MLP AI for Special Education

 # Step 1: Import necessary libraries

import pandas as pd

import numpy as np

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import LabelEncoder, StandardScaler

from sklearn.svm import SVC

from sklearn.tree import DecisionTreeClassifier, plot_tree

from sklearn.metrics import classification_report, confusion_matrix

import matplotlib.pyplot as plt

import seaborn as sns

# Step 2: Create a sample dataset

# Features: Attention Span, Response Time, Interaction Level, Comprehension Score

data = {

'attention_span': [20, 50, 15, 45, 10, 55, 12, 48, 25, 60], # in minutes

'response_time': [5, 3, 8, 2, 10, 2, 9, 3, 6, 2], # in seconds

'interaction_level': [1, 3, 1, 4, 1, 4, 2, 5, 2, 5], # scale of 1-5

'comprehension_score': [60, 85, 55, 90, 50, 88, 58, 92, 65, 95], # out of 100

'special_need': [

'Autism', 'None', 'Autism', 'None', 'Dyslexia', 'None', 'ADHD', 'None', 'ADHD', 'None'

]

}

df = pd.DataFrame(data)

# Step 3: Preprocessing

X = df[['attention_span', 'response_time', 'interaction_level', 'comprehension_score']]

y = df['special_need']

# Encode target labels

label_encoder = LabelEncoder()

y_encoded = label_encoder.fit_transform(y)

# Scale feature data

scaler = StandardScaler()

X_scaled = scaler.fit_transform(X)

# Step 4: Train-Test Split

X_train, X_test, y_train, y_test = train_test_split(X_scaled, y_encoded, test_size=0.3, random_state=42)

# Step 5: Apply SVM Classifier

svm_model = SVC(kernel='rbf', gamma='scale', random_state=42)

svm_model.fit(X_train, y_train)

# Step 6: Predict and Evaluate SVM

y_pred_svm = svm_model.predict(X_test)

print("\n--- SVM Classification Report ---")

print(classification_report(y_test, y_pred_svm, target_names=label_encoder.classes_))

# Step 7: Apply Decision Tree Classifier (for suggesting learning strategies)

dt_model = DecisionTreeClassifier(max_depth=3, random_state=42)

dt_model.fit(X_train, y_train)

# Step 8: Predict and Evaluate Decision Tree

y_pred_dt = dt_model.predict(X_test)

print("\n--- Decision Tree Classification Report ---")

print(classification_report(y_test, y_pred_dt, target_names=label_encoder.classes_))

# Step 9: Visualize Decision Tree

plt.figure(figsize=(15,10))

plot_tree(dt_model, filled=True, feature_names=['Attention', 'Response', 'Interaction', 'Comprehension'],

class_names=label_encoder.classes_)

plt.title("Decision Tree: Suggesting Learning Strategies")

plt.show()

# Step 10: Additional - Visualize Confusion Matrix

cm = confusion_matrix(y_test, y_pred_dt)

sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=label_encoder.classes_, yticklabels=label_encoder.classes_)

plt.title("Decision Tree Confusion Matrix")

plt.xlabel('Predicted')

plt.ylabel('Actual')

plt.show()