1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
|
import pandas as pd
import os
import shutil
import sys
import math
participant_table_path = 'Participant_table.csv'
filename_column = 'T1 structural brain images - NIFTI | Instance 2'
source_base_dir = '/mnt/project/Bulk/Brain MRI/T1/'
destination_base_dir = './T1_NIFTI_Batched'
batch_size = 100
file_delimiter=','
try:
os.makedirs(destination_base_dir, exist_ok=True)
print(f"基础目标目录已创建或已存在: {destination_base_dir}")
except OSError as e:
print(f"错误：无法创建基础目标目录 {destination_base_dir}: {e}", file=sys.stderr)
sys.exit(1)
try:
print(f"正在读取参与者表格: {participant_table_path}")
df = pd.read_csv(participant_table_path, delimiter=file_delimiter, dtype=str)
if filename_column not in df.columns:
print(f"错误: 在文件 {participant_table_path} 中未找到列 '{filename_column}'", file=sys.stderr)
print(f"文件中包含的列有: {list(df.columns)}", file=sys.stderr)
print("请检查并更新脚本中的 'filename_column' 变量。", file=sys.stderr)
sys.exit(1)
target_files = set(df[filename_column].dropna().unique())
print(f"从表格中找到 {len(target_files)} 个唯一的目标 .zip 文件名。")
if not target_files:
print("警告：在指定列中未找到任何目标文件名。请检查列名和文件内容。")
sys.exit(0)
except FileNotFoundError:
print(f"错误: 参与者表格文件未找到，路径: {participant_table_path}", file=sys.stderr)
print("请检查并更新脚本中的 'participant_table_path' 变量。", file=sys.stderr)
sys.exit(1)
except Exception as e:
print(f"错误：读取参与者表格 {participant_table_path} 时出错: {e}", file=sys.stderr)
print(f"请检查您的文件分隔符 '{file_delimiter}' 是否设置正确。", file=sys.stderr)
sys.exit(1)
files_copied_count = 0
files_processed = set()
print(f"\n正在搜索目标文件于: {source_base_dir} 及其子目录...")
try:
found_file_paths = {}
for root, dirs, files_in_current_dir in os.walk(source_base_dir):
for file_name in files_in_current_dir:
if file_name in target_files:
if file_name not in found_file_paths:
found_file_paths[file_name] = os.path.join(root, file_name)
print(f"在源目录中初步定位到 {len(found_file_paths)} 个目标文件。开始复制并分批...")
sorted_target_files_found = sorted(list(found_file_paths.keys()))
for filename_to_copy in sorted_target_files_found:
batch_index = (files_copied_count // batch_size) + 1
current_batch_subdir_name = f"batch_{batch_index:03d}"
current_batch_dir = os.path.join(destination_base_dir, current_batch_subdir_name)
os.makedirs(current_batch_dir, exist_ok=True)
source_path = found_file_paths[filename_to_copy]
dest_path = os.path.join(current_batch_dir, filename_to_copy)
try:
print(f" 目标文件: {filename_to_copy}")
print(f" 归入批次: {current_batch_subdir_name}")
print(f" 正在复制...")
shutil.copy2(source_path, dest_path)
files_copied_count += 1
files_processed.add(filename_to_copy)
print(f" 成功复制 {filename_to_copy} 到 {current_batch_subdir_name}")
except Exception as e:
print(f" 错误：复制文件 {filename_to_copy} 时出错: {e}", file=sys.stderr)
except Exception as e:
print(f"在目录遍历或文件处理过程中发生严重错误: {e}", file=sys.stderr)
|