Merge pull request #3 from Za-heer/master

app.py

@@ -6,25 +6,27 @@ from pylint.lint import Run
 from pylint.reporters.text import TextReporter
 from io import StringIO
 
-app = Flask(__name__)
+app = Flask(__name__, static_folder='static')
 UPLOAD_FOLDER = 'uploads'
 app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
-app.static_folder = 'static'
 
-# Load CodeBERT with error handling
+# Load CodeBERT globally (once at startup)
+tokenizer = None
+model = None
 try:
     tokenizer = AutoTokenizer.from_pretrained("microsoft/codebert-base")
     model = AutoModel.from_pretrained("microsoft/codebert-base")
+    if torch.cuda.is_available():
+        model.to('cuda')
+    print("CodeBERT loaded successfully.")
 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)
+        Run([file_path, '--disable=C0114,C0115,C0116,R0903,W0311,W0703,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:
@@ -40,6 +42,8 @@ def analyze_code(file_path):
         codebert_feedback = "CodeBERT not loaded."
         if tokenizer and model:
             inputs = tokenizer(code, return_tensors="pt", truncation=True, max_length=512)
+            if torch.cuda.is_available():
+                inputs = {k: v.to('cuda') for k, v in inputs.items()}
             with torch.no_grad():
                 outputs = model(**inputs)
             codebert_feedback = f"Code analyzed with CodeBERT. Length: {len(code)} characters."
@@ -77,4 +81,4 @@ def upload_file():
 if __name__ == '__main__':
     if not os.path.exists(UPLOAD_FOLDER):
         os.makedirs(UPLOAD_FOLDER)
-    app.run(debug=True, port=5000)
+    app.run(debug=True, port=5001)

uploads/assignment_03.ipynb

@@ -0,0 +1,46 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "4ecafd98",
+   "metadata": {},
+   "source": [
+    "# Assignment 3: Feature Engineering - Encoding Categorical Data\n",
+    "Create a function to encode categorical variables in a dataset using one-hot encoding.\n",
+    "Dataset contains student info with grades (A, B, C) and gender (M, F)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "44ac96ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "    \n",
+    "    # Synthetic dataset\n",
+    "data = {\n",
+    "        'student': ['Alice', 'Bob', 'Charlie'],\n",
+    "        'grade': ['A', 'B', 'C'],\n",
+    "        'gender': ['F', 'M', 'F']\n",
+    "    }\n",
+    "df = pd.DataFrame(data)\n",
+    "\n",
+    "    # One-hot encoding\\n\",\n",
+    "df_encoded = pd.get_dummies(df, columns=['grade', 'gender']) \n",
+    "print(df_encoded)\n",
+    "    \n",
+    "    # Error: Trying to access non-existent column\\n\",\n",
+    "print(df_encoded['grade_D'])"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

uploads/assignment_05.py

@@ -0,0 +1,21 @@
+# Assignment 5: Feature Scaling for KNN
+# Apply feature scaling before training a KNN classifier
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.preprocessing import StandardScaler
+import numpy as np
+
+# Synthetic dataset
+X = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
+y = np.array([0, 0, 1, 1])
+
+# Scale features
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+
+# Train KNN
+knn = KNeighborsClassifier(n_neighbors=3)
+knn.fit(X_scaled, y)
+
+# Predict
+test_data = np.array([2, 3])  # Error: Shape mismatch, should be [[2, 3]]
+print(f"Prediction: {knn.predict(test_data)}")

uploads/assignment_10.py

@@ -0,0 +1,22 @@
+# Assignment 10: Train-Test Split and Evaluation
+# Split dataset and evaluate a model
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+from sklearn.linear_model import LogisticRegression
+import numpy as np
+
+# Synthetic dataset
+X = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
+y = np.array([0, 0, 1, 1])
+
+# Split data
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
+
+# Train model
+model = LogisticRegression()
+model.fit(X_train, y_train)
+
+# Evaluate
+predictions = model.predict(X_test)
+print(f"Accuracy: {accuracy_score(y_test, predictions)}")
+print(f"Confusion Matrix: {confusion_matrix(y_test, predictions)}")  # Error: confusion_matrix not imported