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("tchaikovsky_seasons", 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("Pyotr Tchaikovsky – The Seasons version v2.3")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Pyotr Tchaikovsky – The Seasons version v2.3
Datapackage 'tchaikovsky_seasons' @ v2.3
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'tchaikovsky_seasons': ["'tchaikovsky_seasons.measures' "
                                                 '(MuseScoreFacetName.MuseScoreMeasures)',
                                                 "'tchaikovsky_seasons.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                                 "'tchaikovsky_seasons.expanded' "
                                                 '(MuseScoreFacetName.MuseScoreHarmonies)',
                                                 "'tchaikovsky_seasons.chords' (MuseScoreFacetName.MuseScoreChords)",
                                                 "'tchaikovsky_seasons.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	...	musicbrainz	viaf	wikidata	originalFormat	pdf	score integrity	staff_1_ambitus	staff_1_instrument	staff_2_ambitus	staff_2_instrument
corpus	piece
tchaikovsky_seasons	op37a01	{1: '3/4'}	{1: 3, 29: 1, 63: 3}	103	103	309.0	103	103	309.0	()	1058.17	...	https://musicbrainz.org/work/6460a645-9844-304...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	mxl	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	53-88 (E#3-E6)	Piano	33-88 (A1-E6)	Piano
	op37a02	{1: '2/4'}	{1: 2}	169	169	338.0	181	181	362.0	()	1263.00	...	https://musicbrainz.org/work/b9eb26bd-2d34-390...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	mxl	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	43-93 (G2-A6)	Piano	29-85 (F1-C#6)	Piano
	op37a03	{1: '2/4'}	{1: -2}	46	46	92.0	46	46	92.0	()	321.75	...	https://musicbrainz.org/work/d1adc59b-c23d-301...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	mxl	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	55-86 (G3-D6)	Piano	38-72 (D2-C5)	Piano
	op37a04	{1: '6/8'}	{1: -2}	87	86	258.5	87	86	258.5	()	804.00	...	https://musicbrainz.org/work/d364de99-f08f-322...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	52-86 (E3-D6)	Piano (2)	39-77 (D#2-F5)	Piano (2)
	op37a05	{1: '9/8', 20: '2/4', 68: '9/8'}	{1: 1, 20: 2, 68: 1}	88	88	274.5	88	88	274.5	()	899.50	...	https://musicbrainz.org/work/a0fcf2bc-9344-37e...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	48-86 (C3-D6)	Piano (2)	40-74 (E2-D5)	Piano (2)
	op37a06	{1: '4/4', 40: '3/4', 52: '4/4'}	{1: -2, 32: 1, 52: -2}	99	99	384.0	99	99	384.0	()	1299.50	...	https://musicbrainz.org/work/97abe0e5-11f8-308...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	mxl	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	42-91 (F#2-G6)	Piano	31-88 (G1-E6)	Piano
	op37a07	{1: '4/4'}	{1: -3}	56	56	224.0	56	56	224.0	()	941.17	...	https://musicbrainz.org/work/43198a46-81be-3ce...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	46-89 (Bb2-F6)	Piano (2)	34-77 (Bb1-F5)	Piano (2)
	op37a08	{1: '6/8'}	{1: 2}	199	198	595.5	199	198	595.5	()	1994.00	...	https://musicbrainz.org/work/76f98337-460c-399...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	43-91 (G2-G6)	Piano (2)	35-83 (B1-B5)	Piano (2)
	op37a09	{1: '4/4'}	{1: 1}	90	90	360.0	90	90	360.0	()	1430.33	...	https://musicbrainz.org/work/58e2eb4f-6cee-358...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	54-91 (F#3-G6)	Piano (2)	36-71 (C2-B4)	Piano (2)
	op37a10	{1: '4/4'}	{1: -1}	56	56	224.0	56	56	224.0	()	808.00	...	https://musicbrainz.org/work/b03dde30-6ae2-32e...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	<NA>	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	53-82 (F3-Bb5)	Piano	37-67 (C#2-G4)	Piano
	op37a11	{1: '4/4'}	{1: 4, 28: 1, 51: 4}	83	83	332.0	83	83	332.0	()	967.92	...	https://musicbrainz.org/work/432dd63f-4645-34a...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	45-92 (A2-G#6)	Piano (2)	38-75 (D2-D#5)	Piano (2)
	op37a12	{1: '3/4'}	{1: -4, 88: 4, 149: -4}	176	176	528.0	263	263	789.0	()	1856.50	...	https://musicbrainz.org/work/4a023af1-58db-3ce...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	56-92 (G#3-Ab6)	Piano (2)	39-75 (Eb2-Eb5)	Piano (2)

12 rows × 57 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
tchaikovsky_seasons    1875.5
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 1875 ('tchaikovsky_seasons', 'op37a01') to 1876 ('tchaikovsky_seasons', 'op37a01').

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	...	musicbrainz	viaf	wikidata	originalFormat	pdf	score integrity	staff_1_ambitus	staff_1_instrument	staff_2_ambitus	staff_2_instrument
corpus	piece
tchaikovsky_seasons	op37a01	{1: '3/4'}	{1: 3, 29: 1, 63: 3}	103	103	309.0	103	103	309.0	()	1058.17	...	https://musicbrainz.org/work/6460a645-9844-304...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	mxl	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	53-88 (E#3-E6)	Piano	33-88 (A1-E6)	Piano
	op37a02	{1: '2/4'}	{1: 2}	169	169	338.0	181	181	362.0	()	1263.00	...	https://musicbrainz.org/work/b9eb26bd-2d34-390...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	mxl	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	43-93 (G2-A6)	Piano	29-85 (F1-C#6)	Piano
	op37a03	{1: '2/4'}	{1: -2}	46	46	92.0	46	46	92.0	()	321.75	...	https://musicbrainz.org/work/d1adc59b-c23d-301...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	mxl	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	55-86 (G3-D6)	Piano	38-72 (D2-C5)	Piano
	op37a04	{1: '6/8'}	{1: -2}	87	86	258.5	87	86	258.5	()	804.00	...	https://musicbrainz.org/work/d364de99-f08f-322...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	52-86 (E3-D6)	Piano (2)	39-77 (D#2-F5)	Piano (2)
	op37a05	{1: '9/8', 20: '2/4', 68: '9/8'}	{1: 1, 20: 2, 68: 1}	88	88	274.5	88	88	274.5	()	899.50	...	https://musicbrainz.org/work/a0fcf2bc-9344-37e...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	48-86 (C3-D6)	Piano (2)	40-74 (E2-D5)	Piano (2)
	op37a06	{1: '4/4', 40: '3/4', 52: '4/4'}	{1: -2, 32: 1, 52: -2}	99	99	384.0	99	99	384.0	()	1299.50	...	https://musicbrainz.org/work/97abe0e5-11f8-308...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	mxl	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	42-91 (F#2-G6)	Piano	31-88 (G1-E6)	Piano
	op37a07	{1: '4/4'}	{1: -3}	56	56	224.0	56	56	224.0	()	941.17	...	https://musicbrainz.org/work/43198a46-81be-3ce...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	46-89 (Bb2-F6)	Piano (2)	34-77 (Bb1-F5)	Piano (2)
	op37a08	{1: '6/8'}	{1: 2}	199	198	595.5	199	198	595.5	()	1994.00	...	https://musicbrainz.org/work/76f98337-460c-399...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	43-91 (G2-G6)	Piano (2)	35-83 (B1-B5)	Piano (2)
	op37a09	{1: '4/4'}	{1: 1}	90	90	360.0	90	90	360.0	()	1430.33	...	https://musicbrainz.org/work/58e2eb4f-6cee-358...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	54-91 (F#3-G6)	Piano (2)	36-71 (C2-B4)	Piano (2)
	op37a10	{1: '4/4'}	{1: -1}	56	56	224.0	56	56	224.0	()	808.00	...	https://musicbrainz.org/work/b03dde30-6ae2-32e...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	<NA>	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	53-82 (F3-Bb5)	Piano	37-67 (C#2-G4)	Piano
	op37a11	{1: '4/4'}	{1: 4, 28: 1, 51: 4}	83	83	332.0	83	83	332.0	()	967.92	...	https://musicbrainz.org/work/432dd63f-4645-34a...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	45-92 (A2-G#6)	Piano (2)	38-75 (D2-D#5)	Piano (2)
	op37a12	{1: '3/4'}	{1: -4, 88: 4, 149: -4}	176	176	528.0	263	263	789.0	()	1856.50	...	https://musicbrainz.org/work/4a023af1-58db-3ce...	https://viaf.org/viaf/183857288	https://www.wikidata.org/wiki/Q2914902	xml	https://imslp.org/wiki/Special:ReverseLookup/1...	Tom Schreyer	56-92 (G#3-Ab6)	Piano (2)	39-75 (Eb2-Eb5)	Piano (2)

12 rows × 57 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
The Seasons	12	1250	3919	18169	3059
sum	12	1250	3919	18169	3059

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 |
|:--------------------|---------:|-----------:|---------:|--------:|---------:|
| tchaikovsky_seasons |       12 |       1250 |     3919 |   18169 |     3059 |
| sum                 |       12 |       1250 |     3919 |   18169 |     3059 |

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()

1252 measures over 12 files.

			mc	mn	quarterbeats	duration_qb	keysig	timesig	act_dur	mc_offset	numbering_offset	dont_count	barline	breaks	repeats	next	markers	jump_bwd	jump_fwd	play_until
corpus	piece	i
tchaikovsky_seasons	op37a01	0	1	1	0	3.0	3	3/4	3/4	0	<NA>	<NA>	<NA>	<NA>	firstMeasure	(2,)	<NA>	<NA>	<NA>	<NA>
		1	2	2	3	3.0	3	3/4	3/4	0	<NA>	<NA>	<NA>	<NA>	<NA>	(3,)	<NA>	<NA>	<NA>	<NA>
		2	3	3	6	3.0	3	3/4	3/4	0	<NA>	<NA>	<NA>	<NA>	<NA>	(4,)	<NA>	<NA>	<NA>	<NA>
		3	4	4	9	3.0	3	3/4	3/4	0	<NA>	<NA>	<NA>	<NA>	<NA>	(5,)	<NA>	<NA>	<NA>	<NA>
		4	5	5	12	3.0	3	3/4	3/4	0	<NA>	<NA>	<NA>	<NA>	<NA>	(6,)	<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	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
tchaikovsky_seasons	op37a01	0	1	1	0	0	2.0	0	0	3/4	2	1	...	V	(M2, a4, M6)	(M3, P5, m7)	(4, 5, 7, 2)	(4, 5, 7, 2), major	(4, 5, 7, 2)	(4, 5, #7, 2)	A	I	V2
		1	1	1	2	2	1.0	1/2	1/2	3/4	2	1	...	I	(m3, m6)	(M3, P5)	(3, 5, 1)	(3, 5, 1), major	(3, 5, 1)	(#3, 5, 1)	A	I	I6
		2	2	2	3	3	0.5	0	0	3/4	2	1	...	V	(P4, M6)	(M3, P5)	(2, 5, 7)	(2, 5, 7), major	(2, 5, 7)	(2, 5, #7)	A	I	V64
		3	2	2	7/2	7/2	0.5	1/8	1/8	3/4	2	1	...	I	(M3, P5)	(M3, P5)	(1, 3, 5)	(1, 3, 5), major	(1, 3, 5)	(1, #3, 5)	A	I	I
		4	2	2	4	4	1.0	1/4	1/4	3/4	2	1	...	V	(m3, m6)	(M3, P5)	(7, 2, 5)	(7, 2, 5), major	(7, 2, 5)	(#7, 2, 5)	A	I	V6

5 rows × 52 columns

Concatenated annotation tables contains 2992 rows.
Dataset contains 2992 tokens and 278 types over 12 documents.