NdR_female_superheros.py

import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# Set random seed for reproducibility
np.random.seed(42)
torch.manual_seed(42)

# Number of samples per superhero
N_per_class = 200

# List of female superheroes
superheroes = ['Wonder Woman', 'Captain Marvel', 'Black Widow', 'Storm', 'Supergirl']

# Total number of classes
num_classes = len(superheroes)

# Total number of samples
N = N_per_class * num_classes

# Number of original features
D = 5  # Strength, Speed, Intelligence, Durability, Energy Projection

# Update the total number of features after adding the interaction term
total_features = D + 1  # Original features plus the interaction term

# Initialize feature matrix X and label vector y
X = np.zeros((N, total_features))
y = np.zeros(N, dtype=int)

# Define the mean and standard deviation for each feature per superhero
# Features: [Strength, Speed, Intelligence, Durability, Energy Projection]
superhero_stats = {
    'Wonder Woman': {
        'mean': [9, 9, 8, 9, 8],
        'std':  [0.5, 0.5, 0.5, 0.5, 0.5]
    },
    'Captain Marvel': {
        'mean': [10, 9, 7, 10, 10],
        'std':  [0.5, 0.5, 0.5, 0.5, 0.5]
    },
    'Black Widow': {
        'mean': [5, 7, 8, 6, 2],
        'std':  [0.5, 0.5, 0.5, 0.5, 0.5]
    },
    'Storm': {
        'mean': [6, 7, 8, 6, 9],
        'std':  [0.5, 0.5, 0.5, 0.5, 0.5]
    },
    'Supergirl': {
        'mean': [10, 10, 8, 10, 9],
        'std':  [0.5, 0.5, 0.5, 0.5, 0.5]
    },
}

# Generate synthetic data for each superhero with non-linear relationships
for idx, hero in enumerate(superheroes):
    start = idx * N_per_class
    end = (idx + 1) * N_per_class
    means = superhero_stats[hero]['mean']
    stds = superhero_stats[hero]['std']
    X_hero = np.random.normal(means, stds, (N_per_class, D))
    # Ensure feature values are within reasonable ranges before computing interaction
    X_hero = np.clip(X_hero, 1, 10)
    # Introduce non-linear feature interactions
    interaction_term = np.sin(X_hero[:, 1]) * np.log(X_hero[:, 4])  # Interaction between Speed and Energy Projection
    X_hero = np.hstack((X_hero, interaction_term.reshape(-1, 1)))
    X[start:end] = X_hero
    y[start:end] = idx

# Ensure all feature values are within reasonable ranges
X[:, :D] = np.clip(X[:, :D], 1, 10)

# Shuffle the dataset
X, y = shuffle(X, y, random_state=42)

# Normalize the features
scaler = StandardScaler()
X = scaler.fit_transform(X)

# Split data into training and test sets
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42)

# Convert data to torch tensors
X_train_tensor = torch.from_numpy(X_train).float()
y_train_tensor = torch.from_numpy(y_train).long()
X_test_tensor = torch.from_numpy(X_test).float()
y_test_tensor = torch.from_numpy(y_test).long()

# Random prediction function
def random_prediction(X):
    num_samples = X.shape[0]
    random_preds = np.random.randint(num_classes, size=num_samples)
    return random_preds

# Random prediction and evaluation
random_preds = random_prediction(X_test)
random_accuracy = (random_preds == y_test).sum() / y_test.size
print('Random Prediction Accuracy: {:.2f}%'.format(100 * random_accuracy))

# Define Linear Model
class LinearModel(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(LinearModel, self).__init__()
        self.linear = nn.Linear(input_dim, output_dim)

    def forward(self, x):
        return self.linear(x)

# Initialize Linear Model
input_dim = total_features
output_dim = num_classes
linear_model = LinearModel(input_dim, output_dim)

# Loss and optimizer for Linear Model
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(linear_model.parameters(), lr=0.01, weight_decay=1e-4)

# Training the Linear Model
num_epochs = 100
for epoch in range(num_epochs):
    linear_model.train()
    outputs = linear_model(X_train_tensor)
    loss = criterion(outputs, y_train_tensor)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    if (epoch + 1) % 20 == 0:
        print('Linear Model - Epoch [{}/{}], Loss: {:.4f}'.format(
            epoch + 1, num_epochs, loss.item()))

# Evaluate Linear Model
linear_model.eval()
with torch.no_grad():
    outputs = linear_model(X_test_tensor)
    _, predicted = torch.max(outputs.data, 1)
    linear_accuracy = (predicted == y_test_tensor).sum().item() / y_test_tensor.size(0)
    print('Linear Model Accuracy: {:.2f}%'.format(100 * linear_accuracy))

# Define Neural Network Model with regularization
class NeuralNet(nn.Module):
    def __init__(self, input_dim, hidden_dims, output_dim):
        super(NeuralNet, self).__init__()
        layers = []
        in_dim = input_dim
        for h_dim in hidden_dims:
            layers.append(nn.Linear(in_dim, h_dim))
            layers.append(nn.ReLU())
            layers.append(nn.BatchNorm1d(h_dim))
            layers.append(nn.Dropout(0.3))
            in_dim = h_dim
        layers.append(nn.Linear(in_dim, output_dim))
        self.model = nn.Sequential(*layers)

    def forward(self, x):
        return self.model(x)

# Initialize Neural Network Model
hidden_dims = [128, 64, 32]
neural_model = NeuralNet(input_dim, hidden_dims, output_dim)

# Loss and optimizer for Neural Network Model
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(neural_model.parameters(), lr=0.001, weight_decay=1e-4)

# Training the Neural Network Model
num_epochs = 200
for epoch in range(num_epochs):
    neural_model.train()
    outputs = neural_model(X_train_tensor)
    loss = criterion(outputs, y_train_tensor)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    if (epoch + 1) % 20 == 0:
        print('Neural Network - Epoch [{}/{}], Loss: {:.4f}'.format(
            epoch + 1, num_epochs, loss.item()))

# Evaluate Neural Network Model
neural_model.eval()
with torch.no_grad():
    outputs = neural_model(X_test_tensor)
    _, predicted = torch.max(outputs.data, 1)
    neural_accuracy = (predicted == y_test_tensor).sum().item() / y_test_tensor.size(0)
    print('Neural Network Model Accuracy: {:.2f}%'.format(100 * neural_accuracy))

# Summary of Accuracies
print("\nSummary of Accuracies:")
print('Random Prediction Accuracy: {:.2f}%'.format(100 * random_accuracy))
print('Linear Model Accuracy: {:.2f}%'.format(100 * linear_accuracy))
print('Neural Network Model Accuracy: {:.2f}%'.format(100 * neural_accuracy))