split_train_validate.py

def prepare_data_x(x, window_size):
    # perform windowing
    n_row = x.shape[0] - window_size + 1
    output = np.lib.stride_tricks.as_strided(x, shape=(n_row, window_size), strides=(x.strides[0], x.strides[0]))
    return output[:-1], output[-1]


def prepare_data_y(x, window_size):
    # # perform simple moving average
    # output = np.convolve(x, np.ones(window_size), 'valid') / window_size

    # use the next day as label
    output = x[window_size:]
    return output

data_x, data_x_unseen = prepare_data_x(normalized_data_close_price, window_size=config["data"]["window_size"])
data_y = prepare_data_y(normalized_data_close_price, window_size=config["data"]["window_size"])

# split dataset

split_index = int(data_y.shape[0]*config["data"]["train_split_size"])
data_x_train = data_x[:split_index]
data_x_val = data_x[split_index:]
data_y_train = data_y[:split_index]
data_y_val = data_y[split_index:]

# prepare data for plotting

to_plot_data_y_train = np.zeros(num_data_points)
to_plot_data_y_val = np.zeros(num_data_points)

to_plot_data_y_train[config["data"]["window_size"]:split_index+config["data"]["window_size"]] = scaler.inverse_transform(data_y_train)
to_plot_data_y_val[split_index+config["data"]["window_size"]:] = scaler.inverse_transform(data_y_val)

to_plot_data_y_train = np.where(to_plot_data_y_train == 0, None, to_plot_data_y_train)
to_plot_data_y_val = np.where(to_plot_data_y_val == 0, None, to_plot_data_y_val)

## plots

fig = figure(figsize=(25, 5), dpi=80)
fig.patch.set_facecolor((1.0, 1.0, 1.0))
plt.plot(data_date, to_plot_data_y_train, label="Prices (train)", color=config["plots"]["color_train"])
plt.plot(data_date, to_plot_data_y_val, label="Prices (validation)", color=config["plots"]["color_val"])
xticks = [data_date[i] if ((i%config["plots"]["xticks_interval"]==0 and (num_data_points-i) > config["plots"]["xticks_interval"]) or i==num_data_points-1) else None for i in range(num_data_points)] # make x ticks nice
x = np.arange(0,len(xticks))
plt.xticks(x, xticks, rotation='vertical')
plt.title("Daily close prices for " + config["alpha_vantage"]["symbol"] + " - showing training and validation data")
plt.grid(b=None, which='major', axis='y', linestyle='--')
plt.legend()
plt.show()