chore: add animated emoji progress indicators to progress tracker (#273)

* chore: add animated emoji progress indicators to progress tracker

Add fun visual feedback during dataset generation with emoji that evolve
based on completion percentage. Randomly selects from moon phases,
weather, or hatching styles at tracker initialization.

* always log 100%

* refactor: move progress emoji logic into RandomEmoji class

Add progress() method to RandomEmoji that returns an emoji based on
completion percentage. This centralizes the progress style logic that
was previously duplicated in ProgressTracker.

* add some tests

Author: johnnygreco

packages/data-designer-config/src/data_designer/logging.py

@@ -50,6 +50,14 @@ def debug(cls):
 class RandomEmoji:
     """A generator for various themed emoji collections."""
 
+    def __init__(self) -> None:
+        self._progress_style = random.choice(_PROGRESS_STYLES)
+
+    def progress(self, percent: float) -> str:
+        """Get a progress emoji based on completion percentage (0-100)."""
+        phase_idx = min(int(percent / 25), len(self._progress_style) - 1)
+        return self._progress_style[phase_idx]
+
     @staticmethod
     def cooking() -> str:
         """Get a random cooking or food preparation emoji."""
@@ -163,3 +171,10 @@ def _make_stream_formatter() -> logging.Formatter:
 
 
 _DEFAULT_NOISY_LOGGERS = ["httpx", "matplotlib"]
+
+
+_PROGRESS_STYLES: list[list[str]] = [
+    ["🌑", "🌘", "🌗", "🌖", "🌕"],  # Moon phases
+    ["🌧️", "🌦️", "⛅", "🌤️", "☀️"],  # Weather (storm to sun)
+    ["🥚", "🐣", "🐥", "🐤", "🐔"],  # Hatching (egg to chicken)
+]

packages/data-designer-config/tests/test_logging.py

@@ -208,3 +208,54 @@ def test_random_emoji_randomness():
     emojis = [RandomEmoji.magic() for _ in range(100)]
     # If we get 100 samples, we should get at least 2 different emojis
     assert len(set(emojis)) > 1
+
+
+def test_random_emoji_progress_returns_valid_emoji() -> None:
+    emoji_gen = RandomEmoji()
+    emoji = emoji_gen.progress(50.0)
+    assert emoji is not None
+    assert len(emoji) > 0
+
+
+def test_random_emoji_progress_is_deterministic() -> None:
+    emoji_gen = RandomEmoji()
+    # Same percentage should always return the same emoji for a given instance
+    assert emoji_gen.progress(0.0) == emoji_gen.progress(0.0)
+    assert emoji_gen.progress(50.0) == emoji_gen.progress(50.0)
+    assert emoji_gen.progress(100.0) == emoji_gen.progress(100.0)
+
+
+def test_random_emoji_progress_phases_are_distinct() -> None:
+    emoji_gen = RandomEmoji()
+    # Each 25% phase should return a different emoji
+    phase_emojis = [
+        emoji_gen.progress(0.0),  # phase 0
+        emoji_gen.progress(25.0),  # phase 1
+        emoji_gen.progress(50.0),  # phase 2
+        emoji_gen.progress(75.0),  # phase 3
+        emoji_gen.progress(100.0),  # phase 4
+    ]
+    # All 5 phases should have distinct emojis
+    assert len(set(phase_emojis)) == 5
+
+
+def test_random_emoji_progress_phase_boundaries() -> None:
+    emoji_gen = RandomEmoji()
+    # Values within the same phase should return the same emoji
+    assert emoji_gen.progress(0.0) == emoji_gen.progress(24.9)
+    assert emoji_gen.progress(25.0) == emoji_gen.progress(49.9)
+    assert emoji_gen.progress(50.0) == emoji_gen.progress(74.9)
+    assert emoji_gen.progress(75.0) == emoji_gen.progress(99.9)
+    # Phase transitions should return different emojis
+    assert emoji_gen.progress(24.9) != emoji_gen.progress(25.0)
+    assert emoji_gen.progress(49.9) != emoji_gen.progress(50.0)
+    assert emoji_gen.progress(74.9) != emoji_gen.progress(75.0)
+    assert emoji_gen.progress(99.9) != emoji_gen.progress(100.0)
+
+
+def test_random_emoji_progress_clamps_over_100() -> None:
+    emoji_gen = RandomEmoji()
+    emoji_100 = emoji_gen.progress(100.0)
+    emoji_over = emoji_gen.progress(150.0)
+    # Both should return the same final emoji
+    assert emoji_100 == emoji_over

packages/data-designer-engine/src/data_designer/engine/dataset_builders/utils/progress_tracker.py

@@ -7,6 +7,8 @@
 import time
 from threading import Lock
 
+from data_designer.logging import RandomEmoji
+
 logger = logging.getLogger(__name__)
 
 
@@ -51,6 +53,7 @@ def __init__(self, total_records: int, label: str, log_interval_percent: int = 1
 
         self.start_time = time.perf_counter()
         self.lock = Lock()
+        self._random_emoji = RandomEmoji()
 
     def log_start(self, max_workers: int) -> None:
         """Log the start of processing with worker count and interval information."""
@@ -76,7 +79,9 @@ def record_failure(self) -> None:
     def log_final(self) -> None:
         """Log final progress if not already logged at completion."""
         with self.lock:
-            if self.total_records > 0 and self.completed < self.total_records:
+            if self.completed > 0 and self.completed == self.total_records:
+                self._log_progress_unlocked()  # always log 100%
+            elif self.total_records > 0 and self.completed < self.total_records:
                 self._log_progress_unlocked()
             elif self.completed > 0 and self.completed >= self.next_log_at - self.log_interval:
                 pass  # Already logged at the last interval
@@ -110,7 +115,8 @@ def _log_progress_unlocked(self) -> None:
         percent = (self.completed / self.total_records) * 100 if self.total_records else 100.0
 
         logger.info(
-            "  |-- 📈 %s progress: %d/%d (%.0f%%) complete, %d ok, %d failed, %.2f rec/s, eta %s",
+            "  |-- %s %s progress: %d/%d (%.0f%%) complete, %d ok, %d failed, %.2f rec/s, eta %s",
+            self._random_emoji.progress(percent),
             self.label,
             self.completed,
             self.total_records,