update

Author: ANGELOANTU7

Backend/NotesToText.py

@@ -19,23 +19,8 @@
 
 router = APIRouter()
 
-def download_files_from_s3(bucket_name, prefix, local_directory):
-    
-    paginator = s3.get_paginator('list_objects_v2')
-    operation_parameters = {'Bucket': bucket_name, 'Prefix': prefix}
-
-    page_iterator = paginator.paginate(**operation_parameters)
-
-    for page in page_iterator:
-        if 'Contents' in page:
-            for item in page['Contents']:
-                key = item['Key']
-                local_file_path = os.path.join(local_directory, os.path.basename(key))
-                s3.download_file(bucket_name, key, local_file_path)
-                print(f"Downloaded {key} to {local_file_path}")
 
 
-
 def pdf_to_images_from_bytes(pdf_content, output_folder, file_name):
     s3_bucket_name = 'learnmateai'
 

Backend/__pycache__/NotesToText.cpython-310.pyc

@@ -1,4 +1,3 @@
-#pyqsorter , sorts set of pyqs into modules
 from fastapi import APIRouter
 import os
 import re
@@ -7,36 +6,72 @@
 import tensorflow as tf
 import tensorflow_hub as hub
 from sklearnex import patch_sklearn
+import boto3
+from botocore.exceptions import NoCredentialsError
 patch_sklearn()
 from sklearn.cluster import KMeans
-
-
-
+import tempfile
+from io import BytesIO
 
 # Create an instance of APIRouter
 test = APIRouter()
 
+# AWS S3 configuration
+AWS_ACCESS_KEY_ID = 'AKIAZTHHIOR4CN6UXO6N'
+AWS_SECRET_ACCESS_KEY = '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'
+AWS_BUCKET_NAME = 'learnmateai'
+AWS_BUCKET_FOLDER = 'pyqs_txt'
+
+s3_client = boto3.client(
+    's3',
+    aws_access_key_id=AWS_ACCESS_KEY_ID,
+    aws_secret_access_key=AWS_SECRET_ACCESS_KEY
+)
+
 def extract_questions_from_file(filepath):
-    with open(filepath, 'rb') as f:
-        result = chardet.detect(f.read())
-    encoding = result['encoding']
-    with open(filepath, encoding=encoding) as f:
-        content = f.read()
-        pattern = r'((?:[IVX]+|\([a-z]\))\. .*(?:\n\s+\(\w\)\. .*)*)'
-        matches = re.findall(pattern, content)
-        questions = [re.sub(r'\n\s+\(\w\)\. ', ' ', match.strip()) for match in matches]
+    questions = []
+    with open(filepath, 'rb') as file:
+        content = file.read()
+        encoding = chardet.detect(content)['encoding']
+        decoded_content = content.decode(encoding, errors='ignore')
+        questions = re.findall(r'\b(?:what|where|why|how|when|which|who|whom|whose)\b.*[?!.]', decoded_content, re.IGNORECASE)
     return questions
 
-
 def extract_questions_from_directory(directory):
+    paginator = s3_client.get_paginator('list_objects_v2')
+    operation_parameters = {'Bucket': AWS_BUCKET_NAME, 'Prefix': directory}
+
+    page_iterator = paginator.paginate(**operation_parameters)
+
+    try:
+        if not os.path.exists("temp1/pyqs_txt"):
+            os.makedirs("temp1/pyqs_txt")  # Create directory if it doesn't exist
+        for page in page_iterator:
+            if 'Contents' in page:
+                for item in page['Contents']:
+                    key = item['Key']
+                    local_file_path = os.path.join("temp1/pyqs_txt", os.path.basename(key))  # Use basename of key as local file name
+                    try:
+                        s3_client.download_file(AWS_BUCKET_NAME, key, local_file_path)
+                        print(f"Downloaded {key} to {local_file_path}")
+                    except Exception as e:
+                        print(f"Failed to download {key}: {str(e)}")
+    except Exception as e:
+        print(f"An error occurred during pagination: {str(e)}")
+        return []
+
     questions = []
-    for filename in os.listdir(directory):
-        filepath = os.path.join(directory, filename)
+    for filename in os.listdir("temp1/pyqs_txt"):
+        filepath = os.path.join("temp1/pyqs_txt", filename)
         if os.path.isfile(filepath):
             questions += extract_questions_from_file(filepath)
+
     return questions
 
-def cluster_questions_1(questions, num_clusters):
+def cluster_questions(questions, num_clusters):
+    if len(questions) == 0:
+        return None, []
+
     module_url = "https://tfhub.dev/google/universal-sentence-encoder-large/5"
 
     embed = hub.load(module_url)
@@ -53,17 +88,17 @@ def cluster_questions_1(questions, num_clusters):
 
     return y_kmeans, repeated_indices
 
-
 @test.get("/api1")
 def api1_handler():
-    questions = extract_questions_from_directory('Local_Storage/pyqs_text')
+    questions = extract_questions_from_directory(AWS_BUCKET_FOLDER)
     num_clusters = 4
-    
-    labels, repeated_indices = cluster_questions_1(questions, num_clusters)
+
+    labels, repeated_indices = cluster_questions(questions, num_clusters)
 
     print("Clustering questions")
     for i in range(num_clusters):
-        cluster_questions = np.array(questions)[np.where(labels == i)[0]]
+        cluster_indices = np.where(labels == i)[0]
+        cluster_questions = np.array(questions)[cluster_indices]
         print(f"Module {i+1}:")
         for question in cluster_questions:
             print(f" - {question}")
@@ -74,21 +109,33 @@ def api1_handler():
         for index in repeated_indices:
             print(f" - {questions[index]}")
 
-    with open('Local_Storage/Generated_Files/cluster_questions.txt', 'w') as f:
+    try:
+        # Write cluster questions to S3
+        cluster_questions_content = ""
         for i in range(num_clusters):
-            cluster_questions = np.array(questions)[np.where(labels == i)[0]]
-            f.write(f"Module {i+1}:\n")
+            cluster_indices = np.where(labels == i)[0]
+            cluster_questions = np.array(questions)[cluster_indices]
+            cluster_questions_content += f"Module {i+1}:\n"
             for question in cluster_questions:
-                f.write(f" - {question}\n")
-            f.write("\n")
+                cluster_questions_content += f" - {question}\n"
+            cluster_questions_content += "\n"
 
-        # Write repeated questions to file
+        # Write repeated questions to S3
         if repeated_indices:
-            f.write("Repeated Questions:\n")
+            cluster_questions_content += "Repeated Questions:\n"
             for index in repeated_indices:
-                f.write(f" - {questions[index]}\n")
+                cluster_questions_content += f" - {questions[index]}\n"
+
+        s3_client.put_object(
+            Body=cluster_questions_content.encode(),
+            Bucket=AWS_BUCKET_NAME,
+            Key='Generated_Files/cluster_questions.txt'
+        )
+
+        return {"message": "Previous Year question papers sorted into modules"}
+    except NoCredentialsError:
+        return {"message": "Failed to write to S3. Credentials not available."}
 
-    return {"message": "Previous Year question papers sorted to modules"}
 
 @test.post("/api1")
 def api1_post_handler():

Backend/__pycache__/new_sorter.cpython-310.pyc

@@ -9,7 +9,7 @@
 from sklearnex import patch_sklearn
 patch_sklearn()
 from sklearn.cluster import KMeans
-from pathlib import path
+from pathlib import Path
 
 
 

Backend/__pycache__/pyqsorter.cpython-310.pyc

@@ -1,56 +1,14 @@
 Module 1:
- - II.     Simplify the following Boolean function into (1) sum-of-products form
- - V.      Implement the following function using a multiplexer
- - II.        Simplify the following function using Quine McCluskey method.
- - IV.                   Simplify the following Boolean function into (i) sum-of-products form and
- - V.                    Implement the following Boolean function with NAND gates: OR
- - VI.                   Implement the following function using a multiplexer (Use B as input).
- - I.   (a) (
- - III. (a) Simplify the followng Boolean functions using K-map                                 (5)
- - I.  (a) Perform the following:
- - III.      Simplify the following Boolean function using the tabulation method.
- - VIII.       Differentiate PLA and PAL. Draw the PLA for functions:                    (10)
- - III.  (a)  Simplify the following Boolean function into                               (6)
- - IV.   (a)  Implement the following four Boolean expressions with three half adders:   (6)
- - VIII.  (a)  Design a PLA circuit to implement the functions                            (6)
+ - VII. (a) Explain the internal organization of a memory chip which has 16 words
+ - VIII. (a)
 
 Module 2:
- - III.    Prove the theorems of Boolean algebra by using postulates.
- - I.   (a) Perform the following number conversions:
- - IV.        Derive the expressions for a 4-bit magnitude comparator and implement it
- - V.    (a) Design a decimal adder using 4-bit binary parallel adders.
- - IV. (a) Explain the working of a 4-bit BCD adder with block diagram                          (7)
- - V. (a) Explain the working of a 4-bit magnitude comparator.                                  (5)
- - II. (a) What is a gray code? What are the advantages of gray code? Find the gray (3)
- - V. (a) Explain the working of Decimal adder with block diagram and explain the        (5)
- - X.                                     (5)
- - I.    (a) Given the two binary numbers X = 1010100 and Y = 1000011, perform the
- - V.    (a)  What is Carry Propagation delay? Design a 4- bit binary parallel adder     (6)
+ - I. (a) With necessary diagrams, explain the mechanism of address ffanslation
 
 Module 3:
- - I.  (a) Convert (63.25) 10 to Hexa decimal and octal.
- - VII.    Design and explain a 4 bit asynchronous up-down binary counter.
- - VIII.   Write short notes on (1) Fan in and Fan out (ii) Propogation delay
- - VI.        Design a 4-bit Johnson counter. How does it differ from a ring counter?
- - VII.       Design a 4-bit binary ripple counter using JK flip flops.
- - VIII.      Design a RAM consisting of four words of four bits each. Also show the
- - I.         (a) Convert (AB2)16 to octal.
- - VII.                  Design a 4 bit binary ripple counter using JK flip flops. OR
- - II. (a) Using 10's complement, subtract 3250-72532.                                          (2)
- - VII.                         Design a counter that has repeated sequence of six states 0,1,2,4,5,6 using JK OR                                                                                                        (10)
- - VII. (a) Design a 2 bit synchronous up counter using .1K flipflops.                    (5)
- - VI.   (a)  Design a synchronous counter using .T flip-flops which counts the          (6)
- - VII.  (a)  Draw the logic diagram of a four-bit binary ripple counter. Show that a    (6)
+ - II. (a) With a neat diagram,,t explain the functional units of a computer.
+ - V. (a) Explain the purpose of carry save addition of summands in
 
 Module 4:
- - IV.     Explain the design procedure of combinational circuit with an example
- - IX.     Compare TTL and CMOS logic families.
- - VIII.                   Explain the operation of 2 input CMOS NOR gate and CMOS inverter in
- - IX.                   Explain with circuit diagram a typical 2 input TTL NAND gate.
- - VI. (a) Explain the working of SR latch with NAND gate with the help of logic diagram                                                                                                                                 (6)
- - VIII. (a) Design a combinational circuit using a ROM.The circuit accepts three bit                                                                                                                                      (6)
- - IX.                        Explain the working of RTL and DTL circuit. Explain how fan-out of DTL gate                                                                                                              (10)
- - VI. (a) Explain the working of SR latch using NOR gate with the help of logic          (6)
- - IX. (a) Draw and explain the working of Basic RTL NOR gate.                            (5)
- - IX.   (a)  Draw circuit of an TTL NAND gate and explain the operation.                (7)
+ - I. (a) Explain the single bus structure with a neat diagrarn.
 

Backend/__pycache__/updated_sorter.cpython-310.pyc

@@ -0,0 +1 @@
+