Overview

This notebook gives a general overview of the features included in the dataset.

Show imports Hide imports

%load_ext autoreload
%autoreload 2
import os

import dimcat as dc
import pandas as pd
import plotly.express as px
from dimcat import filters, plotting
from IPython.display import display

import utils

RESULTS_PATH = os.path.abspath(os.path.join(utils.OUTPUT_FOLDER, "overview"))
os.makedirs(RESULTS_PATH, exist_ok=True)


def make_output_path(
    filename: str,
    extension=None,
    path=RESULTS_PATH,
) -> str:
    return utils.make_output_path(filename=filename, extension=extension, path=path)


def save_figure_as(
    fig, filename, formats=("png", "pdf"), directory=RESULTS_PATH, **kwargs
):
    if formats is not None:
        for fmt in formats:
            plotting.write_image(fig, filename, directory, format=fmt, **kwargs)
    else:
        plotting.write_image(fig, filename, directory, **kwargs)

Loading data

D = utils.get_dataset("bach_solo", corpus_release="v2.19")
package = D.inputs.get_package()
package_info = package._package.custom
git_tag = package_info.get("git_tag")
utils.print_heading("Data and software versions")
print("J.S. Bach – Solo Pieces version v2.19")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

Data and software versions
--------------------------

J.S. Bach – Solo Pieces version v2.19
Datapackage 'bach_solo' @ v2.19
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'bach_solo': ["'bach_solo.measures' (MuseScoreFacetName.MuseScoreMeasures)",
                                       "'bach_solo.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                       "'bach_solo.expanded' (MuseScoreFacetName.MuseScoreHarmonies)",
                                       "'bach_solo.chords' (MuseScoreFacetName.MuseScoreChords)",
                                       "'bach_solo.metadata' (FeatureName.Metadata)"]}},
 'outputs': {'basepath': None, 'packages': {}},
 'pipeline': []}

filtered_D = filters.HasHarmonyLabelsFilter(keep_values=[True]).process(D)
all_metadata = filtered_D.get_metadata()
assert len(all_metadata) > 0, "No pieces selected for analysis."
all_metadata

		TimeSig	KeySig	last_mc	last_mn	length_qb	last_mc_unfolded	last_mn_unfolded	length_qb_unfolded	volta_mcs	all_notes_qb	...	ambitus	originalFormat	P86 (composer)	wikidata	viaf	musicbrainz	imslp	pdf	staff_1_ambitus	staff_1_instrument
corpus	piece
bach_solo	BWV1001_01_Adagio	{1: '4/4'}	{1: -1}	22	22	88.00	22	22	88.00	()	157.50	...	55-82 (G3-Bb5)	cap	Q1339	https://www.wikidata.org/wiki/Q20646569	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/a7c0ad42-a277-35c...	https://imslp.org/wiki/Violin_Sonata_No.1_in_G...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-82 (G3-Bb5)	Violin
	BWV1001_02_Fuga	{1: '2/2'}	{1: -1}	94	94	376.00	94	94	376.00	()	642.50	...	55-89 (G3-F6)	cap	Q1339	https://www.wikidata.org/wiki/Q20646569	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/20a9c7e7-6d81-3e1...	https://imslp.org/wiki/Violin_Sonata_No.1_in_G...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-89 (G3-F6)	Violin
	BWV1001_03_Siciliano	{1: '12/8'}	{1: -1}	20	20	120.00	20	20	120.00	()	196.00	...	55-86 (G3-D6)	cap	Q1339	https://www.wikidata.org/wiki/Q20646569	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/b89f8b50-b671-3bc...	https://imslp.org/wiki/Violin_Sonata_No.1_in_G...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-86 (G3-D6)	Violin
	BWV1001_04_Presto	{1: '3/8'}	{1: -1}	136	136	204.00	272	272	408.00	()	214.00	...	55-86 (G3-D6)	cap	Q1339	https://www.wikidata.org/wiki/Q20646569	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/d3c98683-e7ed-33e...	https://imslp.org/wiki/Violin_Sonata_No.1_in_G...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-86 (G3-D6)	Violin
	BWV1002_01_Allemanda	{1: '4/4'}	{1: 2}	27	24	104.25	49	48	192.25	(13], [14]], [[26], [27)	149.63	...	55-86 (G3-D6)	cap	Q1339	https://www.wikidata.org/wiki/Q7140627	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/0d94a02f-68d6-308...	https://imslp.org/wiki/Violin_Partita_No.1_in_...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-86 (G3-D6)	Violin
	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
	BWV1012_07_Gique	{1: '6/8'}	{1: 2}	69	68	204.00	138	136	408.00	()	245.50	...	37-74 (C#2-D5)	<NA>	Q1339	https://www.wikidata.org/wiki/Q20645428	https://viaf.org/viaf/212878335	https://musicbrainz.org/work/ddd9f05c-b5a4-3ea...	https://imslp.org/wiki/Cello_Suite_No.6_in_D_m...	https://imslp.org/wiki/Special:ReverseLookup/4...	37-74 (C#2-D5)	Piano
	BWV1013_01_Allemande	{1: '4/4'}	{1: 0}	49	46	196.00	92	92	368.00	(19], [20, 21]], [[47, 48], [49)	195.50	...	62-93 (D4-A6)	<NA>	Q1339	https://www.wikidata.org/wiki/Q989855	<NA>	https://musicbrainz.org/work/1158ae1f-4cb5-315...	https://imslp.org/wiki/Partita_in_A_minor,_BWV...	https://imslp.org/wiki/Special:ReverseLookup/9...	62-93 (D4-A6)	Flute
	BWV1013_02_Corrente	{1: '3/4'}	{1: 0}	63	62	186.00	126	124	372.00	()	186.00	...	62-87 (D4-D#6)	<NA>	Q1339	https://www.wikidata.org/wiki/Q989855	<NA>	https://musicbrainz.org/work/7392fcf6-65b4-379...	https://imslp.org/wiki/Partita_in_A_minor,_BWV...	https://imslp.org/wiki/Special:ReverseLookup/9...	62-87 (D4-D#6)	Flute
	BWV1013_03_Sarabande	{1: '3/4'}	{1: 0}	46	46	138.00	92	92	276.00	()	138.00	...	62-86 (D4-D6)	<NA>	Q1339	https://www.wikidata.org/wiki/Q989855	<NA>	https://musicbrainz.org/work/9e2df6c8-b70e-318...	https://imslp.org/wiki/Partita_in_A_minor,_BWV...	https://imslp.org/wiki/Special:ReverseLookup/9...	62-86 (D4-D6)	Flute
	BWV1013_04_BourreeAnglaise	{1: '2/4'}	{1: 0}	71	70	140.00	142	140	280.00	()	140.00	...	62-86 (D4-D6)	<NA>	Q1339	https://www.wikidata.org/wiki/Q989855	<NA>	https://musicbrainz.org/work/69bec9a9-d970-305...	https://imslp.org/wiki/Partita_in_A_minor,_BWV...	https://imslp.org/wiki/Special:ReverseLookup/9...	62-86 (D4-D6)	Flute

68 rows × 54 columns

mean_composition_years = utils.corpus_mean_composition_years(all_metadata)
chronological_order = mean_composition_years.index.to_list()
corpus_colors = dict(zip(chronological_order, utils.CORPUS_COLOR_SCALE))
corpus_names = {
    corp: utils.get_corpus_display_name(corp) for corp in chronological_order
}
chronological_corpus_names = list(corpus_names.values())
corpus_name_colors = {
    corpus_names[corp]: color for corp, color in corpus_colors.items()
}

mean_composition_years

corpus
bach_solo    1720.147059
Name: mean_composition_year, dtype: float64

Composition dates

This section relies on the dataset’s metadata.

valid_composed_start = pd.to_numeric(all_metadata.composed_start, errors="coerce")
valid_composed_end = pd.to_numeric(all_metadata.composed_end, errors="coerce")
print(
    f"Composition dates range from {int(valid_composed_start.min())} {valid_composed_start.idxmin()} "
    f"to {int(valid_composed_end.max())} {valid_composed_end.idxmax()}."
)

Composition dates range from 1717 ('bach_solo', 'BWV1007_01_Prelude') to 1723 ('bach_solo', 'BWV1007_01_Prelude').

Mean composition years per corpus

def make_summary(metadata_df):
    piece_is_annotated = metadata_df.label_count > 0
    return metadata_df[piece_is_annotated].copy()

Show source Hide source

summary = make_summary(all_metadata)
bar_data = pd.concat(
    [
        mean_composition_years.rename("year"),
        summary.groupby(level="corpus").size().rename("pieces"),
    ],
    axis=1,
).reset_index()

N = len(summary)
fig = px.bar(
    bar_data,
    x="year",
    y="pieces",
    color="corpus",
    color_discrete_map=corpus_colors,
    title=f"Temporal coverage of the {N} annotated pieces in the Distant Listening Corpus",
)
fig.update_traces(width=5)
fig.update_layout(**utils.STD_LAYOUT)
fig.update_traces(width=5)
save_figure_as(fig, "pieces_timeline_bars")
fig.show()

summary

		TimeSig	KeySig	last_mc	last_mn	length_qb	last_mc_unfolded	last_mn_unfolded	length_qb_unfolded	volta_mcs	all_notes_qb	...	ambitus	originalFormat	P86 (composer)	wikidata	viaf	musicbrainz	imslp	pdf	staff_1_ambitus	staff_1_instrument
corpus	piece
bach_solo	BWV1001_01_Adagio	{1: '4/4'}	{1: -1}	22	22	88.00	22	22	88.00	()	157.50	...	55-82 (G3-Bb5)	cap	Q1339	https://www.wikidata.org/wiki/Q20646569	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/a7c0ad42-a277-35c...	https://imslp.org/wiki/Violin_Sonata_No.1_in_G...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-82 (G3-Bb5)	Violin
	BWV1001_02_Fuga	{1: '2/2'}	{1: -1}	94	94	376.00	94	94	376.00	()	642.50	...	55-89 (G3-F6)	cap	Q1339	https://www.wikidata.org/wiki/Q20646569	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/20a9c7e7-6d81-3e1...	https://imslp.org/wiki/Violin_Sonata_No.1_in_G...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-89 (G3-F6)	Violin
	BWV1001_03_Siciliano	{1: '12/8'}	{1: -1}	20	20	120.00	20	20	120.00	()	196.00	...	55-86 (G3-D6)	cap	Q1339	https://www.wikidata.org/wiki/Q20646569	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/b89f8b50-b671-3bc...	https://imslp.org/wiki/Violin_Sonata_No.1_in_G...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-86 (G3-D6)	Violin
	BWV1001_04_Presto	{1: '3/8'}	{1: -1}	136	136	204.00	272	272	408.00	()	214.00	...	55-86 (G3-D6)	cap	Q1339	https://www.wikidata.org/wiki/Q20646569	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/d3c98683-e7ed-33e...	https://imslp.org/wiki/Violin_Sonata_No.1_in_G...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-86 (G3-D6)	Violin
	BWV1002_01_Allemanda	{1: '4/4'}	{1: 2}	27	24	104.25	49	48	192.25	(13], [14]], [[26], [27)	149.63	...	55-86 (G3-D6)	cap	Q1339	https://www.wikidata.org/wiki/Q7140627	https://viaf.org/viaf/178649074/	https://musicbrainz.org/work/0d94a02f-68d6-308...	https://imslp.org/wiki/Violin_Partita_No.1_in_...	https://imslp.org/wiki/Special:ReverseLookup/4...	55-86 (G3-D6)	Violin
	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
	BWV1012_07_Gique	{1: '6/8'}	{1: 2}	69	68	204.00	138	136	408.00	()	245.50	...	37-74 (C#2-D5)	<NA>	Q1339	https://www.wikidata.org/wiki/Q20645428	https://viaf.org/viaf/212878335	https://musicbrainz.org/work/ddd9f05c-b5a4-3ea...	https://imslp.org/wiki/Cello_Suite_No.6_in_D_m...	https://imslp.org/wiki/Special:ReverseLookup/4...	37-74 (C#2-D5)	Piano
	BWV1013_01_Allemande	{1: '4/4'}	{1: 0}	49	46	196.00	92	92	368.00	(19], [20, 21]], [[47, 48], [49)	195.50	...	62-93 (D4-A6)	<NA>	Q1339	https://www.wikidata.org/wiki/Q989855	<NA>	https://musicbrainz.org/work/1158ae1f-4cb5-315...	https://imslp.org/wiki/Partita_in_A_minor,_BWV...	https://imslp.org/wiki/Special:ReverseLookup/9...	62-93 (D4-A6)	Flute
	BWV1013_02_Corrente	{1: '3/4'}	{1: 0}	63	62	186.00	126	124	372.00	()	186.00	...	62-87 (D4-D#6)	<NA>	Q1339	https://www.wikidata.org/wiki/Q989855	<NA>	https://musicbrainz.org/work/7392fcf6-65b4-379...	https://imslp.org/wiki/Partita_in_A_minor,_BWV...	https://imslp.org/wiki/Special:ReverseLookup/9...	62-87 (D4-D#6)	Flute
	BWV1013_03_Sarabande	{1: '3/4'}	{1: 0}	46	46	138.00	92	92	276.00	()	138.00	...	62-86 (D4-D6)	<NA>	Q1339	https://www.wikidata.org/wiki/Q989855	<NA>	https://musicbrainz.org/work/9e2df6c8-b70e-318...	https://imslp.org/wiki/Partita_in_A_minor,_BWV...	https://imslp.org/wiki/Special:ReverseLookup/9...	62-86 (D4-D6)	Flute
	BWV1013_04_BourreeAnglaise	{1: '2/4'}	{1: 0}	71	70	140.00	142	140	280.00	()	140.00	...	62-86 (D4-D6)	<NA>	Q1339	https://www.wikidata.org/wiki/Q989855	<NA>	https://musicbrainz.org/work/69bec9a9-d970-305...	https://imslp.org/wiki/Partita_in_A_minor,_BWV...	https://imslp.org/wiki/Special:ReverseLookup/9...	62-86 (D4-D6)	Flute

68 rows × 54 columns

Composition years histogram

Show source Hide source

hist_data = summary.reset_index()
hist_data.corpus = hist_data.corpus.map(corpus_names)
fig = px.histogram(
    hist_data,
    x="composed_end",
    color="corpus",
    labels=dict(
        composed_end="decade",
        count="pieces",
    ),
    color_discrete_map=corpus_name_colors,
    title=f"Temporal coverage of the {N} annotated pieces in the Distant Listening Corpus",
)
fig.update_traces(xbins=dict(size=10))
fig.update_layout(**utils.STD_LAYOUT)
fig.update_legends(font=dict(size=16))
save_figure_as(fig, "pieces_timeline_histogram", height=1250)
fig.show()

Dimensions

Overview

def make_overview_table(groupby, group_name="pieces"):
    n_groups = groupby.size().rename(group_name)
    absolute_numbers = dict(
        measures=groupby.last_mn.sum(),
        length=groupby.length_qb.sum(),
        notes=groupby.n_onsets.sum(),
        labels=groupby.label_count.sum(),
    )
    absolute = pd.DataFrame.from_dict(absolute_numbers)
    absolute = pd.concat([n_groups, absolute], axis=1)
    sum_row = pd.DataFrame(absolute.sum(), columns=["sum"]).T
    absolute = pd.concat([absolute, sum_row])
    return absolute


absolute = make_overview_table(summary.groupby("workTitle"))
# print(absolute.astype(int).to_markdown())
absolute.astype(int)

	pieces	measures	length	notes	labels
Partita No. 1 in B minor	8	408	1476	4002	743
Partita No. 2 in D minor	2	86	290	978	165
Partita No. 3 in E major	3	134	438	1006	233
Partita in A minor	4	224	660	2141	438
Sonata No. 1 in G minor	4	272	788	3468	745
Sonata No. 2 in A minor	4	396	989	4346	855
Sonata No. 3 in C major	1	354	1416	3051	748
Suite No. 1 in G major	7	214	716	2213	365
Suite No. 2 in D minor	7	271	723	2261	429
Suite No. 3 in C major	7	380	1054	3078	567
Suite No. 4 in E-flat major	7	329	1304	2973	529
Suite No. 5 in C minor	7	433	1087	2912	710
Suite No. 6 in D major	7	348	1524	3936	654
sum	68	3849	12465	36365	7181

def summarize_dataset(D):
    all_metadata = D.get_metadata()
    summary = make_summary(all_metadata)
    return make_overview_table(summary.groupby(level=0))


corpus_summary = summarize_dataset(D)
print(corpus_summary.astype(int).to_markdown())

|           |   pieces |   measures |   length |   notes |   labels |
|:----------|---------:|-----------:|---------:|--------:|---------:|
| bach_solo |       68 |       3849 |    12465 |   36365 |     7181 |
| sum       |       68 |       3849 |    12465 |   36365 |     7181 |

Measures

all_measures = D.get_feature("measures")
print(
    f"{len(all_measures.index)} measures over {len(all_measures.groupby(level=[0,1]))} files."
)
all_measures.head()

3904 measures over 68 files.

			mc	mn	quarterbeats	duration_qb	keysig	timesig	act_dur	mc_offset	numbering_offset	dont_count	barline	breaks	repeats	next	volta
corpus	piece	i
bach_solo	BWV1001_01_Adagio	0	1	1	0	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	<NA>	firstMeasure	(2,)	<NA>
		1	2	2	4	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	line	<NA>	(3,)	<NA>
		2	3	3	8	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	line	<NA>	(4,)	<NA>
		3	4	4	12	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(5,)	<NA>
		4	5	5	16	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	line	<NA>	(6,)	<NA>

all_measures.get_default_analysis().plot_grouped()

Harmony labels

All symbols, independent of the local key (the mode of which changes their semantics).

try:
    all_annotations = D.get_feature("harmonylabels").df
except Exception:
    all_annotations = pd.DataFrame()
n_annotations = len(all_annotations.index)
includes_annotations = n_annotations > 0
if includes_annotations:
    display(all_annotations.head())
    print(f"Concatenated annotation tables contains {all_annotations.shape[0]} rows.")
    no_chord = all_annotations.root.isna()
    if no_chord.sum() > 0:
        print(
            f"{no_chord.sum()} of them are not chords. Their values are:"
            f" {all_annotations.label[no_chord].value_counts(dropna=False).to_dict()}"
        )
    all_chords = all_annotations[~no_chord].copy()
    print(
        f"Dataset contains {all_chords.shape[0]} tokens and {len(all_chords.chord.unique())} types over "
        f"{len(all_chords.groupby(level=[0,1]))} documents."
    )
    all_annotations["corpus_name"] = all_annotations.index.get_level_values(0).map(
        utils.get_corpus_display_name
    )
    all_chords["corpus_name"] = all_chords.index.get_level_values(0).map(
        utils.get_corpus_display_name
    )
else:
    print("Dataset contains no annotations.")

			mc	mn	quarterbeats	duration_qb	mc_onset	mn_onset	timesig	staff	voice	volta	...	numeral_or_applied_to_numeral	intervals_over_bass	intervals_over_root	scale_degrees	scale_degrees_and_mode	scale_degrees_major	scale_degrees_minor	globalkey	localkey	chord
corpus	piece	i
bach_solo	BWV1001_01_Adagio	0	1	1	0	2.0	0	0	4/4	1	1	<NA>	...	i	(m3, P5)	(m3, P5)	(1, 3, 5)	(1, 3, 5), minor	(1, b3, 5)	(1, 3, 5)	g	i	i
		1	1	1	2	0.5	1/2	1/2	4/4	1	1	<NA>	...	#vii	(m3, m7)	(m3, d5, m2)	(2, 4, 1)	(2, 4, 1), minor	(2, 4, 1)	(2, 4, 1)	g	i	#viio6(2)
		2	1	1	5/2	0.5	5/8	5/8	4/4	1	1	<NA>	...	#vii	(m3, M6)	(m3, d5)	(2, 4, #7)	(2, 4, #7), minor	(2, 4, 7)	(2, 4, #7)	g	i	#viio6
		3	1	1	3	1.0	3/4	3/4	4/4	1	1	<NA>	...	V	(M3, P5)	(M3, P5)	(5, #7, 2)	(5, #7, 2), minor	(5, 7, 2)	(5, #7, 2)	g	i	V
		4	2	2	4	2.0	0	0	4/4	1	1	<NA>	...	V	(M3, P5, m7)	(M3, P5, m7)	(5, #7, 2, 4)	(5, #7, 2, 4), minor	(5, 7, 2, 4)	(5, #7, 2, 4)	g	i	V7

5 rows × 51 columns

Concatenated annotation tables contains 7026 rows.
Dataset contains 7026 tokens and 474 types over 68 documents.