def plot_tnk(mrs):
test_bi_pca_all = data_utils.get_test_transformed('tnk', mrs)
ot = test_bi_pca_all[test_bi_pca_all['label'] == -1]
plt.scatter(ot[['pca_1']], ot[['pca_2']], linewidth=0, c='red', marker='^')
noot = test_bi_pca_all[test_bi_pca_all['label'] != -1]
plt.scatter(noot[['pca_1']],
noot[['pca_2']],
linewidth=0,
c='blue',
marker='X')
def plot_new_points(test_dataset, mrs):
test_bi_pca_all = data_utils.get_test_transformed(test_dataset, mrs)
# see what happened
ot = test_bi_pca_all[test_bi_pca_all['label'] == -1]
plt.scatter(ot[['pca_1']], ot[['pca_2']], s=50, linewidth=0, c='yellow', alpha=1, label='Test outliers')
noot = test_bi_pca_all[test_bi_pca_all['label'] != -1]
plt.scatter(noot[['pca_1']], noot[['pca_2']], s=50, linewidth=0, c='blue', alpha=1, label='Test data points')
legend = plt.legend(loc='upper left')
legend.legendHandles[2]._sizes = [30]
legend.legendHandles[3]._sizes = [40]
def plot_nih(mrs):
test_bi_pca_all = data_utils.get_test_transformed('nih', mrs)
ot = test_bi_pca_all[test_bi_pca_all['label'] == -1]
plt.scatter(ot[['pca_1']],
ot[['pca_2']],
linewidth=0,
c='red',
marker='^',
label='testing outliers')
noot = test_bi_pca_all[test_bi_pca_all['label'] != -1]
plt.scatter(noot[['pca_1']],
noot[['pca_2']],
linewidth=0,
c='blue',
marker='X',
label='testing normal data')
def predict_new_points(test_dataset, clusterer, mrs):
test_bi_pca_all = data_utils.get_test_transformed(test_dataset, mrs)
labels = test_bi_pca_all[['label']]
test_bi_pca = test_bi_pca_all.drop(['label'], axis=1)
# see what happened
ot = test_bi_pca_all[test_bi_pca_all['label'] == -1]
plt.scatter(ot[['pca_1']], ot[['pca_2']], s=50, linewidth=0, c='yellow', alpha=1, label='Test outliers')
noot = test_bi_pca_all[test_bi_pca_all['label'] != -1]
plt.scatter(noot[['pca_1']], noot[['pca_2']], s=50, linewidth=0, c='blue', alpha=1, label='Test data points')
legend = plt.legend(loc='upper left')
legend.legendHandles[2]._sizes = [30]
legend.legendHandles[3]._sizes = [40]
#
test_labels, strengths = hdbscan.approximate_predict(clusterer, test_bi_pca)
test_labels [test_labels > -1] = 0
sensitivity, specificity, accuracy = data_utils.show_performance(labels, test_labels)
return sensitivity, specificity, accuracy
def predict_new_points(bi_df_pca_unique, test_dataset, mrs, cutoff):
test_bi_pca_all = data_utils.get_test_transformed(test_dataset, mrs)
true_labels = test_bi_pca_all[['label']]
test_bi_pca = test_bi_pca_all.drop(['label'], axis=1)
train_bi_pca = bi_df_pca_unique.drop(['label'], axis=1)
# see what happened
ot = test_bi_pca_all[test_bi_pca_all['label'] == -1]
plt.scatter(ot[['pca_1']],
ot[['pca_2']],
s=50,
linewidth=0,
c='yellow',
alpha=1,
label='Test outliers')
noot = test_bi_pca_all[test_bi_pca_all['label'] != -1]
plt.scatter(noot[['pca_1']],
noot[['pca_2']],
s=50,
linewidth=0,
c='blue',
alpha=1,
label='Test data points')
legend = plt.legend(loc='upper left')
legend.legendHandles[2]._sizes = [30]
legend.legendHandles[3]._sizes = [40]
#
clf_predict = LocalOutlierFactor(n_neighbors=k_neighbors,
contamination=outliers_fraction,
novelty=True)
clf_predict.fit(train_bi_pca)
outlier_scores = -clf_predict.score_samples(test_bi_pca)
test_labels = (outlier_scores > cutoff).astype(int) * -1
sensitivity, specificity, accuracy = data_utils.show_performance(
true_labels, test_labels)
return sensitivity, specificity, accuracy