Merge pull request #128 from NickleDave/rename-hz-ind

CLN: rename `on/offsets_Hz` -> `on/offset_inds`, fix #87
vocalpy · Jan 2, 2022 · da1f84f · da1f84f
2 parents c44f9a8 + de67b78
commit da1f84f
Show file tree

Hide file tree

Showing 30 changed files with 264 additions and 264 deletions.
diff --git a/README.md b/README.md
@@ -17,17 +17,17 @@ work with any format: namely, `Sequence`s made up of `Segment`s.
     >>> from crowsetta import Segment, Sequence
     >>> a_segment = Segment.from_keyword(
     ...     label='a',
-    ...     onset_Hz=16000,
-    ...     offset_Hz=32000,
+    ...     onset_ind=16000,
+    ...     offset_ind=32000,
     ...     file='bird21.wav'
     ...     )
     >>> list_of_segments = [a_segment] * 3
     >>> seq = Sequence(segments=list_of_segments)
     >>> print(seq)
-    Sequence(segments=[Segment(label='a', onset_s=None, offset_s=None, onset_Hz=16000, 
-    offset_Hz=32000, file='bird21.wav'), Segment(label='a', onset_s=None, offset_s=None, 
-    onset_Hz=16000, offset_Hz=32000, file='bird21.wav'), Segment(label='a', onset_s=None, 
-    offset_s=None, onset_Hz=16000, offset_Hz=32000, file='bird21.wav')])
+    Sequence(segments=[Segment(label='a', onset_s=None, offset_s=None, onset_ind=16000, 
+    offset_ind=32000, file='bird21.wav'), Segment(label='a', onset_s=None, offset_s=None, 
+    onset_ind=16000, offset_ind=32000, file='bird21.wav'), Segment(label='a', onset_s=None, 
+    offset_s=None, onset_ind=16000, offset_ind=32000, file='bird21.wav')])
 ```
 
 You can load annotation from your format of choice into `Sequence`s of `Segment`s 

diff --git a/doc/CHANGELOG.md b/doc/CHANGELOG.md
@@ -193,8 +193,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## 0.2.0a5
 ### added
-- Sequence instances have attributes: labels, onsets_s, offsets_s, onsets_Hz, 
-  offsets_Hz, and file. 
+- Sequence instances have attributes: labels, onsets_s, offsets_s, onset_inds, 
+  offset_inds, and file. 
 - Explanation of default `to_csv` function for user formats in `howto-user-config`.
 
 ### changed

diff --git a/doc/howto-user-format.rst b/doc/howto-user-format.rst
@@ -225,8 +225,8 @@ us back an instance of a ``Sequence``. One such factory function is
     a_sequence = Sequence.from_keyword(labels=annot_dict['seg_types'],
                                        onsets_s=annot_dict['seg_start_times'],
                                        offsets_s=annot_dict['seg_end_times'],
-                                       onsets_Hz=annot_dict['seg_start_times_Hz'],
-                                       offsets_Hz=annot_dict['seg_end_times_Hz'],
+                                       onset_inds=annot_dict['seg_start_times_Hz'],
+                                       offset_inds=annot_dict['seg_end_times_Hz'],
                                        file=annot_dict['audio_file'])
     print("a_sequence:\n", a_sequence)
 
@@ -268,8 +268,8 @@ Then at the end of your main loop, instead of making your
                                 labels=seg_types,
                                 onsets_s=seg_start_times,
                                 offsets_s=seg_end_times,
-                                onsets_Hz=seg_start_times_Hz,
-                                offsets_Hz=seg_end_times_Hz)
+                                onset_inds=seg_start_times_Hz,
+                                offset_inds=seg_end_times_Hz)
     seq_list.append(seq)
         return seq_list
 
@@ -391,7 +391,7 @@ of ``Sequence``\ s from your format:
 
     First item in seq_list: <Sequence with 15 segments>
     First segment in first sequence:
-    Segment(label='1', file='lbr3009_0005_2017_04_27_06_14_46.wav', onset_s=0.0029761904761904934, offset_s=0.14150432900432905, onset_Hz=143, offset_Hz=6792)
+    Segment(label='1', file='lbr3009_0005_2017_04_27_06_14_46.wav', onset_s=0.0029761904761904934, offset_s=0.14150432900432905, onset_ind=143, offset_ind=6792)
 
 
 Notice that we also get a ``to_csv`` function for free:
@@ -411,7 +411,7 @@ Notice that we also get a ``to_csv`` function for free:
 
 .. parsed-literal::
 
-    ['label', 'onset_s', 'offset_s', 'onset_Hz', 'offset_Hz', 'file']
+    ['label', 'onset_s', 'offset_s', 'onset_ind', 'offset_ind', 'file']
     ['1', '0.0029761904761904934', '0.14150432900432905', '143', '6792', 'lbr3009_0005_2017_04_27_06_14_46.wav']
     ['1', '0.279125', '0.504625', '13398', '24222', 'lbr3009_0005_2017_04_27_06_14_46.wav']
     ['5', '0.5556472915365209', '0.5962916666666667', '26671', '28622', 'lbr3009_0005_2017_04_27_06_14_46.wav']

diff --git a/doc/index.rst b/doc/index.rst
@@ -28,26 +28,26 @@ The code block below shows some of the features of these data types.
     >>> from crowsetta import Segment, Sequence
     >>> a_segment = Segment.from_keyword(
     ...     label='a',
-    ...     onset_Hz=16000,
-    ...     offset_Hz=32000,
+    ...     onset_ind=16000,
+    ...     offset_ind=32000,
     ...     file='bird21.wav'
     ...     )
     >>> another_segment = Segment.from_keyword(
     ...     label='b',
-    ...     onset_Hz=36000,
-    ...     offset_Hz=48000,
+    ...     onset_ind=36000,
+    ...     offset_ind=48000,
     ...     file='bird21.wav'
     ...     )
     >>> list_of_segments = [a_segment, another_segment]
     >>> seq = Sequence.from_segments(segments=list_of_segments)
     >>> print(seq)
     <Sequence with 2 segments>
     >>> for segment in seq.segments: print(segment)
-    Segment(label='a', file='bird21.wav', onset_s=None, offset_s=None, onset_Hz=16000, offset_Hz=32000)
-    Segment(label='b', file='bird21.wav', onset_s=None, offset_s=None, onset_Hz=36000, offset_Hz=48000)
+    Segment(label='a', file='bird21.wav', onset_s=None, offset_s=None, onset_ind=16000, offset_ind=32000)
+    Segment(label='b', file='bird21.wav', onset_s=None, offset_s=None, onset_ind=36000, offset_ind=48000)
     >>> seq.file
     bird21.wav
-    >>> seq.onsets_Hz
+    >>> seq.onset_inds
     array([16000, 36000])
 
 You load annotation from your format of choice into ``Sequence``\ s of ``Segment``\ s

diff --git a/doc/notebooks/batlab2seq.py b/doc/notebooks/batlab2seq.py
@@ -57,7 +57,7 @@ def batlab2seq(mat_file):
                                     labels=seg_types,
                                     onsets_s=seg_start_times,
                                     offsets_s=seg_end_times,
-                                    onsets_Hz=seg_start_times_Hz,
-                                    offsets_Hz=seg_end_times_Hz)
+                                    onset_inds=seg_start_times_Hz,
+                                    offset_inds=seg_end_times_Hz)
         seq_list.append(seq)
     return seq_list
diff --git a/doc/notebooks/howto-user-format.ipynb b/doc/notebooks/howto-user-format.ipynb
@@ -212,8 +212,8 @@
     "a_sequence = Sequence.from_keyword(labels=annot_dict['seg_types'],\n",
     "                                   onsets_s=annot_dict['seg_start_times'],\n",
     "                                   offsets_s=annot_dict['seg_end_times'],\n",
-    "                                   onsets_Hz=annot_dict['seg_start_times_Hz'],\n",
-    "                                   offsets_Hz=annot_dict['seg_end_times_Hz'],\n",
+    "                                   onset_inds=annot_dict['seg_start_times_Hz'],\n",
+    "                                   offset_inds=annot_dict['seg_end_times_Hz'],\n",
     "                                   file=annot_dict['audio_file'])\n",
     "print(\"a_sequence:\\n\", a_sequence)"
    ]
@@ -261,8 +261,8 @@
     "                            labels=seg_types,\n",
     "                            onsets_s=seg_start_times,\n",
     "                            offsets_s=seg_end_times,\n",
-    "                            onsets_Hz=seg_start_times_Hz,\n",
-    "                            offsets_Hz=seg_end_times_Hz)\n",
+    "                            onset_inds=seg_start_times_Hz,\n",
+    "                            offset_inds=seg_end_times_Hz)\n",
     "seq_list.append(seq)\n",
     "    return seq_list"
    ]
@@ -370,7 +370,7 @@
      "text": [
       "First item in seq_list: <Sequence with 15 segments>\n",
       "First segment in first sequence:\n",
-      "Segment(label='1', file='lbr3009_0005_2017_04_27_06_14_46.wav', onset_s=0.0029761904761904934, offset_s=0.14150432900432905, onset_Hz=143, offset_Hz=6792)\n"
+      "Segment(label='1', file='lbr3009_0005_2017_04_27_06_14_46.wav', onset_s=0.0029761904761904934, offset_s=0.14150432900432905, onset_ind=143, offset_ind=6792)\n"
      ]
     }
    ],
@@ -395,7 +395,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "['label', 'onset_s', 'offset_s', 'onset_Hz', 'offset_Hz', 'file']\n",
+      "['label', 'onset_s', 'offset_s', 'onset_ind', 'offset_ind', 'file']\n",
       "['1', '0.0029761904761904934', '0.14150432900432905', '143', '6792', 'lbr3009_0005_2017_04_27_06_14_46.wav']\n",
       "['1', '0.279125', '0.504625', '13398', '24222', 'lbr3009_0005_2017_04_27_06_14_46.wav']\n",
       "['5', '0.5556472915365209', '0.5962916666666667', '26671', '28622', 'lbr3009_0005_2017_04_27_06_14_46.wav']\n"

diff --git a/doc/notebooks/tutorial.ipynb b/doc/notebooks/tutorial.ipynb
@@ -278,8 +278,8 @@
       "first element of seq:  <Sequence with 54 segments>\n",
       "\n",
       "First two Segments of first Sequence:\n",
-      "Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.435, offset_s=0.511, onset_Hz=13924, offset_Hz=16350)\n",
-      "Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.583, offset_s=0.662, onset_Hz=18670, offset_Hz=21184)\n"
+      "Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.435, offset_s=0.511, onset_ind=13924, offset_ind=16350)\n",
+      "Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.583, offset_s=0.662, onset_ind=18670, offset_ind=21184)\n"
      ]
     }
    ],
@@ -417,7 +417,7 @@
     "    smoothed = evfuncs.smooth_data(raw_audio, samp_freq,\n",
     "                                   freq_cutoffs=(500, 10000))\n",
     "    for segment in sequence.segments:\n",
-    "        smoothed_seg = smoothed[segment.onset_Hz:segment.offset_Hz]\n",
+    "        smoothed_seg = smoothed[segment.onset_ind:segment.offset_ind]\n",
     "        mean_seg_amp = np.mean(smoothed_seg)\n",
     "        syl_amp_dict[segment.label].append(mean_seg_amp)\n",
     "\n",

diff --git a/doc/tutorial.rst b/doc/tutorial.rst
@@ -205,8 +205,8 @@ part of the sequence defined by an ``onset`` and ``offset`` that has a
     first element of seq:  <Sequence with 54 segments>
     
     First two Segments of first Sequence:
-    Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.435, offset_s=0.511, onset_Hz=13924, offset_Hz=16350)
-    Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.583, offset_s=0.662, onset_Hz=18670, offset_Hz=21184)
+    Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.435, offset_s=0.511, onset_ind=13924, offset_ind=16350)
+    Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.583, offset_s=0.662, onset_ind=18670, offset_ind=21184)
 
 
 **Using** ``crowsetta`` **data types to write clean code**
@@ -329,7 +329,7 @@ the signal, and then smooths it with a sliding window.
         smoothed = evfuncs.smooth_data(raw_audio, samp_freq,
                                        freq_cutoffs=(500, 10000))
         for segment in sequence.segments:
-            smoothed_seg = smoothed[segment.onset_Hz:segment.offset_Hz]
+            smoothed_seg = smoothed[segment.onset_ind:segment.offset_ind]
             mean_seg_amp = np.mean(smoothed_seg)
             syl_amp_dict[segment.label].append(mean_seg_amp)
     

diff --git a/notebooks/batlab2seq.py b/notebooks/batlab2seq.py
@@ -57,7 +57,7 @@ def batlab2seq(mat_file):
                                     labels=seg_types,
                                     onsets_s=seg_start_times,
                                     offsets_s=seg_end_times,
-                                    onsets_Hz=seg_start_times_Hz,
-                                    offsets_Hz=seg_end_times_Hz)
+                                    onset_inds=seg_start_times_Hz,
+                                    offset_inds=seg_end_times_Hz)
         seq_list.append(seq)
     return seq_list
diff --git a/notebooks/howto-user-format.ipynb b/notebooks/howto-user-format.ipynb
@@ -212,8 +212,8 @@
     "a_sequence = Sequence.from_keyword(labels=annot_dict['seg_types'],\n",
     "                                   onsets_s=annot_dict['seg_start_times'],\n",
     "                                   offsets_s=annot_dict['seg_end_times'],\n",
-    "                                   onsets_Hz=annot_dict['seg_start_times_Hz'],\n",
-    "                                   offsets_Hz=annot_dict['seg_end_times_Hz'],\n",
+    "                                   onset_inds=annot_dict['seg_start_times_Hz'],\n",
+    "                                   offset_inds=annot_dict['seg_end_times_Hz'],\n",
     "                                   file=annot_dict['audio_file'])\n",
     "print(\"a_sequence:\\n\", a_sequence)"
    ]
@@ -261,8 +261,8 @@
     "                            labels=seg_types,\n",
     "                            onsets_s=seg_start_times,\n",
     "                            offsets_s=seg_end_times,\n",
-    "                            onsets_Hz=seg_start_times_Hz,\n",
-    "                            offsets_Hz=seg_end_times_Hz)\n",
+    "                            onset_inds=seg_start_times_Hz,\n",
+    "                            offset_inds=seg_end_times_Hz)\n",
     "seq_list.append(seq)\n",
     "    return seq_list"
    ]
@@ -370,7 +370,7 @@
      "text": [
       "First item in seq_list: <Sequence with 15 segments>\n",
       "First segment in first sequence:\n",
-      "Segment(label='1', file='lbr3009_0005_2017_04_27_06_14_46.wav', onset_s=0.0029761904761904934, offset_s=0.14150432900432905, onset_Hz=143, offset_Hz=6792)\n"
+      "Segment(label='1', file='lbr3009_0005_2017_04_27_06_14_46.wav', onset_s=0.0029761904761904934, offset_s=0.14150432900432905, onset_ind=143, offset_ind=6792)\n"
      ]
     }
    ],
@@ -395,7 +395,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "['label', 'onset_s', 'offset_s', 'onset_Hz', 'offset_Hz', 'file']\n",
+      "['label', 'onset_s', 'offset_s', 'onset_ind', 'offset_ind', 'file']\n",
       "['1', '0.0029761904761904934', '0.14150432900432905', '143', '6792', 'lbr3009_0005_2017_04_27_06_14_46.wav']\n",
       "['1', '0.279125', '0.504625', '13398', '24222', 'lbr3009_0005_2017_04_27_06_14_46.wav']\n",
       "['5', '0.5556472915365209', '0.5962916666666667', '26671', '28622', 'lbr3009_0005_2017_04_27_06_14_46.wav']\n"

diff --git a/notebooks/tutorial.ipynb b/notebooks/tutorial.ipynb
@@ -278,8 +278,8 @@
       "first element of seq:  <Sequence with 54 segments>\n",
       "\n",
       "First two Segments of first Sequence:\n",
-      "Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.435, offset_s=0.511, onset_Hz=13924, offset_Hz=16350)\n",
-      "Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.583, offset_s=0.662, onset_Hz=18670, offset_Hz=21184)\n"
+      "Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.435, offset_s=0.511, onset_ind=13924, offset_ind=16350)\n",
+      "Segment(label='i', file='./data/cbin-notmat/032312/gy6or6_baseline_230312_0819.190.cbin', onset_s=0.583, offset_s=0.662, onset_ind=18670, offset_ind=21184)\n"
      ]
     }
    ],
@@ -417,7 +417,7 @@
     "    smoothed = evfuncs.smooth_data(raw_audio, samp_freq,\n",
     "                                   freq_cutoffs=(500, 10000))\n",
     "    for segment in sequence.segments:\n",
-    "        smoothed_seg = smoothed[segment.onset_Hz:segment.offset_Hz]\n",
+    "        smoothed_seg = smoothed[segment.onset_ind:segment.offset_ind]\n",
     "        mean_seg_amp = np.mean(smoothed_seg)\n",
     "        syl_amp_dict[segment.label].append(mean_seg_amp)\n",
     "\n",

diff --git a/src/crowsetta/birdsongrec.py b/src/crowsetta/birdsongrec.py
@@ -82,8 +82,8 @@ def birdsongrec2annot(annot_path='Annotation.xml', concat_seqs_into_songs=True,
 
     annot_list = []
     for seq_xml in seq_list_xml:
-        onsets_Hz = np.asarray([syl.position for syl in seq_xml.syls])
-        offsets_Hz = np.asarray([syl.position + syl.length for syl in seq_xml.syls])
+        onset_inds = np.asarray([syl.position for syl in seq_xml.syls])
+        offset_inds = np.asarray([syl.position + syl.length for syl in seq_xml.syls])
         labels = [syl.label for syl in seq_xml.syls]
 
         wav_filename = os.path.join(wavpath, seq_xml.wav_file)
@@ -94,11 +94,11 @@ def birdsongrec2annot(annot_path='Annotation.xml', concat_seqs_into_songs=True,
                 f'annotation file {annot_path} is not found'
             )
         samp_freq = soundfile.info(wav_filename).samplerate
-        onsets_s = np.round(onsets_Hz / samp_freq, decimals=3)
-        offsets_s = np.round(offsets_Hz / samp_freq, decimals=3)
+        onsets_s = np.round(onset_inds / samp_freq, decimals=3)
+        offsets_s = np.round(offset_inds / samp_freq, decimals=3)
 
-        seq = Sequence.from_keyword(onsets_Hz=onsets_Hz,
-                                    offsets_Hz=offsets_Hz,
+        seq = Sequence.from_keyword(onset_inds=onset_inds,
+                                    offset_inds=offset_inds,
                                     onsets_s=onsets_s,
                                     offsets_s=offsets_s,
                                     labels=labels

diff --git a/src/crowsetta/csv.py b/src/crowsetta/csv.py
@@ -13,8 +13,8 @@
     'label',
     'onset_s',
     'offset_s',
-    'onset_Hz',
-    'offset_Hz',
+    'onset_ind',
+    'offset_ind',
     'audio_path',
     'annot_path',
     'sequence',
@@ -26,8 +26,8 @@
     'label': str,
     'onset_s': float,
     'offset_s': float,
-    'onset_Hz': int,
-    'offset_Hz': int,
+    'onset_ind': int,
+    'offset_ind': int,
     'audio_path': str,
     'annot_path': str,
     'sequence': int,

diff --git a/src/crowsetta/phn.py b/src/crowsetta/phn.py
@@ -65,17 +65,17 @@ def phn2annot(annot_path,
 
     annot = []
     for a_phn in annot_path:
-        labels, onsets_Hz, offsets_Hz = [], [], []
+        labels, onset_inds, offset_inds = [], [], []
         with open(a_phn) as fp:
             lines = fp.read().splitlines()
         for line in lines:
             onset, offset, label = line.split()
-            onsets_Hz.append(int(onset))
-            offsets_Hz.append(int(offset))
+            onset_inds.append(int(onset))
+            offset_inds.append(int(offset))
             labels.append(label)
 
-        onsets_Hz = np.asarray(onsets_Hz)
-        offsets_Hz = np.asarray(offsets_Hz)
+        onset_inds = np.asarray(onset_inds)
+        offset_inds = np.asarray(offset_inds)
         labels = np.asarray(labels)
 
         # checking for audio_pathname need to be case insensitive
@@ -89,8 +89,8 @@ def phn2annot(annot_path,
                 )
 
         samp_freq = soundfile.info(audio_pathname).samplerate
-        onsets_s = onsets_Hz / samp_freq
-        offsets_s = offsets_Hz / samp_freq
+        onsets_s = onset_inds / samp_freq
+        offsets_s = offset_inds / samp_freq
 
         if round_times:
             onsets_s = np.around(onsets_s, decimals=decimals)
@@ -104,8 +104,8 @@ def phn2annot(annot_path,
             a_phn = os.path.basename(a_phn)
 
         phn_seq = Sequence.from_keyword(labels=labels,
-                                        onsets_Hz=onsets_Hz,
-                                        offsets_Hz=offsets_Hz,
+                                        onset_inds=onset_inds,
+                                        offset_inds=offset_inds,
                                         onsets_s=onsets_s,
                                         offsets_s=offsets_s)
         annot.append(
@@ -174,8 +174,8 @@ def annot2phn(annot,
     annot_path = Path(annot_path)
 
     lines = []
-    onsets_Hz, offsets_Hz, labels = annot.seq.onsets_Hz, annot.seq.offsets_Hz, annot.seq.labels
-    for onset, offset, label in zip(onsets_Hz, offsets_Hz, labels):
+    onset_inds, offset_inds, labels = annot.seq.onset_inds, annot.seq.offset_inds, annot.seq.labels
+    for onset, offset, label in zip(onset_inds, offset_inds, labels):
         lines.append(
             f'{onset} {offset} {label}\n'
         )