Upload 3 files

app.py

@@ -0,0 +1,99 @@
+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
+from sklearn.metrics import classification_report, confusion_matrix
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Load data
+@st.cache_data
+def load_data():
+    return pd.read_csv("Global_Cybersecurity_Threats_2015-2024.csv")
+
+df = load_data()
+st.title("Cybersecurity Attack Type Classifier")
+
+st.write("### Data Preview", df.head())
+
+# Define features
+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)'
+]
+
+# Preprocessing
+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)
+
+# Model settings
+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)
+
+# Build model
+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.")
+
+    # Plot loss
+    st.subheader("Training History")
+    fig, ax = plt.subplots()
+    ax.plot(history.history['loss'], label='Training Loss')
+    ax.plot(history.history['val_loss'], label='Validation Loss')
+    ax.legend()
+    st.pyplot(fig)
+
+    # Evaluate
+    st.subheader("Evaluation")
+    test_loss, test_acc = model.evaluate(X_test, y_test, verbose=0)
+    st.write(f"Test Accuracy: **{test_acc:.4f}**")
+
+    y_pred = np.argmax(model.predict(X_test), axis=1)
+    cm = confusion_matrix(y_test, y_pred)
+    st.write("### Confusion Matrix")
+    fig, ax = plt.subplots()
+    sns.heatmap(cm, annot=True, fmt="d", cmap="Blues", ax=ax)
+    st.pyplot(fig)
+
+    report = classification_report(y_test, y_pred, target_names=le.classes_, output_dict=True)
+    st.write("### Classification Report")
+    st.dataframe(pd.DataFrame(report).transpose())

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+tensorflow
+numpy
+pandas
+keras
+scikit-learn
+matplotlib
+seaborn