File size: 5,634 Bytes
5626a1a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
import os
import pandas as pd
def delete_images_with_patterns(directory: str, patterns: list):
"""
Deletes image files in the given directory if their filenames contain any of the specified patterns.
Args:
directory (str): The path to the directory containing images.
patterns (list): A list of substrings to check in filenames.
"""
if not os.path.exists(directory):
print(f"Directory '{directory}' does not exist.")
return
for filename in os.listdir(directory):
file_path = os.path.join(directory, filename)
# Check if the filename contains any of the specified patterns
if any("dr"+pattern in filename for pattern in patterns):
try:
os.remove(file_path)
print(f"Deleted: {file_path}")
except Exception as e:
print(f"Error deleting {file_path}: {e}")
def clean_csv(csv_path: str, patterns: list):
"""
Removes rows from the CSV if the first column contains filenames matching any pattern (e.g., "1_1" -> "dr1_1").
Ensures that there are no additional digits after the pattern unless separated by an underscore `_`.
"""
if not os.path.exists(csv_path):
print(f"CSV file '{csv_path}' does not exist.")
return
# Load CSV into a DataFrame
df = pd.read_csv(csv_path)
# Ensure the first column is treated as a string
df.iloc[:, 0] = df.iloc[:, 0].astype(str)
# Create modified patterns to match filenames
modified_patterns = [f"dr{p}" for p in patterns]
# Build a regex pattern to match filenames exactly or with an underscore and additional digits
regex_patterns = []
for pattern in modified_patterns:
# Match the pattern exactly or with an underscore and additional digits
regex_patterns.append(f"^{pattern}(_\\d+)?$")
# Combine all regex patterns into a single pattern
combined_regex = '|'.join(regex_patterns)
# Filter out rows where the first column matches any of the regex patterns
df = df[~df.iloc[:, 0].str.match(combined_regex, na=False)]
# Remove duplicates
df.drop_duplicates(inplace=True)
# Save cleaned data back to CSV
df.to_csv(csv_path, index=False)
print(f"Updated CSV saved: {csv_path}")
# List of text patterns to match in filenames
patterns_to_delete = [
"1_1",
"4_1",
"4_2",
"4_3",
"4_4",
"4_5",
"4_6",
"5_1",
"5_2",
"7_1",
"10_1",
"24_1",
"24_2",
"25_1",
"25_2",
"29_1",
"30_1",
"33_1",
"36_1",
"36_4",
"36_5",
"36_6",
"38_1",
"38_2",
"38_3",
"38_4",
"38_5",
"38_6",
"38_7",
"38_8",
"38_9",
"42_1",
"42_2",
"42_4",
"43_1",
"43_2",
"43_3",
"43_4",
"43_5",
"44_1",
"44_2",
"44_3",
"44_4",
"44_6",
"45_1",
"47_1",
"50_1",
"57_1",
"57_2",
"63_1",
"64_1",
"64_2",
"64_3",
"64_4",
"64_5",
"64_6",
"64_7",
"64_8",
"64_9",
"65_1",
"65_2",
"66_1",
"66_2",
"66_3",
"66_4",
"66_5",
"66_6",
"66_7",
"66_8",
"69_1",
"69_2",
"69_3",
"69_4",
"69_5",
"69_6",
"69_7",
"69_8",
"69_9",
"71_1",
"71_2",
"71_3",
"71_4",
"71_5",
"73_1",
"74_1",
"75_1",
"75_2",
"75_3",
"75_4",
"75_5",
"75_6",
"77_1",
"77_2",
"77_3",
"76_1",
"76_2",
"76_3",
"76_4",
"76_5",
"80_1",
"80_2",
"82_1",
"86_1",
"86_2",
"86_3",
"86_4",
"86_5",
"87_1",
"87_2",
"87_3",
"87_4",
"87_5",
"87_6",
"89_1",
"92_1",
"92_2",
"93_1",
"94_2",
"94_1",
"95_1",
"97_1",
"97_2",
"102_1",
"104_1",
"108_1",
"109_1",
"112_1",
"114_1",
"114_2",
"114_3",
"114_4",
"114_5",
"114_6",
"114_7",
"114_8",
"114_9",
"115_1",
"115_2",
"116_1",
"116_2",
"116_3",
"117_1",
"128_1",
"130_1",
"132_1",
"132_2",
"132_3",
"137_1",
"137_2",
"137_3",
"137_4",
"137_5",
"137_6",
"137_7",
"137_8",
"137_9",
"140_5",
"146_1",
"146_2",
"146_3",
"151_1",
"151_2",
"163_1",
"169_1",
"173_1",
"173_2",
"100_1"
]
# Specify your target directory
target_directory = "./cropped_images" # Change this to your actual directory
# Run the deletion function
# delete_images_with_patterns(target_directory, patterns_to_delete)
patterns_to_delete = [
"dr80_2",
"dr80_3",
"dr81_1",
"dr81_1",
"dr81_2",
"dr83_1",
"dr86_1",
"dr86_2",
"dr86_3",
"dr86_4",
"dr86_5",
"dr87_1",
"dr87_2",
"dr87_3",
"dr87_4",
"dr87_5",
"dr87_6",
"dr88_1",
"dr89_1",
"dr89_2",
"dr9_1",
"dr90_1",
"dr92_1",
"dr92_1",
"dr92_2",
"dr92_3",
"dr93_1",
"dr93_2",
"dr94_1",
"dr94_2",
"dr94_3",
"dr95_1",
"dr95_2",
"dr96_1",
"dr97_1",
"dr97_2",
"dr97_3",
"dr98_1",
]
clean_csv("all_cropped_data.csv",patterns=patterns_to_delete) |