def plot_knn_var_threshold(self,
drop: bool = True,
norm: bool = False,
thresholds: list = None,
n_iter: int = 20,
parity: bool = False,
smote: bool = False):
"""
Plots the knn accuracy as function of n for given thresholds list.
:return: --- <class 'NoneType'>
"""
if thresholds is None:
thresholds = [
0.81, 0.83, 0.85, 0.87, 0.89, 0.91, 0.93, 0.95, 0.97, 0.99
]
else:
thresholds = sorted(thresholds)
if parity:
nvalues = [2 * i + 2 for i in range(round(n_iter / 2))]
else:
nvalues = [2 * i + 1 for i in range(round(n_iter / 2))]
if drop:
x = len(thresholds)
fig, axs = plt.subplots(int(x / 5),
int(x / (x / 5)),
figsize=(15, 6),
squeeze=False)
fig.subplots_adjust(hspace=.5, wspace=.001)
axs = axs.ravel()
for j in range(int(len(thresholds))):
axs[j].set_title('n')
layout = pF.LayoutStyleObject(
title='KNN variants - threshold ' + str(thresholds[j]),
xlabel='n',
ylabel='accuracy',
grid=True)
pF.multiple_line_chart(axs[j],
nvalues,
self.compute_knn(drop,
norm,
thresholds[j],
n_iter,
parity,
smote=smote),
layout=layout,
percentage=True,
legends=True)
fig.tight_layout()
plt.show()
else:
plt.figure()
pF.multiple_line_chart(plt.gca(),
nvalues,
self.compute_knn(drop, norm, thresholds),
title='KNN variants',
xlabel='n',
ylabel='accuracy',
percentage=True)
plt.show()
def plot_forest_features(self,
drop: bool = True,
norm: bool = False,
thresholds: list = None,
idx: int = -1):
"""
Plot the forest features obtained previously.
:return: --- <class 'NoneType'>
"""
if thresholds is None:
thresholds = [1]
else:
thresholds = sorted(thresholds)
max_features = ['sqrt', 'log2']
n_estimators = [5, 10, 25, 50, 75, 100, 150, 200, 250, 300]
thr_len = len(thresholds)
fig, axs = plt.subplots(thr_len, 2, figsize=(10, 4), squeeze=False)
for i in range(thr_len):
aux = self.compute_forest_features(drop, norm, thresholds[i], idx)
for k in range(len(max_features)):
layout = pF.LayoutStyleObject(
title='Random Forests with %s features' % max_features[k] +
'[T=' + str(thresholds[i]) + ']',
xlabel='Number of estimators',
ylabel='Accuracy',
grid=True)
pF.multiple_line_chart(axs[i, k],
n_estimators,
aux[k],
layout=layout,
percentage=True)
plt.show()
def plot_tree_criteria(self,
drop: bool = True,
norm: bool = False,
thresholds: list = None,
idx: int = -1):
"""
For the given thresholds, plots the decision trees criteria, according to 'entropy' and 'gini' criteria.
:return: --- <class 'NoneType'>
"""
if thresholds is None:
thresholds = [1]
else:
thresholds = sorted(thresholds)
criteria = ['entropy', 'gini']
min_samples_leaf = [.10]
thr_len = len(thresholds)
fig, axs = plt.subplots(thr_len, 2, figsize=(10, 4), squeeze=False)
for i in range(thr_len):
for k in range(len(criteria)):
layout = pF.LayoutStyleObject(
title='Decision Trees with %s criteria' % criteria[k] +
'[T=' + str(thresholds[i]) + ']',
xlabel='Number of estimators',
ylabel='Accuracy',
grid=True)
pF.multiple_line_chart(axs[i, k],
min_samples_leaf,
self.compute_tree_criteria(
drop, norm, thresholds[i], idx)[k],
layout=layout,
percentage=True)
plt.show()