Random cleanups and type safety. Created ml subdir.

1 files changed, 123 insertions, 0 deletions

diff --git a/ml/quick_label.py b/ml/quick_label.py
new file mode 100644
index 0000000..1ed4296
--- /dev/null
+++ b/ml/quick_label.py
@@ -0,0 +1,123 @@
+#!/usr/bin/env python3
+
+import glob
+import logging
+import os
+from typing import Callable, List, NamedTuple, Optional, Set
+
+import argparse_utils
+import config
+
+logger = logging.getLogger(__name__)
+parser = config.add_commandline_args(
+    f"ML Quick Labeler ({__file__})",
+    "Args related to quick labeling of ML training data",
+)
+parser.add_argument(
+    "--ml_quick_label_skip_list_path",
+    default="./qlabel_skip_list.txt",
+    metavar="FILENAME",
+    type=argparse_utils.valid_filename,
+    help="Path to file in which to store already labeled data.",
+)
+parser.add_argument(
+    "--ml_quick_label_use_skip_lists",
+    default=True,
+    action=argparse_utils.ActionNoYes,
+    help='Should we use a skip list file to speed up execution?',
+)
+parser.add_argument(
+    "--ml_quick_label_overwrite_labels",
+    default=False,
+    action=argparse_utils.ActionNoYes,
+    help='Enable overwriting existing labels; default is to not relabel.',
+)
+
+
+class InputSpec(NamedTuple):
+    image_file_glob: Optional[str]
+    image_file_prepopulated_list: Optional[List[str]]
+    image_file_to_features_file: Callable[[str], str]
+    label: str
+    valid_keystrokes: List[str]
+    prompt: str
+    keystroke_to_label: Callable[[str], str]
+
+
+def read_skip_list() -> Set[str]:
+    ret: Set[str] = set()
+    if config.config['ml_quick_label_use_skip_lists']:
+        quick_skip_file = config.config['ml_quick_label_skip_list_path']
+        if os.path.exists(quick_skip_file):
+            with open(quick_skip_file, 'r') as f:
+                lines = f.readlines()
+            for line in lines:
+                line = line[:-1]
+                line.strip()
+                ret.add(line)
+        logger.debug(f'Read {quick_skip_file} and found {len(ret)} entries.')
+    return ret
+
+
+def write_skip_list(skip_list) -> None:
+    if config.config['ml_quick_label_use_skip_lists']:
+        quick_skip_file = config.config['ml_quick_label_skip_list_path']
+        with open(quick_skip_file, 'w') as f:
+            for filename in skip_list:
+                filename = filename.strip()
+                if len(filename) > 0:
+                    f.write(f'{filename}\n')
+        logger.debug(f'Updated {quick_skip_file}')
+
+
+def label(in_spec: InputSpec) -> None:
+    import input_utils
+
+    images = []
+    if in_spec.image_file_glob is not None:
+        images += glob.glob(in_spec.image_file_glob)
+    elif in_spec.image_file_prepopulated_list is not None:
+        images += in_spec.image_file_prepopulated_list
+    else:
+        raise ValueError(
+            'One of image_file_glob or image_file_prepopulated_list is required'
+        )
+
+    skip_list = read_skip_list()
+    for image in images:
+        if image in skip_list:
+            logger.debug(f'Skipping {image} because of the skip list')
+            continue
+        features = in_spec.image_file_to_features_file(image)
+        if features is None or not os.path.exists(features):
+            logger.warning(
+                f'File {image} yielded file {features} which does not exist, SKIPPING.'
+            )
+            continue
+
+        # Render features and image.
+        filtered_lines = []
+        with open(features, "r") as f:
+            lines = f.readlines()
+        saw_label = False
+        for line in lines:
+            line = line[:-1]
+            if in_spec.label not in line:
+                filtered_lines.append(line)
+            else:
+                saw_label = True
+
+        if not saw_label or config.config['ml_quick_label_overwrite_labels']:
+            logger.info(features)
+            os.system(f'xv {image} &')
+            keystroke = input_utils.single_keystroke_response(
+                in_spec.valid_keystrokes,
+                prompt=in_spec.prompt,
+            )
+            os.system('killall xv')
+            label_value = in_spec.keystroke_to_label(keystroke)
+            filtered_lines.append(f"{in_spec.label}: {label_value}\n")
+            with open(features, 'w') as f:
+                f.writelines("%s\n" % line for line in filtered_lines)
+            skip_list.add(image)
+    write_skip_list(skip_list)