def plot_num_var_threshold(self,
tmin: float = 0,
tmax: float = 1,
step: float = 0.01):
"""
Plots the number of variables as a function of the threshold defined to drop.
Goes from 'tmin' to 'tmax' on 'step' steps.
:return: --- <class 'NoneType'>
"""
indexes = [0, 1, 2, 3, 4, 5, 6, 7]
plt.figure(figsize=(7, 5))
for i in indexes:
print(i)
vals = self.compute_num_var_threshold(tmin=tmin,
tmax=tmax,
step=step,
idx=i)
pF.single_line_chart(
plt.gca(),
vals[0],
vals[1],
layout=pF.LayoutStyleObject(
title='Number of Variables as a function of the Threshold',
xlabel='Threshold',
ylabel='Number of Variables',
grid=True),
plotstyle=pF.PlotStyleObject(color='Blue',
marker='o',
alpha=0.5))
plt.show()
def plot_gradient_boost(self,
drop: bool = True,
norm: bool = False,
threshold: float = 1):
"""
For the given input, plots the single line chart for Gradient Boost results as a function of max_depths.
:return: --- <class 'NoneType'>
"""
plt.subplots(1, 1, figsize=(16, 4), squeeze=False)
max_depths = [5, 10, 15, 20]
pF.single_line_chart(plt.gca(),
max_depths,
self.compute_gradient_boost(
drop, norm, threshold),
'XGBoost',
'XGBoost',
'Max Depths',
'accuracy',
percentage=True)
plt.show()
def Boost(drop: bool = True, norm: bool = False, threshold: float = 1):
if drop:
full_set = data.compute_data_drop(threshold)
else:
full_set = data.compute_data_average(threshold)
y: np.ndarray = full_set.pop('class').values
if norm:
X: np.ndarray = preprocessing.normalize(full_set.values)
else:
X: np.ndarray = full_set.values
labels = pd.unique(y)
trnX, tstX, trnY, tstY = train_test_split(X, y, train_size=0.7, stratify=y)
max_depths = [5, 10, 15, 20]
fig, axs = plt.subplots(1, 1, figsize=(16, 4), squeeze=False)
values = []
for d in max_depths:
yvalues = []
boost = XGBClassifier(max_depth=d)
boost.fit(trnX, trnY)
prdY = boost.predict(tstX)
yvalues.append(metrics.accuracy_score(tstY, prdY))
values.append(yvalues)
pF.single_line_chart(plt.gca(),
max_depths,
values,
'XGBoost',
'XGBoost',
'Max Depths',
'accuracy',
percentage=True)
plt.show()