def roc_decision_rule(decision_rate, thr, decision_threshold):
"""
cf :
- https://openclassrooms.com/fr/courses/4297211-evaluez-les-performances-dun-modele-de-machine-learning/
4308261-evaluez-un-algorithme-de-classification-qui-retourne-des-scores
"""
idx = np.min(np.where(decision_rate > decision_threshold))
threshold = thr[idx]
return threshold, idx
def scree_plot(self,
threshold=None,
save_as_img=False): # (% Explained Variance)
"""
"""
scree = self.evr * 100
plt.bar(np.arange(len(scree)) + 1, scree)
if threshold is not None:
scree_freq = scree / scree.sum()
scree_cumsum = np.cumsum(scree_freq)
# Number of features needed for threshold cumulative importance
n_features = np.min(np.where(scree_cumsum > threshold)) + 1
threshold_percentage = 100 * threshold
threshold_legend = '{} features required for {:.0f}% of inertia.'.format(
n_features, threshold_percentage)
# Threshold vertical line plot
plt.vlines(n_features,
ymin=0,
ymax=threshold_percentage,
linestyles='--',
colors='red')
plt.plot(np.arange(len(scree)) + 1,
scree.cumsum(),
c="red",
marker='o',
label=threshold_legend)
plt.legend(loc='lower right', fontsize=12)
else:
plt.plot(np.arange(len(scree)) + 1,
scree.cumsum(),
c="red",
marker='o')
plt.xlabel("Inertia axis rank", labelpad=20)
plt.ylabel("Inertia (%)", labelpad=20)
plt.title("Scree plot" +
"\n(Kaiser criterion = {} : Elbow criterion = {})".format(
self.kaiser_criterion(),
elbow_criterion(total_inertia=self.evr)),
pad=20)
if save_as_img:
plt.tight_layout()
plt.savefig('scree.jpg')
plt.show(block=False)
def elbow_criterion(total_inertia, threshold=0.25):
"""
Find total components/clusters number based on Elbow criterion :
(cf : https://en.wikipedia.org/wiki/Elbow_method_(clustering))
"""
features_nb = len(total_inertia)
var_cumsum = total_inertia.cumsum()
# Compute variations ratio from cumulated explained variance values
variations = [
abs(percentage_change(var_cumsum[i + 1], x))
for i, x in enumerate(var_cumsum) if i + 1 < features_nb
]
# Get total components selected
if threshold is 'min':
n_selected = variations.index(min(variations)) + 1
elif type(threshold) is float:
variations = np.array(variations)
n_selected = np.min(
np.where(variations <= np.quantile(variations, q=threshold))) + 1
return n_selected