def multivariate_gaussian(x_train, y_train, x_test, y_test, outdir):
# Score with Multivariate Gaussian
# Transform data using boxcox transform, and fit multivariate gaussians.
x_train_boxcox, x_test_boxcox = mv.transform_features(x_train, x_test)
rv_pos, rv_neg = mv.fit_gaussians(x_train_boxcox, y_train)
# Compute melodiness scores on train and test set
m_train, m_test = mv.compute_all_melodiness(x_train_boxcox, x_test_boxcox,
rv_pos, rv_neg)
# Compute various metrics based on melodiness scores.
melodiness_scores = mv.melodiness_metrics(m_train, m_test, y_train, y_test)
best_thresh, max_fscore, thresh_plot_data = \
eu.get_best_threshold(y_test, m_test) # THIS SHOULD PROBABLY BE VALIDATION NUMBERS...
# thresh_plot_data = pd.DataFrame(np.array(thresh_plot_data).transpose(),
# columns=['recall', 'precision',
# 'thresh', 'f1'])
# fpath = os.path.join(outdir, 'thresh_plot_data.csv')
# thresh_plot_data.to_csv(fpath)
melodiness_scores = pd.DataFrame.from_dict(melodiness_scores)
fpath = os.path.join(outdir, 'melodiness_scores.csv')
melodiness_scores.to_csv(fpath)
print "Melodiness best thresh = %s" % best_thresh
print "Melodiness max f1 score = %s" % max_fscore
print "overall melodiness scores:"
print melodiness_scores
def classifier(x_train, y_train, x_valid, y_valid, x_test, y_test, outdir):
""" Train Classifier
"""
# Cross Validation
best_depth, _, cv_plot_data = cu.cross_val_sweep(x_train, y_train)
print "Classifier best depth = %s" % best_depth
cv_plot_data = pd.DataFrame(np.array(cv_plot_data).transpose(),
columns=['max depth', 'accuracy', 'std'])
fpath = os.path.join(outdir, 'cv_plot_data.csv')
cv_plot_data.to_csv(fpath)
# Training
clf = cu.train_clf(x_train, y_train, best_depth)
# Predict and Score
p_train, p_valid, p_test = cu.clf_predictions(x_train, x_valid, x_test,
clf)
clf_scores = cu.clf_metrics(p_train, p_test, y_train, y_test)
print "Classifier scores:"
print clf_scores
# Get threshold that maximizes F1 score
best_thresh, max_fscore, thresh_plot_data = \
eu.get_best_threshold(y_valid, p_valid)
# thresh_plot_data = pd.DataFrame(np.array(thresh_plot_data).transpose(),
# columns=['recall', 'precision',
# 'thresh', 'f1'])
# fpath = os.path.join(outdir, 'thresh_plot_data.csv')
# thresh_plot_data.to_csv(fpath)
clf_scores = pd.DataFrame.from_dict(clf_scores)
fpath = os.path.join(outdir, 'classifier_scores.csv')
clf_scores.to_csv(fpath)
clf_outdir = os.path.join(outdir, 'classifier')
if not os.path.exists(clf_outdir):
os.mkdir(clf_outdir)
clf_fpath = os.path.join(clf_outdir, 'rf_clf.pkl')
joblib.dump(clf, clf_fpath)
print "Classifier best threshold = %s" % best_thresh
print "Classifier maximum f1 score = %s" % max_fscore
return clf, best_thresh
def train_and_classify(mdb_files, train, test, dset_contour_dict,
dset_annot_dict):
'''
- cross validate best depth of Randon Forest Classifier: cu.cross_val_sweep
- classify all contours and get scikitlearn metrics: cu.clf_predictions
- get threshold with best f-measure on validation dataset get_best_threshold(Y_valid, P_valid) on validation
- classify test contours : contour_probs
- melody decoding: gm.melody_from_cl
labeling should be already done
'''
random.shuffle(train)
n_train = len(train) - (len(test) / 2)
train_tracks = mdb_files[train[:n_train]]
valid_tracks = mdb_files[train[n_train:]]
test_tracks = mdb_files[test]
train_contour_dict = {k: dset_contour_dict[k] for k in train_tracks}
valid_contour_dict = {k: dset_contour_dict[k] for k in valid_tracks}
test_contour_dict = {k: dset_contour_dict[k] for k in test_tracks}
train_annot_dict = {k: dset_annot_dict[k] for k in train_tracks}
valid_annot_dict = {k: dset_annot_dict[k] for k in valid_tracks}
test_annot_dict = {k: dset_annot_dict[k] for k in test_tracks}
reload(eu)
partial_olap_stats, zero_olap_stats = eu.olap_stats(train_contour_dict)
print 'overlapped stats on train data...'
print partial_olap_stats
len(train_contour_dict)
reload(cc)
anyContourDataFrame = dset_contour_dict[dset_contour_dict.keys()[0]]
#### CONVERT PANDAS DATA to DATA for scikit Learn
feats, idxStartFeatures, idxEndFeatures = getFeatureInfo(
anyContourDataFrame)
print 'idxStartFeatures'
print idxStartFeatures
print 'idxEndFeatures'
print idxEndFeatures
X_train, Y_train = cc.pd_to_sklearn(train_contour_dict, idxStartFeatures,
idxEndFeatures)
from numpy import inf
idx = X_train == -inf
X_train[idx] = 0
X_train = np.nan_to_num(X_train)
X_valid, Y_valid = cc.pd_to_sklearn(valid_contour_dict, idxStartFeatures,
idxEndFeatures)
X_valid = np.nan_to_num(X_valid)
X_test, Y_test = cc.pd_to_sklearn(test_contour_dict, idxStartFeatures,
idxEndFeatures)
X_test = np.nan_to_num(X_test)
np.max(X_train, 0)
##################### cross-val of best depth of RFC
reload(cu)
best_depth, max_cv_accuracy, plot_dat = cu.cross_val_sweep(X_train,
Y_train,
plot=False)
print "best depth is {}".format(best_depth)
print "max_cv_accuracy is {}".format(max_cv_accuracy)
df = pd.DataFrame(np.array(plot_dat).transpose(),
columns=['max depth', 'accuracy', 'std'])
##################### 3.2 TRAIN and CLASSIFY
clf = cu.train_clf(X_train, Y_train, best_depth)
reload(cu)
P_train, P_valid, P_test = cu.clf_predictions(X_train, X_valid, X_test,
clf)
clf_scores = cu.clf_metrics(P_train, P_test, Y_train, Y_test)
print clf_scores['test']
#### get threshold with best f-measure on validation dataset
reload(eu)
best_thresh, max_fscore, plot_data = eu.get_best_threshold(
Y_valid, P_valid)
max_fscore = 0.0
print "best threshold = %s" % best_thresh
print "maximum achieved f score = %s" % max_fscore
# classify and add the melody probability for each contour as a field in the dict
for key in test_contour_dict.keys():
test_contour_dict[key] = eu.contour_probs(clf, test_contour_dict[key],
idxStartFeatures,
idxEndFeatures)
################### 3.3. Melody decoding.
##### viterbi decoding
reload(gm)
mel_output_dict = {}
for i, key in enumerate(test_contour_dict.keys()):
print key
mel_output_dict[key] = gm.melody_from_clf(test_contour_dict[key],
prob_thresh=best_thresh)
# mel_output_dict[key] = contours_to_vocal(test_contour_dict[key], prob_thresh=best_thresh)
return mel_output_dict, test_annot_dict, clf, feats
print best_depth
print max_cv_accuracy
df = pd.DataFrame(np.array(plot_dat).transpose(),
columns=['max depth', 'accuracy', 'std'])
clf = cu.train_clf(X_train, Y_train, best_depth)
reload(cu)
P_train, P_valid, P_test = cu.clf_predictions(X_train, X_valid, X_test,
clf)
clf_scores = cu.clf_metrics(P_train, P_test, Y_train, Y_test)
print clf_scores['test']
reload(eu)
best_thresh, max_fscore, plot_data = eu.get_best_threshold(
Y_valid, P_valid)
print "besth threshold = %s" % best_thresh
print "maximum achieved f score = %s" % max_fscore
for key in test_contour_dict.keys():
test_contour_dict[key] = eu.contour_probs(clf,
test_contour_dict[key],
idxStartFeatures,
idxEndFeatures)
reload(gm)
mel_output_dict = {}
for i, key in enumerate(test_contour_dict.keys()):
print key
mel_output_dict[key] = gm.melody_from_clf(test_contour_dict[key],
prob_thresh=best_thresh)