def extract_figure3_data(input_folder: pathlib.Path,
output_folder: pathlib.Path) -> None:
# STEP1: Loop through each DC method
for dc_method in DC_METHODS:
workflow = "denoise_cluster"
module = dc_method
process = "hashed_output"
# STEP2: Extract the data
output_subfolder = output_folder / module
extract_data(input_folder, workflow, module, process, "",
output_subfolder)
def extract_figure4_data(input_folder: pathlib.Path,
output_folder: pathlib.Path) -> None:
# STEP1: Loop through each TA method
for ta_method in TA_METHODS:
workflow = "tax_assignment"
module = ta_method
process = "taxonomy_tables"
prev_process = "dada2-remove_bimera"
# STEP2: Extract the data
output_subfolder = output_folder / module
extract_data(input_folder, workflow, module, process, prev_process,
output_subfolder)
def extract_figure5_data(input_folder: pathlib.Path,
output_folder: pathlib.Path) -> None:
# STEP1: Loop through each NI method
for ni_type, ni_method in NI_METHODS:
workflow = "network_inference"
module = "network"
process = make_process_string((ni_type, ni_method))
prev_process = make_prevprocess_string(
DC="dada2",
CC="remove_bimera",
TA="naive_bayes(gg_13_8_99)",
OP="normalize_filter(on)",
GROUP="group(Genus)",
NI=ni_method,
)
# STEP2: Extract the data
output_subfolder = output_folder / ni_method
extract_data(input_folder, workflow, module, process, prev_process,
output_subfolder)
def load_all_data(self):
try:
load_files=return_checked_values(self.listView_files)
except Exception:
# QtWidgets.QMessageBox.warning(self, 'Select a motor, propeller and plane.',
# "The system of interest must be selected (different to being checked).",
# QtWidgets.QMessageBox.Ok)
return
for file in load_files:
if file in self.current_data_files:
continue
data_file=self.file_folder+"/" + file + ".csv"
loaded_data=data_extraction.extract_data(data_file)
self.current_data.append(loaded_data)
self.current_data_files.append(file)
self.pop_combo_box()
return
def extract_step_data(step: str, input_folder: pathlib.Path,
output_folder: pathlib.Path):
workflow = "network_inference"
module = "network"
default_dc = DEFAULT["DC"]
default_cc = DEFAULT["CC"]
default_ta = DEFAULT["TA"]
default_op = DEFAULT["OP"]
group_level = GROUP_LEVEL
method_dict = dict()
method_dict["GROUP"] = group_level
if step == "default":
method_dict["DC"] = default_dc
method_dict["CC"] = default_cc
method_dict["TA"] = default_ta
method_dict["OP"] = default_op
loop_list_1 = DC_METHODS
loop_list_2 = NI_METHODS
elif step == "DC":
method_dict["CC"] = default_cc
method_dict["TA"] = default_ta
method_dict["OP"] = default_op
loop_list_1 = DC_METHODS
loop_list_2 = NI_METHODS
elif step == "CC":
method_dict["DC"] = default_dc
method_dict["TA"] = default_ta
method_dict["OP"] = default_op
loop_list_1 = CC_METHODS
loop_list_2 = NI_METHODS
elif step == "TA":
method_dict["DC"] = default_dc
method_dict["CC"] = default_cc
method_dict["OP"] = default_op
loop_list_1 = TA_METHODS
loop_list_2 = NI_METHODS
elif step == "OP":
method_dict["DC"] = default_dc
method_dict["CC"] = default_cc
method_dict["TA"] = default_ta
loop_list_1 = OP_METHODS
loop_list_2 = NI_METHODS
elif step == "NI":
method_dict["DC"] = default_dc
method_dict["CC"] = default_cc
method_dict["TA"] = default_ta
method_dict["OP"] = default_op
loop_list_1 = [m[1] for m in NI_METHODS]
loop_list_2 = NI_METHODS
else:
raise ValueError(f"Unsupported step {step}")
if step != "default":
for method in loop_list_1:
if method != DEFAULT[step]:
method_dict[step] = method
output_sub_folder = output_folder / method
for ni_type, ni_method in loop_list_2:
if step == "NI" and ni_method != method:
continue
method_dict["NI"] = ni_method
process = make_process_string((ni_type, ni_method))
previous_process = make_prevprocess_string(**method_dict)
extract_data(
input_folder,
workflow,
module,
process,
previous_process,
output_sub_folder,
)
else:
output_sub_folder = output_folder / "default"
for ni_type, ni_method in loop_list_2:
method_dict["NI"] = ni_method
process = make_process_string((ni_type, ni_method))
previous_process = make_prevprocess_string(**method_dict)
extract_data(
input_folder,
workflow,
module,
process,
previous_process,
output_sub_folder,
)
def extract_step_data(process: str, input_folder: pathlib.Path,
output_folder: pathlib.Path) -> None:
workflow = "network_inference"
module = "network"
extract_data(input_folder, workflow, module, process, "", output_folder)
# This script extracts NYSE (New York Stock Exchange) prices
# Author: fedimser
from data_extraction import extract_data
with open('nyse_symbols.txt') as f:
nyse_symbols = [line.split()[0] for line in f.readlines()][1:]
extract_data(nyse_symbols[::50], dataset_name='nyse_each_50')
#extract_data(nyse_symbols[::10], dataset_name='nyse_each_10')
#extract_data(nyse_symbols, dataset_name='nyse')
def load_data(self, file):
data_file=self.file_folder+file
print(data_file)
loaded_data=data_extraction.extract_data(data_file)
return loaded_data