added FR demo notebook

2 files changed, 111 insertions, 28 deletions

diff --git a/megapixels/commands/datasets/file_meta.py b/megapixels/commands/datasets/file_meta.py
new file mode 100644
index 00000000..e1456f44
--- /dev/null
+++ b/megapixels/commands/datasets/file_meta.py
@@ -0,0 +1,84 @@
+"""
+Begin with this file to process folder of images
+- Converts folders and subdirectories into CSV with file attributes split
+"""
+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', required=True,
+  help='Input directory')
+@click.option('-o', '--output', 'opt_fp_out', required=True,
+  help='Output file for file meta CSV')
+@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None),
+  help='Slice list of files')
+@click.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False,
+  help='Use glob recursion (slower)')
+@click.option('-t', '--threads', 'opt_threads', default=4,
+  help='Number of threads')
+@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_slice, opt_recursive, opt_threads, opt_force):
+  """Multithreading test"""
+  
+  from glob import glob
+  from os.path import join
+  from pathlib import Path
+  import time
+  from multiprocessing.dummy import Pool as ThreadPool 
+  import random
+
+  import pandas as pd
+  from tqdm import tqdm
+  from glob import glob
+  
+  from app.utils import file_utils, im_utils
+
+
+  if not opt_force and Path(opt_fp_out).exists():
+    log.error('File exists. Use "-f / --force" to overwite')
+    return
+
+  fp_ims = []
+  log.info(f'Globbing {opt_fp_in}')
+  for ext in ['jpg', 'png']:
+    if opt_recursive:
+      fp_glob = join(opt_fp_in, '**/*.{}'.format(ext))
+      fp_ims += glob(fp_glob, recursive=True)
+    else:
+      fp_glob = join(opt_fp_in, '*.{}'.format(ext))
+      fp_ims += glob(fp_glob)
+
+  if not fp_ims:
+    log.warn('No images. Try with "--recursive"')
+    return
+
+  if opt_slice:
+    fp_ims = fp_ims[opt_slice[0]:opt_slice[1]]
+
+  log.info('Processing {:,} images'.format(len(fp_ims)))
+
+
+  # convert data to dict
+  data = []
+  for i, fp_im in enumerate(tqdm(fp_ims)):
+    fpp_im = Path(fp_im)
+    subdir = str(fpp_im.parent.relative_to(opt_fp_in))
+    data.append( {
+      'subdir': subdir,
+      'fn': fpp_im.stem,
+      'ext': fpp_im.suffix.replace('.','')
+      })
+
+  # save to CSV
+  file_utils.mkdirs(opt_fp_out)
+  df = pd.DataFrame.from_dict(data)
+  df.index.name = 'index'
+  df.to_csv(opt_fp_out)
\ No newline at end of file
diff --git a/megapixels/commands/datasets/sha256.py b/megapixels/commands/datasets/sha256.py
index c04fb504..4c734073 100644
--- a/megapixels/commands/datasets/sha256.py
+++ b/megapixels/commands/datasets/sha256.py
@@ -10,18 +10,18 @@ log = Logger.getLogger()
 @click.command()
 @click.option('-i', '--input', 'opt_fp_in', required=True,
   help='Input directory')
-@click.option('-o', '--output', 'opt_fp_out',
+@click.option('-m', '--media', 'opt_dir_media', required=True,
+  help='Input media directory')
+@click.option('-o', '--output', 'opt_fp_out', required=True,
   help='Output directory')
 @click.option('--slice', 'opt_slice', type=(int, int), default=(None, None),
   help='Slice list of files')
-@click.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False,
-  help='Use glob recursion (slower)')
 @click.option('-t', '--threads', 'opt_threads', default=4,
   help='Number of threads')
 @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_slice, opt_recursive, opt_threads, opt_force):
+def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_slice, opt_threads, opt_force):
   """Multithreading test"""
   
   from glob import glob
@@ -42,47 +42,46 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_slice, opt_recursive, opt_threads, opt_f
     log.error('File exists. Use "-f / --force" to overwite')
     return
 
-  fp_ims = []
-  for ext in ['jpg', 'png']:
-    if opt_recursive:
-      fp_glob = join(opt_fp_in, '**/*.{}'.format(ext))
-      fp_ims += glob(fp_glob, recursive=True)
-    else:
-      fp_glob = join(opt_fp_in, '*.{}'.format(ext))
-      fp_ims += glob(fp_glob)
+  df_files = pd.read_csv(opt_fp_in).set_index('index')
 
   if opt_slice:
-    fp_ims = fp_ims[opt_slice[0]:opt_slice[1]]
+    df_files = df_files[opt_slice[0]:opt_slice[1]]
 
-  log.info('Processing {:,} images'.format(len(fp_ims)))
+  log.info('Processing {:,} images'.format(len(df_files)))
 
-  pbar = tqdm(total=100)
+  
+  # prepare list of images to multithread into sha256s
+  file_objs = []
+  for ds_file in df_files.itertuples():
+    fp_im = join(opt_dir_media, str(ds_file.subdir), f"{ds_file.fn}.{ds_file.ext}")
+    file_objs.append({'fp': fp_im, 'index': ds_file.Index})
+
+  # convert to thread pool
+  pbar = tqdm(total=len(file_objs))
 
-  def as_sha256(fp_im):
+  def as_sha256(file_obj):
     pbar.update(1)
-    return file_utils.sha256(fp_im)
+    file_obj['sha256'] = file_utils.sha256(file_obj['fp'])
+    return file_obj
 
   # multithread pool
+  pool_file_objs = []
   st = time.time()
   pool = ThreadPool(opt_threads) 
-  with tqdm(total=len(fp_ims)) as pbar:
-    sha256s = pool.map(as_sha256, fp_ims)
+  with tqdm(total=len(file_objs)) as pbar:
+    pool_file_objs = pool.map(as_sha256, file_objs)
   pbar.close()
-
+  
   # convert data to dict
   data = []
-  for i, fp_im in enumerate(fp_ims):
-    fpp_im = Path(fp_im)
-    subdir = str(fpp_im.parent.relative_to(opt_fp_in))
-    sha256 = sha256s[i]
+  for pool_file_obj in pool_file_objs:
     data.append( {
-      'sha256': sha256, 
-      'subdir': subdir,
-      'fn': fpp_im.stem,
-      'ext': fpp_im.suffix.replace('.','')
+      'sha256': pool_file_obj['sha256'], 
+      'index': pool_file_obj['index']
       })
 
   # save to CSV
+  file_utils.mkdirs(opt_fp_out)
   df = pd.DataFrame.from_dict(data)
   df.to_csv(opt_fp_out, index=False)