import matplotlib.pyplot as plt import numpy as np import pandas as pd from sklearn.preprocessing import MinMaxScaler from tensorflow import keras from tensorflow.keras.layers import Bidirectional, LSTM, Dropout, Activation, Dense RANDOM_SEED = 42 SEQ_LEN = 100 DROPOUT = 0.2 WINDOW_SIZE = SEQ_LEN - 1 BATCH_SIZE = 64 def load_data(csv_path): df = pd.read_csv(csv_path, parse_dates=['Date']) df = df.sort_values('Date') return df def plot_data(df): ax = df.plot(x='Date', y='Close') ax.set_xlabel("Date") ax.set_ylabel("Close Price (USD)") def scale_data(data): scaler = MinMaxScaler() scaled_data = scaler.fit_transform(data.values.reshape(-1, 1)) scaled_data = scaled_data[~pd.isnull(scaled_data)] return scaled_data.reshape(-1, 1), scaler def to_sequences(data, seq_len): d = [] for index in range(len(data) - seq_len): d.append(data[index: index + seq_len]) return np.array(d) def preprocess(data_raw, seq_len, train_split): data = to_sequences(data_raw, seq_len) num_train = int(train_split * data.shape[0]) X_train = data[:num_train, :-1, :] y_train = data[:num_train, -1, :] X_test = data[num_train:, :-1, :] y_test = data[num_train:, -1, :] return X_train, y_train, X_test, y_test def build_model(X_train): model = keras.Sequential() model.add( Bidirectional(LSTM(WINDOW_SIZE, return_sequences=True), input_shape=(WINDOW_SIZE, X_train.shape[-1]))) model.add(Dropout(rate=DROPOUT)) model.add(Bidirectional(LSTM((WINDOW_SIZE * 2), return_sequences=True))) model.add(Dropout(rate=DROPOUT)) model.add(Bidirectional(LSTM(WINDOW_SIZE, return_sequences=False))) model.add(Dense(units=1)) model.add(Activation('linear')) model.compile(loss='mean_squared_error', optimizer='adam') return model def train_model(model, X_train, y_train): return model.fit( X_train, y_train, epochs=50, batch_size=BATCH_SIZE, shuffle=False, validation_split=0.1 ) def plot_model_loss(history): plt.plot(history.history['loss']) plt.plot(history.history['val_loss']) plt.title('model loss') plt.ylabel('loss') plt.xlabel('epoch') plt.legend(['train', 'test'], loc='upper left') plt.show() def plot_predicted_price(X_test, y_test, model, scaler): y_hat_inverse = scaler.inverse_transform(model.predict(X_test)) y_test_inverse = scaler.inverse_transform(y_test) plt.plot(y_test_inverse, label="Actual Price", color='green') plt.plot(y_hat_inverse, label="Predicted Price", color='red') plt.title('Bitcoin price prediction') plt.xlabel('Time [days]') plt.ylabel('Price') plt.legend(loc='best') plt.show() def main(): csv_path = "https://raw.githubusercontent.com/curiousily/Deep-Learning-For-Hackers/master/data/3.stock-prediction/BTC-USD.csv" df = load_data(csv_path) plot_data(df) scaled_data, scaler = scale_data(df['Close']) X_train, y_train, X_test, y_test = preprocess(scaled_data, SEQ_LEN, train_split=0.95) model = build_model(X_train) history = train_model(model, X_train, y_train) plot_model_loss(history) plot_predicted_price(X_test, y_test, model, scaler) if __name__ == "__main__": main()