Merge pull request #1 from Za-heer/master

Working on AI & Data Science Assignment

.pylintrc

@@ -0,0 +1,20 @@
+[MASTER]
+# Disable specific warnings/errors to make Pylint less strict
+disable=
+    C0114,  # Missing module docstring
+    C0115,  # Missing class docstring
+    C0116,  # Missing function docstring
+    R0903,  # Too few public methods
+    W0311,  # Bad indentation
+    W0703,  # Broad-except
+    C0303,  # Trailing whitespace
+    C0301,  # Line too long
+
+# Set maximum line length to a reasonable value
+max-line-length=120
+
+# Allow fewer checks for small scripts
+min-similarity-lines=6
+
+# Ignore minor style issues
+ignore-patterns=.*\.ipynb

app.py

@@ -0,0 +1,80 @@
+from flask import Flask, request, render_template
+import os
+from transformers import AutoTokenizer, AutoModel
+import torch
+from pylint.lint import Run
+from pylint.reporters.text import TextReporter
+from io import StringIO
+
+app = Flask(__name__)
+UPLOAD_FOLDER = 'uploads'
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+app.static_folder = 'static'
+
+# Load CodeBERT with error handling
+try:
+    tokenizer = AutoTokenizer.from_pretrained("microsoft/codebert-base")
+    model = AutoModel.from_pretrained("microsoft/codebert-base")
+except Exception as e:
+    print(f"Error loading CodeBERT: {e}")
+    tokenizer = None
+    model = None
+
+def pylint_check(file_path):
+    try:
+        output = StringIO()
+        reporter = TextReporter(output)
+        Run([file_path, '--disable=C0114,C0115,W0311,W0703,C0116,R0903,C0303,C0301', '--max-line-length=120'], reporter=reporter, exit=False)
+        pylint_output = output.getvalue()
+        return pylint_output if pylint_output.strip() else "No critical issues found. Code looks good!"
+    except Exception as e:
+        return f"Pylint error: {str(e)}"
+
+def analyze_code(file_path):
+    try:
+        # Read the code file
+        with open(file_path, 'r', encoding='utf-8') as file:
+            code = file.read()
+        
+        # CodeBERT analysis
+        codebert_feedback = "CodeBERT not loaded."
+        if tokenizer and model:
+            inputs = tokenizer(code, return_tensors="pt", truncation=True, max_length=512)
+            with torch.no_grad():
+                outputs = model(**inputs)
+            codebert_feedback = f"Code analyzed with CodeBERT. Length: {len(code)} characters."
+
+        # Pylint analysis
+        pylint_feedback = pylint_check(file_path)
+        
+        # Combine and format feedback
+        feedback = f"<h3>Analysis Report</h3><p><strong>CodeBERT Feedback:</strong> {codebert_feedback}</p><p><strong>Pylint Feedback:</strong><br><pre>{pylint_feedback}</pre></p>"
+        return feedback
+    except Exception as e:
+        return f"Error analyzing file: {str(e)}"
+
+@app.route('/')
+def index():
+    return render_template('upload.html')
+
+@app.route('/upload', methods=['POST'])
+def upload_file():
+    try:
+        if 'file' not in request.files:
+            return 'No file uploaded', 400
+        file = request.files['file']
+        if file.filename == '':
+            return 'No file selected', 400
+        if file and (file.filename.endswith('.py') or file.filename.endswith('.ipynb')):
+            file_path = os.path.abspath(os.path.join(app.config['UPLOAD_FOLDER'], file.filename))
+            file.save(file_path)
+            feedback = analyze_code(file_path)
+            return f'<h2>File {file.filename} uploaded successfully!</h2>{feedback}'
+        return 'Invalid file type', 400
+    except Exception as e:
+        return f'Error during upload: {str(e)}', 500
+
+if __name__ == '__main__':
+    if not os.path.exists(UPLOAD_FOLDER):
+        os.makedirs(UPLOAD_FOLDER)
+    app.run(debug=True, port=5000)

requirements.txt

@@ -0,0 +1,6 @@
+flask==3.0.3
+transformers==4.44.2
+torch==2.4.1
+pandas==2.2.2
+notebook==7.2.2
+pylint==3.2.7

static/style.css

@@ -0,0 +1,84 @@
+/* General Styling */
+body {
+    background-color: #f8f9fa;
+    font-family: 'Arial', sans-serif;
+}
+
+/* Card Styling for Form and Feedback */
+.card {
+    border-radius: 10px;
+    background-color: #ffffff;
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+}
+
+/* Form Styling */
+.form-label {
+    font-weight: bold;
+    color: #333;
+}
+
+.form-control {
+    border: 2px solid #ced4da;
+    border-radius: 5px;
+    transition: border-color 0.3s;
+}
+
+.form-control:focus {
+    border-color: #007bff;
+    box-shadow: 0 0 5px rgba(0, 123, 255, 0.5);
+}
+
+.btn-primary {
+    background-color: #007bff;
+    border: none;
+    padding: 10px 20px;
+    font-size: 1.1rem;
+    border-radius: 5px;
+    transition: background-color 0.3s;
+}
+
+.btn-primary:hover {
+    background-color: #0056b3;
+}
+
+/* Feedback Section Styling */
+h2 {
+    color: #007bff;
+    margin-bottom: 20px;
+    text-align: center;
+}
+
+h3 {
+    color: #333;
+    font-size: 1.5rem;
+    margin-top: 20px;
+    border-bottom: 2px solid #007bff;
+    padding-bottom: 5px;
+}
+
+pre {
+    background-color: #f1f3f5;
+    padding: 15px;
+    border-radius: 5px;
+    font-size: 0.9rem;
+    white-space: pre-wrap;
+    word-wrap: break-word;
+    max-height: 400px;
+    overflow-y: auto;
+    border: 1px solid #ced4da;
+}
+
+/* Responsive Design */
+@media (max-width: 576px) {
+    .card {
+        padding: 15px;
+    }
+
+    h1 {
+        font-size: 1.8rem;
+    }
+
+    .btn-primary {
+        width: 100%;
+    }
+}

templates/upload.html

@@ -0,0 +1,26 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Assignment Checker</title>
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet">
+    <link rel="stylesheet" href="{{ url_for('static', filename='style.css') }}">
+</head>
+
+<body class="container mt-5">
+    <h1 class="text-center mb-4">Assignment Checker</h1>
+    <div class="card p-4 shadow">
+        <h3>Upload Your Assignment</h3>
+        <form method="post" action="/upload" enctype="multipart/form-data">
+            <div class="mb-3">
+                <label for="file" class="form-label">Select a .py or .ipynb file:</label>
+                <input type="file" name="file" accept=".py,.ipynb" class="form-control">
+            </div>
+            <button type="submit" class="btn btn-primary">Upload</button>
+        </form>
+    </div>
+</body>
+
+</html>

testpylint.py

@@ -0,0 +1,14 @@
+from pylint.lint import Run
+from pylint.reporters.text import TextReporter
+from io import StringIO
+
+def pylint_check(file_path):
+    try:
+        output = StringIO()
+        reporter = TextReporter(output)
+        Run([file_path, '--disable=C0114,C0115,C0116,R0903,W0311,W0703,C0303,C0301', '--max-line-length=120'], reporter=reporter, exit=False)
+        return output.getvalue()
+    except Exception as e:
+        return f"Pylint error: {str(e)}"
+
+print(pylint_check("uploads/test.py"))

uploads/assignment_01.ipynb

@@ -0,0 +1,71 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c37acdaf",
+   "metadata": {},
+   "source": [
+    "# Assignment 1: Calculate the Factorial\n",
+    "    \"Write a function to compute the factorial of a given number n.\n",
+    "    The factorial of a number n is the product of all positive integers less than or equal to n.\n",
+    "    For example, factorial of 5 is 5 * 4 * 3 * 2 * 1 = 120."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ac5b116f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Factorial of 5 is 120\n"
+     ]
+    }
+   ],
+   "source": [
+    "def factorial(n):\n",
+    "       if n == 0 or n == 1:\n",
+    "            return 1\n",
+    "       else:\n",
+    "            return n * factorial(n - 1)\n",
+    "    \n",
+    "    # Test the function\\,\n",
+    "number = 5\n",
+    "result = factorial(number)\n",
+    "print(f'Factorial of {number} is {result}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "80df5cfc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ml_env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

uploads/assignment_01.py

@@ -0,0 +1,12 @@
+# Assignment 1: Calculate the factorial of a number
+# Write a function to compute the factorial of a given number n
+def factorial(n):
+    if n == 0 or n == 1:
+        return 1
+    else:
+        return n * factorial(n - 1)
+
+# Test the function
+number = 5
+result = factorial(number)
+print(f"Factorial of {number} is {result}")

uploads/assignment_02.py

@@ -0,0 +1,17 @@
+# Assignment 2: Check if a number is prime
+# Write a function to check if a number is prime
+
+
+def is_prime(n):
+    if n <= 1:
+        return False
+    for i in range(2, n):  
+        if n % i == 0:
+            return False
+    return True
+
+# Test the function
+num = 17
+print(f"Is {num} prime? {is_prime(num)}")
+print(f"Is 4 prime? {is_prime(4)}")
+print(f"Is {undefined_var} prime?")  

uploads/assignment_03.py

@@ -0,0 +1,27 @@
+# Assignment 3: EDA on Synthetic Dataset
+# Perform EDA on a dataset of student scores
+import pandas as pd
+import numpy as np
+
+# Synthetic dataset
+data = {
+    'name': ['Alice', 'Bob', 'Charlie', 'David'],
+    'math_score': [85, 90, 78, 92],
+    'science_score': [88, 95, 80, 90]
+}
+df = pd.DataFrame(data)
+
+# Calculate average scores
+avg_math = df['math_score'].mean()
+avg_science = df['science_score'].mean()
+print(f"Average Math Score: {avg_math}")
+print(f"Average Science Score: {avg_science}")
+
+# Plot histogram of math scores
+import matplotlib.pyplot as plt
+plt.hist(df['math_score'], bins=5)
+plt.title('Math Score Distribution')
+plt.xlabel('Score')
+plt.ylabel('Frequency')
+plt.show()  # Error: May not display in non-interactive environments
+print(df['english_score'])  # Error: 'english_score' column doesn't exist

uploads/assignment_04.ipynb

@@ -0,0 +1,52 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "86625251",
+   "metadata": {},
+   "source": [
+    "# Assignment 4: EDA - Correlation Analysis\n",
+    "Perform correlation analysis on a dataset of car features and prices.\n",
+    "Calculate correlation matrix and plot a heatmap."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d3ae5847",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Synthetic dataset\n",
+    "data = {\n",
+    "    'horsepower': [120, 150, 100, 180],\n",
+    "    'weight': [3000, 3200, 2800, 3500],\n",
+    "    'price': [20000, 25000, 18000, 30000]\n",
+    "}\n",
+    "df = pd.DataFrame(data)\n",
+    "\n",
+    "# Correlation matrix\n",
+    "corr_matrix = df.corr()\n",
+    "\n",
+    "# Plot heatmap\n",
+    "sns.heatmap(corr_matrix, annot=True)\n",
+    "plt.title('Correlation Heatmap')\n",
+    "plt.show()\n",
+    "\n",
+    "# Error: Incorrect column name\n",
+    "print(df['Price'])"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

uploads/assignment_04.py

@@ -0,0 +1,16 @@
+# Assignment 4: Linear Regression on Synthetic Data
+# Build a linear regression model to predict house prices
+import numpy as np
+from sklearn.linear_model import LinearRegression
+
+# Synthetic dataset
+X = np.array([[1, 2], [2, 4], [3, 6], [4, 8]])  # Features: size, rooms
+y = np.array([100, 200, 300, 400])  # Prices
+
+# Train model
+model = LinearRegression()
+model.fit(X, y)
+
+# Predict on new data
+new_data = np.array([5, 10])  # Error: Shape mismatch, should be [[5, 10]]
+print(f"Predicted price: {model.predict(new_data)}")

uploads/assignment_05.ipynb

@@ -0,0 +1,49 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "10d2cf4b",
+   "metadata": {},
+   "source": [
+    "# Assignment 5: Decision Tree Classifier\n",
+    "Train a decision tree classifier on a synthetic dataset of customer purchases.\n",
+    "Predict whether a customer will buy based on age and income."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "10abdab6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "\n",
+    "# Synthetic dataset\n",
+    "data = {\n",
+    "    'age': [25, 30, 35, 40],\n",
+    "    'income': [50000, 60000, 55000, 70000],\n",
+    "    'buy': [0, 1, 0, 1]\n",
+    "}\n",
+    "df = pd.DataFrame(data)\n",
+    "\n",
+    "# Train model\n",
+    "X = df[['age', 'income']]\n",
+    "y = df['buy']\n",
+    "model = DecisionTreeClassifier()\n",
+    "model.fit(X, y)  # Error: Missing arguments, should be model.fit(X, y)\\n\",\n",
+    "\n",
+    "# Predict\\n\",\n",
+    "print(model.predict([[30, 65000]]))"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

uploads/assignment_06.py

@@ -0,0 +1,19 @@
+# Assignment 6: Missing Value Imputation
+# Impute missing values in a dataset using mean strategy
+import pandas as pd
+import numpy as np
+from sklearn.impute import SimpleImputer
+
+# Synthetic dataset
+data = {
+    'feature1': [1, 2, np.nan, 4],
+    'feature2': [10, np.nan, 30, 40]
+}
+df = pd.DataFrame(data)
+
+# Impute missing values
+imputer = SimpleImputer(strategy='mean')
+df_imputed = imputer.fit_transform(df)
+
+# Error: Incorrectly printing DataFrame as array
+print(df_imputed['feature1'])  # Should use pd.DataFrame(df_imputed)

uploads/assignment_07.py

@@ -0,0 +1,15 @@
+# Assignment 7: Feature Engineering - Polynomial Features
+# Create polynomial features for a regression model
+from sklearn.preprocessing import PolynomialFeatures
+import numpy as np
+
+# Synthetic dataset
+X = np.array([[1], [2], [3], [4]])
+
+# Create polynomial features
+poly = PolynomialFeatures(degree=2)
+X_poly = poly.fit_transform(X)
+
+# Error: Incorrectly accessing feature names
+print(poly.feature_names)  # Error: Should use get_feature_names_out()
+print(X_poly)

uploads/assignment_09.py

@@ -0,0 +1,15 @@
+# Assignment 9: PCA for Dimensionality Reduction
+# Apply PCA to reduce dimensions of a dataset
+from sklearn.decomposition import PCA
+import numpy as np
+
+# Synthetic dataset
+X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]])
+
+# Apply PCA
+pca = PCA(n_components=2)
+X_reduced = pca.fit_transform(X)
+
+# Error: Accessing undefined attribute
+print(pca.explained_variance)  # Should be explained_variance_ratio_
+print(X_reduced)

uploads/test.py

@@ -0,0 +1,6 @@
+# test.py
+def factorial(n):
+if n == 0:
+return 1
+else:
+    return n * factorial(n-1)