Code Editor for app.py

import streamlit as st
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Dropout
from sklearn.metrics import mean_squared_error

# Load data
@st.cache_data
def load_data():
    data = {
        'timeStamp': [1712659388813, 1712659388813],
        'elapsed': [894, 189],
        'label': ['HTTP Request', 'HTTP Request-0'],
        'responseCode': [200, 301],
        'responseMessage': ['OK', 'Moved Permanently'],
        'threadName': ['SkillsFactoryTest 1-3'] * 2,
        'dataType': ['text'] * 2,
        'success': [True, True],
        'failureMessage': [None, None],
        'bytes': [17415, 470],
        'sentBytes': [406, 135],
        'grpThreads': [5] * 2,
        'allThreads': [5] * 2,
        'URL': ['https://www.jenkins.io/doc/book/installing/', 'http://www.jenkins.io/doc/book/installing'],
        'Latency': [189, 189],
        'IdleTime': [0, 0],
        'Connect': [89, 89]
    }
    return pd.DataFrame(data)

# LSTM model
def create_lstm_model(input_shape):
    model = Sequential()
    model.add(LSTM(50, activation='relu', input_shape=input_shape))
    model.add(Dropout(0.2))
    model.add(Dense(1))
    model.compile(optimizer='adam', loss='mse')
    return model

# Function to train model
def train_model(data):
    # Preprocess data
    data = data[['elapsed', 'Latency']].values
    X, y = data[:-1], data[1:, 0]
    X = np.reshape(X, (X.shape[0], 1, X.shape[1]))
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    model = create_lstm_model((X_train.shape[1], X_train.shape[2]))
    model.fit(X_train, y_train, epochs=100, batch_size=32, verbose=0)

    return model, X_test, y_test

# Main Streamlit app
def main():
    st.title('Performance Degradation Detection with LSTM')

    data = load_data()
    st.write('### Raw Data', data)

    model, X_test, y_test = train_model(data)
    preds = model.predict(X_test)

    st.write('### Model Predictions', preds)
    st.write('### Expected Values', y_test)
    st.write('### Mean Squared Error', mean_squared_error(y_test, preds))

if __name__ == '__main__':
    main()