def training_set(events_file: str, no_event_time_shift: int, table_name: str,
directory):
logging.info('start')
# stiahnutie dat
con = ConnectionUtil.create_con()
storage = Storage(events_file, no_event_time_shift, table_name)
d = storage.load_data(con, 0, 0, 'co2_in_ppm')
logging.info('downloaded events: %d' % len(d))
# aplikovanie filtrov na eventy
filtered = FilterUtil.only_valid_events(d)
# for travis
no_ev_records = no_events_records
if ConnectionUtil.is_testable_system():
filtered = filtered[:ConnectionUtil.MAX_TESTABLE_EVENTS]
no_ev_records = no_events_records[:ConnectionUtil.MAX_TESTABLE_EVENTS]
logging.info('events after applying the filter: %d' % len(filtered))
# selector pre data
row_selector = CachedDiffRowWithIntervalSelector(con, table_name, 0, 0)
interval_selector = None
# trenovacia mnozina
logging.info('start computing of training set')
training, tr_events = AttributeUtil.cached_training_data(
con, table_name, filtered, func, row_selector, interval_selector,
'open', '{0}/training_cached.csv'.format(directory))
count = len(training)
logging.info('training set contains %d events (%d records)' %
(count / 2, count))
GraphUtil.gen_duration_histogram(tr_events, 'save', ['png'],
'Histogram dlzok vetrania',
[x for x in range(5, 60, 5)], 1)
training2 = AttributeUtil.additional_training_set(con, table_name,
no_ev_records, func,
row_selector,
interval_selector)
count2 = len(training2)
logging.info('additional training set contains %d records' % count2)
logging.info('end computing of training set')
logging.info('start preparing file of training set')
balanced = AttributeUtil.balance_set(training, training2)
CSVUtil.create_csv_file(balanced, '{0}/training.csv'.format(directory))
logging.info('end preparing file of training set')
def training_set(events_file: str, no_event_time_shift: int, table_name: str):
logging.info('start')
# download data
con = ConnectionUtil.create_con()
storage = Storage(events_file, no_event_time_shift, table_name)
d = storage.load_data(con, 0, 0, 'rh_in2_specific_g_kg')
logging.info('downloaded events: %d' % len(d))
# apply filters to data
filtered = FilterUtil.only_valid_events(d)
# filtered = FilterUtil.temperature_diff(filtered, 5, 100)
# filtered = FilterUtil.temperature_out_max(filtered, 15)
# filtered = FilterUtil.humidity(filtered, 6, 1.6, 100)
# for travis
no_ev_records = no_events_records
if ConnectionUtil.is_testable_system():
filtered = filtered[:ConnectionUtil.MAX_TESTABLE_EVENTS]
no_ev_records = no_events_records[:ConnectionUtil.MAX_TESTABLE_EVENTS]
logging.info('events after applying the filter: %d' % len(filtered))
row_selector = CachedDiffRowWithIntervalSelector(con, table_name, 0, 0)
interval_selector = SimpleIntervalSelector(con, table_name)
logging.info('start computing of training set')
training, tr_events = AttributeUtil.training_data(con, table_name,
filtered, func,
row_selector,
interval_selector,
'open')
count = len(training)
logging.info('training set contains %d events (%d records)' %
(count / 2, count))
training2 = AttributeUtil.additional_training_set(con, table_name,
no_ev_records, func,
row_selector,
interval_selector)
count2 = len(training2)
logging.info('additional training set contains %d records' % count2)
logging.info('end computing of training set')
logging.info('start preparing file of training set')
balanced = AttributeUtil.balance_set(training, training2)
CSVUtil.create_csv_file(balanced, 'training.csv')
logging.info('end preparing file of training set')
def test_db_connection():
con = ConnectionUtil.create_con()
cur = con.cursor()
cur.execute('SELECT VERSION()')
res = cur.fetchone()
logging.info(res)
def testing_set(table_name: str, start, end, filename):
logging.info('start')
con = ConnectionUtil.create_con()
logging.info('start computing of testing set')
length = AttributeUtil.testing_data_with_write(con, table_name, start, end, 30, func,
None, None, 'open', filename)
logging.info('testing set contains %d records' % length)
logging.info('end computing of testing set')
logging.info('end')
def generate_file(con, start_shift, end_shift, output_file, enable_regression):
logging.info('start: ' + output_file)
graphs = Graph("./../../src/graph")
# stiahnutie dat
storage = Storage('examples/events_peto.json', 0, 'measured_filtered_peto')
d = storage.load_data(con, start_shift, end_shift, 'co2_in_ppm')
logging.info('downloaded events: %d' % len(d))
# aplikovanie filtrov na eventy
filtered = FilterUtil.only_valid_events(d)
# for travis
if ConnectionUtil.is_testable_system():
filtered = filtered[:ConnectionUtil.MAX_TESTABLE_EVENTS]
logging.info('events after applying the filter: %d' % len(filtered))
# spocitanie regresie
if enable_regression:
filtered = compute_regression(filtered)
logging.info('start generating graphs')
gr = []
for event in filtered:
t = DateTimeUtil.utc_timestamp_to_str(event['e_start']['timestamp'], '%d.%m. %H:%M:%S')
t += ' - '
t += DateTimeUtil.utc_timestamp_to_str(event['e_end']['timestamp'], '%H:%M:%S')
if enable_regression:
gg = [
Graph.db_to_simple_graph(event, 'co2_in_ppm', 'green', 'CO2', 50),
Graph.db_to_simple_graph(event, 'co2_in_ppm_exp', 'red', 'SimpleExpRegression', 50),
Graph.db_to_simple_graph(event, 'co2_in_ppm_exp2', 'orange', 'ExpRegressionWithDelay', 50),
]
else:
gg = [
Graph.db_to_simple_graph(event, 'co2_in_ppm', 'green', 'CO2', 50),
]
g = {
'title': t,
'graphs': gg
}
gr.append(g)
graphs.gen(gr, output_file + '.html', 0, 0)
logging.info('end generating graphs')
logging.info('end')
def training_set(events_file: str, no_event_time_shift: int, table_name: str):
logging.info('start')
# stiahnutie dat
con = ConnectionUtil.create_con()
storage = Storage(events_file, no_event_time_shift, table_name)
d = storage.load_data(con, 0, 0, 'co2_in_ppm')
logging.info('downloaded events: %d' % len(d))
# aplikovanie filtrov na eventy
filtered = FilterUtil.only_valid_events(d)
# for travis
if ConnectionUtil.is_testable_system():
filtered = filtered[:ConnectionUtil.MAX_TESTABLE_EVENTS]
logging.info('events after applying the filter: %d' % len(filtered))
# selector pre data
row_selector = CachedDiffRowWithIntervalSelector(con, table_name, 0, 0)
interval_selector = None
# datova mnozina
logging.info('start computing of data set')
data = AttributeUtil.training_data_without_opposite(
con, table_name, filtered, func, row_selector, interval_selector)
logging.info('data set contains %d events' % len(data))
logging.info('end computing of data set')
# generovanie suborov
logging.info('start preparing file of training and testing set')
random.seed(len(data) // 2)
random.shuffle(data)
CSVUtil.create_csv_file(data, 'data.csv')
logging.info('end preparing file of training and testing set')
logging.info('end')
def list_of_processes(directory='ventilation_length'):
return [
'//DIP/{0}/RandomForest'.format(directory),
'//DIP/{0}/NeuralNet'.format(directory),
]
if __name__ == '__main__':
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(levelname)s %(message)s')
logging.info('start')
launcher = ConnectionUtil.rapid_miner()['launcher']
out_s_maskou = []
out_s_exp = []
all = []
for proc in list_of_processes():
proc_name = proc.split('/')[-1]
row_klasicky = [('nazov', proc_name), ('pristup', 'klasicky')]
row_s_maskou = [('nazov', proc_name), ('pristup', 's_maskou')]
row_s_exp = [('nazov', proc_name), ('pristup', 's_exp')]
for bin in range(2, 33):
cmd = [
launcher,
proc,
title = 'window_size:{0},threshold:{1}'.format(window_size, threshold)
gen_graph(events_delays, action, extensions, title)
logger.disabled = False
if __name__ == '__main__':
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(levelname)s %(message)s')
logging.info('start')
table_name = 'measured_filtered_peto'
# stiahnutie dat
con = ConnectionUtil.create_con()
storage = Storage('examples/events_peto.json', 0, table_name)
d = storage.load_data(con, 0, 0, 'co2_in_ppm')
logging.info('downloaded events: %d' % len(d))
# aplikovanie filtrov na eventy
filtered = FilterUtil.only_valid_events(d)
# for travis
if ConnectionUtil.is_testable_system():
filtered = filtered[:ConnectionUtil.MAX_TESTABLE_EVENTS]
logging.info('events after applying the filter: %d' % len(filtered))
extensions = ['eps']
delays(filtered, extensions, ['save'], 11, 15)
def main(events_file: str, owner: str, start_shift: int, end_shift: int,
output_filename: str, number_output_records: int):
"""
:param events_file: path to file containing list of events
:param owner: sensor owner(klarka|peto), name must be the same as in database
:param start_shift: shift of beginning of data downloading
:param end_shift: shift of end of data downloading
:param output_filename: filename to store a graph
:param number_output_records: number of points that are required in graph
:return:
"""
logging.info('start: ' + output_filename)
graphs = Graph("./../../src/graph")
# download data
con = ConnectionUtil.create_con()
storage = Storage(events_file, 0, 'measured_' + owner)
d = storage.load_data(con, start_shift, end_shift,
'temperature_in_celsius')
logging.info('downloaded events: %d' % len(d))
# apply filters to downloaded data
filtered = FilterUtil.only_valid_events(d)
filtered = FilterUtil.temperature_diff(filtered, 5, 100)
filtered = FilterUtil.temperature_out_max(filtered, 15)
filtered = FilterUtil.humidity(filtered, 6, 1.6, 100)
# for travis
if ConnectionUtil.is_testable_system():
filtered = filtered[:ConnectionUtil.MAX_TESTABLE_EVENTS]
if owner == 'klarka':
filtered = FilterUtil.attribute(filtered, 'window', 'dokoran')
logging.info('events after applying the filter: %d' % len(filtered))
# data for graph generation measured using sensor 1
sensor1_events = filtered
logging.info('event count: %d for senzor 1' % len(sensor1_events))
# data for graph generation measured using sensor 2
sensor2 = [
'rh_in2_percentage', 'rh_in2_specific_g_kg', 'rh_in2_absolute_g_m3'
]
sensor2_events = FilterUtil.measured_values_not_empty(filtered, sensor2)
logging.info('event count: %d for senzor 2' % len(sensor2_events))
# graph generation - sensor 1
logging.info('start generating graphs of events from sensor 1')
graphs_sensor_1 = []
for event in sensor1_events:
graphs_sensor_1 += generate_graphs_sensor_1(event, owner,
number_output_records)
graphs.gen(graphs_sensor_1, 'sensor1_' + output_filename, 0, 0)
logging.info('end generating graphs of events from sensor 1')
# graph generation - sensor 2
logging.info('start generating graphs of events from sensor 2')
graphs_sensor_2 = []
for event in sensor2_events:
graphs_sensor_2 += generate_graphs_sensor_2(event, owner,
number_output_records)
graphs.gen(graphs_sensor_2, 'sensor2_' + output_filename, 0, 0)
logging.info('end generating graphs of events from sensor 2')
logging.info('end')
def generate_file(con, start_shift, end_shift, output_file):
logging.info('start: ' + output_file)
graphs = Graph("./../../src/graph")
# download data
storage = Storage('examples/events_klarka_shower.json', 0, 'measured_klarka_shower')
d = storage.load_data(con, start_shift, end_shift, 'temperature_in_celsius')
logging.info('downloaded events: %d' % len(d))
# apply filters to events
filtered = FilterUtil.only_valid_events(d)
# for travis
if ConnectionUtil.is_testable_system():
filtered = filtered[:ConnectionUtil.MAX_TESTABLE_EVENTS]
logging.info('events after applying the filter: %d' % len(filtered))
fill_start_end(filtered)
logging.info('start generating graphs')
gr = []
for event in filtered:
t = DateTimeUtil.utc_timestamp_to_str(event['e_start']['timestamp'], '%d.%m. %H:%M:%S')
t += ' - '
t += DateTimeUtil.utc_timestamp_to_str(event['e_end']['timestamp'], '%H:%M:%S')
g = {
'title': t,
'group': 'one',
'graphs': [
Graph.db_to_simple_graph(event, 'temperature_in_celsius', 'blue',
'Temperature', 75),
Graph.db_to_simple_graph(event, 'open_close', 'orange', 'Open', 75),
]
}
gr.append(g)
g = {
'title': t,
'group': 'two',
'graphs': [
Graph.db_to_simple_graph(event, 'rh_in_percentage', 'red',
'Relative humidity [%]', 75),
Graph.db_to_simple_graph(event, 'open_close', 'orange', 'Open', 75),
]
}
gr.append(g)
g = {
'title': t,
'group': 'tree',
'graphs': [
Graph.db_to_simple_graph(event, 'rh_in_absolute_g_m3', 'green',
'Absolute humidity [g/m3]', 75),
Graph.db_to_simple_graph(event, 'open_close', 'orange', 'Open', 75),
]
}
gr.append(g)
g = {
'title': t,
'group': 'four',
'graphs': [
Graph.db_to_simple_graph(event, 'rh_in_specific_g_kg', 'purple',
'Specific humidity [g/kg]', 75),
Graph.db_to_simple_graph(event, 'open_close', 'orange', 'Open', 75),
]
}
gr.append(g)
graphs.gen(gr, output_file + '.html', 0, 0, global_range=True)
logging.info('end generating graphs')
Graph.db_to_simple_graph(event, 'rh_in_absolute_g_m3', 'green',
'Absolute humidity [g/m3]', 75),
Graph.db_to_simple_graph(event, 'open_close', 'orange', 'Open', 75),
]
}
gr.append(g)
g = {
'title': t,
'group': 'four',
'graphs': [
Graph.db_to_simple_graph(event, 'rh_in_specific_g_kg', 'purple',
'Specific humidity [g/kg]', 75),
Graph.db_to_simple_graph(event, 'open_close', 'orange', 'Open', 75),
]
}
gr.append(g)
graphs.gen(gr, output_file + '.html', 0, 0, global_range=True)
logging.info('end generating graphs')
if __name__ == '__main__':
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(levelname)s %(message)s', )
con = ConnectionUtil.create_con()
generate_file(con, 0, 0, 'shower')
generate_file(con, -900, +900, 'shower_with_shift')
def main(events_file: str, no_event_time_shift: int):
logging.info('start')
table_name = 'measured_klarka'
# download data
con = ConnectionUtil.create_con()
storage = Storage(events_file, no_event_time_shift, table_name)
d = storage.load_data(con, 0, 0, 'rh_in2_specific_g_kg')
logging.info('downloaded events: %d' % len(d))
# apply filters to data
filtered = FilterUtil.only_valid_events(d)
# filtered = FilterUtil.temperature_diff(filtered, 5, 17.5)
# filtered = FilterUtil.temperature_diff(filtered, 17.5, 30)
# filtered = FilterUtil.temperature_diff(filtered, 5, 13.3)
# filtered = FilterUtil.temperature_diff(filtered, 13.3, 21.6)
# filtered = FilterUtil.temperature_diff(filtered, 21.6, 30)
# filtered = FilterUtil.temperature_diff(filtered, 10, 15)
# filtered = FilterUtil.temperature_diff(filtered, 15, 20)
# filtered = FilterUtil.temperature_diff(filtered, 20, 25)
logging.info('events after applying the filter: %d' % len(filtered))
row_selector = CachedDiffRowWithIntervalSelector(con, table_name, 0, 0)
interval_selector = SimpleIntervalSelector(con, table_name)
# data set
logging.info('start computing of data set')
data = AttributeUtil.training_data_without_opposite(
con, table_name, filtered, func, row_selector, interval_selector)
logging.info('data set contains %d events' % len(data))
logging.info('end computing of data set')
# split data set into training and testing set
random.seed(len(data) // 2)
random.shuffle(data)
training, testing, minimum = training_testing_data(data, 0.7)
logging.info('training set contains %d records, each %d-krat' %
(len(training), minimum))
logging.info('testing set contains %d records' % len(testing))
training_testing_data_with_distance(copy.deepcopy(training),
copy.deepcopy(testing), 0,
CenterLineSlope(), "trendline_", False,
False, False, False)
training_testing_data_with_distance(copy.deepcopy(training),
copy.deepcopy(testing), 1,
PolyfitLineAvgSlope(), "polyfit_",
False, False, False, False)
training_testing_data_with_distance(copy.deepcopy(training),
copy.deepcopy(testing), 2,
CenterLineSlope(), "center_", False,
False, False, False)
training_testing_data_only_distance(copy.deepcopy(training),
copy.deepcopy(testing), 3,
CenterLineSlope(), "trendline_", False,
False, False, False)
training_testing_data_only_distance(copy.deepcopy(training),
copy.deepcopy(testing), 4,
PolyfitLineAvgSlope(), "polyfit_",
False, False, False, False)
training_testing_data_only_distance(copy.deepcopy(training),
copy.deepcopy(testing), 5,
CenterLineSlope(), "center_", False,
False, False, False)
training_testing_data_without_distance(copy.deepcopy(training),
copy.deepcopy(testing), 6,
CenterLineSlope(), "trendline_",
False, False, False, False)
logging.info('end')
def main(events_file: str, start_shift: int, end_shift: int,
output_filename: str, output_records: int):
logging.info('start')
graphs = Graph("./../../src/graph")
# download data
con = ConnectionUtil.create_con()
storage = Storage(events_file, 0, 'measured_klarka')
d = storage.load_data(con, start_shift, end_shift,
'temperature_in_celsius')
logging.info('downloaded events: %d' % len(d))
# apply filters to events
filtered = FilterUtil.only_valid_events(d)
filtered = FilterUtil.temperature_diff(filtered, 5, 100)
filtered = FilterUtil.temperature_out_max(filtered, 15)
filtered = FilterUtil.humidity(filtered, 6, 1.6, 100)
min_timestamp = int(
DateTimeUtil.local_time_str_to_utc('2018/11/01 00:01:00').timestamp())
filtered = FilterUtil.min_timestamp(filtered, min_timestamp)
filtered = FilterUtil.min_max_time_interval(filtered, 1440, 1620)
# for travis
if ConnectionUtil.is_testable_system():
filtered = filtered[:ConnectionUtil.MAX_TESTABLE_EVENTS]
logging.info('events after applying the filter: %d' % len(filtered))
# data for graph generation measured using sensor 1
sensor1_events = filtered
logging.info('event count: %d for senzor 1' % len(sensor1_events))
linear_reg(sensor1_events, 'rh_in_specific_g_kg', 'linear1_sh')
linear_reg(sensor1_events, 'rh_in_absolute_g_m3', 'linear1_ah')
linear_reg(sensor1_events, 'temperature_in_celsius', 'linear1_temp')
# graph generation - sensor 1
logging.info('start generating graphs of events from sensor 1')
graphs_sensor_1 = []
for event in sensor1_events:
graphs_sensor_1 += gen_graphs(event, output_records, [
'rh_in_specific_g_kg', 'rh_in_absolute_g_m3',
'temperature_in_celsius'
], ['linear1_sh', 'linear1_ah', 'linear1_temp'])
graphs.gen(graphs_sensor_1,
'sensor1_' + output_filename,
0,
0,
global_range=True)
logging.info('end generating graphs of events from sensor 1')
# data for graph generation measured using sensor 2
sensor2_events = filtered
logging.info('event count: %d for sensor 2' % len(sensor2_events))
sensor2_events = FilterUtil.measured_values_not_empty(
sensor2_events, 'rh_in2_specific_g_kg')
sensor2_events = FilterUtil.measured_values_not_empty(
sensor2_events, 'rh_in2_absolute_g_m3')
sensor2_events = FilterUtil.measured_values_not_empty(
sensor2_events, 'temperature_in2_celsius')
logging.info('events after applying the filter: %d' % len(sensor2_events))
linear_reg(sensor2_events, 'rh_in2_specific_g_kg', 'linear2_sh')
linear_reg(sensor2_events, 'rh_in2_absolute_g_m3', 'linear2_ah')
linear_reg(sensor2_events, 'temperature_in2_celsius', 'linear2_temp')
humidity_info_csv(sensor2_events, start_shift, end_shift)
# graph generation - sensor 2
logging.info('start generating graphs of events from sensor 2')
graphs_sensor_2 = []
for event in sensor2_events:
graphs_sensor_2 += gen_graphs(event, output_records, [
'rh_in2_specific_g_kg', 'rh_in2_absolute_g_m3',
'temperature_in2_celsius'
], ['linear2_sh', 'linear2_ah', 'linear2_temp'])
graphs.gen(graphs_sensor_2,
'sensor2_' + output_filename,
0,
0,
global_range=True)
logging.info('end generating graphs of events from sensor 2')
logging.info('end')