Create app.py

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+import pandas as pd
+from transformers import BertForSequenceClassification, Trainer, TrainingArguments, BertTokenizer
+from datasets import Dataset
+from huggingface_hub import HfApi
+
+class CSVTrainer:
+    def __init__(self):
+        self.csv_files = []
+        self.model_dir = "./Personal"
+        self.repo_id = "luohoa97/PersonalBot-o"
+
+    def upload_and_train(self, csv_files):
+        if not csv_files:
+            return "Please upload at least one CSV file."
+
+        dataframes = [pd.read_csv(file.name) for file in csv_files]
+        combined_df = pd.concat(dataframes, ignore_index=True)
+        
+        combined_df['text'] = combined_df.apply(lambda row: f"{row['Event']} in {row['Location']} on {row['Date']}, {row['Time']}", axis=1)
+        combined_df['labels'] = pd.factorize(combined_df['Category'])[0]
+        
+        dataset = Dataset.from_pandas(combined_df[['text', 'labels']])
+        tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+
+        def tokenize_function(examples):
+            return tokenizer(examples['text'], padding='max_length', truncation=True)
+
+        tokenized_datasets = dataset.map(tokenize_function, batched=True)
+        tokenized_datasets.set_format("torch", columns=['input_ids', 'attention_mask', 'labels'])
+
+        model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=len(combined_df['labels'].unique()))
+
+        training_args = TrainingArguments(
+            output_dir='./results',
+            num_train_epochs=3,
+            per_device_train_batch_size=16,
+            per_device_eval_batch_size=64,
+            warmup_steps=500,
+            weight_decay=0.01,
+            logging_dir='./logs',
+            logging_steps=10,
+            evaluation_strategy="epoch",
+            save_strategy="epoch"
+        )
+
+        trainer = Trainer(
+            model=model,
+            args=training_args,
+            train_dataset=tokenized_datasets,
+            eval_dataset=tokenized_datasets
+        )
+
+        trainer.train()
+        model.save_pretrained(self.model_dir)
+        self.upload_to_huggingface()
+
+        return "Model uploaded to Hugging Face successfully!"
+
+    def upload_to_huggingface(self):
+        api = HfApi()
+        try:
+            api.create_repo(repo_id=self.repo_id)
+        except Exception as e:
+            print(f"Repo creation failed: {e}")
+        model = BertForSequenceClassification.from_pretrained(self.model_dir)
+        model.push_to_hub(self.repo_id)
+
+trainer = CSVTrainer()
+
+def gradio_interface(file):
+    return trainer.upload_and_train(file)
+
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs=gr.inputs.File(label="Upload CSV Files", type="file", multiple=True),
+    outputs="text",
+    title="CSV Trainer",
+    description="Upload CSV files for training a BERT model."
+)
+
+iface.launch()