MLP Personalize Training

 # Step 1: Import Required Libraries

import pandas as pd

import numpy as np

from sklearn.cluster import KMeans

from sklearn.neighbors import KNeighborsClassifier

from sklearn.preprocessing import StandardScaler

import matplotlib.pyplot as plt

import seaborn as sns

# Step 2: Create Sample Data

# Each student: video_time, story_time, exercise_time (in minutes)

data = {

'video_time': [30, 5, 10, 50, 40, 15, 5, 45, 8, 60],

'story_time': [5, 30, 25, 5, 10, 35, 45, 10, 40, 5],

'exercise_time': [10, 15, 40, 5, 10, 20, 30, 5, 30, 10],

'preferred_material': [

'Video', 'Story', 'Exercise', 'Video', 'Video', 'Story', 'Story', 'Video', 'Story', 'Video'

]

}

df = pd.DataFrame(data)

# Step 3: Preprocess Data

features = ['video_time', 'story_time', 'exercise_time']

X = df[features]

scaler = StandardScaler()

X_scaled = scaler.fit_transform(X)

# Step 4: Apply Clustering (KMeans) - Group Students by Learning Style

kmeans = KMeans(n_clusters=3, random_state=42)

df['cluster'] = kmeans.fit_predict(X_scaled)

# Step 5: Visualize Clusters

plt.figure(figsize=(8,5))

sns.scatterplot(data=df, x='video_time', y='story_time', hue='cluster', palette='Set1', s=100)

plt.title('Student Clustering Based on Learning Behavior')

plt.xlabel('Video Time (minutes)')

plt.ylabel('Story Time (minutes)')

plt.show()

# Step 6: Train a KNN Model to Recommend Learning Material

knn = KNeighborsClassifier(n_neighbors=3)

knn.fit(X_scaled, df['preferred_material'])

# Step 7: Predict for a New Student

# Example: new student data

new_student = np.array([[35, 10, 5]]) # This student spends more time on video

new_student_scaled = scaler.transform(new_student)

predicted_material = knn.predict(new_student_scaled)

print("\nRecommended Learning Material for New Student:", predicted_material[0])

# Step 8: Bonus - Predict Cluster (Learning Style) for New Student

predicted_cluster = kmeans.predict(new_student_scaled)

print("Predicted Learning Style Group (Cluster):", predicted_cluster[0])