Upload synth.py

synth.py

@@ -0,0 +1,190 @@
+import csv
+import torch
+from transformers import pipeline
+import random
+
+# Initialize the chatbot with half-precision
+chatbot = pipeline(
+    "text-generation", 
+    model="mistralai/Mistral-7B-Instruct-v0.3",
+    torch_dtype=torch.float16,
+    device=0  # Assuming you are using a GPU
+)
+
+# Sentiments and their labels
+sentiments = ["Positive or Encouraging", "Neutral or Factual", "Negative or Toxic"]
+
+# List of content formats to cycle through
+formats = [
+    "Feature Stories", "Instructional Manuals", "FAQs", "Policy Documents", "Live Stream Descriptions", 
+    "Editorial Content", "Research Papers", "User Manuals", "Commentaries", "Opinion Pieces", 
+    "Newsletters", "Online Courses", "Photo Essays", "Annual Reports", "User-Generated Content", 
+    "Testimonials", "DIY Content", "How-To Videos", "Campaign Reports", "Legal Briefs",
+    "Blog Posts", "Case Studies", "Tutorials", "Interviews", "Press Releases", 
+    "eBooks", "Infographics", "Webinars", "Podcast Descriptions", "Video Scripts",
+    "Advertisements", "Forum Discussions", "Whitepapers", "Surveys", "Product Reviews",
+    "Event Summaries", "Opinion Editorials", "Letters to the Editor", "Round-Up Posts", 
+    "Buying Guides", "Checklists", "Cheat Sheets", "Recipes", "Travel Guides",
+    "Profiles", "Lists", "Q&A Sessions", "Debates", "Polls"
+]
+
+# List of topics to cycle through
+topics = [
+    "Family", "Travel", "Politics", "Science", "Health", "Technology", "Sports", 
+    "Education", "Environment", "Economics", "Culture", "History", "Music", 
+    "Literature", "Food", "Art", "Fashion", "Entertainment", "Business", 
+    "Relationships", "Fitness", "Automotive", "Finance", "Real Estate", "Law", 
+    "Psychology", "Philosophy", "Religion", "Gardening", "DIY", "Hobbies", 
+    "Pets", "Career", "Marketing", "Customer Service", "Networking", "Innovation", 
+    "Artificial Intelligence", "Sustainability", "Social Issues", "Digital Media", 
+    "Programming", "Cybersecurity", "Astronomy", "Geography", "Travel Tips", 
+    "Cooking", "Parenting", "Productivity", "Mindfulness", "Mental Health", 
+    "Self-Improvement", "Leadership", "Teamwork", "Volunteering", "Nonprofits", 
+    "Gaming", "E-commerce", "Photography", "Videography", "Film", "Television", 
+    "Streaming Services", "Podcasts", "Public Speaking", "Event Planning", 
+    "Interior Design", "Architecture", "Urban Development", "Agriculture", 
+    "Climate Change", "Renewable Energy", "Space Exploration", "Biotechnology", 
+    "Cryptocurrency", "Blockchain", "Robotics", "Automated Systems", "Genetics", 
+    "Medicine", "Pharmacy", "Veterinary Science", "Marine Biology", "Ecology", 
+    "Conservation", "Wildlife", "Botany", "Zoology", "Geology", "Meteorology", 
+    "Aviation", "Maritime", "Logistics", "Supply Chain", "Human Resources", 
+    "Diversity and Inclusion", "Ethics", "Corporate Governance", "Public Relations", 
+    "Journalism", "Advertising", "Sales", "Customer Experience", "Retail", 
+    "Hospitality", "Tourism", "Luxury Goods", "Consumer Electronics", "Fashion Design", 
+    "Textiles", "Jewelry", "Cosmetics", "Skincare", "Perfume", "Toys", "Gadgets", 
+    "Home Appliances", "Furniture", "Home Improvement", "Landscaping", "Real Estate Investment"
+]
+
+# List of styles to cycle through
+styles = [
+    "Super Casual", "Internet Slang", "Every Day", "Formal", "Conversational", 
+    "Bad Grammar and Spelling", "Lazy typing", "Professional", "Academic", 
+    "Technical", "Narrative", "Descriptive", "Analytical", "Critical", 
+    "Objective", "Subjective", "Third Person", "First Person", 
+    "Persuasive", "Informative", "Journalistic", "Reflective",
+    "DM", "Social", "Informal", "Casual", "Colloquial"
+]
+
+# List of starting phrases
+starting_phrases = [
+    "Have you ever wondered", "Let's talk about", "It's interesting how", 
+    "Did you know", "The reality is", "Many people believe", 
+    "It's surprising that", "You might not know", "Let's dive into", 
+    "Here's the thing", "A common misconception is", "It's clear that", 
+    "Most people don't realize", "One thing to note is", 
+    "The fact is", "Consider this", "Here's an example", 
+    "Think about", "For instance", "To illustrate", 
+    "In my experience", "A key point is", "It's worth noting", 
+    "Let's explore", "Interestingly enough", "I want to highlight", 
+    "When it comes to", "The truth is", "Many experts agree", 
+    "Research shows", "Statistics indicate", "It's often said", 
+    "In reality", "From my perspective", "Surprisingly", 
+    "One thing I've noticed", "In recent studies", "Let's break down", 
+    "People often forget", "You should know", "Interestingly", 
+    "It turns out", "As it happens", "Experts suggest", 
+    "The surprising fact is", "It's commonly known", "Let's be honest", 
+    "The reality of", "It's fascinating that", "Have you noticed", 
+    "The thing is", "It's a fact that", "Let's not forget", 
+    "Studies have shown", "A notable point is", "It's often overlooked", 
+    "An important aspect is", "Let's take a closer look", 
+    "It's essential to understand", "Interestingly, research suggests", 
+    "One aspect to consider is", "It's beneficial to know", 
+    "It's worth considering", "The interesting thing is", "Let's examine", 
+    "A surprising fact is", "It's helpful to know", "One surprising element is", 
+    "Imagine this", "Here's a thought", "You might be surprised", 
+    "Think of it this way", "Here's an idea", "It's funny how", 
+    "Let me tell you", "Picture this", "The question is", 
+    "Believe it or not", "You won't believe", "Let's face it", 
+    "The best part is", "What's interesting is", "I discovered that", 
+    "It's amazing how", "The funny thing is", "Here's why", 
+    "What if I told you", "It's worth mentioning", "This reminds me of", 
+    "Let me explain", "Here's something new", "I realized that", 
+    "Have you seen", "You might enjoy", "I learned that", 
+    "It's clear to see", "What's fascinating is", "Here's a question", 
+    "I heard that", "The cool part is", "Here's what happened", 
+    "It appears that", "It's evident that", "Let me share", 
+    "You'll find that", "What's notable is", "Consider the fact that", 
+    "It's interesting to note", "Hello everyone", "Hi there", 
+    "Greetings", "Hey folks", "Good morning", "Good afternoon", 
+    "Good evening", "Hey", "What's up", "Hi", "Hello", 
+    "Amazing!", "Serious?", "Wow...", "That's pretty cool.", 
+    "Can you believe it?", "Unbelievable!", "Incredible!", "No way!", 
+    "Check this out", "Guess what?", "Surprise!", "Fascinating!", 
+    "Impressive!", "I don't get it?", "Really?", "What?", 
+    "Why?", "How come?", "Is that so?", "Are you sure?", 
+    "What do you think?", "By the way", "Just so you know", 
+    "For your information", "Incidentally", "On a side note", 
+    "As a reminder", "In addition", "Besides that", 
+    "While we're on the subject", "Speaking of which", 
+    "Have you", "Has anyone", "Would we", "Would it be", 
+    "OK, now", "OK but", "OK you", "OK nobody",
+    "Here's a quick fact", "To put it simply", "Here's why this matters", 
+    "Let's consider", "Now, think about this", "Take this into account", 
+    "Here's something to think about", "On that note", 
+    "Interestingly enough", "Just imagine", "That reminds me", 
+    "As it turns out", "Here's a fun fact", "The reality of it is", 
+    "By the way, did you know", "Interestingly", "Speaking of", 
+    "Now, let's dive in", "You'll be surprised to know", 
+    "I recently discovered", "Would you believe", "Can you imagine", 
+    "What's more", "Even more interesting is"
+]
+
+# CSV file setup with utf-8 encoding and quoting minimal
+csv_file = "sentences.csv"
+with open(csv_file, mode='w', newline='', encoding='utf-8') as file:
+    writer = csv.writer(file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
+    writer.writerow(["text", "label"])
+
+# Function to ensure correct quoting
+def ensure_correct_quoting(text):
+    # Check if the text is already properly quoted
+    if text.startswith('"') and text.endswith('"'):
+        return text
+    else:
+        return f'"{text}"'
+
+# Collect and save responses until reaching 100,000 rows
+row_count = 0
+format_index = 0
+topic_index = 0
+style_index = 0
+
+while row_count < 100000:
+    for idx, sentiment in enumerate(sentiments):
+        format_type = formats[format_index % len(formats)]
+        format_index += 1
+        topic = topics[topic_index % len(topics)]
+        topic_index += 1
+        style = styles[style_index % len(styles)]
+        style_index += 1
+        start_phrase = random.choice(starting_phrases)
+
+        # Add the current sentiment prompt with the format, topic, and style
+        prompt = f"Start your paragraph with '{start_phrase}'. Write a single paragraph of text. Format: {format_type}. Topic: {topic}. Vibe: {sentiment}. Style: {style}."
+        
+        response = chatbot(prompt, max_new_tokens=100)  # Adjusted max_new_tokens for longer responses
+
+        # Debug print to check response format
+        print(f"Full model response: {response}")
+
+        # Extract the generated text from the response structure
+        generated_text = response[0]['generated_text']
+
+        # Remove any part of the prompt from the generated text if it exists
+        clean_text = generated_text.replace(prompt, "").strip().split('\n')[0]
+
+        # Ensure the text starts and ends with quotes only if it doesn't already
+        correctly_quoted_text = ensure_correct_quoting(clean_text)
+
+        # Append the clean response text to the CSV
+        with open(csv_file, mode='a', newline='', encoding='utf-8') as file:
+            writer = csv.writer(file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
+            writer.writerow([correctly_quoted_text, idx])
+
+        row_count += 1
+        print(f"Response for sentiment '{sentiment}' saved to {csv_file}. Total rows: {row_count}")
+
+        if row_count >= 100000:
+            break
+
+print("All responses saved. Total rows:", row_count)