Files
smt-optimizer/dataloader.py

187 lines
9.0 KiB
Python

import copy
from base_optimizer.optimizer_common import *
def load_data(filename: str, load_feeder=False, auto_register=True):
filename = 'data/' + filename
part_content, step_content, feeder_content = False, False, False
part_start_line, step_start_line, feeder_start_line = -1, -1, -1
part_end_line, step_end_line, feeder_end_line = -1, -1, -1
line_counter = 0
with open(filename, 'r') as file:
line = file.readline()
while line:
if line == '[Part]\n':
part_content, part_start_line = True, line_counter
elif line == '[Step]\n':
step_content, step_start_line = True, line_counter
elif line == '[Feeder]\n':
feeder_content, feeder_start_line = True, line_counter
elif line == '\n':
if part_content:
part_content, part_end_line = False, line_counter
elif step_content:
step_content, step_end_line = False, line_counter
elif feeder_content:
feeder_content, feeder_end_line = False, line_counter
line_counter += 1
line = file.readline()
if part_content:
part_end_line = line_counter
elif feeder_content:
feeder_end_line = line_counter
else:
step_end_line = line_counter
file_data = pd.DataFrame(
pd.read_csv(filepath_or_buffer=filename, skiprows=step_start_line + 1, nrows=step_end_line - step_start_line + 1,
sep='\t', header=None))
if len(file_data.columns) == 22:
data_col = ["machine", "bl", "ref", "x", "y", "z", "r", "part", "desc", "group", "fdr", "nz", "hd", "cs", "cy",
"sk", "ar", "fid", "pop", "pl", "lv", "pr"]
elif len(file_data.columns) <= 17:
data_col = ["ref", "x", "y", "z", "r", "part", "desc", "fdr", "nz", "hd", "cs", "cy", "sk", "bl", "ar",
"pl", "lv"]
elif len(file_data.columns) <= 18:
data_col = ["ref", "x", "y", "z", "r", "part", "desc", "fdr", "nz", "hd", "cs", "cy", "sk", "bl", "ar", "fid",
"pl", "lv"]
else:
data_col = ["ref", "x", "y", "z", "r", "part", "desc", "fdr", "nz", "hd", "cs", "cy", "sk", "bl", "ar", "fid",
"", "pl", "lv"]
file_data.columns = data_col
pcb_data, component_data, feeder_data = defaultdict(pd.DataFrame), defaultdict(pd.DataFrame), defaultdict(
pd.DataFrame)
# line_data = line_data.dropna(axis=1)
step_col = ["ref", "x", "y", "z", "r", "part", "desc", "fdr", "nz", "hd", "cs", "cy", "sk", "bl", "ar", "pl", "lv"]
machine_name = defaultdict(int)
for _, data in file_data.iterrows():
if "machine" in file_data.columns:
if data['machine'] not in machine_name.keys():
machine_name[data['machine']] = len(machine_name)
machine_index = machine_name[data['machine']]
else:
machine_index = 0
# pcb_data[machine_index] = pcb_data[machine_index]._append(data[step_col], ignore_index=True)
pcb_data[machine_index] = pd.concat([pcb_data[machine_index], pd.DataFrame(data[step_col]).T], ignore_index=True)
part_col = ["part", "fdr", "nz", 'fdn']
try:
if part_start_line != -1:
part_data = pd.DataFrame(
pd.read_csv(filepath_or_buffer=filename, sep='\t', header=None, skiprows=part_start_line + 1,
nrows=part_end_line - part_start_line - 1))
part_data.columns = part_col
else:
part_data = pd.DataFrame(columns=part_col)
except:
part_data = pd.DataFrame(columns=part_col)
part_data['points'] = 0
part_col = ["part", "fdr", "nz", 'fdn', 'points']
machine_num = len(pcb_data)
for machine_index in range(machine_num):
component_data[machine_index] = pd.DataFrame(columns=part_col)
component_slot = defaultdict(set)
for idx, data in pcb_data[machine_index].iterrows():
if pos := data.fdr.find('F') != 0:
pcb_data[machine_index].loc[idx, 'fdr'] = data.fdr[pos:pos + 1:1] + data.fdr[pos + 2::]
if pos := data.nz.find('F') != -1:
pcb_data[machine_index].loc[idx, 'nz'] = data.nz[0:pos:1] + data.nz[pos + 1::]
if isinstance(data.hd, str) and (pos := data.hd.find('F') != -1):
pcb_data[machine_index].loc[idx, 'hd'] = int(data.hd[pos + 2::])
part, nozzle = data.part, data.nz.split(' ')[1]
if part not in component_data[machine_index]['part'].values:
if not auto_register:
raise Exception("unregistered component: " + component_data[machine_index]['part'].values)
else:
component_data[machine_index] = pd.concat([component_data[machine_index], pd.DataFrame(
[part, 'SM8', nozzle, 0, 0], index=part_col).T], ignore_index=True)
# warning_info = 'register component ' + part + ' with default feeder type'
# warnings.warn(warning_info, UserWarning)
part_index = component_data[machine_index][component_data[machine_index]['part'] == part].index.tolist()[0]
component_data[machine_index].loc[part_index, 'points'] += 1
if (fdr := data['fdr'].split(' ')[0]) not in component_slot[part]:
component_data[machine_index].loc[part_index, 'fdn'] += 1
component_slot[part].add(fdr)
for idx, data in part_data.iterrows():
if data.part in component_slot.keys():
part_data.loc[idx, 'fdn'] = part_data.loc[idx, 'fdn'] - len(component_slot[data.part])
assert part_data.loc[idx, 'fdn'] >= 0
for idx, data in part_data.iterrows():
for machine_index in range(machine_num):
if data.part not in component_data[machine_index].part.values:
continue
part_index = component_data[machine_index][component_data[machine_index].part == data.part].index.tolist()[
0]
if component_data[machine_index].loc[part_index].nz != data.nz:
component_data[machine_index].loc[part_index].nz = data.nz
warning_info = 'the nozzle type of component ' + data.part + ' is not consistent with the pcb data'
warnings.warn(warning_info, UserWarning)
component_data[machine_index].loc[part_index].fdr = data.fdr
if data.fdn == 0:
continue
if data.part in component_data[0].part.values:
part_index = component_data[0][component_data[0].part == data.part].index.tolist()[0]
component_data[0].loc[part_index, 'fdn'] += data.fdn
else:
component_data[0] = pd.concat([component_data[0], pd.DataFrame(data).T], ignore_index=True)
for machine_index in range(machine_num):
for idx, data in component_data[machine_index].iterrows():
if data['fdr'][0:3] == 'SME': # 电动供料器和气动供料器参数一致
component_data[machine_index].at[idx, 'fdr'] = data['fdr'][0:2] + data['fdr'][3:]
# pcb_data[machine_index].sort_values(by="x", ascending=False, inplace=True)
# pcb_data[machine_index].reset_index(inplace=True)
# 读取供料器基座数据
feeder_columns = ['slot', 'part']
if load_feeder:
try:
if feeder_start_line != -1:
feeder_data = pd.DataFrame(
pd.read_csv(filepath_or_buffer=filename, sep='\t', header=None, skiprows=feeder_start_line + 1,
nrows=feeder_end_line - feeder_start_line - 1))
feeder_data.columns = feeder_columns
else:
feeder_data = pd.DataFrame(columns=feeder_columns)
except:
feeder_data = pd.DataFrame(columns=feeder_columns)
else:
feeder_data = pd.DataFrame(columns=feeder_columns)
feeder_data.sort_values(by='slot', ascending=True, inplace=True, ignore_index=True)
return pcb_data, component_data, feeder_data
def merge_data(partial_pcb_data, partial_component_data):
assert len(partial_pcb_data) == len(partial_component_data)
machine_num = len(partial_pcb_data)
pcb_data, component_data = copy.deepcopy(partial_pcb_data[0]), copy.deepcopy(partial_component_data[0])
for machine_index in range(1, machine_num):
pcb_data = pd.concat([pcb_data, partial_pcb_data[machine_index]], ignore_index=True)
for _, data in partial_component_data[machine_index].iterrows():
if data.part in component_data.part.values:
part_index = component_data[component_data.part == data.part].index.tolist()[0]
component_data.loc[part_index, 'points'] += data.points
component_data.loc[part_index, 'fdn'] += data.fdn
else:
component_data = pd.concat([component_data, pd.DataFrame(data).T], ignore_index=True)
component_data = component_data[component_data['points'] != 0].reset_index(drop=True)
return pcb_data, component_data