nuluh/thesis
1
0
Fork 0
Code Issues 47 Pull Requests Actions Packages Projects Releases 1 Wiki Activity

fix(data): Fix export_to_csv to adapt new added undamaged scenario and add new parameter include_time to include 'Time' data

Browse Source
This commit is contained in:
nuluh
2025-06-18 01:54:12 +07:00
parent 58a672a680
commit 1164627bac
1 changed files with 14 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
data/QUGS/convert.py
View File

@@ -103,9 +103,10 @@ def generate_df_tuples(total_dfs=30, group_size=5, prefix="zzzAD", ext="TXT", fi
class DataProcessor: class DataProcessor:
def __init__(self, file_index, cache_path: str = None, base_path: str = None): def __init__(self, file_index, cache_path: str = None, base_path: str = None, include_time: bool = False):
self.file_index = file_index self.file_index = file_index
self.base_path = base_path self.base_path = base_path
self.include_time = include_time
if cache_path: if cache_path:
self.data = load(cache_path) self.data = load(cache_path)
else: else:
@@ -115,7 +116,10 @@ class DataProcessor:
for idxs, group in enumerate(self.file_index): for idxs, group in enumerate(self.file_index):
for idx, tuple in enumerate(group): for idx, tuple in enumerate(group):
file_path = os.path.join(self.base_path, tuple[0]) # ('zzzAD1.TXT') file_path = os.path.join(self.base_path, tuple[0]) # ('zzzAD1.TXT')
col_indices = tuple[1] # [1, 26] if self.include_time:
col_indices = [0] + tuple[1] # [1, 26] + [0] -> [0, 1, 26]
else:
col_indices = tuple[1] # [1, 26]
try: try:
# Read the CSV file # Read the CSV file
df = pd.read_csv(file_path, delim_whitespace=True, skiprows=10, header=0, memory_map=True) df = pd.read_csv(file_path, delim_whitespace=True, skiprows=10, header=0, memory_map=True)
@@ -272,30 +276,18 @@ class DataProcessor:
:param output_dir: Directory to save the CSV files. :param output_dir: Directory to save the CSV files.
:param file_prefix: Prefix for the output filenames. :param file_prefix: Prefix for the output filenames.
""" """
for group_idx, group in enumerate(self.data, start=0): for group_idx, group in enumerate(self.file_index, start=0):
group_folder = os.path.join(output_dir, f"{file_prefix}_{group_idx}") group_folder = os.path.join(output_dir, f"{file_prefix}_{group_idx}")
os.makedirs(group_folder, exist_ok=True) os.makedirs(group_folder, exist_ok=True)
for test_idx, df in enumerate(group, start=1): for test_idx, df in enumerate(group, start=1):
# Ensure columns are named uniquely if duplicated out1 = os.path.join(group_folder, f"{file_prefix}_{group_idx}_TEST{test_idx}_01.csv")
df = df.copy() cols_to_export = [0, 1] if self.include_time else [1]
df.columns = ["Time", "Real_0", "Real_1"] # Rename df.iloc[:, cols_to_export].to_csv(out1, index=False)
# Export first Real column
out1 = os.path.join(
group_folder, f"{file_prefix}_{group_idx}_TEST{test_idx}_01.csv"
)
df[["Time", "Real_0"]].rename(columns={"Real_0": "Real"}).to_csv(
out1, index=False
)
# Export last Real column
out2 = os.path.join(
group_folder, f"{file_prefix}_{group_idx}_TEST{test_idx}_02.csv"
)
df[["Time", "Real_1"]].rename(columns={"Real_1": "Real"}).to_csv(
out2, index=False
)
out2 = os.path.join(group_folder, f"{file_prefix}_{group_idx}_TEST{test_idx}_02.csv")
cols_to_export = [0, 2] if self.include_time else [2]
df.iloc[:, cols_to_export].to_csv(out2, index=False)
# def create_damage_files(base_path, output_base, prefix): # def create_damage_files(base_path, output_base, prefix):
# # Initialize colorama # # Initialize colorama