name_train = np.genfromtxt(ivec.get_name_path(None), dtype=str)
I_test = F.MmapData(path=ivec.get_i_path(name='test'), read_only=True)
F_test = F.MmapData(path=ivec.get_f_path(name='test'), read_only=True)
name_test = np.genfromtxt(ivec.get_name_path(name='test'), dtype=str)
# ===========================================================================
# I-vector
# ===========================================================================
X_train = I_train
X_test = I_test
# ====== cosine scoring ====== #
print(ctext("==== '%s'" % "Ivec cosine-scoring", 'cyan'))
scorer = ml.Scorer(centering=True, wccn=True, lda=True, method='cosine')
scorer.fit(X=X_train, y=y_train)
scorer.evaluate(X_test, y_test, labels=labels)
# ====== plda scoring ====== #
print(ctext("==== '%s'" % "Ivec PLDA-scoring", 'cyan'))
scorer = ml.PLDA(n_phi=100,
n_iter=12,
centering=True,
wccn=True,
unit_length=True,
random_state=1234)
scorer.fit(X=X_train, y=y_train)
scorer.evaluate(X_test, y_test, labels=labels)
# ====== svm scoring ====== #
print(ctext("==== '%s'" % "Ivec SVM-scoring", 'cyan'))
scorer = ml.Scorer(wccn=True, lda=True, method='svm')
scorer.fit(X=X_train, y=y_train)
scorer.evaluate(X_test, y_test, labels=labels)
# ====== GMM scoring ====== #
print(ctext("==== '%s'" % "Ivec GMM-scoring-all", 'cyan'))
scorer = ml.GMMclassifier(strategy="all",
covariance_type='full',
centering=True,
wccn=True,
unit_length=True,
lda=False,
concat=False)
scorer.fit(X=X_train, y=y_true['train'])
scorer.evaluate(X_test, y_true['test'], labels=labels)
# ====== plda scoring ====== #
print(ctext("==== '%s'" % "Ivec PLDA-scoring", 'cyan'))
scorer = ml.PLDA(n_phi=TV_DIM // 2,
n_iter=12,
centering=True,
wccn=True,
unit_length=True,
random_state=5218)
scorer.fit(X=X_train, y=y_true['train'])
scorer.evaluate(X_test, y_true['test'], labels=labels)
# ====== svm scoring ====== #
print(ctext("==== '%s'" % "Ivec SVM-scoring", 'cyan'))
scorer = ml.Scorer(wccn=True, lda=True, method='svm')
scorer.fit(X=X_train, y=y_true['train'])
scorer.evaluate(X_test, y_true['test'], labels=labels)
# ===========================================================================
# Super-vector
# ===========================================================================
X_train = stats['train'][1]
X_test = stats['test'][1]
X_train, X_test = ml.fast_pca(X_train,
def compare_methods(X, y, dim, title, n_iter='auto', verbose=0, plda=False):
print(title, ':', dim)
#
pca = PCA(n_components=dim, random_state=random_state)
pca.fit(X)
X_pca = pca.transform(X)
#
if plda:
plda = ml.PLDA(n_phi=dim, verbose=verbose)
plda.fit(X=X_iris, y=y_iris)
X_plda = plda.transform(X_iris)
n_col = 5
else:
plda = None
X_plda = None
n_col = 4
#
ppca = ml.PPCA(n_components=dim,
verbose=verbose,
n_iter=n_iter,
random_state=random_state)
ppca.fit(X)
X_ppca = ppca.transform(X)
#
sppca1 = ml.SupervisedPPCA(n_components=dim,
verbose=verbose,
extractor='supervised',
n_iter=n_iter,
random_state=random_state)
sppca1.fit(X, y)
X_sppca1 = sppca1.transform(X)
#
sppca2 = ml.SupervisedPPCA(n_components=dim,
verbose=verbose,
extractor='unsupervised',
n_iter=n_iter,
random_state=random_state)
sppca2.fit(X, y)
X_sppca2 = sppca2.transform(X)
# T-SNE if necessary
if dim > 2:
X_pca = ml.fast_tsne(X_pca, n_components=2)
X_ppca = ml.fast_tsne(X_ppca, n_components=2)
X_sppca1 = ml.fast_tsne(X_sppca1, n_components=2)
X_sppca2 = ml.fast_tsne(X_sppca2, n_components=2)
if X_plda is not None:
X_plda = ml.fast_tsne(X_plda, n_components=2)
# Plotting
V.plot_figure(nrow=4, ncol=18)
plt.subplot(1, n_col, 1)
plt.scatter(x=X_pca[:, 0], y=X_pca[:, 1], c=y, marker='o', alpha=0.5, s=1)
plt.xticks([], [])
plt.yticks([], [])
plt.title("PCA")
plt.subplot(1, n_col, 2)
plt.scatter(x=X_ppca[:, 0],
y=X_ppca[:, 1],
c=y,
marker='o',
alpha=0.5,
s=1)
plt.xticks([], [])
plt.yticks([], [])
plt.title("PPCA")
plt.subplot(1, n_col, 3)
plt.scatter(x=X_sppca1[:, 0],
y=X_sppca1[:, 1],
c=y,
marker='o',
alpha=0.5,
s=1)
plt.xticks([], [])
plt.yticks([], [])
plt.title("S-PPCA (supervised extractor)")
plt.subplot(1, n_col, 4)
plt.scatter(x=X_sppca2[:, 0],
y=X_sppca2[:, 1],
c=y,
marker='o',
alpha=0.5,
s=1)
plt.xticks([], [])
plt.yticks([], [])
plt.title("S-PPCA (unsupervised extractor")
if plda is not None:
plt.subplot(1, n_col, 5)
plt.scatter(x=X_plda[:, 0],
y=X_plda[:, 1],
c=y,
marker='o',
alpha=0.5,
s=1)
plt.xticks([], [])
plt.yticks([], [])
plt.title("PLDA")
plt.suptitle('[%d]%s' % (dim, title))