1 files changed, 93 insertions, 0 deletions
diff --git a/megapixels/commands/datasets/identity_meta_lfw.py b/megapixels/commands/datasets/identity_meta_lfw.py
new file mode 100644
index 00000000..45386b23
--- /dev/null
+++ b/megapixels/commands/datasets/identity_meta_lfw.py
@@ -0,0 +1,93 @@
+'''
+add identity from description using subdir
+'''
+import click
+
+from app.settings import types
+from app.models.dataset import Dataset
+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', required=True,
+  help='Identity meta file')
+@click.option('-o', '--output', 'opt_fp_out', default=None,
+  help='Override enum output filename CSV')
+@click.option('--column', 'opt_identity_key', default='identity_key',
+  help='Match column')
+@click.option('--data_store', 'opt_data_store',
+  type=cfg.DataStoreVar,
+  default=click_utils.get_default(types.DataStore.SSD),
+  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_identity_key, opt_data_store, opt_force):
+  """Display image info"""
+  
+  import sys
+  from glob import glob
+  from os.path import join
+  from pathlib import Path
+  import time
+
+  import pandas as pd
+  import cv2 as cv
+  from tqdm import tqdm
+  
+  from app.utils import file_utils, im_utils
+  from app.models.data_store import DataStore
+
+  log = Logger.getLogger()
+  
+  # output file
+  opt_dataset = types.Dataset.LFW
+  data_store = DataStore(opt_data_store, opt_dataset)
+  fp_out = data_store.metadata(types.Metadata.IDENTITY) if opt_fp_out is None else opt_fp_out
+  # exit if exists
+  log.debug(fp_out)
+  if not opt_force and Path(fp_out).exists():
+    log.error('File exists. Use "-f / --force" to overwite')
+    return
+
+  # init dataset
+  # load file records
+  fp_record = data_store.metadata(types.Metadata.FILE_RECORD)
+  df_record = pd.read_csv(fp_record).set_index('index')
+
+  # load identity meta
+  # this file is maybe prepared in a Jupyter notebook
+  # the "identity_key"
+  df_identity_meta = pd.read_csv(opt_fp_in).set_index('index')
+  # create a new file called 'identity.csv'
+  identities = []
+  # iterate records and get identity index where 'identity_key' matches
+  log.debug(type(df_record))
+  identity_indices = []
+  for record_idx, ds_record in tqdm(df_record.iterrows(), total=len(df_record)):
+    identity_value = ds_record[opt_identity_key]
+    identity_index = ds_record.identity_index
+    ds_identity_meta = df_identity_meta.loc[(df_identity_meta[opt_identity_key] == identity_value)]
+    if identity_index not in identity_indices:
+      identity_indices.append(identity_index)
+      identities.append({
+        'description': ds_identity_meta.description.values[0],
+        'name': ds_identity_meta.name.values[0],
+        'images': ds_identity_meta.images.values[0],
+        'gender': ds_identity_meta.gender.values[0],
+        })
+
+  # write to csv
+  df_identity = pd.DataFrame.from_dict(identities)
+  df_identity.index.name = 'index'
+  df_identity.to_csv(fp_out)
+  '''
+  index,name,name_orig,description,gender,images,image_index,identity_key
+  0,A. J. Cook,AJ Cook,Canadian actress,f,1,0,AJ_Cook
+  '''
+
+