Merge branch 'dev1'

Author: heyronjmilton

.gitignore

@@ -1,3 +1,5 @@
 venv/
 Backend/requirements.txt
-dat.txt
+dat.txt
+temp.txt
+Backend/test.py

Backend/__pycache__/summariser.cpython-310.pyc

@@ -0,0 +1,63 @@
+import re
+
+def remove_extra_whitespace(input_file, output_file):
+    with open(input_file, 'r') as file:
+        content = file.read()
+
+    # Remove unwanted characters before numbering
+    content = re.sub(r'(?<=\n)\s*-+\s*', '', content)
+
+    # Remove Roman numbering and add decimal numbering
+    decimal_number = 1
+    content = re.sub(r'(?<=\n)([IVXLCDM]+\.)(?=\s)', lambda match: str(decimal_number) + '.', content)
+    decimal_number += 1
+
+    # Remove extra white spaces
+    content = re.sub(' +', ' ', content)
+
+    with open(output_file, 'w') as file:
+        file.write(content)
+
+
+def number_questions(input_filename, output_filename):
+    section_count = 0
+    question_count = 0
+    current_section = ""
+
+    with open(input_filename, 'r') as input_file:
+        lines = input_file.readlines()
+
+    with open(output_filename, 'w') as output_file:
+        for line in lines:
+            # Check if the line starts with "Module X:"
+            if re.match(r'^Module \d+:', line):
+                section_count += 1
+                question_count = 0
+                current_section = re.findall(r'^Module \d+', line)[0]
+                output_file.write(line)
+            # Check if the line starts with "1.", "(a)", or "(i)"
+            elif re.match(r'^\d+\.|^[(a-z)]\.|^[(i)]\.', line):
+                question_count += 1
+                # Modify the line to include the correct question number
+                modified_line = re.sub(r'^(\d+\.|^[(a-z)]\.|^[(i)]\.)', str(question_count) + '.', line)
+                # Replace the section number if necessary
+                modified_line = modified_line.replace(current_section, 'Module ' + str(section_count))
+                output_file.write(modified_line)
+            else:
+                output_file.write(line)
+
+
+# Usage example
+input_file = 'Local_Storage\Generated_Files\cluster_questions.txt'  # Replace with your input file path
+temp_file = 'temp_output.txt'  # Replace with a temporary output file path
+output_file = 'final_output.txt'  # Replace with your final output file path
+
+# Step 1: Remove extra whitespace
+remove_extra_whitespace(input_file, temp_file)
+
+# Step 2: Number the questions
+number_questions(temp_file, output_file)
+
+# Step 3: Clean up the temporary file
+import os
+os.remove(temp_file)

Backend/__pycache__/t1.cpython-310.pyc

@@ -0,0 +1,24 @@
+import re
+
+def remove_extra_whitespace(input_file, output_file):
+    with open(input_file, 'r') as file:
+        content = file.read()
+
+    # Remove unwanted characters before numbering
+    content = re.sub(r'(?<=\n)\s*-+\s*', '', content)
+
+    # Remove Roman numbering and add decimal numbering
+    decimal_number = 1
+    content = re.sub(r'(?<=\n)([IVXLCDM]+\.)(?=\s)', lambda match: str(decimal_number) + '.', content)
+    decimal_number += 1
+
+    # Remove extra white spaces
+    content = re.sub(' +', ' ', content)
+
+    with open(output_file, 'w') as file:
+        file.write(content)
+
+# Usage example
+input_file = 'Local_Storage\Generated_Files\cluster_questions.txt'  # Replace with your input file path
+output_file = 'output.txt'  # Replace with your output file path
+remove_extra_whitespace(input_file, output_file)

Backend/__pycache__/test.cpython-310.pyc

@@ -0,0 +1,33 @@
+import re
+
+def number_questions(input_filename, output_filename):
+    section_count = 0
+    question_count = 0
+    current_section = ""
+
+    with open(input_filename, 'r') as input_file:
+        lines = input_file.readlines()
+
+    with open(output_filename, 'w') as output_file:
+        for line in lines:
+            # Check if the line starts with "Module X:"
+            if re.match(r'^Module \d+:', line):
+                section_count += 1
+                question_count = 0
+                current_section = re.findall(r'^Module \d+', line)[0]
+                output_file.write(line)
+            # Check if the line starts with "1.", "(a)", or "(i)"
+            elif re.match(r'^\d+\.|^[(a-z)]\.|^[(i)]\.', line):
+                question_count += 1
+                # Modify the line to include the correct question number
+                modified_line = re.sub(r'^(\d+\.|^[(a-z)]\.|^[(i)]\.)', str(question_count) + '.', line)
+                # Replace the section number if necessary
+                modified_line = modified_line.replace(current_section, 'Module ' + str(section_count))
+                output_file.write(modified_line)
+            else:
+                output_file.write(line)
+
+# Usage
+input_filename = "output.txt"  # Replace with the actual input filename
+output_filename = "numbered_questions.txt"  # Replace with the desired output filename
+number_questions(input_filename, output_filename)

Backend/__pycache__/updated_sorter.cpython-310.pyc

@@ -0,0 +1,33 @@
+import re
+
+# Read input from text file
+with open('question_papers/cluster_questions.txt', 'r') as file:
+    text = file.read()
+
+# Remove old numbering and add decimal numbering
+lines = text.split('\n')
+module_questions = {}
+current_module = None
+question_number = 1
+
+for line in lines:
+    if line.startswith('Module'):
+        current_module = re.findall(r'\d+', line)[0]
+        module_questions[current_module] = []
+        question_number = 1
+    elif line.strip().startswith('-'):
+        question = line.strip()[1:].strip()
+        if question.startswith('('):
+            question = question[1:].strip()
+        question = re.sub(r'^[IVX]+\.?\s*', str(question_number) + '. ', question)
+        module_questions[current_module].append(question)
+        question_number += 1
+
+# Save module questions to a file
+with open('module_questions.txt', 'w') as file:
+    for module, questions in module_questions.items():
+        file.write(f"Module {module}:\n")
+        for question in questions:
+            file.write(f"{question}\n")
+
+print("Module questions saved to 'module_questions.txt' file.")

Backend/cluster_processor.py

@@ -0,0 +1,47 @@
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+# Load the pre-trained model and tokenizer
+model_name = 'gpt2'
+model = GPT2LMHeadModel.from_pretrained(model_name)
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+
+def generate_model_questions(input_questions, num_questions=1):
+    # Encode input questions
+    input_ids = tokenizer.encode(input_questions, return_tensors='pt')
+
+    # Generate model questions
+    max_length = 512  # Adjust the maximum length of the generated questions
+    temperature = 1.0  # Adjust the temperature for controlling randomness
+
+    model_questions = []
+    for _ in range(num_questions):
+        outputs = model.generate(
+            input_ids,
+            max_length=max_length,
+            num_return_sequences=1,
+            temperature=temperature,
+            repetition_penalty=1.0,
+            pad_token_id=tokenizer.eos_token_id,
+            early_stopping=True
+        )
+
+        # Decode the generated model question
+        model_question = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        model_questions.append(model_question)
+
+    return model_questions
+
+# Example usage
+input_questions = """1. Explain the design procedure of combinational circuit with an example
+2. Implement the following function using a multiplexer
+3. Compare TTL and CMOS logic families.
+4. Implement the following Boolean function with NAND gates: OR
+5. Implement the following function using a multiplexer (Use B as input)"""
+model_questions = generate_model_questions(input_questions)
+
+print("Input Question:")
+print(input_questions)
+print("\nModel Questions:")
+for i, question in enumerate(model_questions, 1):
+    print(f"{i}. {question}")