Skip to content
TheChatArchiveThe Chat Archive
gpt-4-0314· OpenAIAi2 WildChat-4.8M (AI2)

Make a stock market prediction model using LSTM use the below code as starting point(You…

  1. User

    Make a stock market prediction model using LSTM use the below code as starting point(You may need to modify it) using supertrend as indicator you also need to make prediction for the next day (For eg the data is trained on start='2009-01-01', end='2021-01-01' make prediction for price at '2021-01-02'):

    Code: import yfinance as yf import pandas as pd import numpy as np from sklearn.preprocessing import MinMaxScaler from keras.models import Sequential from keras.layers import Dense, LSTM from keras.callbacks import LambdaCallback import datetime import matplotlib.pyplot as plt import matplotlib.dates as mdates

    nifty = yf.download('^NSEI', start='2009-01-01', end='2021-01-01')

    def supertrend(df, period=10, multiplier=3): hl = (df['High'] + df['Low']) / 2 atr = df['High'].rolling(period).max() - df['Low'].rolling(period).min()

    up = hl - multiplier * atr
    dn = hl + multiplier * atr
    
    df['ST'] = 0
    df['ST'][0] = (df['High'][0] + df['Low'][0]) / 2
    
    position = 'none'
    
    for i in range(1, len(df)):
        if df['Close'][i] > up[i]:
            if position != 'buy':
                position = 'buy'
                df['ST'][i] = dn[i]
            else:
                df['ST'][i] = max(df['ST'][i - 1], dn[i])
        elif df['Close'][i] < dn[i]:
            if position != 'sell':
                position = 'sell'
                df['ST'][i] = up[i]
            else:
                df['ST'][i] = min(df['ST'][i - 1], up[i])
        else:
            df['ST'][i] = df['ST'][i - 1]
    
    return df
    

    nifty = supertrend(nifty) nifty.head()

    dataset = nifty['Close'].values dataset = dataset.astype('float32') dataset = dataset.reshape(-1, 1) scaler = MinMaxScaler(feature_range=(0, 1)) dataset = scaler.fit_transform(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)

    train_size = int(len(dataset) * 0.8) test_size = len(dataset) - train_size train, test = dataset[:train_size], dataset[train_size:]

    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]))

    model = Sequential() model.add(LSTM(100, input_shape=(1, look_back))) model.add(Dense(1))

    model.compile(loss='mean_squared_error', optimizer='adam') model.fit(trainX, trainY, epochs=200, batch_size=1, verbose=0)

    trainPredict = model.predict(trainX) testPredict = model.predict(testX)

    trainPredict = scaler.inverse_transform(trainPredict) trainY = scaler.inverse_transform([trainY]) testPredict = scaler.inverse_transform(testPredict) testY = scaler.inverse_transform([testY])

    import matplotlib.pyplot as plt

    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.plot(scaler.inverse_transform(dataset), label='Actual') plt.plot(trainPredictPlot, label='Train Prediction') plt.plot(testPredictPlot, label='Test Prediction') plt.legend() plt.show()

    model.save('my_model.h5')

    from sklearn.metrics import mean_squared_error import math

    trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0])) print('Train Score: %.2f RMSE' % (trainScore)) testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0])) print('Test Score: %.2f RMSE' % (testScore))

  2. Assistant

    To predict the price at '2021-01-02', we need to modify the code and train a model that will use Supertrend as an indicator. As a first step, let's add the Supertrend indicator to the dataset alongside the 'Close' prices.

    def create_dataset_with_supertrend(dataset, st, look_back=1):
        dataX, dataY = [], []
        for i in range(len(dataset)-look_back-1):
            a = np.append(dataset[i:(i+look_back), 0], st[i+look_back-1])
            dataX.append(a)
            dataY.append(dataset[i + look_back, 0])
        return np.array(dataX), np.array(dataY)
    
    trainX, trainY = create_dataset_with_supertrend(train, nifty['ST'].values[:train_size])
    testX, testY = create_dataset_with_supertrend(test, nifty['ST'].values[train_size:])
    

    Next, let's adjust the shape of the input data to account for the additional Supertrend feature and train the LSTM model.

    trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
    testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
    
    model = Sequential()
    model.add(LSTM(100, input_shape=(1, trainX.shape[2])))
    model.add(Dense(1))
    
    model.compile(loss='mean_squared_error', optimizer='adam')
    model.fit(trainX, trainY, epochs=200, batch_size=1, verbose=0)
    

    Lastly, make the next day prediction based on the last data point in the dataset.

    last_close = dataset[-1, :]
    last_supertrend = nifty['ST'].values[-1]
    last_data_point = np.append(last_close, last_supertrend).reshape(1, 1, 2)
    
    next_day_prediction = model.predict(last_data_point)
    next_day_close = scaler.inverse_transform(next_day_prediction)
    
    print("The predicted next day price (2021-01-02) is: ", next_day_close[0, 0])
    

    Here is the complete code:

    import yfinance as yf
    import pandas as pd
    import numpy as np
    from sklearn.preprocessing import MinMaxScaler
    from keras.models import Sequential
    from keras.layers import Dense, LSTM
    import datetime
    import matplotlib.pyplot as plt
    import matplotlib.dates as mdates
    
    nifty = yf.download('^NSEI', start='2009-01-01', end='2021-01-01')
    
    def supertrend(df, period=10, multiplier=3):
        hl = (df['High'] + df['Low']) / 2
        atr = df['High'].rolling(period).max() - df['Low'].rolling(period).min()
        
        up = hl - multiplier * atr
        dn = hl + multiplier * atr
    
        df['ST'] = 0
        df['ST'][0] = (df['High'][0] + df['Low'][0]) / 2
        
        position = 'none'
        
        for i in range(1, len(df)):
            if df['Close'][i] > up[i]:
                if position != 'buy':
                    position = 'buy'
                    df['ST'][i] = dn[i]
                else:
                    df['ST'][i] = max(df['ST'][i - 1], dn[i])
            elif df['Close'][i] < dn[i]:
                if position != 'sell':
                    position = 'sell'
                    df['ST'][i] = up[i]
                else:
                    df['ST'][i] = min(df['ST'][i - 1], up[i])
            else:
                df['ST'][i] = df['ST'][i - 1]
    
        return df
    
    nifty = supertrend(nifty)
    nifty.head()
    
    dataset = nifty['Close'].values
    dataset = dataset.astype('float32')
    dataset = dataset.reshape(-1, 1)
    scaler = MinMaxScaler(feature_range=(0, 1))
    dataset = scaler.fit_transform(dataset)
    
    def create_dataset_with_supertrend(dataset, st, look_back=1):
        dataX, dataY = [], []
        for i in range(len(dataset)-look_back-1):
            a = np.append(dataset[i:(i+look_back), 0], st[i+look_back-1])
            dataX.append(a)
            dataY.append(dataset[i + look_back, 0])
        return np.array(dataX), np.array(dataY)
    
    train_size = int(len(dataset) * 0.8)
    test_size = len(dataset) - train_size
    train, test = dataset[:train_size], dataset[train_size:]
    
    look_back = 1
    trainX, trainY = create_dataset_with_supertrend(train, nifty['ST'].values[:train_size], look_back)
    testX, testY = create_dataset_with_supertrend(test, nifty['ST'].values[train_size:], look_back)
    
    trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
    testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
    
    model = Sequential()
    model.add(LSTM(100, input_shape=(1, trainX.shape[2])))
    model.add(Dense(1))
    
    model.compile(loss='mean_squared_error', optimizer='adam')
    model.fit(trainX, trainY, epochs=200, batch_size=1, verbose=0)
    
    trainPredict = model.predict(trainX)
    testPredict = model.predict(testX)
    
    trainPredict = scaler.inverse_transform(trainPredict)
    trainY = scaler.inverse_transform([trainY])
    testPredict = scaler.inverse_transform(testPredict)
    testY = scaler.inverse_transform([testY])
    
    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.plot(scaler.inverse_transform(dataset), label='Actual')
    plt.plot(trainPredictPlot, label='Train Prediction')
    plt.plot(testPredictPlot, label='Test Prediction')
    plt.legend()
    plt.show()
    
    model.save('my_model.h5')
    
    from sklearn.metrics import mean_squared_error
    import math
    
    trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
    print('Train Score: %.2f RMSE' % (trainScore))
    testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
    print('Test Score: %.2f RMSE' % (testScore))
    
    last_close = dataset[-1, :]
    last_supertrend = nifty['ST'].values[-1]
    last_data_point = np.append(last_close, last_supertrend).reshape(1, 1, 2)
    
    next_day_prediction = model.predict(last_data_point)
    next_day_close = scaler.inverse_transform(next_day_prediction)
    
    print("The predicted next day price (2021-01-02) is: ", next_day_close[0, 0])
    

    After running this code, you should get the predicted next day price for January 2, 2021. Remember that this is just a prediction model, and the actual performance may significantly vary. To improve prediction accuracy, you can tweak the model parameters, experiment with different indicators, or even use more complex architectures such as attention mechanisms or transformers. Always validate your model with out-of-sample data and use proper evaluation metrics.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.