Update basic_training_data.py

basic_training_data.py

@@ -1,70 +1,64 @@
-import pandas as pd
-import numpy as np
-
-def create_basic_training_data():
-    """Create basic training data for the course recommender"""
-    
-    # Define available courses
-    courses = [
-        "Computer Science", "Information Technology", "Data Science", 
-        "Software Engineering", "Cybersecurity", "Computer Engineering",
-        "Business Administration", "Marketing", "Finance", "Accounting",
-        "Psychology", "Education", "Literature", "History", "Philosophy",
-        "Nursing", "Medicine", "Engineering", "Architecture", "Design"
-    ]
-    
-    # Define strands
-    strands = ["STEM", "ABM", "HUMSS", "GAS", "TVL"]
-    
-    # Define common hobbies
-    hobbies_list = [
-        "Programming", "Reading", "Sports", "Music", "Art", "Gaming",
-        "Photography", "Writing", "Dancing", "Cooking", "Traveling",
-        "Mathematics", "Science", "History", "Literature", "Technology"
-    ]
-    
-    # Generate synthetic data
-    np.random.seed(42)  # For reproducible results
-    n_samples = 1000
-    
-    data = []
-    for _ in range(n_samples):
-        # Generate random but realistic data
-        stanine = np.random.randint(1, 10)
-        gwa = np.random.uniform(75, 100)  # GWA between 75-100
-        strand = np.random.choice(strands)
-        course = np.random.choice(courses)
-        hobbies = np.random.choice(hobbies_list, size=np.random.randint(1, 4), replace=False)
-        hobbies_str = ", ".join(hobbies)
-        
-        # Generate rating based on some logic
-        if stanine >= 7 and gwa >= 85:
-            rating = np.random.choice([4, 5], p=[0.3, 0.7])
-        elif stanine >= 5 and gwa >= 80:
-            rating = np.random.choice([3, 4, 5], p=[0.2, 0.5, 0.3])
-        else:
-            rating = np.random.choice([1, 2, 3, 4], p=[0.1, 0.3, 0.4, 0.2])
-        
-        count = np.random.randint(1, 10)
-        
-        data.append({
-            'course': course,
-            'stanine': stanine,
-            'gwa': gwa,
-            'strand': strand,
-            'rating': rating,
-            'hobbies': hobbies_str,
-            'count': count
-        })
-    
-    return pd.DataFrame(data)
-
-def save_basic_data():
-    """Save basic training data to CSV"""
-    df = create_basic_training_data()
-    df.to_csv('basic_training_data.csv', index=False)
-    print(f"Basic training data saved with {len(df)} samples")
-    return df
-
-if __name__ == "__main__":
-    save_basic_data()
+import pandas as pd
+import numpy as np
+from database_connection import DatabaseConnection
+
+def create_basic_training_data():
+    """Create basic training data for the course recommender - DEPRECATED"""
+    print("WARNING: Basic training data is deprecated. Use student feedback data instead.")
+    raise ValueError("Basic training data is no longer used. Please use student feedback data from /student_feedback_counts endpoint.")
+    
+    # Define strands
+    strands = ["STEM", "ABM", "HUMSS", "GAS", "TVL"]
+    
+    # Define common hobbies
+    hobbies_list = [
+        "Programming", "Reading", "Sports", "Music", "Art", "Gaming",
+        "Photography", "Writing", "Dancing", "Cooking", "Traveling",
+        "Mathematics", "Science", "History", "Literature", "Technology"
+    ]
+    
+    # Generate synthetic data
+    np.random.seed(42)  # For reproducible results
+    n_samples = 1000
+    
+    data = []
+    for _ in range(n_samples):
+        # Generate random but realistic data
+        stanine = np.random.randint(1, 10)
+        gwa = np.random.uniform(75, 100)  # GWA between 75-100
+        strand = np.random.choice(strands)
+        course = np.random.choice(courses)
+        hobbies = np.random.choice(hobbies_list, size=np.random.randint(1, 4), replace=False)
+        hobbies_str = ", ".join(hobbies)
+        
+        # Generate rating based on some logic
+        if stanine >= 7 and gwa >= 85:
+            rating = np.random.choice([4, 5], p=[0.3, 0.7])
+        elif stanine >= 5 and gwa >= 80:
+            rating = np.random.choice([3, 4, 5], p=[0.2, 0.5, 0.3])
+        else:
+            rating = np.random.choice([1, 2, 3, 4], p=[0.1, 0.3, 0.4, 0.2])
+        
+        count = np.random.randint(1, 10)
+        
+        data.append({
+            'course': course,
+            'stanine': stanine,
+            'gwa': gwa,
+            'strand': strand,
+            'rating': rating,
+            'hobbies': hobbies_str,
+            'count': count
+        })
+    
+    return pd.DataFrame(data)
+
+def save_basic_data():
+    """Save basic training data to CSV"""
+    df = create_basic_training_data()
+    df.to_csv('basic_training_data.csv', index=False)
+    print(f"Basic training data saved with {len(df)} samples")
+    return df
+
+if __name__ == "__main__":
+    save_basic_data()