# Step 1: Import libraries
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix
import matplotlib.pyplot as plt # Import matplotlib.pyplot
 
# Step 2: Load Moodle data
# Generate sample data
data = pd.DataFrame({
    'login_count': [10, 8, 15, 20, 5, 12, 18, 25, 3, 10],
    'resource_views': [5, 3, 10, 12, 2, 7, 11, 15, 1, 6],
    'total_time': [120, 90, 300, 400, 60, 180, 360, 500, 30, 150],
    'final_grade': [55, 45, 75, 80, 30, 60, 70, 85, 20, 50]
})
  # Replace with actual file path
 
# Step 3: Preprocess data
data['login_count'] = data['login_count'].fillna(0)  # Handle missing values
data['total_time'] = pd.to_numeric(data['total_time'], errors='coerce').fillna(0)
data['passed'] = data['final_grade'] >= 50  # Binary target variable
 
# Step 4: Split dataset
X = data[['login_count', 'resource_views', 'total_time']]  # Features
y = data['passed']  # Target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
 
# Step 5: Train model
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)
 
# Step 6: Evaluate model
y_pred = model.predict(X_test)
print("Confusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print("\nClassification Report:")
print(classification_report(y_test, y_pred))
 
# Step 7: Feature importance visualization
importances = model.feature_importances_
features = X.columns
plt.bar(features, importances) # plt is now defined and can be used
plt.title("Feature Importance")
plt.show()
 

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