This Python script is designed to traverse a directory structure to find files with a '.track' extension, read their contents using a specialized function (read_trk), and aggregate specific information from these files into a single CSV file named 'lastModels.csv'. It specifically extracts the last entry from each track file, adds the model name derived from the file's name, and then compiles these entries into a DataFrame. This aggregated data is then saved in the specified directory. The script also counts and reports the number of track files that were skipped due to size constraints.

import os
from pysep.io.trk import read_trk
import pandas as pd
from tqdm import tqdm
import sys
trks = list()
for root, dirs, files in os.walk(sys.argv[1]):
    trkFiles = list(filter(lambda x: x.endswith(".track"), files))
    if trkFiles:
        trkFile = trkFiles[0]
        trks.append(os.path.join(root, trkFile))
temp, meta = read_trk(trks[0])
names = [x for x in temp[0].columns]
names.append("MODELName")
lastModels = pd.DataFrame(columns=names)
skipped = 0
for trk in tqdm(trks):
    modelName = '.'.join(os.path.basename(trk).split('.')[:2])
    if not os.stat(trk).st_size < 1e4:
        trkContnent, metaContnent = read_trk(trk)
        trkContnent = trkContnent[0]
        lastModel = trkContnent.iloc[-1]
        lastModel["MODELName"] = modelName
        lastModels = lastModels.append(lastModel)
    else:
        skipped += 1
lastModels.reset_index().to_csv(os.path.join(sys.argv[1], "lastModels.csv"), index=False)
print(f"Skipped {skipped} track files")