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

# fix random seed for reproducibility
tf.random.set_seed(7)

def train_and_predict(file, epochs):
    # Load the dataset
    dataframe = pd.read_csv(file.name, usecols=[1], engine='python', encoding="big5")
    dataset = dataframe.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),:]

    # Convert an array of values into a dataset matrix
    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)

    # Reshape into X=t and Y=t+1
    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=epochs, batch_size=1, verbose=2)

    # 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 root mean squared error
    trainScore = np.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
    testScore = np.sqrt(mean_squared_error(testY[0], testPredict[:,0]))

    # Plot predictions
    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

    plt.figure(figsize=(12, 8))
    plt.plot(scaler.inverse_transform(dataset), label='Original Data')
    plt.plot(trainPredictPlot, label='Training Predictions', linestyle='--')
    plt.plot(testPredictPlot, label='Test Predictions', linestyle='--')
    plt.xlabel('Time')
    plt.ylabel('Scaled Values')
    plt.title('Original Data and Predictions')
    plt.legend()

    return (f'Train Score: {trainScore:.2f} RMSE\nTest Score: {testScore:.2f} RMSE'), plt

# Gradio interface
file_input = gr.File(label="Upload CSV File")
epochs_input = gr.Slider(minimum=1, maximum=100, value=50, label="Epochs")
output_text = gr.Textbox(label="Training and Testing RMSE Scores")
output_plot = gr.Plot(label="Original Data and Predictions")

gr.Interface(
    fn=train_and_predict,
    inputs=[file_input, epochs_input],
    outputs=[output_text, output_plot],
    title="LSTM Model for Time Series Prediction",
    description="Upload a CSV file with time series data and specify the number of epochs to train the model."
).launch()