still sorting CSV vectors indexes

1 files changed, 65 insertions, 0 deletions

diff --git a/megapixels/commands/datasets/gen_uuid.py b/megapixels/commands/datasets/gen_uuid.py
new file mode 100644
index 00000000..612c43ee
--- /dev/null
+++ b/megapixels/commands/datasets/gen_uuid.py
@@ -0,0 +1,65 @@
+import click
+
+from app.settings import types
+from app.utils import click_utils
+from app.settings import app_cfg as cfg
+from app.utils.logger_utils import Logger
+
+log = Logger.getLogger()
+
+@click.command()
+@click.option('-i', '--input', 'opt_fp_in', default=None,
+  help='Override enum input filename CSV')
+@click.option('-o', '--output', 'opt_fp_out', default=None,
+  help='Override enum output filename CSV')
+@click.option('--data_store', 'opt_data_store',
+  type=cfg.DataStoreVar,
+  default=click_utils.get_default(types.DataStore.NAS),
+  show_default=True,
+  help=click_utils.show_help(types.Dataset))
+@click.option('--dataset', 'opt_dataset',
+  type=cfg.DatasetVar,
+  required=True,
+  show_default=True,
+  help=click_utils.show_help(types.Dataset))
+@click.option('-f', '--force', 'opt_force', is_flag=True,
+  help='Force overwrite file')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_fp_out, opt_data_store, opt_dataset, opt_force):
+  """Appends UUID to records CSV"""
+  
+  from glob import glob
+  from os.path import join
+  from pathlib import Path
+  import base64
+  import uuid
+
+  from tqdm import tqdm
+  import pandas as pd
+
+  from app.models import DataStore
+  
+
+  # set data_store
+  data_store = DataStore(opt_data_store, opt_dataset)
+  # get filepath out
+  fp_out = data_store.metadata(types.Metadata.UUID) if opt_fp_out is None else opt_fp_out
+  # exit if exists
+  if not opt_force and Path(fp_out).exists():
+    log.error('File exists. Use "-f / --force" to overwite')
+    return
+
+  # load sha256 records
+  fp_in = data_store.metadata(types.Metadata.SHA256) if opt_fp_in is None else opt_fp_in
+  log.info(f'Loading: {fp_in}')
+  df_records = pd.read_csv(fp_in).set_index('index')
+  
+  df_uuids = df_records.copy()
+  df_uuids['uuid'] = [uuid.uuid4()] * len(df_uuids)
+
+  for df_record in tqdm(df_records.itertuples(), total=len(df_uuids)):
+    image_index = df_record.Index
+    df_uuids.at[image_index, 'uuid'] = uuid.uuid4()
+
+  df_uuids = df_uuids.drop(['sha256', 'identity_index'], axis=1)
+  df_uuids.to_csv(fp_out)
\ No newline at end of file