lingualabpy 0.0.2__py3-none-any.whl → 0.0.4__py3-none-any.whl

lingualabpy/__init__.py

@@ -4,12 +4,17 @@
 """lingualabpy"""
 from __future__ import annotations
 
-__version__ = "0.0.2"
+__version__ = "0.0.4"
 
 default_config = {
     "participant_col": "participant_id",
     "participant_label": "IE",
     "clinician_label": "IV",
+    "f0_bounds": {
+        "female": [100.0, 600.0],
+        "male": [75.0, 300.0],
+    },
+    "unit_frequency": "Hertz",
 }
 
 from lingualabpy.io import read_audio, read_docx, read_json, write_json, read_textgrid

lingualabpy/audio/metrics.py

@@ -0,0 +1,85 @@
+from collections import defaultdict
+import numpy as np
+from parselmouth import Sound
+from parselmouth.praat import call
+
+from lingualabpy.tools.data import UnchangeableDict
+
+
+def measure_pitch(sound: Sound, f0min: str, f0max: str, unit: str) -> UnchangeableDict:
+    """
+    This function measures duration, pitch, HNR, jitter, and shimmer
+    This is the function to measure source acoustics using default male parameters.
+    """
+    # compute usefull praat object
+    pitch = call(sound, "To Pitch", 0.0, f0min, f0max)
+    harmonicity = call(sound, "To Harmonicity (cc)", 0.01, f0min, 0.1, 1.0)
+    point_process = call(sound, "To PointProcess (periodic, cc)", f0min, f0max)
+
+    # metrics container
+    metrics = UnchangeableDict()
+
+    # Metrics computation
+    metrics["duration"] = call(sound, "Get total duration")
+    metrics["f0_mean"] = call(pitch, "Get mean", 0, 0, unit)
+    metrics["F0_std"] = call(pitch, "Get standard deviation", 0, 0, unit)
+    metrics["hnr"] = call(harmonicity, "Get mean", 0, 0)
+
+    # jitter
+    jitter_types = ["local", ["local", "absolute"], "rap", "ppq5", "ddp"]
+    for jitter_type in jitter_types:
+        if isinstance(jitter_type, list):
+            metric_name = f"jitter_{'_'.join(jitter_type)}"
+            praat_function = f"Get jitter ({', '.join(jitter_type)})"
+        else:
+            metric_name = f"jitter_{jitter_type}"
+            praat_function = f"Get jitter ({jitter_type})"
+        metrics[metric_name] = call(
+            point_process, praat_function, 0, 0, 0.0001, 0.02, 1.3
+        )
+
+    # shimmer
+    shimmer_types = ["local", "local_dB", "apq3", "apq5", "apq11", "dda"]
+    for shimmer_type in shimmer_types:
+        metric_name = f"shimmer_{shimmer_type}"
+        praat_function = f"Get shimmer ({shimmer_type})"
+        metrics[metric_name] = call(
+            [sound, point_process], praat_function, 0, 0, 0.0001, 0.02, 1.3, 1.6
+        )
+
+    return metrics
+
+
+def measure_formants(
+    sound: Sound, f0min: str, f0max: str, unit: str
+) -> UnchangeableDict:
+    """
+    This function measures formants at each glottal pulse
+
+    Puts, D. A., Apicella, C. L., & Cárdenas, R. A. (2012). Masculine voices signal men's threat potential in forager and industrial societies. Proceedings of the Royal Society of London B: Biological Sciences, 279(1728), 601-609.
+
+    Adapted from: DOI 10.17605/OSF.IO/K2BHS
+    """
+    # compute usefull praat object
+    point_process = call(sound, "To PointProcess (periodic, cc)", f0min, f0max)
+    formants = call(sound, "To Formant (burg)", 0.0025, 5, 5000, 0.025, 50)
+    number_of_points = call(point_process, "Get number of points")
+
+    # metrics container
+    metrics = UnchangeableDict()
+
+    # Measure formants only at glottal pulses
+    formants_list = defaultdict(list)
+    for index in range(1, number_of_points + 1):
+        time = call(point_process, "Get time from index", index)
+        for pulse in [1, 2, 3, 4]:
+            value = call(formants, "Get value at time", pulse, time, unit, "Linear")
+            if str(value) != "nan":
+                formants_list[pulse].append(value)
+
+    # calculate mean and median formants across pulses, median is what is used in all subsequent calculations
+    for pulse in [1, 2, 3, 4]:
+        metrics[f"formants_{pulse}_mean"] = np.mean(formants_list[pulse])
+        metrics[f"formants_{pulse}_median"] = np.median(formants_list[pulse])
+
+    return metrics

lingualabpy/cli/audio_metrics.py

@@ -0,0 +1,57 @@
+import click
+from parselmouth import Sound
+from pathlib import Path
+
+from lingualabpy import default_config, write_json
+from lingualabpy.audio.metrics import measure_pitch, measure_formants
+
+
+@click.command()
+@click.option(
+    "--sex",
+    type=click.Choice(["female", "male"]),
+    help=f"Set f0min and f0max for praat analysis. {default_config['f0_bounds']}",
+)
+@click.option(
+    "--f0min",
+    type=float,
+    help="Define f0min for praat analysis. Not required if sex is specify",
+)
+@click.option(
+    "--f0max",
+    type=float,
+    help="Define f0max for praat analysis. Not required if sex is specify",
+)
+@click.option(
+    "--unit_frequency",
+    default=default_config["unit_frequency"],
+    show_default=True,
+)
+@click.option("--participant_id", "-p", default=None, help="")
+@click.option("--output_json", default=None, help="")
+@click.argument("audiofile", nargs=1, type=click.Path(exists=True))
+def main(sex, f0min, f0max, unit_frequency, participant_id, output_json, audiofile):
+    """Doc"""
+    if sex:
+        f0min, f0max = default_config["f0_bounds"][sex]
+    else:
+        if not f0min or not f0max:
+            raise click.UsageError(
+                "'--f0min' and '--f0max' are required if '--sex' is not specified"
+            )
+
+    sound = Sound(audiofile)
+    metrics = measure_pitch(sound, f0min, f0max, unit_frequency)
+    metrics.update(measure_formants(sound, f0min, f0max, unit_frequency))
+
+    audiofile_stem = Path(audiofile).stem
+
+    if participant_id:
+        metrics["participant_id"] = participant_id
+    else:
+        metrics["participant_id"] = audiofile_stem.split("_")[0]
+
+    if not output_json:
+        output_json = audiofile_stem + "_metric-audio.json"
+
+    write_json(dict(metrics), output_json)

lingualabpy/cli/audio_triming.py

@@ -23,9 +23,14 @@ from lingualabpy.tools.interval import intervals_masking
 def main(participant_label, clinician_label, textgrid, audiofile, output):
     """Doc"""
     grid = read_textgrid(textgrid)
-    participant_intervals, clinician_intervals = extract_intervals(
-        grid, [participant_label, clinician_label]
-    )
+
+    try:
+        participant_intervals, clinician_intervals = extract_intervals(
+            grid, [participant_label, clinician_label]
+        )
+    except Exception as e:
+        raise Exception(f"Failed to extract intervals for {textgrid}", repr(e))
+
     participant_intervals_clean = intervals_masking(
         participant_intervals, clinician_intervals
     )

lingualabpy/cli/jsons2csv.py

@@ -2,7 +2,7 @@ import click
 import json
 
 from lingualabpy import default_config, read_json
-from lingualabpy.tools import merge_participants_to_df
+from lingualabpy.tools.data import merge_participants_to_df
 
 
 @click.command()

lingualabpy/io.py

@@ -33,7 +33,7 @@ def read_json(json_path: str) -> Union[list, dict]:
 def write_json(data: Union[list, dict], json_path: str) -> None:
     """"""
     with open(json_path, "w") as file:
-        json.dump(data, file)
+        json.dump(data, file, indent=4)
 
 
 # .TextGrid files

lingualabpy/text/textgrid.py

@@ -1,11 +1,35 @@
+import re
 from textgrids import TextGrid, Interval
+import warnings
 
 
-def extract_intervals(grid: TextGrid, speakers: list[str]) -> tuple[list[Interval]]:
+def extract_intervals(textgrid: TextGrid, speakers: list[str]) -> list[list[Interval]]:
     """"""
+    # Check if speakers are in the textgrid tiers
+    tiers = set(textgrid.keys())
+    if not set(speakers).issubset(tiers):
+        raise ValueError(
+            f"Some speaker(s) '{speakers}' are not a tier in the TextGrid '{tiers}'"
+        )
+
+    # Check if there is other speaker in the textgrid
+    if not set(speakers) == tiers:
+        warnings.warn(
+            f"TextGrid '{tiers}' have more speakers than specify '{speakers}'"
+        )
+
+    # Extraction of intervals with text value
     speakers_intervals = []
     for speaker in speakers:
-        speakers_intervals.append([_ for _ in grid[speaker] if _.text])
+        speaker_intervals = []
+        for interval in textgrid[speaker]:
+            # Cleaning of the interval text
+            interval.text = (
+                interval.text.encode().decode("unicode_escape").strip(" \n\r\t")
+            )
+            if interval.text:
+                speaker_intervals.append(interval)
+        speakers_intervals.append(speaker_intervals)
 
     # Checking if all intervals are correctly labeled
     def interval_qc(intervals, label):

lingualabpy/tools/data.py

@@ -1,12 +1,24 @@
-import pandas as pd
+from collections import UserDict
+from pandas import DataFrame
 
 from typing import Any, Dict, List
 
 
+class UnchangeableDict(UserDict):
+    """A dictionary in which you can add new keys but not modify them in the future."""
+
+    def __setitem__(self, key: Any, item: Any) -> None:
+        try:
+            self.__getitem__(key)
+            raise ValueError("duplicate key '{}' found".format(key))
+        except KeyError:
+            return super().__setitem__(key, item)
+
+
 def merge_participants_to_df(
     data_participants: List[Dict[Any, Any]],
     participant_col: str,
-) -> pd.DataFrame:
+) -> DataFrame:
     # Check if all data have a `participant_col` key
     participant_col_checks = [_.get(participant_col) for _ in data_participants]
     if not all(participant_col_checks):
@@ -15,7 +27,7 @@ def merge_participants_to_df(
         )
 
     # Check if there are no duplicates in the data
-    df_raw = pd.DataFrame.from_dict(data_participants)
+    df_raw = DataFrame.from_dict(data_participants)
     df_melt = df_raw.melt(id_vars=[participant_col]).dropna()
     df_for_test = df_melt.drop(columns="value")
     duplicates = df_for_test[df_for_test.duplicated()]

{lingualabpy-0.0.2.dist-info → lingualabpy-0.0.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lingualabpy
-Version: 0.0.2
+Version: 0.0.4
 Summary: Tools and utilities from the LINGUA laboratory
 Author-email: Christophe Bedetti <christophe.bedetti@umontreal.ca>
 Requires-Python: >=3.8.1
@@ -24,18 +24,18 @@ Requires-Dist: praat-parselmouth
 Requires-Dist: praat-textgrids
 Requires-Dist: pydub
 Requires-Dist: python-docx
-Requires-Dist: lingualabpy[tests, docs, lint, feature] ; extra == "dev"
+Requires-Dist: lingualabpy[test, doc, lint, feature] ; extra == "dev"
 Requires-Dist: black ; extra == "lint"
-Requires-Dist: pytest ; extra == "tests"
-Requires-Dist: pytest-cov ; extra == "tests"
+Requires-Dist: pytest ; extra == "test"
+Requires-Dist: pytest-cov ; extra == "test"
 Project-URL: Documentation, https://github.com/lingualab/lingualabpy
 Project-URL: Source, https://github.com/lingualab/lingualabpy
 Project-URL: Tracker, https://github.com/lingualab/lingualabpy/issues
 Provides-Extra: dev
-Provides-Extra: docs
+Provides-Extra: doc
 Provides-Extra: feature
 Provides-Extra: lint
-Provides-Extra: tests
+Provides-Extra: test
 
 # lingualabpy
 

lingualabpy-0.0.4.dist-info/RECORD

@@ -0,0 +1,21 @@
+lingualabpy/__init__.py,sha256=9r7VH5hUUG5UFPACgN3-Y_v0ZeJC3vTnQ7eyc5B4IVY,642
+lingualabpy/io.py,sha256=RY8gsfKmkIpBC9I3XOX-VcLuPvlElxGR7P8iyY1wOUc,888
+lingualabpy/audio/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lingualabpy/audio/metrics.py,sha256=u5FlADmqeYQOSpqhY2l1l8CSC4tfBV6cWp3g6Hri6bE,3502
+lingualabpy/audio/triming.py,sha256=6CY9pH43KFGAPj8Nw34y1YnlOb8gxGLU1btcuRy-Hgc,288
+lingualabpy/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lingualabpy/cli/audio_metrics.py,sha256=scuJoncBPauMvgOVaSCyrOgbnWC3tGpqDyxVP0RNfs0,1801
+lingualabpy/cli/audio_triming.py,sha256=rG0gk-epVWb_jvPHAmk2Lhm4LvGkFzSUW20wi2DZBP0,1329
+lingualabpy/cli/docx2json.py,sha256=Bj5f89B76NtA7Xx71xXGnSucrDEyaH9mUFifQo0wfn4,590
+lingualabpy/cli/jsons2csv.py,sha256=_AcIXiQUCF5SsKqMg6WjTr8fhbuflaJNFrCP91ccSYs,596
+lingualabpy/text/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lingualabpy/text/parser.py,sha256=qZqhzi-6UHdbsXEWi5IMxsDK5Tsosb3pdSo67hcA6To,913
+lingualabpy/text/textgrid.py,sha256=LXdDAY4aEl3Q998Uq28fz0gryFj3KWq1j0RsuWOlEC0,1632
+lingualabpy/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lingualabpy/tools/data.py,sha256=FU0_3TaeAZNCu1WpNIOkVBV3bYiEhI1rPw_l8q8z0gk,1523
+lingualabpy/tools/interval.py,sha256=50lzbMTNHF26mPRG50mykCUQE3pdyRjPWMwsskwy0tg,2060
+lingualabpy-0.0.4.dist-info/entry_points.txt,sha256=IXEsa7Cgqjph5bkKSBMXZIBVP4ocrRaSh13dFPBwBmE,247
+lingualabpy-0.0.4.dist-info/LICENSE,sha256=s3hbMsmwGq2XFcxpMD3oHc8GSUeXAmPVXJbn7SYXdos,1095
+lingualabpy-0.0.4.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+lingualabpy-0.0.4.dist-info/METADATA,sha256=REDE0J8FGCnciM2CIJbJsRj7WFLZd2BqgDC1PY_C2-0,1703
+lingualabpy-0.0.4.dist-info/RECORD,,

{lingualabpy-0.0.2.dist-info → lingualabpy-0.0.4.dist-info}/entry_points.txt

@@ -1,4 +1,5 @@
 [console_scripts]
+lingualabpy_audio_metrics=lingualabpy.cli.audio_metrics:main
 lingualabpy_audio_triming=lingualabpy.cli.audio_triming:main
 lingualabpy_docx2json=lingualabpy.cli.docx2json:main
 lingualabpy_jsons2csv=lingualabpy.cli.jsons2csv:main

lingualabpy-0.0.2.dist-info/RECORD

@@ -1,19 +0,0 @@
-lingualabpy/__init__.py,sha256=8Opixd2cbELk9IqSFfGxZCTgz93fX92jXQQk78MkYNU,515
-lingualabpy/io.py,sha256=TF8eSuX_xfGWWbQ1C0TLnia7HS1Vexn0RqKMvCzHGnE,878
-lingualabpy/audio/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lingualabpy/audio/triming.py,sha256=6CY9pH43KFGAPj8Nw34y1YnlOb8gxGLU1btcuRy-Hgc,288
-lingualabpy/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lingualabpy/cli/audio_triming.py,sha256=pAsLv2IuAKLoj8jBHB-SR5mZ7Jb0w26m41-Cya4VvoU,1194
-lingualabpy/cli/docx2json.py,sha256=Bj5f89B76NtA7Xx71xXGnSucrDEyaH9mUFifQo0wfn4,590
-lingualabpy/cli/jsons2csv.py,sha256=mwe2KO6oI0TkZML41-ezA5fo8UjPRlT_37vcv6eqiCE,591
-lingualabpy/text/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lingualabpy/text/parser.py,sha256=qZqhzi-6UHdbsXEWi5IMxsDK5Tsosb3pdSo67hcA6To,913
-lingualabpy/text/textgrid.py,sha256=8mkFHCLpFmlzUQpZoysXRyeES6VjwLMEqY2-IZEfQkU,779
-lingualabpy/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lingualabpy/tools/data.py,sha256=hsGxu6KQ-ltK5AstwVVpvJpBYaAIc_XT5SP0BVAQlss,1103
-lingualabpy/tools/interval.py,sha256=50lzbMTNHF26mPRG50mykCUQE3pdyRjPWMwsskwy0tg,2060
-lingualabpy-0.0.2.dist-info/entry_points.txt,sha256=QvnRy1hJXRGGbVQgS-u--5Rgs7rPBmgWC9K1iaxS5gQ,186
-lingualabpy-0.0.2.dist-info/LICENSE,sha256=s3hbMsmwGq2XFcxpMD3oHc8GSUeXAmPVXJbn7SYXdos,1095
-lingualabpy-0.0.2.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
-lingualabpy-0.0.2.dist-info/METADATA,sha256=nJgDfrbvhZYyU4wQXLD_dzdcwkA1wKze5bYjraTdAyc,1709
-lingualabpy-0.0.2.dist-info/RECORD,,