"""lda plan for a random forest classifier model."""
from dbispipeline.evaluators import GridEvaluator
import dbispipeline.result_handlers as result_handlers
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from nlp4musa2020.dataloaders import vectorizer
from nlp4musa2020.dataloaders.alf200k import ALF200KLoader
from nlp4musa2020.dataloaders.alf200k import genre_target_labels
import nlp4musa2020.evaluators as evaluators
dataloader = ALF200KLoader(
path='data/processed/dataset-lfm-genres.pickle',
load_feature_groups=[],
text_vectorizers=vectorizer.lda(),
target=genre_target_labels(),
)
pipeline = Pipeline([
('scaler', StandardScaler()),
('model', RandomForestClassifier(n_jobs=-1)),
])
evaluator = GridEvaluator(
parameters={
'model__n_estimators': [10, 100, 300],
},
grid_parameters=evaluators.grid_parameters_genres(),
)
from sklearn.preprocessing import StandardScaler
from nlp4musa2020.dataloaders.vectorizer import lda, tfidf
from nlp4musa2020.dataloaders.alf200k import ALF200KLoader, genre_target_labels
import nlp4musa2020.evaluators as evaluators
from sklearn.svm import LinearSVC
from sklearn.multioutput import MultiOutputClassifier
dataloader = ALF200KLoader(path='data/processed/dataset-lfm-genres.pickle',
load_feature_groups=[
'rhymes',
'statistical',
'statistical_time',
'explicitness',
],
text_vectorizers=lda() + tfidf(),
target=genre_target_labels())
pipeline = Pipeline([
('scaler', StandardScaler()),
('model', MultiOutputClassifier(LinearSVC())),
])
evaluator = GridEvaluator(
parameters={
'model__estimator__C': [
0.1,
0.5,
1.0,
2.0,
5.0,
"""Plan for a knn model, lda."""
from dbispipeline.evaluators import GridEvaluator
import dbispipeline.result_handlers as result_handlers
from sklearn.neighbors import KNeighborsClassifier
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from nlp4musa2020.dataloaders.alf200k import ALF200KLoader
from nlp4musa2020.dataloaders.vectorizer import lda
import nlp4musa2020.evaluators as evaluators
dataloader = ALF200KLoader(path='data/processed/dataset-lfm-genres.pickle',
load_feature_groups=[],
text_vectorizers=lda(),
target=[
'alternative', 'blues', 'country', 'dance',
'electronic', 'funk', 'hip hop', 'indie',
'jazz', 'metal', 'pop', 'punk', 'rap', 'rnb',
'rock', 'soul'
])
pipeline = Pipeline([
('scaler', StandardScaler()),
('model', KNeighborsClassifier(n_jobs=-1, algorithm='ball_tree')),
])
evaluator = GridEvaluator(
parameters={
'model__n_neighbors': [3, 4, 5, 10],
'model__weights': ['distance'],
'model__p': [1, 2],
from nlp4musa2020.dataloaders import vectorizer
from nlp4musa2020.dataloaders.alf200k import ALF200KLoader
from nlp4musa2020.dataloaders.alf200k import genre_target_labels
import nlp4musa2020.evaluators as evaluators
dataloader = ALF200KLoader(
path='data/processed/dataset-lfm-genres.pickle',
load_feature_groups=[
'rhymes',
'statistical',
'statistical_time',
'explicitness',
'audio',
],
text_vectorizers=vectorizer.lda() + vectorizer.tfidf(),
target=genre_target_labels(),
)
pipeline = Pipeline([
('scaler', StandardScaler()),
('model', ExtraTreesClassifier(n_jobs=-1)),
])
evaluator = GridEvaluator(
parameters={
'model__n_estimators': [10, 100, 300],
},
grid_parameters=evaluators.grid_parameters_genres(),
)
