Delete train.py

train.py

@@ -1,64 +0,0 @@
-import pandas as pd
-import torch
-import re
-from datasets import Dataset
-from transformers import (
-    AutoModelForTokenClassification,
-    AutoTokenizer,
-    Trainer,
-    TrainingArguments,
-    DataCollatorForTokenClassification,
-)
-from huggingface_hub import notebook_login
-
-# Login to Hugging Face Hub (Make sure your Space is set to private if needed)
-notebook_login()
-
-# Step 1: Load Luxury Fashion Dataset (Replace with actual dataset)
-df = pd.read_csv("luxury_apparel_data.csv")  # Update with correct dataset file
-
-# Keep only relevant columns
-df = df[['brand', 'category', 'description', 'price']].dropna()
-
-# Generate search queries from dataset
-df['query'] = df.apply(lambda x: f"{x['brand']} {x['category']} under {x['price']} AED", axis=1)
-
-# Step 2: Tokenization
-model_name = "dslim/bert-base-NER"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-def tokenize_batch(batch):
-    return tokenizer(batch['query'], padding=True, truncation=True)
-
-# Convert dataframe into Hugging Face dataset
-hf_dataset = Dataset.from_pandas(df[['query']])
-hf_dataset = hf_dataset.map(tokenize_batch, batched=True)
-
-# Step 3: Fine-tune the Pretrained NER Model
-model = AutoModelForTokenClassification.from_pretrained(model_name)
-
-training_args = TrainingArguments(
-    output_dir="./luxury_ner_model",
-    evaluation_strategy="epoch",
-    save_strategy="epoch",
-    per_device_train_batch_size=8,
-    per_device_eval_batch_size=8,
-    num_train_epochs=3,
-    logging_dir="./logs",
-    logging_steps=500,
-)
-
-trainer = Trainer(
-    model=model,
-    args=training_args,
-    train_dataset=hf_dataset,
-    eval_dataset=hf_dataset,
-    tokenizer=tokenizer,
-    data_collator=DataCollatorForTokenClassification(tokenizer),
-)
-
-trainer.train()
-
-# Save model to Hugging Face Hub
-model.push_to_hub("luxury-fashion-ner")
-tokenizer.push_to_hub("luxury-fashion-ner")