102 lines
3.3 KiB
Python
102 lines
3.3 KiB
Python
import pandas as pd
|
|
import os
|
|
import re
|
|
from pathlib import Path
|
|
import matplotlib.pyplot as plt
|
|
from datetime import datetime, timedelta
|
|
import sys
|
|
|
|
tstamp_s = '%d.%m.%Y %H:%M:%S.%f'
|
|
ox_dtime_format = '%d.%m.%Y %H:%M'
|
|
|
|
path_itog_brd_data = '../data/brd_data/'
|
|
|
|
|
|
class PathFileNotFound(Exception):
|
|
pass
|
|
|
|
|
|
def find_required_files(root_dir, pattern):
|
|
result = []
|
|
for dirpath, _, filenames in os.walk(root_dir):
|
|
for filename in filenames:
|
|
match = re.match(pattern, filename)
|
|
if match:
|
|
result.append(dirpath + '/' + filename)
|
|
|
|
if len(result) == 0:
|
|
raise PathFileNotFound(
|
|
f'error: check that the path is correct ({root_dir}) or files pattern is correct ({pattern})')
|
|
|
|
return sorted(result)
|
|
|
|
|
|
def read_files_into_df(fname_list, column_list, dtype_columns={}):
|
|
data_itog = pd.DataFrame()
|
|
epoch_start = pd.Timestamp('2000-01-01')
|
|
|
|
for fname in fname_list:
|
|
data = pd.read_csv(fname, sep=r'\s+', dtype=str)
|
|
data = data.dropna()
|
|
data = data[column_list]
|
|
|
|
if 'TIME' in column_list:
|
|
# convert TIME value to human-readable timestamp (sinse epoch 01.01.2000)
|
|
time = data['TIME'].astype(float)
|
|
tstamp = epoch_start + pd.to_timedelta(time, unit='s')
|
|
timestamp = tstamp.dt.strftime(tstamp_s)
|
|
data['timestamp'] = timestamp
|
|
|
|
# clear dataframe rows where time value == 0
|
|
data['time'] = time
|
|
data_clear = data.query('time != 0.0')
|
|
|
|
data_itog = pd.concat([data_itog, data_clear], ignore_index=True)
|
|
|
|
return data_itog
|
|
|
|
|
|
def collect_tm_brd_files(root_dir_tm_data, column_list, column_list_itog):
|
|
patterns_tm = [r'mvn_tm_brd01_(.*)', r'mvn_tm_brd02_(.*)', r'mvn_tm_brd03_(.*)',
|
|
r'mvn_tm_brd04_(.*)']
|
|
|
|
for pattern in patterns_tm:
|
|
fname = path_itog_brd_data + pattern[:12] + '.csv'
|
|
try:
|
|
found_files = find_required_files(root_dir_tm_data, pattern)
|
|
data = read_files_into_df(found_files, column_list, dtype_columns={11: float})
|
|
except KeyError as e:
|
|
print(
|
|
f'error in collect_tm_brd_files: the specified column name was not found in the data file (path: {root_dir_tm_data}) ({e})')
|
|
break
|
|
except Exception as e:
|
|
print(f'error in collect_tm_brd_files: {e}')
|
|
break
|
|
|
|
data.to_csv(fname, index=False, sep=';', columns=column_list_itog, encoding='utf-8-sig')
|
|
print('data saved: ' + fname)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
if len(sys.argv) != 2:
|
|
print("Usage: python tm_brd_parser.py /path/to/tm_brd_data/")
|
|
else:
|
|
root_dir_tm_data = sys.argv[1]
|
|
|
|
print('collect raw brd tm data into one file for each brd')
|
|
|
|
column_list = ['TIME', 'PER_1Hz', 'ST_HV']
|
|
column_list_itog = ['TIME', 'timestamp', 'PER_1Hz', 'ST_HV']
|
|
|
|
collect_tm_brd_files(root_dir_tm_data, column_list, column_list_itog)
|
|
|
|
## plot 'evolution' 1 Hz from tm brd data
|
|
print('plot evolution 1 Hz from tm brd data')
|
|
|
|
fname = path_itog_brd_data + 'mvn_tm_brd01.csv'
|
|
df = pd.read_csv(fname, sep=';', parse_dates=['timestamp'], date_format="%d.%m.%Y %H:%M:%S.%f")
|
|
|
|
plt.plot(df['timestamp'], df['PER_1Hz'], '.')
|
|
plt.show()
|