app.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LSTM
import tensorflow as tf
import streamlit as st

def predict_stock(csv_file):
    # Load and preprocess data
    dataset = pd.read_csv(csv_file, usecols=[1], engine='python', encoding="big5")
    dataset = dataset.values.astype('float32')
    
    # Normalize the dataset
    scaler = MinMaxScaler(feature_range=(0, 1))
    dataset = scaler.fit_transform(dataset)
    
    # Split into train and test sets
    train_size = int(len(dataset) * 0.8)
    train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
    
    # Create dataset function
    def create_dataset(dataset, look_back=1):
        dataX, dataY = [], []
        for i in range(len(dataset)-look_back-1):
            a = dataset[i:(i+look_back), 0]
            dataX.append(a)
            dataY.append(dataset[i + look_back, 0])
        return np.array(dataX), np.array(dataY)
    
    # Prepare data for LSTM
    look_back = 1
    trainX, trainY = create_dataset(train, look_back)
    testX, testY = create_dataset(test, look_back)
    trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
    testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
    
    # Create and fit the LSTM network
    model = Sequential()
    model.add(LSTM(4, input_shape=(1, look_back)))
    model.add(Dense(1))
    model.compile(loss='mean_squared_error', optimizer='adam')
    model.fit(trainX, trainY, epochs=50, batch_size=1, verbose=0)
    
    # Make predictions
    trainPredict = model.predict(trainX)
    testPredict = model.predict(testX)
    
    # Invert predictions
    trainPredict = scaler.inverse_transform(trainPredict)
    trainY = scaler.inverse_transform([trainY])
    testPredict = scaler.inverse_transform(testPredict)
    testY = scaler.inverse_transform([testY])
    
    # Calculate RMSE
    trainScore = np.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
    testScore = np.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
    
    # Prepare plot data
    trainPredictPlot = np.empty_like(dataset)
    trainPredictPlot[:, :] = np.nan
    trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict
    testPredictPlot = np.empty_like(dataset)
    testPredictPlot[:, :] = np.nan
    testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict
    
    # Create plot
    fig, ax = plt.subplots(figsize=(12, 8))
    ax.plot(scaler.inverse_transform(dataset), label='Original Data', color='blue')
    ax.plot(trainPredictPlot, label='Training Predictions', linestyle='--', color='green')
    ax.plot(testPredictPlot, label='Test Predictions', linestyle='--', color='red')
    ax.set_xlabel('Time')
    ax.set_ylabel('Stock Price')
    ax.set_title('Stock Price Prediction')
    ax.legend()
    ax.grid(True, linestyle='--', alpha=0.7)
    
    return fig, trainScore, testScore

# Streamlit UI
st.set_page_config(page_title="Stock Price Prediction with LSTM", layout="wide")

st.title("Stock Price Prediction with LSTM")
st.write("Upload the 2330TW.csv file to predict stock prices using LSTM.")

uploaded_file = st.file_uploader("Choose a CSV file", type="csv")

if uploaded_file is not None:
    with st.spinner('Predicting...'):
        fig, train_score, test_score = predict_stock(uploaded_file)
    
    st.pyplot(fig)
    
    col1, col2 = st.columns(2)
    with col1:
        st.metric("Train Score (RMSE)", f"{train_score:.2f}")
    with col2:
        st.metric("Test Score (RMSE)", f"{test_score:.2f}")

st.markdown("---")
st.write("Created with ❤️ using Streamlit")