def extract_current_data_at_index(fixed_df, current_gauge_column_index):
current_gauge_number = fixed_df.iloc[1, current_gauge_column_index]
current_gauge_class = fixed_df.iloc[0, current_gauge_column_index]
print('Gaguge Class: {}'.format(int(current_gauge_class)))
print('Gauge Number: {}'.format(int(current_gauge_number)))
if is_multiple_date_data(fixed_df):
raw_date_column = fixed_df.iloc[:, current_gauge_column_index - 1]
else:
raw_date_column = fixed_df.iloc[:, 0]
raw_flow_column = fixed_df.iloc[:, current_gauge_column_index]
return current_gauge_class, current_gauge_number, raw_date_column, raw_flow_column
def calculate(self):
for root, dirs, files in os.walk(self.directory_name):
for file in files:
if file.endswith(self.end_with):
fixed_df = pd.read_csv('{}/{}'.format(
self.directory_name, file),
sep=',',
encoding='latin1',
dayfirst=False,
header=None,
low_memory=False).dropna(axis=1,
how='all')
step = is_multiple_date_data(fixed_df)
current_gauge_column_index = 1
if not self.class_number and not self.gauge_numbers:
while current_gauge_column_index <= (
len(fixed_df.iloc[1, :]) - 1):
self._get_result_arrays(
fixed_df, current_gauge_column_index)
current_gauge_column_index = current_gauge_column_index + step
elif self.gauge_numbers:
while current_gauge_column_index <= (
len(fixed_df.iloc[1, :]) - 1):
if int(fixed_df.iloc[1, current_gauge_column_index]
) in self.gauge_numbers:
self._get_result_arrays(
fixed_df, current_gauge_column_index)
current_gauge_column_index = current_gauge_column_index + step
elif self.class_number:
while current_gauge_column_index <= (
len(fixed_df.iloc[1, :]) - 1):
if int(fixed_df.iloc[
0, current_gauge_column_index]) == int(
self.class_number):
self._get_result_arrays(
fixed_df, current_gauge_column_index)
current_gauge_column_index = current_gauge_column_index + step
else:
print('Something went wrong!')
self.result_to_csv()
def dim_hydrograph_plotter_layer(start_date, directory_name, end_with, class_number, gauge_numbers, plot):
for root,dirs,files in os.walk(directory_name):
for file in files:
if file.endswith(end_with):
fixed_df = pd.read_csv('{}/{}'.format(directory_name, file), sep=',', encoding='latin1', dayfirst=False, header=None).dropna(axis=1, how='all')
step = is_multiple_date_data(fixed_df);
current_gauge_column_index = 1
while current_gauge_column_index <= (len(fixed_df.iloc[1,:]) - 1):
if gauge_numbers:
if int(fixed_df.iloc[1, current_gauge_column_index]) in gauge_numbers:
current_gauge_class, current_gauge_number, year_ranges, flow_matrix, julian_dates = convert_raw_data_to_matrix(fixed_df, current_gauge_column_index, start_date)
start_year_index = find_index(year_ranges, int(gauge_reference[int(current_gauge_number)]['start']))
end_year_index = find_index(year_ranges, int(gauge_reference[int(current_gauge_number)]['end']))
flow_matrix = flow_matrix[:,start_year_index:end_year_index]
_plotter(flow_matrix, julian_dates, current_gauge_number, plot, start_date)
elif not class_number and not gauge_numbers:
current_gauge_class, current_gauge_number, year_ranges, flow_matrix, julian_dates = convert_raw_data_to_matrix(fixed_df, current_gauge_column_index, start_date)
start_year_index = find_index(year_ranges, int(gauge_reference[int(current_gauge_number)]['start']))
end_year_index = find_index(year_ranges, int(gauge_reference[int(current_gauge_number)]['end']))
flow_matrix = flow_matrix[:,start_year_index:end_year_index]
_plotter(flow_matrix, julian_dates, current_gauge_number, plot, start_date)
elif int(fixed_df.iloc[0, current_gauge_column_index]) == int(class_number):
current_gauge_class, current_gauge_number, year_ranges, flow_matrix, julian_dates = convert_raw_data_to_matrix(fixed_df, current_gauge_column_index, start_date)
start_year_index = find_index(year_ranges, int(gauge_reference[int(current_gauge_number)]['start']))
end_year_index = find_index(year_ranges, int(gauge_reference[int(current_gauge_number)]['end']))
flow_matrix = flow_matrix[:,start_year_index:end_year_index]
_plotter(flow_matrix, julian_dates, current_gauge_number, plot, start_date)
current_gauge_column_index = current_gauge_column_index + step
def dim_hydrograph_plotter_agg(start_date, directory_name, end_with,
class_number, gauge_numbers, plot):
aggregate_matrix = np.zeros(
(366, 7)) # change to 5 for matrix without min/max
counter = 0
for root, dirs, files in os.walk(directory_name):
for file in files:
if file.endswith(end_with):
fixed_df = pd.read_csv('{}/{}'.format(directory_name, file),
sep=',',
encoding='latin1',
dayfirst=False,
header=None).dropna(axis=1, how='all')
step = is_multiple_date_data(fixed_df)
current_gauge_column_index = 1
while current_gauge_column_index <= (len(fixed_df.iloc[1, :]) -
1):
if gauge_numbers:
if int(fixed_df.iloc[
1,
current_gauge_column_index]) in gauge_numbers:
current_gauge_class, current_gauge_number, year_ranges, flow_matrix, julian_dates = convert_raw_data_to_matrix(
fixed_df, current_gauge_column_index,
start_date)
start_year_index = find_index(
year_ranges,
int(gauge_reference[int(current_gauge_number)]
['start']))
end_year_index = find_index(
year_ranges,
int(gauge_reference[int(current_gauge_number)]
['end']))
flow_matrix = flow_matrix[:, start_year_index:
end_year_index]
aggregate_matrix = np.add(
aggregate_matrix, _getAggMatrix(flow_matrix))
counter = counter + 1
elif int(fixed_df.iloc[0,
current_gauge_column_index]) == int(
class_number):
current_gauge_class, current_gauge_number, year_ranges, flow_matrix, julian_dates = convert_raw_data_to_matrix(
fixed_df, current_gauge_column_index, start_date)
start_year_index = find_index(
year_ranges,
int(gauge_reference[int(current_gauge_number)]
['start']))
end_year_index = find_index(
year_ranges,
int(gauge_reference[int(current_gauge_number)]
['end']))
flow_matrix = flow_matrix[:, start_year_index:
end_year_index]
aggregate_matrix = np.add(aggregate_matrix,
_getAggMatrix(flow_matrix))
counter = counter + 1
current_gauge_column_index = current_gauge_column_index + step
final_aggregate = aggregate_matrix / counter
if class_number:
np.savetxt(
"post_processedFiles/Hydrographs/Class_{}_aggregate.csv".
format(int(current_gauge_class)),
final_aggregate,
delimiter=",",
fmt="%s")
else:
np.savetxt(
"post_processedFiles/Hydrographs/plot_data_{}.csv".format(
int(current_gauge_number)),
final_aggregate,
delimiter=",",
fmt="%s")
"""To output plot, uncomment line below"""
_plotter(final_aggregate, start_date)