import common
from dbispipeline.evaluators import FixedSplitEvaluator
from dbispipeline.evaluators import ModelCallbackWrapper
import dbispipeline.result_handlers as result_handlers
from dbispipeline.utils import prefix_path
from loaders.melspectrograms import MelSpectrogramsLoader
from models.crnn import CRNNModel
from sklearn.pipeline import Pipeline
WINDOW_SIZE = 1366
dataloader = MelSpectrogramsLoader(
data_path=prefix_path("melspec_data", common.DEFAULT_PATH),
training_path=prefix_path("autotagging_moodtheme-train.tsv",
common.DEFAULT_PATH),
test_path=prefix_path("autotagging_moodtheme-test.tsv",
common.DEFAULT_PATH),
validate_path=prefix_path("autotagging_moodtheme-validation.tsv",
common.DEFAULT_PATH),
window_size=WINDOW_SIZE,
window='random',
num_windows=5,
)
pipeline = Pipeline([
("model", CRNNModel(epochs=32, dataloader=dataloader, attention=True)),
])
evaluator = ModelCallbackWrapper(
FixedSplitEvaluator(**common.fixed_split_params()),
lambda model: common.store_prediction(model, dataloader),
import common
from dbispipeline.evaluators import FixedSplitEvaluator
from dbispipeline.evaluators import ModelCallbackWrapper
import dbispipeline.result_handlers as result_handlers
from dbispipeline.utils import prefix_path
from loaders.combined import CombinedLoader
from models.crnn import CRNNPlusModel
from sklearn.pipeline import Pipeline
dataloader = CombinedLoader(
mel_data_path=prefix_path("melspec_data", common.DEFAULT_PATH),
mel_training_path=prefix_path("autotagging_moodtheme-train.tsv",
common.DEFAULT_PATH),
mel_test_path=prefix_path("autotagging_moodtheme-test.tsv",
common.DEFAULT_PATH),
mel_validate_path=prefix_path("autotagging_moodtheme-validation.tsv",
common.DEFAULT_PATH),
ess_training_path=prefix_path("accousticbrainz-train.pickle",
common.DEFAULT_PATH),
ess_test_path=prefix_path("accousticbrainz-test.pickle",
common.DEFAULT_PATH),
ess_validate_path=prefix_path("accousticbrainz-validation.pickle",
common.DEFAULT_PATH),
window='random',
num_windows=5,
)
pipeline = Pipeline([
("model", CRNNPlusModel(epochs=48, dataloader=dataloader, attention=True)),
])
import common
from dbispipeline.evaluators import FixedSplitGridEvaluator
import dbispipeline.result_handlers as result_handlers
from dbispipeline.utils import prefix_path
from loaders.librosa_features import LibRosaLoader
from sklearn.neighbors import KNeighborsClassifier
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
dataloader = LibRosaLoader(
prefix_path("autotagging_moodtheme-train-librosa.pickle",
common.DEFAULT_PATH),
prefix_path("autotagging_moodtheme-test-librosa.pickle",
common.DEFAULT_PATH),
)
pipeline = Pipeline([("scaler", StandardScaler()),
("model", KNeighborsClassifier())])
evaluator = FixedSplitGridEvaluator(
params={
"model__n_neighbors": [1, 3, 5, 10],
},
grid_params=common.grid_params(),
)
result_handlers = [
result_handlers.print_gridsearch_results,
]
'tonal.chords_key',
'tonal.chords_scale',
'tonal.key_scale',
'tonal.key_key',
]
for c in string_columns:
dummies = pd.get_dummies(df[c], prefix=c, drop_first=False)
df = pd.concat([df.drop(c, axis=1), dummies], axis=1)
# Save dataframe.
pickle.dump(df, open(target_file, "wb"))
if __name__ == "__main__":
create_dataset(
prefix_path("autotagging_moodtheme-train.tsv", common.DEFAULT_PATH),
prefix_path("acousticbrainz_data", common.DEFAULT_PATH),
prefix_path("accousticbrainz-train.pickle", common.DEFAULT_PATH),
)
create_dataset(
prefix_path("autotagging_moodtheme-test.tsv", common.DEFAULT_PATH),
prefix_path("acousticbrainz_data", common.DEFAULT_PATH),
prefix_path("accousticbrainz-test.pickle", common.DEFAULT_PATH),
)
create_dataset(
prefix_path("autotagging_moodtheme-validation.tsv",
common.DEFAULT_PATH),
prefix_path("acousticbrainz_data", common.DEFAULT_PATH),
prefix_path("accousticbrainz-validation.pickle", common.DEFAULT_PATH),
)
import common
from dbispipeline.evaluators import FixedSplitGridEvaluator
import dbispipeline.result_handlers as result_handlers
from dbispipeline.utils import prefix_path
from loaders.acousticbrainz import AcousticBrainzLoader
from sklearn.multioutput import MultiOutputClassifier
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
dataloader = AcousticBrainzLoader(
training_path=prefix_path("accousticbrainz-train.pickle",
common.DEFAULT_PATH),
test_path=prefix_path("accousticbrainz-test.pickle", common.DEFAULT_PATH),
validation_path=prefix_path("accousticbrainz-validation.pickle",
common.DEFAULT_PATH),
)
pipeline = Pipeline([
("scaler", StandardScaler()),
("model", MultiOutputClassifier(SVC(probability=True))),
])
evaluator = FixedSplitGridEvaluator(
params={"model__estimator__C": [0.1, 1.0, 10.0]},
grid_params=common.grid_params(),
)
result_handlers = [
result_handlers.print_gridsearch_results,
]
# Create a data set using features extracted by librosa.
import multiprocessing
from os import path
import pickle
import common
from dbispipeline.utils import prefix_path
import librosa
import numpy as np
import pandas as pd
DATA_PATH = prefix_path("audio_data", common.DEFAULT_PATH)
def extract_features(song_path):
# Load song.
song, sr = librosa.load(song_path)
# Extract BPM.
bpm, _ = librosa.beat.beat_track(y=song, sr=sr)
# Extract zero-crossing rate.
zcr = sum(librosa.zero_crossings(y=song)) / len(song)
# Extract spectral centroid.
spec_centroid = np.mean(
librosa.feature.spectral_centroid(y=song, sr=sr)[0])
spec_centroid_stddev = np.std(
librosa.feature.spectral_centroid(y=song, sr=sr)[0])
# Extract spectral rolloff.
