lingualabpy 0.0.2__py3-none-any.whl → 0.0.3__py3-none-any.whl

lingualabpy/__init__.py

@@ -4,7 +4,7 @@
 """lingualabpy"""
 from __future__ import annotations
 
-__version__ = "0.0.2"
+__version__ = "0.0.3"
 
 default_config = {
     "participant_col": "participant_id",

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/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

@@ -1,4 +1,4 @@
-import pandas as pd
+from pandas import DataFrame
 
 from typing import Any, Dict, List
 
@@ -6,7 +6,7 @@ from typing import Any, Dict, List
 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 +15,7 @@ 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-0.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lingualabpy
-Version: 0.0.2
+Version: 0.0.3
 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-0.0.2.dist-info → lingualabpy-0.0.3.dist-info}/RECORD

@@ -1,19 +1,19 @@
-lingualabpy/__init__.py,sha256=8Opixd2cbELk9IqSFfGxZCTgz93fX92jXQQk78MkYNU,515
+lingualabpy/__init__.py,sha256=Klpz9mrtYXzZ3eSXg7ciwak9mAkgKVC5G1w0uaMn7Q8,515
 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/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=8mkFHCLpFmlzUQpZoysXRyeES6VjwLMEqY2-IZEfQkU,779
+lingualabpy/text/textgrid.py,sha256=LXdDAY4aEl3Q998Uq28fz0gryFj3KWq1j0RsuWOlEC0,1632
 lingualabpy/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lingualabpy/tools/data.py,sha256=hsGxu6KQ-ltK5AstwVVpvJpBYaAIc_XT5SP0BVAQlss,1103
+lingualabpy/tools/data.py,sha256=FTjxbckza65vZ_MWEO5wi4mDXpJ2u9KkiEA3-HGfOt8,1106
 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,,
+lingualabpy-0.0.3.dist-info/entry_points.txt,sha256=QvnRy1hJXRGGbVQgS-u--5Rgs7rPBmgWC9K1iaxS5gQ,186
+lingualabpy-0.0.3.dist-info/LICENSE,sha256=s3hbMsmwGq2XFcxpMD3oHc8GSUeXAmPVXJbn7SYXdos,1095
+lingualabpy-0.0.3.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+lingualabpy-0.0.3.dist-info/METADATA,sha256=JI1jTk5UA5CeLCcLO6HCC157WmeUW0aUTm0hKZaEXm8,1703
+lingualabpy-0.0.3.dist-info/RECORD,,