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("schulhoff_suite_dansante_en_jazz", corpus_release="v2.3")
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("Erwin Schulhoff – Suite dansante en jazz version v2.3")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Erwin Schulhoff – Suite dansante en jazz version v2.3
Datapackage 'schulhoff_suite_dansante_en_jazz' @ v2.3
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'schulhoff_suite_dansante_en_jazz': ["'schulhoff_suite_dansante_en_jazz.measures' "
                                                              '(MuseScoreFacetName.MuseScoreMeasures)',
                                                              "'schulhoff_suite_dansante_en_jazz.notes' "
                                                              '(MuseScoreFacetName.MuseScoreNotes)',
                                                              "'schulhoff_suite_dansante_en_jazz.expanded' "
                                                              '(MuseScoreFacetName.MuseScoreHarmonies)',
                                                              "'schulhoff_suite_dansante_en_jazz.chords' "
                                                              '(MuseScoreFacetName.MuseScoreChords)',
                                                              "'schulhoff_suite_dansante_en_jazz.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	...	imslp	musicbrainz	typesetter	viaf	P86 (composer)	pdf	staff_1_instrument	staff_1_ambitus	staff_2_instrument	staff_2_ambitus
corpus	piece
schulhoff_suite_dansante_en_jazz	suite_dansante_en_jazz_1_stomp	{1: '2/2'}	{1: 0}	46	46	184.0	46	46	184.0	()	505.83	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/2bfa37b6-bc13-4e9...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	34-94 (Bb1-Bb6)	Piano	35-77 (B1-F5)
	suite_dansante_en_jazz_2_strait	{1: '2/2'}	{1: 0}	40	39	160.0	76	76	304.0	(38], [39)	735.25	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/5c0b4b0a-eee3-491...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	55-93 (G3-A6)	Piano	31-91 (G1-G6)
	suite_dansante_en_jazz_3_waltz	{1: '3/4'}	{1: 0}	71	70	213.0	134	134	402.0	(68], [69, 70, 71)	989.00	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/876be800-80fe-437...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	56-93 (Ab3-A6)	Piano	28-68 (E1-G#4)
	suite_dansante_en_jazz_4_tango	{1: '2/4'}	{1: 0}	41	40	82.0	80	80	160.0	(40], [41)	267.50	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/44b22f8e-949f-464...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	57-89 (A3-F6)	Piano	38-78 (D2-Gb5)
	suite_dansante_en_jazz_5_slow	{1: '2/2'}	{1: 0}	42	41	168.0	65	65	260.0	(40], [41, 42)	859.33	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/3dbf5c4a-ef31-4a1...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	54-90 (F#3-F#6)	Piano	34-69 (Bb1-A4)
	suite_dansante_en_jazz_6_fox-trot	{1: '2/2'}	{1: 0}	50	50	200.0	82	82	328.0	()	711.33	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/f3bc4a4f-0ba2-45e...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	38-90 (D2-F#6)	Piano	26-94 (D1-A#6)

6 rows × 53 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
schulhoff_suite_dansante_en_jazz    1931.0
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 1931 ('schulhoff_suite_dansante_en_jazz', 'suite_dansante_en_jazz_1_stomp') to 1931 ('schulhoff_suite_dansante_en_jazz', 'suite_dansante_en_jazz_1_stomp').

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	...	imslp	musicbrainz	typesetter	viaf	P86 (composer)	pdf	staff_1_instrument	staff_1_ambitus	staff_2_instrument	staff_2_ambitus
corpus	piece
schulhoff_suite_dansante_en_jazz	suite_dansante_en_jazz_1_stomp	{1: '2/2'}	{1: 0}	46	46	184.0	46	46	184.0	()	505.83	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/2bfa37b6-bc13-4e9...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	34-94 (Bb1-Bb6)	Piano	35-77 (B1-F5)
	suite_dansante_en_jazz_2_strait	{1: '2/2'}	{1: 0}	40	39	160.0	76	76	304.0	(38], [39)	735.25	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/5c0b4b0a-eee3-491...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	55-93 (G3-A6)	Piano	31-91 (G1-G6)
	suite_dansante_en_jazz_3_waltz	{1: '3/4'}	{1: 0}	71	70	213.0	134	134	402.0	(68], [69, 70, 71)	989.00	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/876be800-80fe-437...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	56-93 (Ab3-A6)	Piano	28-68 (E1-G#4)
	suite_dansante_en_jazz_4_tango	{1: '2/4'}	{1: 0}	41	40	82.0	80	80	160.0	(40], [41)	267.50	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/44b22f8e-949f-464...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	57-89 (A3-F6)	Piano	38-78 (D2-Gb5)
	suite_dansante_en_jazz_5_slow	{1: '2/2'}	{1: 0}	42	41	168.0	65	65	260.0	(40], [41, 42)	859.33	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/3dbf5c4a-ef31-4a1...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	54-90 (F#3-F#6)	Piano	34-69 (Bb1-A4)
	suite_dansante_en_jazz_6_fox-trot	{1: '2/2'}	{1: 0}	50	50	200.0	82	82	328.0	()	711.33	...	https://imslp.org/wiki/Suite_dansante_en_Jazz_...	https://musicbrainz.org/work/f3bc4a4f-0ba2-45e...	Anna Yuferova	https://viaf.org/viaf/180885757/#Schulhoff,_Er...	Q89540	https://imslp.org/wiki/Special:ReverseLookup/2...	Piano	38-90 (D2-F#6)	Piano	26-94 (D1-A#6)

6 rows × 53 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
Suite dansante en jazz	6	286	1007	5390	488
sum	6	286	1007	5390	488

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 |
|:---------------------------------|---------:|-----------:|---------:|--------:|---------:|
| schulhoff_suite_dansante_en_jazz |        6 |        286 |     1007 |    5390 |      488 |
| sum                              |        6 |        286 |     1007 |    5390 |      488 |

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()

286 measures over 6 files.

			mc	mn	quarterbeats	duration_qb	keysig	timesig	act_dur	mc_offset	numbering_offset	dont_count	barline	breaks	repeats	next	volta	markers	jump_bwd	jump_fwd	play_until
corpus	piece	i
schulhoff_suite_dansante_en_jazz	suite_dansante_en_jazz_1_stomp	0	1	1	0	4.0	0	2/2	1	0	<NA>	<NA>	<NA>	<NA>	firstMeasure	(2,)	<NA>	<NA>	<NA>	<NA>	<NA>
		1	2	2	4	4.0	0	2/2	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(3,)	<NA>	<NA>	<NA>	<NA>	<NA>
		2	3	3	8	4.0	0	2/2	1	0	<NA>	<NA>	<NA>	line	<NA>	(4,)	<NA>	<NA>	<NA>	<NA>	<NA>
		3	4	4	12	4.0	0	2/2	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(5,)	<NA>	<NA>	<NA>	<NA>	<NA>
		4	5	5	16	4.0	0	2/2	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(6,)	<NA>	<NA>	<NA>	<NA>	<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
schulhoff_suite_dansante_en_jazz	suite_dansante_en_jazz_1_stomp	0	1	1	0	8.0	0	0	2/2	2	1	<NA>	...	I	(M3, P5)	(M3, P5)	(1, 3, 5)	(1, 3, 5), major	(1, 3, 5)	(1, #3, 5)	E	I	I(13#11)
		1	3	3	8	1.0	0	0	2/2	2	1	<NA>	...	i	(M3, P5, M6)	(m3, P5, m7)	(b3, 5, b7, 1)	(b3, 5, b7, 1), major	(b3, 5, b7, 1)	(3, 5, 7, 1)	E	I	i65
		2	3	3	9	1.0	1/4	1/4	2/2	2	1	<NA>	...	bV	(M3, a5)	(M3, a5)	(b2, 4, 6)	(b2, 4, 6), major	(b2, 4, 6)	(b2, 4, #6)	E	I	V+(9)/bV
		3	3	3	10	4.0	1/2	1/2	2/2	2	1	<NA>	...	bV	(M3, P5, M7)	(M3, P5, M7)	(b5, b7, b2, 4)	(b5, b7, b2, 4), major	(b5, b7, b2, 4)	(b5, 7, b2, 4)	E	I	IM7(+13)/bV
		4	4	4	14	2.0	1/2	1/2	2/2	2	1	<NA>	...	bV	(m3, P5, m7)	(m3, P5, m7)	(b5, bb7, b2, b4)	(b5, bb7, b2, b4), major	(b5, bb7, b2, b4)	(b5, b7, b2, b4)	E	I	i7(+13)/bV

5 rows × 52 columns

Concatenated annotation tables contains 478 rows.
Dataset contains 478 tokens and 250 types over 6 documents.