def plot_validation_predict_and_obs(self, show_title=True, save_loc=None, plot_bounds=None):
show_title = False
save_loc = None
plot_bounds = None
#plot_bounds=(1150, 1200)
#save_loc = 'pic_ANN_set0_validation1'
plot_bounds=(5180, 5230)
save_loc = 'pic_ANN_set0_validation2'
label_font = {'size': 20}
tick_label_size = 15
title_label_size = 30
predictions = self.ml_obj.best_network[0].sim(self.ml_obj.validation_input)
observations = self.ml_obj.validation_target
if True: # this can be changed to self.min_max_scaler_target is not None (cant yet due to legacy)
min_max_scaler_target = preprocessing.MinMaxScaler()
training_target = min_max_scaler_target.fit_transform(self.data_package.training_target)
predictions = min_max_scaler_target.inverse_transform(predictions)
observations = min_max_scaler_target.inverse_transform(observations)
print(get_all_error_metrics(observations, predictions, None))
#if self.ml_obj.min_max_scaler_target is not None:
# predictions = self.min_max_scaler_target.inverse_transform(predictions)
# observations = self.min_max_scaler_target.inverse_transform(observations)
fig_validation = plt.figure(figsize=(10, 8))
ax = fig_validation.add_subplot(111)
x = []
dt = datetime.datetime.combine(self.data_package.validation_start_date, datetime.datetime.min.time())
for i in range(len(self.ml_obj.validation_input)):
x.append(dt + datetime.timedelta(minutes=(15 * i)))
if plot_bounds is not None:
lower = plot_bounds[0]
upper = plot_bounds[1]
ax.plot(x[lower:upper], observations.clip(min=0)[lower:upper], 'o-', label='observations')
ax.plot(x[lower:upper], predictions.clip(min=0, max=10)[lower:upper], 'r^-', label='predictions')
else:
ax.plot(x, observations.clip(min=0), 'o-', label='observations')
ax.plot(x, predictions.clip(min=0, max=10), 'r^-', label='predictions')
if show_title:
errors_dict = calc_all_error('RMSE, NSE, RSEnaive, R', observations, predictions, round_to=5,
rolling_average_size=96, upper_lim=10, lower_lim=0.05)
fig_validation.suptitle('Validation Data: RMSE: {} NSE: {} RSEnaive: {} R: {}'.format(
errors_dict['RMSE'], errors_dict['NSE'], errors_dict['RSEnaive'], errors_dict['R']), fontsize=title_label_size)
ax.set_ylabel('Turbidity in NTU', fontdict=label_font)
ax.tick_params(axis='both', which='major', labelsize=tick_label_size)
ax.legend(loc='best')
fig_validation.tight_layout()
if show_title:
fig_validation.subplots_adjust(top=0.90)
if save_loc is not None:
plt.savefig(save_loc+'.png')
else:
plt.show()
def run_main():
# load in data settings about a data set from a ini file, ini file must be in same directory as this file
data_settings = DataSetSettings(os.path.join(os.path.dirname(os.getcwd()), ini_file))
data_set_files = data_settings.get_data_set_files()
meter_groups = []
for meter_file in data_set_files:
# create meter groups from csv data
meter_groups.append(MeterGroup(meter_file[0], meter_file[1], meter_file[2]))
# set meter group settings
meter_groups[-1].set_meter_group_settings(data_settings.meter_groups())
# create data packer and add meter groups
data_packer1 = DataPacker(meter_groups)
for time_horizon in range(1, 2):
# package data for machine learning
data_package1 = data_packer1.package_data(data_settings.packer_input(), data_settings.packer_target(),
forecast_horizon_override=time_horizon)
print('Data Packaged')
if False:
data = data_package1.training_input.T
# data = data_package1.validation_input.T
meta = data_package1.training_input_meta[0]
embedding_search_fnn(data, meta, go_to=15, threshold=50, ratio=0.001)
if False:
for ann_count in range(10):
with open(os.path.join(os.path.dirname(os.getcwd()), log_file), 'a') as f:
f.write('Forecast Horizon: {} ANN Count: {}\n'.format(time_horizon, ann_count))
while True:
# create machine learning obj to run ANN
ann1 = MachineLearning('ANN', data_package1, data_settings.ann())
print('Machine Learning Obj Initialized')
# run: ml_type, package_name, network_layout, layer_func, max_epochs, trains_per_validation_run,
# max_worse_validations stop_function, training_goal, verbose_settings
#code, msg = ann1.run(network_layout='{}, 1'.format(time_horizon))
code, msg = ann1.run()
if code == 1: # Failed to learn
print(msg)
with open(os.path.join(os.path.dirname(os.getcwd()), log_file), 'a') as f:
f.write(msg + '\n')
else:
print(msg)
with open(os.path.join(os.path.dirname(os.getcwd()), log_file), 'a') as f:
f.write(msg + '\n')
print('Machine Learning Obj Finished Run')
data_collector1 = DataCollector(ann1, data_package1, data_settings)
pickle_file = 'data\\Hillersdon\\hill-exp{}_p{}-h50-t{}-r{}.pickle'.format(
experiment_id, process_id, time_horizon, ann_count)
with open(pickle_file, 'wb') as pf:
pickle.dump(data_collector1, pf, pickle.HIGHEST_PROTOCOL)
print('Data Collector Pickled')
with open(os.path.join(os.path.dirname(os.getcwd()), log_file), 'a') as f:
f.write('Run Count: {}, Pickled: {}\n'.format(str(len(data_collector1.ml_obj.inbuilt_errors)), pickle_file))
f.write('Training Errors: {}\n'.format(get_last_errors(ann1.training_errors)))
f.write('Validation Errors: {}\n'.format(get_last_errors(ann1.validation_errors)))
predictions = data_collector1.ml_obj.best_network[0].sim(data_collector1.ml_obj.training_input)
observations = data_collector1.ml_obj.training_target
train_errors_str = get_all_error_metrics(observations, predictions, data_collector1.data_package)
predictions = data_collector1.ml_obj.best_network[0].sim(data_collector1.ml_obj.validation_input)
observations = data_collector1.ml_obj.validation_target
val_errors_str = get_all_error_metrics(observations, predictions, data_collector1.data_package)
with open(os.path.join(os.path.dirname(os.getcwd()), results_file), 'a') as f:
f.write('Run Count: {}, Pickled: {}\n'.format(str(len(data_collector1.ml_obj.inbuilt_errors)), pickle_file))
f.write('Training Errors, {}\n'.format(train_errors_str))
f.write('Validation Errors, {}\n'.format(val_errors_str))
#data_collector1.plot_all()
break
print('Done!')
def plot_training_predict_and_obs(self, show_title=True, save_loc=None, plot_bounds=None):
show_title = False
save_loc = None
plot_bounds = None
#plot_bounds=(5750, 6300)
#save_loc = 'pic_ANN_set0_training1'
plot_bounds = (15690, 15760)
save_loc = 'pic_ANN_set0_training2'
label_font = {'size': 20}
tick_label_size = 15
title_label_size = 30
predictions = self.ml_obj.best_network[0].sim(self.ml_obj.training_input)
observations = self.ml_obj.training_target
#if self.ml_obj.min_max_scaler_target is not None:
# predictions = self.min_max_scaler_target.inverse_transform(predictions)
# observations = self.min_max_scaler_target.inverse_transform(observations)
if True: # this can be changed to self.min_max_scaler_target is not None (cant yet due to legacy)
min_max_scaler_target = preprocessing.MinMaxScaler()
training_target = min_max_scaler_target.fit_transform(self.data_package.training_target)
predictions = min_max_scaler_target.inverse_transform(predictions)
observations = min_max_scaler_target.inverse_transform(observations)
if False:
bench = []
hist_error = []
# Mean
for i in range(len(predictions)):
bench.append(observations.mean())
hist_error.append(abs(observations[i] - bench[i]))
# # Rolling Mean
# rolling_average_size = 4
# bench.append(observations[0][0])
# hist_error.append(abs(observations[0] - bench[0]))
# for i in range(1, len(predictions)):
# y = i - rolling_average_size
# if y < 0:
# y = 0
# bench.append(np.mean(observations[y:i]))
# hist_error.append(abs(observations[i] - bench[i]))
# # Naive
# bench.append(observations[0])
# hist_error.append(abs(observations[0] - bench[0]))
# for i in range(1, len(predictions)):
# bench.append(observations[i - 1])
# hist_error.append(abs(observations[i] - bench[i]))
# # Positive Diff Naive
# bench.append(observations[0])
# hist_error.append(abs(observations[0] - bench[0]))
# for i in range(1, len(predictions)):
# bench.append(observations[i-1])
# if observations[i] > observations[i-1]:
# hist_error.append(abs(observations[i] - bench[i]))
# else:
# hist_error.append(0)
# # Positive Diff Naive (only > 2 NTU)
# bench.append(observations[0])
# hist_error.append(abs(observations[0] - bench[0]))
# for i in range(1, len(predictions)):
# bench.append(observations[i - 1])
# if observations[i] > observations[i - 1] and observations[i] >= 2:
# hist_error.append(abs(observations[i] - bench[i]))
# else:
# hist_error.append(0)
hist_error = np.array(hist_error)
predictions = np.array(bench)
print(get_all_error_metrics(observations, predictions, None))
fig_training = plt.figure(figsize=(10, 8))
ax = fig_training.add_subplot(111)
x = []
dt = datetime.datetime.combine(self.data_package.training_start_date, datetime.datetime.min.time())
for i in range(len(self.ml_obj.training_input)):
x.append(dt + datetime.timedelta(minutes=(15*i)))
if plot_bounds is not None:
lower = plot_bounds[0]
upper = plot_bounds[1]
ax.plot(x[lower:upper], observations.clip(min=0)[lower:upper], 'o-', label='observations')
ax.plot(x[lower:upper], predictions.clip(min=0, max=10)[lower:upper], 'r^-', label='predictions')
#ax.bar(x[lower:upper], hist_error[lower:upper], color='g', width=0.005, align='center', label='absolute error')
else:
ax.plot(x, observations.clip(min=0), 'o-', label='observations')
ax.plot(x, predictions.clip(min=0, max=10), 'r^-', label='predictions') # TODO: reassess
if show_title:
errors_dict = calc_all_error('RMSE, NSE, RSEnaive, R', observations, predictions, round_to=5,
rolling_average_size=96, upper_lim=10, lower_lim=0.05) # TODO: make dynamic
fig_training.suptitle('Training Data: RMSE: {} NSE: {} RSEnaive: {} R: {}'.format(
errors_dict['RMSE'], errors_dict['NSE'], errors_dict['RSEnaive'], errors_dict['R']), fontsize=title_label_size)
ax.set_ylabel('Turbidity in NTU', fontdict=label_font)
ax.tick_params(axis='both', which='major', labelsize=tick_label_size)
ax.legend(loc='best')
fig_training.tight_layout()
if show_title:
fig_training.subplots_adjust(top=0.90)
if save_loc is not None:
plt.savefig(save_loc + '.png')
else:
plt.show()
