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("schumann_liederkreis", corpus_release="v2.5")
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("Robert Schumann – Liederkreis version v2.5")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Robert Schumann – Liederkreis version v2.5
Datapackage 'schumann_liederkreis' @ v2.5
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'schumann_liederkreis': ["'schumann_liederkreis.measures' "
                                                  '(MuseScoreFacetName.MuseScoreMeasures)',
                                                  "'schumann_liederkreis.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                                  "'schumann_liederkreis.expanded' "
                                                  '(MuseScoreFacetName.MuseScoreHarmonies)',
                                                  "'schumann_liederkreis.chords' (MuseScoreFacetName.MuseScoreChords)",
                                                  "'schumann_liederkreis.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	all_notes_qb	n_onsets	...	musicbrainz	viaf	imslp	pdf	staff_1_ambitus	staff_1_instrument	staff_2_ambitus	staff_2_instrument	staff_3_ambitus	staff_3_instrument
corpus	piece
schumann_liederkreis	op39n01	{1: '4/4'}	{1: 3}	28	28	112.0	28	28	112.0	301.25	663	...	https://musicbrainz.org/work/b4d6805c-f700-363...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	64-76 (E4-E5)	Voice	58-78 (A#3-F#5)	Grand Piano	37-73 (C#2-C#5)	Grand Piano
	op39n02	{1: '2/4'}	{1: 3}	30	30	60.0	30	30	60.0	310.12	575	...	https://musicbrainz.org/work/754505ae-0fe1-3a2...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	63-78 (D#4-F#5)	Voice	56-85 (G#3-C#6)	Grand Piano	30-69 (F#1-A4)	Grand Piano
	op39n03	{1: '3/4'}	{1: 4, 15: 0, 33: 4}	72	72	216.0	72	72	216.0	867.50	1137	...	https://musicbrainz.org/work/d81c8bf6-f122-3d0...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	59-80 (B3-G#5)	Voice	50-80 (D3-G#5)	Piano	27-76 (D#1-E5)	Piano
	op39n04	{1: '6/8'}	{1: 1}	40	39	117.0	40	39	117.0	392.75	561	...	https://musicbrainz.org/work/e2474c84-f5c3-36a...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	62-76 (D4-E5)	Voice	53-79 (E#3-G5)	Piano	38-67 (D2-G4)	Piano
	op39n05	{1: '3/8'}	{1: 4}	68	68	102.0	68	68	102.0	473.75	1211	...	https://musicbrainz.org/work/3c2809ea-bd3c-3c0...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	64-78 (E4-F#5)	Voice	51-90 (D#3-F#6)	Piano	28-71 (E1-B4)	Piano
	op39n06	{1: '4/4'}	{1: 5}	30	30	120.0	30	30	120.0	530.62	982	...	https://musicbrainz.org/work/59c9c200-401b-352...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	66-80 (F#4-G#5)	Voice	54-80 (F#3-G#5)	Piano	30-63 (F#1-D#4)	Piano
	op39n07	{1: '4/4'}	{1: 0}	39	39	156.0	39	39	156.0	761.50	362	...	https://musicbrainz.org/work/dfff586c-ae68-3c5...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	60-72 (C4-C5)	Voice	53-77 (F3-F5)	Piano	28-64 (E1-E4)	Piano
	op39n08	{1: '2/4'}	{1: 0}	39	39	78.0	39	39	78.0	250.25	748	...	https://musicbrainz.org/work/9435eed9-1d1d-3d9...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	64-77 (E4-F5)	Voice	56-81 (G#3-A5)	Grand Piano	33-69 (A1-A4)	Grand Piano
	op39n09	{1: '3/4'}	{1: 4}	28	28	84.0	28	28	84.0	440.25	505	...	https://musicbrainz.org/work/b4ecf55d-9dd7-339...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	64-76 (E4-E5)	Voice	47-76 (B2-E5)	Grand Piano	28-61 (E1-C#4)	Grand Piano
	op39n10	{1: '4/4'}	{1: 1}	41	41	161.0	41	41	161.0	656.50	620	...	https://musicbrainz.org/work/cbc98b7a-700e-385...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	58-76 (A#3-E5)	Voice	51-76 (D#3-E5)	Piano	28-71 (E1-B4)	Piano
	op39n11	{1: '6/8'}	{1: 3}	50	50	148.5	50	50	148.5	721.00	658	...	https://musicbrainz.org/work/58884708-60c8-34d...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	57-74 (A3-D5)	Oboe	49-79 (C#3-G5)	Piano	33-64 (A1-E4)	Piano
	op39n12	{1: '2/4'}	{1: 6}	31	31	62.0	31	31	62.0	323.17	1500	...	https://musicbrainz.org/work/9d6c9291-7d2b-3fd...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	63-78 (D#4-F#5)	Voice	58-87 (A#3-D#6)	Grand Piano	30-73 (F#1-C#5)	Grand Piano

12 rows × 58 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
schumann_liederkreis    1840.0
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 1840 ('schumann_liederkreis', 'op39n01') to 1840 ('schumann_liederkreis', 'op39n01').

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	all_notes_qb	n_onsets	...	musicbrainz	viaf	imslp	pdf	staff_1_ambitus	staff_1_instrument	staff_2_ambitus	staff_2_instrument	staff_3_ambitus	staff_3_instrument
corpus	piece
schumann_liederkreis	op39n01	{1: '4/4'}	{1: 3}	28	28	112.0	28	28	112.0	301.25	663	...	https://musicbrainz.org/work/b4d6805c-f700-363...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	64-76 (E4-E5)	Voice	58-78 (A#3-F#5)	Grand Piano	37-73 (C#2-C#5)	Grand Piano
	op39n02	{1: '2/4'}	{1: 3}	30	30	60.0	30	30	60.0	310.12	575	...	https://musicbrainz.org/work/754505ae-0fe1-3a2...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	63-78 (D#4-F#5)	Voice	56-85 (G#3-C#6)	Grand Piano	30-69 (F#1-A4)	Grand Piano
	op39n03	{1: '3/4'}	{1: 4, 15: 0, 33: 4}	72	72	216.0	72	72	216.0	867.50	1137	...	https://musicbrainz.org/work/d81c8bf6-f122-3d0...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	59-80 (B3-G#5)	Voice	50-80 (D3-G#5)	Piano	27-76 (D#1-E5)	Piano
	op39n04	{1: '6/8'}	{1: 1}	40	39	117.0	40	39	117.0	392.75	561	...	https://musicbrainz.org/work/e2474c84-f5c3-36a...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	62-76 (D4-E5)	Voice	53-79 (E#3-G5)	Piano	38-67 (D2-G4)	Piano
	op39n05	{1: '3/8'}	{1: 4}	68	68	102.0	68	68	102.0	473.75	1211	...	https://musicbrainz.org/work/3c2809ea-bd3c-3c0...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	64-78 (E4-F#5)	Voice	51-90 (D#3-F#6)	Piano	28-71 (E1-B4)	Piano
	op39n06	{1: '4/4'}	{1: 5}	30	30	120.0	30	30	120.0	530.62	982	...	https://musicbrainz.org/work/59c9c200-401b-352...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	66-80 (F#4-G#5)	Voice	54-80 (F#3-G#5)	Piano	30-63 (F#1-D#4)	Piano
	op39n07	{1: '4/4'}	{1: 0}	39	39	156.0	39	39	156.0	761.50	362	...	https://musicbrainz.org/work/dfff586c-ae68-3c5...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	60-72 (C4-C5)	Voice	53-77 (F3-F5)	Piano	28-64 (E1-E4)	Piano
	op39n08	{1: '2/4'}	{1: 0}	39	39	78.0	39	39	78.0	250.25	748	...	https://musicbrainz.org/work/9435eed9-1d1d-3d9...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	64-77 (E4-F5)	Voice	56-81 (G#3-A5)	Grand Piano	33-69 (A1-A4)	Grand Piano
	op39n09	{1: '3/4'}	{1: 4}	28	28	84.0	28	28	84.0	440.25	505	...	https://musicbrainz.org/work/b4ecf55d-9dd7-339...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	64-76 (E4-E5)	Voice	47-76 (B2-E5)	Grand Piano	28-61 (E1-C#4)	Grand Piano
	op39n10	{1: '4/4'}	{1: 1}	41	41	161.0	41	41	161.0	656.50	620	...	https://musicbrainz.org/work/cbc98b7a-700e-385...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	58-76 (A#3-E5)	Voice	51-76 (D#3-E5)	Piano	28-71 (E1-B4)	Piano
	op39n11	{1: '6/8'}	{1: 3}	50	50	148.5	50	50	148.5	721.00	658	...	https://musicbrainz.org/work/58884708-60c8-34d...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	57-74 (A3-D5)	Oboe	49-79 (C#3-G5)	Piano	33-64 (A1-E4)	Piano
	op39n12	{1: '2/4'}	{1: 6}	31	31	62.0	31	31	62.0	323.17	1500	...	https://musicbrainz.org/work/9d6c9291-7d2b-3fd...	https://viaf.org/viaf/181424943/	https://imslp.org/wiki/Liederkreis%2C_Op.39_%2...	https://imslp.org/wiki/Special:ReverseLookup/5...	63-78 (D#4-F#5)	Voice	58-87 (A#3-D#6)	Grand Piano	30-73 (F#1-C#5)	Grand Piano

12 rows × 58 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
Liederkreis	12	495	1416	9522	892
sum	12	495	1416	9522	892

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 |
|:---------------------|---------:|-----------:|---------:|--------:|---------:|
| schumann_liederkreis |       12 |        495 |     1416 |    9522 |      892 |
| sum                  |       12 |        495 |     1416 |    9522 |      892 |

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()

496 measures over 12 files.

			mc	mn	quarterbeats	duration_qb	keysig	timesig	act_dur	mc_offset	numbering_offset	dont_count	barline	breaks	repeats	next
corpus	piece	i
schumann_liederkreis	op39n01	0	1	1	0	4.0	3	4/4	1	0	<NA>	<NA>	<NA>	<NA>	firstMeasure	(2,)
		1	2	2	4	4.0	3	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(3,)
		2	3	3	8	4.0	3	4/4	1	0	<NA>	<NA>	<NA>	line	<NA>	(4,)
		3	4	4	12	4.0	3	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(5,)
		4	5	5	16	4.0	3	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(6,)

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	quarterbeats_all_endings	duration_qb	mc_onset	mn_onset	timesig	staff	voice	...	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
schumann_liederkreis	op39n01	0	1	1	0	0	8.0	0	0	4/4	3	1	...	i	(m3, P5)	(m3, P5)	(1, 3, 5)	(1, 3, 5), minor	(1, b3, 5)	(1, 3, 5)	f#	i	i
		1	3	3	8	8	4.0	0	0	4/4	3	1	...	V	(M3, P5)	(M3, P5)	(5, #7, 2)	(5, #7, 2), minor	(5, 7, 2)	(5, #7, 2)	f#	i	V
		2	4	4	12	12	2.0	0	0	4/4	3	1	...	i	(m3, P5)	(m3, P5)	(1, 3, 5)	(1, 3, 5), minor	(1, b3, 5)	(1, 3, 5)	f#	i	i
		3	4	4	14	14	2.0	1/2	1/2	4/4	3	1	...	V	(M3, P5, m7)	(M3, P5, m7)	(5, #7, 2, 4)	(5, #7, 2, 4), minor	(5, 7, 2, 4)	(5, #7, 2, 4)	f#	i	V7
		4	5	5	16	16	6.0	0	0	4/4	3	1	...	i	(m3, P5)	(m3, P5)	(1, 3, 5)	(1, 3, 5), minor	(1, b3, 5)	(1, 3, 5)	f#	i	i

5 rows × 52 columns

Concatenated annotation tables contains 892 rows.
Dataset contains 892 tokens and 180 types over 12 documents.