    "whitening": "whitens the skin"
-}
-
-def predict_after_use(input_ingredients):
-    if not input_ingredients:
-        return []
-
-    # Tokenisasi input
-    inputs = tokenizer(input_ingredients, return_tensors="pt", truncation=True, padding=True, max_length=512)
-
-    with torch.no_grad():
-        outputs = model(**inputs)
-        logits = outputs.logits
-        probs = torch.sigmoid(logits)
-
-    # Konversi probabilitas ke numpy dan ratakan
-    probs = probs.squeeze().cpu().numpy()
-    if probs.ndim == 0:
-        probs = [probs]  # Jika scalar, ubah jadi list
-
-    print(f"[DEBUG] Model output shape: {logits.shape}")
-    print(f"[DEBUG] Jumlah output model: {len(probs)} | Jumlah label: {len(afteruse_labels)}")
-
-    # Antisipasi mismatch jumlah output vs label
-    min_len = min(len(probs), len(afteruse_labels))
-    predicted_labels = [
-        afteruse_labels[i]
-        for i in range(min_len)
-        if probs[i] > 0.5
-    ]
-
-    return predicted_labels
-
-def generate_afteruse_sentence_en(predicted_labels):
-    if not predicted_labels:
-        return "No effects were detected based on the provided ingredients."
-
-    descriptions = [afteruse_descriptions_en.get(label, label) for label in predicted_labels]
-
-    if len(descriptions) == 1:
-        return f"This product {descriptions[0]}."
-    elif len(descriptions) == 2:
-        return f"This product {descriptions[0]} and {descriptions[1]}."
-    else:
-        return f"This product {', '.join(descriptions[:-1])}, and {descriptions[-1]}."
-    
-
-def predict_after_use_with_probs(input_ingredients):
-    if not input_ingredients:
-        return [], []
-
-    inputs = tokenizer(input_ingredients, return_tensors="pt", truncation=True, padding=True, max_length=512)
-
-    with torch.no_grad():
-        outputs = model(**inputs)
-        logits = outputs.logits
-        probs = torch.sigmoid(logits)
-
-    probs = probs.squeeze().cpu().numpy()
-    if probs.ndim == 0:
-        probs = [probs]
-
-    min_len = min(len(probs), len(afteruse_labels))
-    predicted_labels = [
-        afteruse_labels[i]
-        for i in range(min_len)
-        if probs[i] > 0.5
-    ]
-    label_probs = {
-        afteruse_labels[i]: float(probs[i])
-        for i in range(min_len)
-    }
-
-    return predicted_labels, label_probs