Added AudioPath as an alias for the path definition

batdetect2/api.py

@@ -99,6 +99,7 @@ consult the API documentation in the code.
 import warnings
 from typing import List, Optional, Tuple, BinaryIO, Any, Union
 
+from .types import AudioPath
 import numpy as np
 import torch
 
@@ -244,9 +245,7 @@ def generate_spectrogram(
 
 
 def process_file(
-    path:  Union[
-        str, int, os.PathLike[Any], sf.SoundFile, audioread.AudioFile, BinaryIO
-    ],
+    path: AudioPath,
     model: DetectionModel = MODEL,
     config: Optional[ProcessingConfiguration] = None,
     device: torch.device = DEVICE,
@@ -256,9 +255,7 @@ def process_file(
 
     Parameters
     ----------
-    path :  Union[
-        str, int, os.PathLike[Any], sf.SoundFile, audioread.AudioFile, BinaryIO
-    ]
+    path : AudioPath
         Path to audio data.
     model : DetectionModel, optional
         Detection model. Uses default model if not specified.

batdetect2/types.py

@@ -1,6 +1,10 @@
 """Types used in the code base."""
 
-from typing import List, NamedTuple, Optional, Union
+from typing import List, NamedTuple, Optional, Union, Any, BinaryIO
+
+import audioread
+import os 
+import soundfile as sf
 
 import numpy as np
 import torch
@@ -40,6 +44,9 @@ __all__ = [
     "SpectrogramParameters",
 ]
 
+AudioPath =  Union[
+        str, int, os.PathLike[Any], sf.SoundFile, audioread.AudioFile, BinaryIO
+    ]
 
 class SpectrogramParameters(TypedDict):
     """Parameters for generating spectrograms."""

batdetect2/utils/audio_utils.py

@@ -1,6 +1,8 @@
 import warnings
 from typing import Optional, Tuple, Union, Any, BinaryIO
 
+from ..types import AudioPath
+
 import librosa
 import librosa.core.spectrum
 import numpy as np
@@ -9,7 +11,6 @@ import torch
 import audioread
 import os 
 import soundfile as sf
-import io
 
 from batdetect2.detector import parameters
 
@@ -17,7 +18,7 @@ from . import wavfile
 
 __all__ = [
     "load_audio",
-    "load_audio_data",
+    "load_audio_and_samplerate",
     "generate_spectrogram",
     "pad_audio",
 ]
@@ -147,9 +148,7 @@ def generate_spectrogram(
     return spec, spec_for_viz
 
 def load_audio(
-    path:  Union[
-        str, int, os.PathLike[Any], sf.SoundFile, audioread.AudioFile, BinaryIO
-    ],
+    path: AudioPath,
     time_exp_fact: float,
     target_samp_rate: int,
     scale: bool = False,
@@ -174,13 +173,11 @@ def load_audio(
         ValueError: If the audio file is stereo.
 
     """
-    sample_rate, audio_data, _ = load_audio_data(path, time_exp_fact, target_samp_rate, scale, max_duration)
+    sample_rate, audio_data, _ = load_audio_and_samplerate(path, time_exp_fact, target_samp_rate, scale, max_duration)
     return sample_rate, audio_data
 
-def load_audio_data(
-    path:  Union[
-        str, int, os.PathLike[Any], sf.SoundFile, audioread.AudioFile, BinaryIO
-    ],
+def load_audio_and_samplerate(
+    path: AudioPath,
     time_exp_fact: float,
     target_samp_rate: int,
     scale: bool = False,
@@ -200,6 +197,7 @@ def load_audio_data(
     Returns:
         sampling_rate: The sampling rate of the audio.
         audio_raw: The audio signal in a numpy array.
+        file_sampling_rate: The original sampling rate of the audio
 
     Raises:
         ValueError: If the audio file is stereo.

batdetect2/utils/detector_utils.py

@@ -2,7 +2,8 @@ import json
 import os
 from typing import Any, Iterator, List, Optional, Tuple, Union, BinaryIO
 
-import librosa
+from ..types import AudioPath
+
 import numpy as np
 import pandas as pd
 import torch
@@ -736,9 +737,7 @@ def process_audio_array(
 
 
 def process_file(
-    path:  Union[
-        str, int, os.PathLike[Any], sf.SoundFile, audioread.AudioFile, BinaryIO
-    ],
+    path: AudioPath,
     model: DetectionModel,
     config: ProcessingConfiguration,
     device: torch.device,
@@ -751,7 +750,7 @@ def process_file(
 
     Parameters
     ----------
-    path : str, int, os.PathLike[Any], sf.SoundFile, audioread.AudioFile, BinaryIO
+    path : AudioPath
         Path to audio file.
 
     model : torch.nn.Module
@@ -759,6 +758,9 @@ def process_file(
 
     config : ProcessingConfiguration
         Configuration for processing.
+    
+    file_id: Optional[str],
+        Give the data an id. Defaults to the filename if path is a string. Otherwise an md5 will be calculated from the binary data.
 
     Returns
     -------
@@ -773,7 +775,7 @@ def process_file(
     spec_slices = []
 
     # load audio file
-    sampling_rate, audio_full, file_samp_rate = au.load_audio_data(
+    sampling_rate, audio_full, file_samp_rate = au.load_audio_and_samplerate(
         path,
         time_exp_fact=config.get("time_expansion", 1) or 1,
         target_samp_rate=config["target_samp_rate"],
@@ -857,9 +859,7 @@ def process_file(
 
     return results
 
-def _generate_id(path:  Union[
-        str, int, os.PathLike[Any], sf.SoundFile, audioread.AudioFile, BinaryIO
-    ]) -> str:
+def _generate_id(path: AudioPath) -> str:
     """ Generate an id based on the path.
     
     If the path is a str or PathLike it will parsed as the basename. 

tests/test_api.py

@@ -284,7 +284,7 @@ def test_process_file_with_empty_predictions_does_not_fail(
     assert len(results["pred_dict"]["annotation"]) == 0
 
 def test_process_file_file_id_defaults_to_basename():
-    """Test that no detections are made above the nyquist frequency."""
+    """Test that process_file assigns basename as an id if no file_id is provided."""
     # Recording donated by @@kdarras
     basename = "20230322_172000_selec2.wav"
     path = os.path.join(DATA_DIR, basename)
@@ -295,7 +295,7 @@ def test_process_file_file_id_defaults_to_basename():
     assert id == basename
 
 def test_bytesio_file_id_defaults_to_md5():
-    """Test that no detections are made above the nyquist frequency."""
+    """Test that process_file assigns an md5 sum as an id if no file_id is provided when using binary data."""
     # Recording donated by @@kdarras
     basename = "20230322_172000_selec2.wav"
     path = os.path.join(DATA_DIR, basename)

tests/test_audio_utils.py

@@ -146,9 +146,9 @@ def test_load_audio_using_bytesio():
     with open(path, "rb") as f:
         data = io.BytesIO(f.read())
     
-    sample_rate, audio_data, file_sample_rate = audio_utils.load_audio_data(data, time_exp_fact=1, target_samp_rate=parameters.TARGET_SAMPLERATE_HZ)
+    sample_rate, audio_data, file_sample_rate = audio_utils.load_audio_and_samplerate(data, time_exp_fact=1, target_samp_rate=parameters.TARGET_SAMPLERATE_HZ)
 
-    expected_sample_rate, expected_audio_data, exp_file_sample_rate = audio_utils.load_audio_data(path, time_exp_fact=1, target_samp_rate=parameters.TARGET_SAMPLERATE_HZ)
+    expected_sample_rate, expected_audio_data, exp_file_sample_rate = audio_utils.load_audio_and_samplerate(path, time_exp_fact=1, target_samp_rate=parameters.TARGET_SAMPLERATE_HZ)
 
     assert expected_sample_rate == sample_rate
     assert exp_file_sample_rate == file_sample_rate