Create app.py

app.py

@@ -0,0 +1,118 @@
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForSequenceClassification, TextClassificationPipeline
+import torch
+import gradio as gr
+from openpyxl import load_workbook
+from numpy import mean
+
+# Load tokenizers and models
+tokenizer = AutoTokenizer.from_pretrained("suriya7/bart-finetuned-text-summarization")
+model = AutoModelForSeq2SeqLM.from_pretrained("suriya7/bart-finetuned-text-summarization")
+
+tokenizer_keywords = AutoTokenizer.from_pretrained("transformer3/H2-keywordextractor")
+model_keywords = AutoModelForSeq2SeqLM.from_pretrained("transformer3/H2-keywordextractor")
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+new_model = AutoModelForSequenceClassification.from_pretrained('roberta-rating')
+new_tokenizer = AutoTokenizer.from_pretrained('roberta-rating')
+
+classifier = TextClassificationPipeline(model=new_model, tokenizer=new_tokenizer, device=device)
+
+label_mapping = {1: '1/5', 2: '2/5', 3: '3/5', 4: '4/5', 5: '5/5'}
+
+# Function to parse Excel file
+def parse_xl(file_path):
+    cells = []
+
+    workbook = load_workbook(filename=file_path)
+    for sheet in workbook.worksheets:
+        for row in sheet.iter_rows():
+            for cell in row:
+                if cell.value != None:
+                    cells.append(cell.value)
+
+    return cells
+
+# Function to evaluate reviews from Excel file
+def evaluate(file):
+    reviews = parse_xl(file)
+    ratings = []
+    text = ""
+    sentiments = []
+
+    for review in reviews:
+        rating = int(classifier(review)[0]['label'].split('_')[1])
+        ratings.append(rating)
+        text += review
+        text += " "
+        
+        sentiment = classifier(review)[0]['label']
+        sentiment_label = "Positive" if sentiment == "LABEL_4" or sentiment == "LABEL_5" else "Negative" if sentiment == "LABEL_1" or sentiment == "LABEL_2" else "Neutral"
+        sentiments.append(sentiment_label)
+    
+    overall_sentiment = "Positive" if sentiments.count("Positive") > sentiments.count("Negative") else "Negative" if sentiments.count("Negative") > sentiments.count("Positive") else "Neutral"
+            
+    inputs = tokenizer([text], max_length=1024, truncation=True, return_tensors="pt")
+    summary_ids = model.generate(inputs["input_ids"], num_beams=2, min_length=10, max_length=50)
+    summary = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+
+    # Modify the summary to third person
+    summary = summary.replace("I", "He/She").replace("my", "his/her").replace("me", "him/her")
+
+    inputs_keywords = tokenizer_keywords([text], max_length=1024, truncation=True, return_tensors="pt")
+    summary_ids_keywords = model_keywords.generate(inputs_keywords["input_ids"], num_beams=2, min_length=0, max_length=100)
+    keywords = tokenizer_keywords.batch_decode(summary_ids_keywords, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]   
+
+    return round(mean(ratings), 2), summary, keywords, overall_sentiment
+
+# Function to test a single text input
+def test_area(text):
+    inputs = tokenizer([text], max_length=1024, truncation=True, return_tensors="pt")
+    summary_ids = model.generate(inputs["input_ids"], num_beams=2, min_length=10, max_length=50)
+    summary = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+
+    # Modify the summary to third person
+    summary = summary.replace("I", "He/She").replace("my", "his/her").replace("me", "him/her")
+
+    inputs_keywords = tokenizer_keywords([text], max_length=1024, truncation=True, return_tensors="pt")
+    summary_ids_keywords = model_keywords.generate(inputs_keywords["input_ids"], num_beams=2, min_length=0, max_length=100)
+    keywords = tokenizer_keywords.batch_decode(summary_ids_keywords, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]   
+
+    sentiment = classifier(text)[0]['label']
+    sentiment_label = "Positive" if sentiment == "LABEL_4" or sentiment == "LABEL_5" else "Negative" if sentiment == "LABEL_1" or sentiment == "LABEL_2" else "Neutral"
+    
+    rating = int(classifier(text)[0]['label'].split('_')[1])
+
+    return rating, summary, keywords, sentiment_label
+
+# Main interface
+main_interface = gr.Interface(
+    fn=evaluate,
+    inputs=gr.File(label="Reviews"),
+    outputs=[gr.Textbox(label="Rating"), gr.Textbox(label="Summary"), gr.Textbox(label="Keywords"), gr.Textbox(label="Overall Sentiment")],
+    title='Summarize Reviews',
+    description="Evaluate and summarize collection of reviews. Reviews are submitted as an Excel file, where each review is in its own cell."
+)
+
+# Testing area interface
+testing_interface = gr.Interface(
+    fn=test_area,
+    inputs=gr.Textbox(label="Input Text"),
+    outputs=[gr.Textbox(label="Rating"), gr.Textbox(label="Summary"), gr.Textbox(label="Keywords"), gr.Textbox(label="Sentiment")],
+    title='Testing Area',
+    description="Test the summarization, keyword extraction, sentiment analysis, and rating on custom text input."
+)
+
+# Combine interfaces into a tabbed interface with a sidebar
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.Markdown("## Sidebar")
+            gr.Button("Button 1")
+            gr.Button("Button 2")
+        with gr.Column(scale=4):
+            iface = gr.TabbedInterface(
+                [main_interface, testing_interface],
+                ["Summarize Reviews", "Testing Area"]
+            )
+
+demo.launch(share=True)