Spaces:
Runtime error
Runtime error
Download ml.py from solomonerous/space1: direct link, hf CLI and curl.
- Browser
- Download file 3.3 kB
-
https://huggingface.co/spaces/solomonerous/space1/resolve/main/ml.py
- Command line
-
hf download hf://spaces/solomonerous/space1/ml.py
-
curl -L -o ml.py https://huggingface.co/spaces/solomonerous/space1/resolve/main/ml.py
3.3 kB
| 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() | |