From: Scott Gasch <scott@gasch.org>
Date: Wed, 20 Apr 2022 03:54:03 +0000 (-0700)
Subject: Work on docs and readability.
X-Git-Url: https://wannabe.guru.org/gitweb/?a=commitdiff_plain;h=9d1940a45a8f073e1f29dd0ee0c2b0e53c3ffc0d;p=python_utils.git

Work on docs and readability.
---

diff --git a/ml/quick_label.py b/ml/quick_label.py
index 00acf05..feab67b 100644
--- a/ml/quick_label.py
+++ b/ml/quick_label.py
@@ -2,7 +2,12 @@
 
 # © Copyright 2021-2022, Scott Gasch
 
-"""A helper to facilitate quick manual labeling of ML training data."""
+"""A helper to facilitate quick manual labeling of ML training data.
+
+To use, implement a subclass that implements the QuickLabelHelper
+interface and pass it into the quick_label function.
+
+"""
 
 import logging
 import os
@@ -70,7 +75,7 @@ class QuickLabelHelper:
 
     @abstractmethod
     def render_example(self, filename: str, features: str, lines: List[str]) -> None:
-        '''Render a raw file with its features for the user.'''
+        '''Render a raw file with its features for the user to judge.'''
         pass
 
     @abstractmethod
@@ -91,7 +96,8 @@ class QuickLabelHelper:
         features: str,
         lines: List[str],
     ) -> Any:
-        '''Ask the current ML model about this example, if necessary.'''
+        '''Ask the current ML model about this example, if necessary/possible.
+        Returns None to indicate no model to consult.'''
         pass
 
     @abstractmethod
@@ -157,6 +163,10 @@ def _maybe_write_skip_list(skip_list) -> None:
 def _filter_images(
     images: List[str], skip_list: Set[str], helper: QuickLabelHelper
 ) -> List[Tuple[str, str]]:
+    '''Discard examples that have particular characteristics.  e.g.
+    those that are already labeled and whose current label agrees with
+    the ML model, etc...'''
+
     filtered_images = []
     label_label = helper.get_label_feature()
     for image in images:
@@ -216,15 +226,18 @@ def _filter_images(
 def _make_prompt(
     helper: QuickLabelHelper,
     cursor: int,
-    filtered_images: List[Tuple[str, str]],
-    image: str,
-    features: str,
-    labeled_features: Dict[Tuple[str, str], str],
+    num_filtered_images: int,
+    current_image: str,
+    current_features: str,
+    labeled_features: Dict[Tuple[str, str], str],  # Examples already labeled
 ) -> None:
-    label_label = helper.get_label_feature()
+    '''Tell an interactive user where they are in the set of examples that
+    may be labeled and the details of the current example.'''
+
+    label_label = helper.get_label_feature()  # the key: of a label in features
     filtered_lines = []
-    label = labeled_features.get((image, features), None)
-    with open(features, 'r') as rf:
+    label = labeled_features.get((current_image, current_features), None)
+    with open(current_features, 'r') as rf:
         lines = rf.readlines()
     for line in lines:
         line = line[:-1]
@@ -237,18 +250,18 @@ def _make_prompt(
             label = line
 
     # Prompt...
-    helper.render_example(image, features, filtered_lines)
-    print(f'{cursor}/{len(filtered_images)} ({cursor/len(filtered_images)*100.0:.1f}%) | ', end='')
-    print(f'{ansi.bold()}{image} / {features}{ansi.reset()}:')
-    print(f'    ...{len(labeled_features)} currently unsaved labels ("W" to save).')
+    helper.render_example(current_image, current_features, filtered_lines)
+    print(f'{cursor}/{num_filtered_images} ({cursor/num_filtered_images*100.0:.1f}%) | ', end='')
+    print(f'{ansi.bold()}{current_image} / {current_features}{ansi.reset()}:')
+    print(f'    ...{len(labeled_features)} currently unwritten label(s) ("W" to write).')
     if label:
-        if (image, features) in labeled_features:
+        if (current_image, current_features) in labeled_features:
             print(f'    ...This example is labeled but not yet saved: {label}')
         else:
             print(f'    ...This example is already labeled on disk: {label}')
     else:
         print('    ...This example is currently unlabeled')
-    guess = helper.ask_current_model_about_example(image, features, filtered_lines)
+    guess = helper.ask_current_model_about_example(current_image, current_features, filtered_lines)
     if guess:
         print(f'    ...The ML Model says {guess}')
     print()
@@ -283,6 +296,10 @@ def _write_labeled_features(
 
 
 def quick_label(helper: QuickLabelHelper) -> None:
+    '''Pass your QuickLabelHelper implementing class to this function and
+    it will allow users to label examples and persist them to disk.
+
+    '''
     skip_list = _maybe_read_skip_list()
 
     # Ask helper for an initial set of files.
@@ -301,7 +318,6 @@ def quick_label(helper: QuickLabelHelper) -> None:
     logger.info('There are %d candidate images post filtering.', len(filtered_images))
 
     # Allow the user to label the non-filtered images one by one.
-
     labeled_features: Dict[Tuple[str, str], str] = {}
     cursor = 0
     while True:
@@ -313,7 +329,7 @@ def quick_label(helper: QuickLabelHelper) -> None:
         assert features and os.path.exists(features)
 
         # Render the features, image and prompt.
-        _make_prompt(helper, cursor, filtered_images, image, features, labeled_features)
+        _make_prompt(helper, cursor, len(filtered_images), image, features, labeled_features)
         try:
             # Did they want everything labelled the same?
             label_everything = helper.get_everything_label()