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("grieg_lyric_pieces", 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("Edvard Grieg – Lyric Pieces version v2.3")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Edvard Grieg – Lyric Pieces version v2.3
Datapackage 'grieg_lyric_pieces' @ v2.3
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'grieg_lyric_pieces': ["'grieg_lyric_pieces.measures' (MuseScoreFacetName.MuseScoreMeasures)",
                                                "'grieg_lyric_pieces.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                                "'grieg_lyric_pieces.expanded' (MuseScoreFacetName.MuseScoreHarmonies)",
                                                "'grieg_lyric_pieces.chords' (MuseScoreFacetName.MuseScoreChords)",
                                                "'grieg_lyric_pieces.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 ... wikidata comments originalFormat pdf staff_1_ambitus staff_1_instrument staff_2_ambitus staff_2_instrument staff_3_ambitus staff_3_instrument
corpus piece
grieg_lyric_pieces op12n01 {1: '2/4'} {1: -3} 23 23 46.0 23 23 46.0 () 135.50 ... https://www.wikidata.org/wiki/Q2304758 <NA> mxl https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 55-79 (G3-G5) <NA> 39-71 (Eb2-Cb5) <NA> <NA> <NA>
op12n02 {1: '3/4'} {1: 0, 37: 3, 53: 0, 71: 3} 79 79 237.0 79 79 237.0 () 731.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> cap https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 59-76 (B3-E5) unbenannt 33-73 (A1-C#5) unbenannt <NA> <NA>
op12n03 {1: '2/2'} {1: 4, 26: 1, 41: 4} 53 52 209.0 53 52 209.0 () 598.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 56-77 (G#3-F5) Midi_1 40-61 (E2-C#4) Midi_1 <NA> <NA>
op12n04 {1: '3/4'} {1: 1} 72 72 216.0 72 72 216.0 () 593.50 ... https://www.wikidata.org/wiki/Q2304758 <NA> mxl https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 54-88 (F#3-E6) Grand Piano 40-71 (E2-B4) Grand Piano <NA> <NA>
op12n05 {1: '3/4'} {1: 3} 41 40 121.0 41 40 121.0 () 460.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 56-78 (G#3-F#5) S. 40-66 (E2-F#4) S. <NA> <NA>
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
op71n03 {1: '2/2'} {1: -6} 80 79 315.0 140 138 551.0 () 847.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 47-90 (Cb3-Gb6) Midi_1 32-78 (Ab1-Gb5) Midi_1 <NA> <NA>
op71n04 {1: '2/2'} {1: 5} 77 77 308.0 77 77 308.0 () 987.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 49-99 (C#3-D#7) Midi_1 25-75 (C#1-D#5) Midi_1 <NA> <NA>
op71n05 {1: '2/4'} {1: 0} 99 98 198.0 170 170 340.0 (84], [85) 526.75 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 43-93 (G2-A6) Midi_1 24-93 (C1-A6) Midi_1 <NA> <NA>
op71n06 {1: '4/4'} {1: 1} 34 32 128.0 34 32 128.0 () 409.50 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 47-84 (B2-C6) Midi_1 28-65 (E1-F4) Midi_1 <NA> <NA>
op71n07 {1: '3/4'} {1: -3, 26: 2, 34: -2, 50: -3} 75 74 223.0 75 74 223.0 () 852.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 55-79 (G3-G5) Midi_1 34-63 (Bb1-Eb4) Midi_1 <NA> <NA>

66 rows × 59 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
grieg_lyric_pieces    1888.227273
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 1864 ('grieg_lyric_pieces', 'op12n01') to 1901 ('grieg_lyric_pieces', 'op71n01').

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 ... wikidata comments originalFormat pdf staff_1_ambitus staff_1_instrument staff_2_ambitus staff_2_instrument staff_3_ambitus staff_3_instrument
corpus piece
grieg_lyric_pieces op12n01 {1: '2/4'} {1: -3} 23 23 46.0 23 23 46.0 () 135.50 ... https://www.wikidata.org/wiki/Q2304758 <NA> mxl https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 55-79 (G3-G5) <NA> 39-71 (Eb2-Cb5) <NA> <NA> <NA>
op12n02 {1: '3/4'} {1: 0, 37: 3, 53: 0, 71: 3} 79 79 237.0 79 79 237.0 () 731.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> cap https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 59-76 (B3-E5) unbenannt 33-73 (A1-C#5) unbenannt <NA> <NA>
op12n03 {1: '2/2'} {1: 4, 26: 1, 41: 4} 53 52 209.0 53 52 209.0 () 598.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 56-77 (G#3-F5) Midi_1 40-61 (E2-C#4) Midi_1 <NA> <NA>
op12n04 {1: '3/4'} {1: 1} 72 72 216.0 72 72 216.0 () 593.50 ... https://www.wikidata.org/wiki/Q2304758 <NA> mxl https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 54-88 (F#3-E6) Grand Piano 40-71 (E2-B4) Grand Piano <NA> <NA>
op12n05 {1: '3/4'} {1: 3} 41 40 121.0 41 40 121.0 () 460.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/8/8e/IMSL... 56-78 (G#3-F#5) S. 40-66 (E2-F#4) S. <NA> <NA>
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
op71n03 {1: '2/2'} {1: -6} 80 79 315.0 140 138 551.0 () 847.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 47-90 (Cb3-Gb6) Midi_1 32-78 (Ab1-Gb5) Midi_1 <NA> <NA>
op71n04 {1: '2/2'} {1: 5} 77 77 308.0 77 77 308.0 () 987.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 49-99 (C#3-D#7) Midi_1 25-75 (C#1-D#5) Midi_1 <NA> <NA>
op71n05 {1: '2/4'} {1: 0} 99 98 198.0 170 170 340.0 (84], [85) 526.75 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 43-93 (G2-A6) Midi_1 24-93 (C1-A6) Midi_1 <NA> <NA>
op71n06 {1: '4/4'} {1: 1} 34 32 128.0 34 32 128.0 () 409.50 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 47-84 (B2-C6) Midi_1 28-65 (E1-F4) Midi_1 <NA> <NA>
op71n07 {1: '3/4'} {1: -3, 26: 2, 34: -2, 50: -3} 75 74 223.0 75 74 223.0 () 852.00 ... https://www.wikidata.org/wiki/Q2304758 <NA> xml https://imslp.eu/files/imglnks/euimg/6/60/IMSL... 55-79 (G3-G5) Midi_1 34-63 (Bb1-Eb4) Midi_1 <NA> <NA>

66 rows × 59 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
Lyric Pieces 66 5414 16496 62431 8236
sum 66 5414 16496 62431 8236 
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 |
|:-------------------|---------:|-----------:|---------:|--------:|---------:|
| grieg_lyric_pieces |       66 |       5414 |    16496 |   62431 |     8236 |
| sum                |       66 |       5414 |    16496 |   62431 |     8236 |

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()

5441 measures over 66 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 volta
corpus piece i
grieg_lyric_pieces op12n01 0 1 1 0 2.0 -3 2/4 1/2 0 <NA> <NA> <NA> <NA> firstMeasure (2,) <NA> <NA> <NA> <NA> <NA>
1 2 2 2 2.0 -3 2/4 1/2 0 <NA> <NA> <NA> <NA> <NA> (3,) <NA> <NA> <NA> <NA> <NA>
2 3 3 4 2.0 -3 2/4 1/2 0 <NA> <NA> <NA> <NA> <NA> (4,) <NA> <NA> <NA> <NA> <NA>
3 4 4 6 2.0 -3 2/4 1/2 0 <NA> <NA> <NA> line <NA> (5,) <NA> <NA> <NA> <NA> <NA>
4 5 5 8 2.0 -3 2/4 1/2 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
grieg_lyric_pieces op12n01 0 1 1 0 2.0 0 0 2/4 2 1 <NA> ... I (M3, P5) (M3, P5) (1, 3, 5) (1, 3, 5), major (1, 3, 5) (1, #3, 5) Eb I I
1 2 2 2 0.5 0 0 2/4 2 1 <NA> ... vii (a2, a5, M6) (P4, d5, d7) (b6, 7, 3, 4) (b6, 7, 3, 4), major (b6, 7, 3, 4) (6, #7, #3, 4) Eb I viio2(4)
2 2 2 5/2 0.5 1/8 1/8 2/4 2 1 <NA> ... vii (a2, a3, M6) (M2, d5, d7) (b6, 7, #1, 4) (b6, 7, #1, 4), major (b6, 7, #1, 4) (6, #7, #1, 4) Eb I viio2(#2)
3 2 2 3 3.0 1/4 1/4 2/4 2 1 <NA> ... vii (a2, a4, M6) (m3, d5, d7) (b6, 7, 2, 4) (b6, 7, 2, 4), major (b6, 7, 2, 4) (6, #7, 2, 4) Eb I viio2
4 4 4 6 0.5 0 0 2/4 2 1 <NA> ... I (M3, P5) (M3, P5) (1, 3, 5) (1, 3, 5), major (1, 3, 5) (1, #3, 5) Eb I I(9)

5 rows × 52 columns

Concatenated annotation tables contains 8141 rows.
Dataset contains 8141 tokens and 1038 types over 66 documents.