app.py

import streamlit as st
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder, StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Input, Dense
import matplotlib.pyplot as plt

@st.cache_data
def load_data():
    return pd.read_csv("Global_Cybersecurity_Threats_2015-2024.csv")

df = load_data()
st.title("Cybersecurity Attack Type - ANN Summary & Metrics")

target = 'Attack Type'

cat_features = [
    'Country',
    'Target Industry',
    'Attack Source',
    'Security Vulnerability Type',
    'Defense Mechanism Used'
]

num_features = [
    'Year',
    'Financial Loss (in Million $)',
    'Number of Affected Users',
    'Incident Resolution Time (in Hours)'
]

X = df.drop(columns=[target])
y = df[target]

preprocessor = ColumnTransformer(
    transformers=[
        ('num', StandardScaler(), num_features),
        ('cat', OneHotEncoder(handle_unknown='ignore'), cat_features)
    ]
)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=27)
X_train = preprocessor.fit_transform(X_train)
X_test = preprocessor.transform(X_test)

le = LabelEncoder()
y_train = le.fit_transform(y_train)
y_test = le.transform(y_test)

st.sidebar.header("Model Parameters")
epochs = st.sidebar.slider("Epochs", 5, 100, 30)
batch_size = st.sidebar.selectbox("Batch Size", [8, 16, 32, 64], index=1)

model = Sequential()
model.add(Input(shape=(X_train.shape[1],)))
model.add(Dense(16, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(len(np.unique(y)), activation='softmax'))
model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

if st.button("Train Model"):
    history = model.fit(X_train, y_train, validation_split=0.2, epochs=epochs, batch_size=batch_size, verbose=0)
    st.success("Model training complete.")

    st.subheader("Model Summary")
    model_summary = []
    model.summary(print_fn=lambda x: model_summary.append(x))
    st.text("\\n".join(model_summary))

    st.subheader("Training and Validation Metrics")
    fig, ax = plt.subplots(2, 1, figsize=(8, 6))
    ax[0].plot(history.history['loss'], label='Loss')
    ax[0].plot(history.history['val_loss'], label='Val Loss')
    ax[0].legend()
    ax[0].set_title("Loss vs Val Loss")

    ax[1].plot(history.history['accuracy'], label='Accuracy')
    ax[1].plot(history.history['val_accuracy'], label='Val Accuracy')
    ax[1].legend()
    ax[1].set_title("Accuracy vs Val Accuracy")

    st.pyplot(fig)

    min_val_loss = min(history.history['val_loss'])
    best_val_acc = max(history.history['val_accuracy'])

    st.write(f"**Minimum Validation Loss:** {min_val_loss:.4f}")
    st.write(f"**Best Validation Accuracy:** {best_val_acc:.4f}")