Overview#

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

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("pleyel_quartets", 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("Ignaz Pleyel – String Quartets version v2.5")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D
Data and software versions
--------------------------

Ignaz Pleyel – String Quartets version v2.5
Datapackage 'pleyel_quartets' @ v2.5
dimcat version 3.4.0
Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'pleyel_quartets': ["'pleyel_quartets.measures' (MuseScoreFacetName.MuseScoreMeasures)",
                                             "'pleyel_quartets.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                             "'pleyel_quartets.expanded' (MuseScoreFacetName.MuseScoreHarmonies)",
                                             "'pleyel_quartets.chords' (MuseScoreFacetName.MuseScoreChords)",
                                             "'pleyel_quartets.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 ... viaf musicbrainz staff_1_ambitus staff_1_instrument staff_2_ambitus staff_2_instrument staff_3_ambitus staff_3_instrument staff_4_ambitus staff_4_instrument
corpus piece
pleyel_quartets b307op2n1a {1: '4/4'} {1: 3} 199 197 788.0 398 394 1576.0 (87], [88) 2674.50 ... http://viaf.org/viaf/315104251 https://musicbrainz.org/work/9565d9eb-6ed0-4ff... 55-93 (G3-A6) Violin 55-81 (G3-A5) Violin 49-71 (C#3-B4) Viola 36-69 (C2-A4) Violoncello
b307op2n1b {1: '6/8'} {1: 0} 108 107 321.5 108 107 321.5 () 1122.50 ... http://viaf.org/viaf/315104251 https://musicbrainz.org/work/1c2e522f-b783-461... 56-86 (G#3-D6) Violin 55-75 (G3-Eb5) Violin 48-70 (C3-Bb4) Viola 36-67 (C2-G4) Violoncello
b307op2n1c {1: '3/4'} {1: 3} 82 78 239.0 160 156 468.0 (20], [21]], [[51], [52) 802.00 ... http://viaf.org/viaf/315104251 https://musicbrainz.org/work/9a63d50a-73b9-451... 56-88 (G#3-E6) Violin 57-71 (A3-B4) Violin 49-66 (C#3-F#4) Viola 40-64 (E2-E4) Violoncello
b309op2n3a {1: '2/2'} {1: -2} 98 98 392.0 98 98 392.0 () 1279.67 ... http://viaf.org/viaf/315104256 https://musicbrainz.org/work/9b6d5d99-449a-477... 55-87 (G3-Eb6) Violin 55-82 (G3-Bb5) Violin 53-75 (F3-Eb5) Viola 36-65 (C2-F4) Violoncello
b309op2n3b {1: '2/2'} {1: -2} 269 269 1076.0 371 371 1484.0 () 3664.00 ... http://viaf.org/viaf/315104256 https://musicbrainz.org/work/21f2278b-24b3-419... 55-86 (G3-D6) Violin 55-82 (G3-Bb5) Violin 48-74 (C3-D5) Viola 36-63 (C2-Eb4) Violoncello
b309op2n3c {1: '3/4'} {1: -2, 57: 1} 74 74 222.0 148 148 444.0 () 727.75 ... http://viaf.org/viaf/315104256 https://musicbrainz.org/work/9cbcee5a-8155-40e... 62-86 (D4-D6) Violin 55-77 (G3-F5) Violin 50-74 (D3-D5) Viola 38-62 (D2-D4) Violoncello

6 rows × 60 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
pleyel_quartets    1784.0
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 1784 ('pleyel_quartets', 'b307op2n1a') to 1784 ('pleyel_quartets', 'b307op2n1a').

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()
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 ... viaf musicbrainz staff_1_ambitus staff_1_instrument staff_2_ambitus staff_2_instrument staff_3_ambitus staff_3_instrument staff_4_ambitus staff_4_instrument
corpus piece
pleyel_quartets b307op2n1a {1: '4/4'} {1: 3} 199 197 788.0 398 394 1576.0 (87], [88) 2674.50 ... http://viaf.org/viaf/315104251 https://musicbrainz.org/work/9565d9eb-6ed0-4ff... 55-93 (G3-A6) Violin 55-81 (G3-A5) Violin 49-71 (C#3-B4) Viola 36-69 (C2-A4) Violoncello
b307op2n1b {1: '6/8'} {1: 0} 108 107 321.5 108 107 321.5 () 1122.50 ... http://viaf.org/viaf/315104251 https://musicbrainz.org/work/1c2e522f-b783-461... 56-86 (G#3-D6) Violin 55-75 (G3-Eb5) Violin 48-70 (C3-Bb4) Viola 36-67 (C2-G4) Violoncello
b307op2n1c {1: '3/4'} {1: 3} 82 78 239.0 160 156 468.0 (20], [21]], [[51], [52) 802.00 ... http://viaf.org/viaf/315104251 https://musicbrainz.org/work/9a63d50a-73b9-451... 56-88 (G#3-E6) Violin 57-71 (A3-B4) Violin 49-66 (C#3-F#4) Viola 40-64 (E2-E4) Violoncello
b309op2n3a {1: '2/2'} {1: -2} 98 98 392.0 98 98 392.0 () 1279.67 ... http://viaf.org/viaf/315104256 https://musicbrainz.org/work/9b6d5d99-449a-477... 55-87 (G3-Eb6) Violin 55-82 (G3-Bb5) Violin 53-75 (F3-Eb5) Viola 36-65 (C2-F4) Violoncello
b309op2n3b {1: '2/2'} {1: -2} 269 269 1076.0 371 371 1484.0 () 3664.00 ... http://viaf.org/viaf/315104256 https://musicbrainz.org/work/21f2278b-24b3-419... 55-86 (G3-D6) Violin 55-82 (G3-Bb5) Violin 48-74 (C3-D5) Viola 36-63 (C2-Eb4) Violoncello
b309op2n3c {1: '3/4'} {1: -2, 57: 1} 74 74 222.0 148 148 444.0 () 727.75 ... http://viaf.org/viaf/315104256 https://musicbrainz.org/work/9cbcee5a-8155-40e... 62-86 (D4-D6) Violin 55-77 (G3-F5) Violin 50-74 (D3-D5) Viola 38-62 (D2-D4) Violoncello

6 rows × 60 columns

Composition years histogram#

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
String Quartet in A major 3 382 1348 6588 748
String Quartet in G minor 3 441 1690 7250 819
sum 6 823 3038 13838 1567
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 |
|:----------------|---------:|-----------:|---------:|--------:|---------:|
| pleyel_quartets |        6 |        823 |     3038 |   13838 |     1567 |
| sum             |        6 |        823 |     3038 |   13838 |     1567 |

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()
828 measures over 6 files.
mc mn quarterbeats duration_qb keysig timesig act_dur mc_offset numbering_offset dont_count barline breaks repeats next volta
corpus piece i
pleyel_quartets b307op2n1a 0 1 0 0 1.0 3 4/4 1/4 3/4 <NA> 1 <NA> <NA> firstMeasure (2,) <NA>
1 2 1 1 4.0 3 4/4 1 0 <NA> <NA> <NA> <NA> <NA> (3,) <NA>
2 3 2 5 4.0 3 4/4 1 0 <NA> <NA> <NA> <NA> <NA> (4,) <NA>
3 4 3 9 4.0 3 4/4 1 0 <NA> <NA> <NA> <NA> <NA> (5,) <NA>
4 5 4 13 4.0 3 4/4 1 0 <NA> <NA> <NA> <NA> <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
pleyel_quartets b307op2n1a 0 1 0 0 1.0 0 3/4 4/4 4 1 <NA> ... I (m3, m6) (M3, P5) (3, 5, 1) (3, 5, 1), major (3, 5, 1) (#3, 5, 1) A I I6
1 2 1 1 4.0 0 0 4/4 4 1 <NA> ... I (M3, P5) (M3, P5) (1, 3, 5) (1, 3, 5), major (1, 3, 5) (1, #3, 5) A I I
2 3 2 5 1.0 0 0 4/4 4 1 <NA> ... V (P4, M6) (P4, M6) (5, 1, 3) (5, 1, 3), major (5, 1, 3) (5, 1, #3) A I V(64)
3 3 2 6 3.0 1/4 1/4 4/4 4 1 <NA> ... V (M3, P5) (M3, P5) (5, 7, 2) (5, 7, 2), major (5, 7, 2) (5, #7, 2) A I V
4 4 3 9 4.0 0 0 4/4 4 1 <NA> ... V (m3, P4, M6) (M3, P5, m7) (2, 4, 5, 7) (2, 4, 5, 7), major (2, 4, 5, 7) (2, 4, 5, #7) A I V43

5 rows × 52 columns

Concatenated annotation tables contains 1532 rows.
Dataset contains 1532 tokens and 179 types over 6 documents.