kurzti88066/Fahrsimulator_MSY2526_AI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fixed blink bug in dataset creation

Browse Source
This commit is contained in:
Michael Weig 2026-01-26 13:11:06 +01:00
parent ee648f9adc
commit 38e9354c42
2 changed files with 7 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
dataset_creation/CPFC_both.py
View File

@ -2,7 +2,7 @@ import os
import pandas as pd
from pathlib import Path
data_dir = Path("/home/jovyan/Fahrsimulator_MSY2526_AI/EDA")
data_dir = Path("/home/jovyan/data-paulusjafahrsimulator-gpu/raw_data")
# Get all .h5 files and sort them
matching_files = sorted(data_dir.glob("*.h5"))
@ -56,16 +56,16 @@ for i, file_path in enumerate(matching_files):
start=start_row,
stop=stop_row
)
# print(f"[DEBUG] Vor Dropna: {df_chunk["EYE_LEFT_PUPIL_VALIDITY"].value_counts()}")
# Add metadata columns
df_chunk["subjectID"] = i
df_chunk["rowID"] = range(start_row, stop_row)
# Clean data
df_chunk = df_chunk[df_chunk["LEVEL"] != 0]
df_chunk = df_chunk.dropna()
# problematisch, weil die eye tracking auflösung kaputt geht
df_chunk = df_chunk.dropna(subset=face_au_cols)
# print(f"[DEBUG] Nach Dropna: {df_chunk["EYE_LEFT_PUPIL_VALIDITY"].value_counts()}")
# Only keep non-empty chunks
if len(df_chunk) > 0:
chunks_to_save.append(df_chunk)

7
dataset_creation/combined_feature_creation.py
View File

@ -11,9 +11,9 @@ from pygazeanalyser.detectors import fixation_detection, saccade_detection
# KONFIGURATION
##############################################################################
INPUT_DIR = Path(r"/home/jovyan/data-paulusjafahrsimulator-gpu/both_mod_parquet_files")
OUTPUT_FILE = Path(r"/home/jovyan/data-paulusjafahrsimulator-gpu/new_datasets/fix_blink_combined_dataset_25hz.parquet")
OUTPUT_FILE = Path(r"/home/jovyan/data-paulusjafahrsimulator-gpu/new_datasets/blink_fix_dataset.parquet")
WINDOW_SIZE_SAMPLES = 1250 # 50s bei 25Hz
WINDOW_SIZE_SAMPLES = 25*50 # 50s bei 25Hz
STEP_SIZE_SAMPLES = 125 # 5s bei 25Hz
SAMPLING_RATE = 25 # Hz
MIN_DUR_BLINKS = 2 # x * 40ms
@ -368,9 +368,6 @@ def main():
print(result.head())
print("\nSpalten-Übersicht:")
print(result.columns.tolist())
print("\nDatentypen:")
print(result.dtypes)
print("\nStatistik:")