Update app.py

app.py

@@ -1,48 +1,16 @@
-from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments
-from datasets import pandas, Dataset
-import csv
+import streamlit as st
+import gradio as gr
+from transformers import pipeline
+pipe = pipeline ('sentiment-analysis')
+text = st.text_area('enter some text!')
+def predict_sentiment(text):
+    result = pipe(text)[0]
+    return result['label']
 
-# Read requirements.txt file
-with open('requirements.txt', 'r') as req_file:
-    requirements = req_file.read().splitlines
 
-for requirement in requirements:
-     ('pip install --use-feature=build-backend')
+iface = gr.Interface(fn=predict_sentiment, inputs="text", outputs="text")
+iface.launch()
 
-    
-# Load and preprocess the IMDB dataset from CSV
-preprocessed_data = []
-with open('IMDB Dataset.csv', 'r') as csv_file:
-    csv_reader = csv.DictReader(csv_file)
-    for row in csv_reader:
-        text = row['review']
-        label = row['sentiment']
-        preprocessed_entry = {
-            'text': text,
-            'label': label
-        }
-        preprocessed_data.append(preprocessed_entry)
 
-# Convert the preprocessed data to a pandas DataFrame
-df = pandas.DataFrame(preprocessed_data)
 
-# Convert the DataFrame to a datasets dataset
-dataset = Dataset.from_pandas(df)
-
-# Tokenize the dataset
-tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-560m")
-def tokenize_function(examples):
-    return tokenizer(examples["text"], padding="max_length", truncation=True)
-
-tokenized_datasets = dataset.map(tokenize_function, batched=True)
-
-# Fine-tune the Bloom model
-model = AutoModelForSequenceClassification.from_pretrained("bigscience/bloom-560m", num_labels=2)
-
-training_args = TrainingArguments(output_dir="test_trainer")
-
-import numpy as np
-import evaluate
-
-metric = evaluate.load("accuracy")