def plot_forecast(data, year, month, day, hour):
day_date_time, inputs, label = get_day_data(data[0]['test'], data[0]['test_datetime'], year, month, day, hour)
for model in data:
pred = tm.get_predictions(model['model'],
inputs.reshape(1, cfg.prediction['num_predictions'], model['num_features']),
label.reshape(1, cfg.prediction['num_predictions']),
model['scaler']).reshape(-1)
plt.plot(day_date_time[cfg.prediction['num_predictions']:], pred, label=model['name'],
color=model.get('plotting', {}).get('color', None),
marker=model.get('plotting', {}).get('marker', 'x'),
linestyle=model.get('plotting', {}).get('linestyle', '-'),
linewidth=2, markersize=5, zorder=2.7)
label = data[0]['scaler'].inverse_transform(label.reshape(-1, 1))
inputs = data[0]['scaler'].inverse_transform(inputs[:, 0].reshape(-1, 1))
plt.plot(day_date_time, np.concatenate([inputs[:, 0], label.reshape(-1)]), color='k',
label='True', marker='.', markersize=3, zorder=2.6)
# plt.title(data[0]['city'].capitalize() + ' ' + str(day) + '.' + str(month) + '.' + str(year))
plt.title(data[0]['city'].capitalize() + ', ' + day_date_time[24].date().strftime('%d.%m.%y'))
plt.ylabel(f'global irradiation [$Wh/m^2$]')
plt.xticks(day_date_time[::6], map(pd.Timestamp.time, day_date_time[::6]), rotation=20)
formatter = DateFormatter('%H:%M')
plt.gca().xaxis.set_major_formatter(formatter)
plt.gcf().autofmt_xdate()
plt.legend()
plt.grid(True)
return plt
def plot(self,
model=None,
plot_col=cfg.label,
max_subplots=3,
myscaler=None):
inputs, labels = self.example
plt.figure(figsize=(12, 8))
plot_col_index = self.column_indices[plot_col]
max_n = min(max_subplots, len(inputs))
if myscaler is None:
file_scaler = open('saver/outputs/scaler/scaler.pckl', 'rb')
scaler = pickle.load(file_scaler)
else:
scaler = myscaler
plt.suptitle(model.my_name)
for n in range(max_n):
plt.subplot(3, 1, n + 1)
plt.ylabel(f'{plot_col} in Wh/m^2')
plt.plot(self.input_indices,
scaler.inverse_transform(
inputs[n, :, plot_col_index].numpy().reshape(-1, 1)),
label='Inputs',
marker='.',
zorder=-10)
if self.label_columns:
label_col_index = self.label_columns_indices.get(
plot_col, None)
else:
label_col_index = plot_col_index
if label_col_index is None:
continue
plt.scatter(self.label_indices,
scaler.inverse_transform(
labels[n, :,
label_col_index].numpy().reshape(-1, 1)),
edgecolors='k',
label='Labels',
c='#2ca02c',
s=64)
if model is not None:
predictions = tm.get_predictions(model, inputs, labels, scaler)
plt.scatter(self.label_indices,
predictions[n, :],
marker='X',
edgecolors='k',
label='Predictions',
c='#ff7f0e',
s=64)
if n == 0:
plt.legend()
plt.xlabel('Time [h]')
plt.show()
def get_metrics(self, model, scaler, city='unknown'):
pred = []
label = []
weight = []
err = []
for data in self.test:
inputs, labels = data
labels = labels.numpy()
# labels = labels[:, :, 0].numpy()
predictions = tm.get_predictions(model, inputs.numpy(), labels,
scaler)
pred.extend(predictions)
label.extend(labels)
weight.extend(determine_weight(labels))
err_help = scaler.inverse_transform(labels) - predictions
err_help[labels == 0] = float('NaN')
err.extend(err_help)
pred = np.array(pred)
label = scaler.inverse_transform(np.array(label))
# print(model.model_type)
# err_test = label-pred
err = np.array(err)
skewness = skew(err, nan_policy='omit')
# if model.model_type == 'lstm_conv':
# plt.hist(err[:, 5], bins=50)
# plt.title('LSTMconv')
# plt.xlabel('error')
# plt.ylabel('frequency')
# plt.show()
if cfg.errors['error_to_excel']:
writepath = 'saver/outputs/errors/' + city + '.xlsx'
mode = 'a' if os.path.exists(writepath) else 'w'
sheet = model.model_type
err_df = pd.DataFrame(err)
err_df.columns = [
'hour' + str(i)
for i in range(cfg.prediction['num_predictions'])
]
with pd.ExcelWriter(writepath, mode=mode) as writer:
# if sheet in writer.book.sheetnames:
# writer.book.remove(writer.book[sheet])
err_df.to_excel(writer, sheet, float_format='%.5f')
writer.save()
rmse = mean_squared_error(label,
pred,
sample_weight=weight,
multioutput='raw_values',
squared=False)
# rmse = mean_squared_error(label, pred, multioutput='raw_values', squared=False)
mae = mean_absolute_error(label,
pred,
sample_weight=weight,
multioutput='raw_values')
# mae = mean_absolute_error(label, pred, multioutput='raw_values')
return rmse, mae, skewness