britekit 0.1.3__py3-none-any.whl → 0.1.4__py3-none-any.whl

britekit/occurrence_db/occurrence_data_provider.py

@@ -10,7 +10,7 @@ class OccurrenceDataProvider:
     you must call the refresh method.
 
     Args:
-        db (OccurrenceDatabase): The database object.
+    - db (OccurrenceDatabase): The database object.
     """
 
     def __init__(self, db: OccurrenceDatabase):
@@ -31,8 +31,8 @@ class OccurrenceDataProvider:
         Return county info for a given latitude/longitude, or None if not found.
 
         Args:
-            latitude (float): Latitude.
-            longitude (float): Longitude.
+        - latitude (float): Latitude.
+        - longitude (float): Longitude.
 
         Returns:
             County object, or None if not found.
@@ -54,8 +54,8 @@ class OccurrenceDataProvider:
         For each week, return the maximum of it and the adjacent weeks.
 
         Args:
-            county_code (str): County code
-            class_name (str): Class name
+        - county_code (str): County code
+        - class_name (str): Class name
 
         Returns:
             List of smoothed occurrence values.
@@ -75,8 +75,8 @@ class OccurrenceDataProvider:
         Return list of occurrence values for given county code and class name.
 
         Args:
-            county_code (str): County code
-            class_name (str): Class name
+        - county_code (str): County code
+        - class_name (str): Class name
 
         Returns:
             List of occurrence values.
@@ -97,9 +97,9 @@ class OccurrenceDataProvider:
         If area_weight = True, weight each county by its area.
 
         Args:
-            county_prefix (str): County code prefix
-            class_name (str): Class name
-            area_weight (bool, Optional): If true, weight by county area (default = False)
+        - county_prefix (str): County code prefix
+        - class_name (str): Class name
+        - area_weight (bool, Optional): If true, weight by county area (default = False)
 
         Returns:
             Numpy array of 48 average occurrence values (one per week, using 4-week months).
@@ -139,9 +139,9 @@ class OccurrenceDataProvider:
         county don't occur in the same week.
 
         Args:
-            county_prefix (str): County code prefix
-            class_name (str): Class name
-            area_weight (bool, Optional): If true, weight by county area (default = False)
+        - county_prefix (str): County code prefix
+        - class_name (str): Class name
+        - area_weight (bool, Optional): If true, weight by county area (default = False)
 
         Returns:
             Numpy average maximum occurrence value.

britekit/training_db/extractor.py

@@ -109,13 +109,45 @@ class Extractor:
 
         return offsets_per_file
 
+    def _insert_by_dict(self, recording_dir, destination_dir, offsets_per_file):
+        """
+        Given a recording directory and a dict from recording stems to offsets,
+        insert the corresponding spectrograms.
+        """
+        num_inserted = 0
+        recording_paths = util.get_audio_files(recording_dir)
+        for recording_dir in recording_paths:
+            filename = Path(recording_dir).stem
+            if filename not in offsets_per_file:
+                continue
+
+            if destination_dir is not None:
+                dest_path = os.path.join(destination_dir, Path(recording_dir).name)
+                if not os.path.exists(dest_path):
+                    shutil.copy(recording_dir, dest_path)
+
+                recording_dir = dest_path
+
+            logging.info(f"Processing {recording_dir}")
+            try:
+                self.audio.load(recording_dir)
+            except Exception as e:
+                logging.error(f"Caught exception: {e}")
+                continue
+
+            num_inserted += self.insert_spectrograms(
+                recording_dir, offsets_per_file[filename]
+            )
+
+        return num_inserted
+
     def insert_spectrograms(self, recording_path, offsets):
         """
         Insert a spectrogram at each of the given offsets of the specified file.
 
         Args:
-            recording_path (str): Path to audio recording.
-            offsets (list[float]): List of offsets, where each represents number of seconds to start of spectrogram.
+        - recording_path (str): Path to audio recording.
+        - offsets (list[float]): List of offsets, where each represents number of seconds to start of spectrogram.
 
         Returns:
             Number of spectrograms inserted.
@@ -156,7 +188,7 @@ class Extractor:
         Extract spectrograms for all recordings in the given directory.
 
         Args:
-            dir_path (str): Directory containing recordings.
+        - dir_path (str): Directory containing recordings.
 
         Returns:
             Number of spectrograms inserted.
@@ -187,45 +219,48 @@ class Extractor:
 
         return num_inserted
 
-    def extract_by_image(
-        self, rec_dir: str, spec_dir: str, dest_dir: Optional[str] = None
+    def extract_by_csv(
+        self, rec_dir: str, csv_path: str, dest_dir: Optional[str] = None
     ):
         """
         Extract spectrograms that match names of spectrogram images in a given directory.
         Typically the spectrograms were generated using the 'search' or 'plot-db' commands.
 
         Args:
-            rec_dir (str): Directory containing recordings.
-            spec_dir (str): Directory containing spectrogram images.
-            dest_dir (str, optional): Optionally copy used recordings to this directory.
+        - rec_dir (str): Directory containing recordings.
+        - csv_path (str): Path to CSV file containing two columns (recording and offset) to identify segments to extract.
+        - dest_dir (str, optional): Optionally copy used recordings to this directory.
 
         Returns:
             Number of spectrograms inserted.
         """
-        offsets_per_file = self._process_image_dir(spec_dir)
-        num_inserted = 0
-        recording_paths = util.get_audio_files(rec_dir)
-        for recording_path in recording_paths:
-            filename = Path(recording_path).stem
-            if filename not in offsets_per_file:
-                continue
+        import pandas as pd
 
-            if dest_dir is not None:
-                dest_path = os.path.join(dest_dir, Path(recording_path).name)
-                if not os.path.exists(dest_path):
-                    shutil.copy(recording_path, dest_path)
+        df = pd.read_csv(csv_path)
+        offsets_per_file: dict[str, list] = {}
+        for i, row in df.iterrows():
+            recording = row["recording"]
+            if recording not in offsets_per_file:
+                offsets_per_file[recording] = []
 
-                recording_path = dest_path
+            offsets_per_file[recording].append(row["offset"])
 
-            logging.info(f"Processing {recording_path}")
-            try:
-                self.audio.load(recording_path)
-            except Exception as e:
-                logging.error(f"Caught exception: {e}")
-                continue
+        return self._insert_by_dict(rec_dir, dest_dir, offsets_per_file)
 
-            num_inserted += self.insert_spectrograms(
-                recording_path, offsets_per_file[filename]
-            )
+    def extract_by_image(
+        self, rec_dir: str, spec_dir: str, dest_dir: Optional[str] = None
+    ):
+        """
+        Extract spectrograms that match names of spectrogram images in a given directory.
+        Typically the spectrograms were generated using the 'search' or 'plot-db' commands.
 
-        return num_inserted
+        Args:
+        - rec_dir (str): Directory containing recordings.
+        - spec_dir (str): Directory containing spectrogram images.
+        - dest_dir (str, optional): Optionally copy used recordings to this directory.
+
+        Returns:
+            Number of spectrograms inserted.
+        """
+        offsets_per_file = self._process_image_dir(spec_dir)
+        return self._insert_by_dict(rec_dir, dest_dir, offsets_per_file)

britekit/training_db/training_data_provider.py

@@ -8,7 +8,7 @@ class TrainingDataProvider:
     Data access layer on top of TrainingDatabase.
 
     Args:
-        db (TrainingDatabase): The database object.
+    - db (TrainingDatabase): The database object.
     """
 
     def __init__(self, db: TrainingDatabase):