def plot_learning_curve(model,
x_train,
y_train,
train_sizes_ratio=np.linspace(0.1, 1.0, 10),
k=10,
scorer=None):
"""
:param model:
:param x_train:
:param y_train:
:param train_sizes_ratio:
:param k:
:param scorer:
:return:
"""
N, train_score, val_score = learning_curve(model,
x_train,
y_train,
train_sizes=train_sizes_ratio,
cv=k,
scoring=scorer)
learning_curve_data = {'train': train_score, 'test': val_score}
for legend, scores in learning_curve_data.items():
plt.plot(N, np.abs(scores.mean(axis=1)), label=legend)
plt.xlabel('train_sizes', labelpad=20)
plt.legend()
plt.show()
def plot_training_curve(self, xticks_step=5):
evolution = pd.DataFrame({
'Generation': self.log.select("gen"),
'Max Accuracy': self.log.select("max"),
'Average Accuracy': self.log.select("avg"),
'Min Accuracy': self.log.select("min")
})
plt.title('Hyperparameter Optimisation')
plt.plot(evolution['Generation'],
evolution['Min Accuracy'],
'b',
color='C1',
label='Min')
plt.plot(evolution['Generation'],
evolution['Average Accuracy'],
'b',
color='C2',
label='Average')
plt.plot(evolution['Generation'],
evolution['Max Accuracy'],
'b',
color='C3',
label='Max')
plt.legend(loc='lower right')
plt.ylabel('Accuracy')
plt.xlabel('Generation')
plt.xticks(
[x for x in range(0, self.number_of_generations + 1, xticks_step)])
plt.show()
def plot_validation_curve(model,
x_train,
y_train,
h_param,
h_range,
k=10,
log_scale=False,
scorer=None):
train_score, val_score = validation_curve(model,
x_train,
y_train,
h_param,
h_range,
cv=k,
scoring=scorer)
validation_curve_data = {'train': train_score, 'test': val_score}
for legend, scores in validation_curve_data.items():
if log_scale:
plt.semilogx(h_range, np.abs(scores.mean(axis=1)), label=legend)
else:
plt.plot(h_range, np.abs(scores.mean(axis=1)), label=legend)
plt.xlabel(h_param, labelpad=20)
plt.ylabel('score', labelpad=20)
plt.legend()
plt.show()
def plot_confusion_matrix(cm, class_names):
"""
Returns a matplotlib figure containing the plotted confusion matrix.
Args:
cm (array, shape = [n, n]): a confusion matrix of integer classes
class_names (array, shape = [n]): String names of the integer classes
"""
size = len(class_names)
figure = plt.figure(figsize=(size, size))
plt.imshow(cm, interpolation='nearest', cmap=plt.cm.Blues)
plt.title("Confusion matrix")
plt.colorbar()
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names, rotation=45)
plt.yticks(tick_marks, class_names)
# Compute the labels from the normalized confusion matrix.
labels = np.around(cm.astype('float') / cm.sum(axis=1)[:, np.newaxis],
decimals=2)
# Use white text if squares are dark; otherwise black.
threshold = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
color = "white" if cm[i, j] > threshold else "black"
plt.text(j, i, labels[i, j], horizontalalignment="center", color=color)
plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')
return figure
def plot_regularization_path(alphas,
coefs,
features_labels,
n_features_labels=None,
legend_size='medium'):
"""
:param alphas:
:param coefs:
:param features_labels:
:param n_features_labels:
:param legend_size:
:return:
"""
plt.figure(figsize=(12, 6))
ax = plt.gca()
ax.plot(alphas, coefs)
ax.set_xscale('log')
plt.xlabel('Alpha')
plt.ylabel('Coefficients')
plt.legend(features_labels[:n_features_labels]
if n_features_labels is not None else features_labels,
loc='upper right',
fontsize=legend_size)
plt.show()
def plot_dendrogram(self, plot_size=(10, 25), title_pad=20, xlabel_pad=20, orient='left', leaf_text_size=16,
save_as_img=False, filename='cah', file_type='jpg'):
plt.figure(figsize=plot_size)
plt.title('Hierarchical Clustering Dendrogram', pad=title_pad)
plt.xlabel('distance', labelpad=xlabel_pad)
self.dendrogram_data = dendrogram(self.Z,
labels=self.categories,
orientation=orient,
leaf_font_size=leaf_text_size)
if save_as_img:
plt.tight_layout()
plt.savefig(f'{filename}.{file_type}')
plt.show()
def plot_lift_curve(y_test,
y_predicted,
curve_color='blue',
font_size=14,
x_lim=(0, 1),
y_lim=(0, 1)):
fpr, tpr, thr = roc_curve(y_test, y_predicted)
percentage_sample = [(n + 1) / len(tpr) for n in range(len(tpr))]
plt.plot(fpr, percentage_sample, color=curve_color, lw=2)
plt.xlim(x_lim)
plt.ylim(y_lim)
plt.xlabel('Percentage of sample', fontsize=font_size)
plt.ylabel('Recall (TPR)', fontsize=font_size)
plt.title('LIFT curve')
def plot_training_curve(history,
value_type='accuracy',
fine_tuning=False,
initial_epochs=None):
"""
https://machinelearningmastery.com/diagnose-overfitting-underfitting-lstm-models/
"""
plt.plot(history.history[value_type])
plt.plot(history.history[f'val_{value_type}'])
if fine_tuning:
plt.plot([initial_epochs - 1, initial_epochs - 1],
plt.ylim(),
label='Start Fine Tuning')
plt.title('Training curve')
plt.ylabel(value_type.capitalize())
plt.xlabel('Epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
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 scree_plot(self,
pair_comp=False,
save_as_img=False): # (% Explained Variance)
scree = self.pca.explained_variance_ratio_ * 100
plt.bar(np.arange(len(scree)) + 1, scree)
plt.plot(np.arange(len(scree)) + 1,
scree.cumsum(),
c="red",
marker='o')
plt.xlabel("rang de l'axe d'inertie", labelpad=20)
plt.ylabel("pourcentage d'inertie", labelpad=20)
plt.title("Eboulis des valeurs propres" +
"\n(Kaiser criterion = {} : Elbow criterion = {})".format(
self.kaiser_criterion(pair_comp),
self.elbow_criterion(pair_comp)),
pad=20)
if save_as_img:
plt.tight_layout()
plt.savefig('scree.jpg')
plt.show(block=False)
def plot_roc_curve(y_test,
y_predicted,
curve_color='coral',
font_size=14,
x_lim=(0, 1),
y_lim=(0, 1)):
"""
cf :
- https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_curve.html
"""
fpr, tpr, thr = roc_curve(y_test, y_predicted)
auroc = auc(fpr, tpr)
plt.plot(fpr, tpr, label=f'AUROC : {auroc:.2f}', color=curve_color, lw=2)
# Random classifier line plot
plt.plot([0, 1], [0, 1], linestyle='--')
plt.xlim(x_lim)
plt.ylim(y_lim)
plt.xlabel('1 - specificity (FPR)', fontsize=font_size)
plt.ylabel('Recall (TPR)', fontsize=font_size)
plt.title('Receiver operating characteristic')
plt.legend(loc="lower right")
def plot_correlation_circle(self,
n_plan=None,
labels=None,
label_rotation=0,
lims=None,
save_as_img=False,
plot_size=(10, 8)):
"""
"""
factorial_plan_nb = self.default_factorial_plan_nb if n_plan is None else n_plan
# Build a list of tuples (example : [(0, 1), (2, 3), ... ])
axis_ranks = [(x, x + 1) for x in range(0, factorial_plan_nb, 2)]
pcs = self.pca.components_
for d1, d2 in axis_ranks:
if d2 < self.n_comp:
fig, ax = plt.subplots(figsize=plot_size)
# Fix factorial plan limits
if lims is not None:
xmin, xmax, ymin, ymax = lims
elif pcs.shape[1] < 30:
xmin, xmax, ymin, ymax = -1, 1, -1, 1
else:
xmin, xmax, ymin, ymax = min(pcs[d1, :]), max(
pcs[d1, :]), min(pcs[d2, :]), max(pcs[d2, :])
# affichage des flèches
# s'il y a plus de 30 flèches, on n'affiche pas le triangle à leur extrémité
if pcs.shape[1] < 30:
plt.quiver(np.zeros(pcs.shape[1]),
np.zeros(pcs.shape[1]),
pcs[d1, :],
pcs[d2, :],
angles='xy',
scale_units='xy',
scale=1,
color="grey")
# (doc : https://matplotlib.org/api/_as_gen/matplotlib.pyplot.quiver.html)
else:
lines = [[[0, 0], [x, y]] for x, y in pcs[[d1, d2]].T]
ax.add_collection(
LineCollection(lines, axes=ax, alpha=.1,
color='black'))
# Display variables labels
if labels is not None:
for i, (x, y) in enumerate(pcs[[d1, d2]].T):
if xmin <= x <= xmax and ymin <= y <= ymax:
plt.text(x,
y,
labels[i],
fontsize='14',
ha='center',
va='center',
rotation=label_rotation,
color="blue",
alpha=0.5) # fontsize : 14
# Plot circle
circle = plt.Circle((0, 0), 1, facecolor='none', edgecolor='b')
plt.gca().add_artist(circle)
# définition des limites du graphique
plt.xlim(xmin, xmax)
plt.ylim(ymin, ymax)
# affichage des lignes horizontales et verticales
plt.plot([-1, 1], [0, 0], color='grey', ls='--')
plt.plot([0, 0], [-1, 1], color='grey', ls='--')
# Axes labels with % explained variance
plt.xlabel('F{} ({}%)'.format(d1 + 1,
round(100 * self.evr[d1], 1)),
labelpad=20)
plt.ylabel('F{} ({}%)'.format(d2 + 1,
round(100 * self.evr[d2], 1)),
labelpad=20)
plt.title("Cercle des corrélations (F{} et F{})".format(
d1 + 1, d2 + 1),
pad=20)
if save_as_img:
plt.tight_layout()
plt.savefig(
'corr_circle_{}.jpg'.format(1 if d1 == 0 else d1))
plt.show(block=False)
def plot_factorial_planes(self,
n_plan=None,
X_projected=None,
labels=None,
alpha=1,
illustrative_var=None,
illustrative_var_title=None,
save_as_img=False,
plot_size=(10, 8)):
"""
:param: axis_nb: the total number of axes to display (default is kaiser criterion divided by 2)
"""
X_projected = self.X_projected if X_projected is None else X_projected
factorial_plan_nb = self.default_factorial_plan_nb if n_plan is None else n_plan
axis_ranks = [(x, x + 1) for x in range(0, factorial_plan_nb, 2)]
for d1, d2 in axis_ranks:
if d2 < self.n_comp:
fig = plt.figure(figsize=plot_size)
# Display data points
if illustrative_var is None:
plt.scatter(X_projected[:, d1],
X_projected[:, d2],
alpha=alpha)
else:
illustrative_var = np.array(illustrative_var)
for value in np.unique(illustrative_var):
selected = np.where(illustrative_var == value)
plt.scatter(X_projected[selected, d1],
X_projected[selected, d2],
alpha=alpha,
label=value)
plt.legend(title=illustrative_var_title
if illustrative_var_title is not None else None)
# Display data points labels
if labels is not None:
for i, (x, y) in enumerate(X_projected[:, [d1, d2]]):
plt.text(x,
y,
labels[i],
fontsize='12',
ha='center',
va='bottom')
# Fix factorial plan limits
boundary = np.max(np.abs(X_projected[:, [d1, d2]])) * 1.1
plt.xlim([-boundary, boundary])
plt.ylim([-boundary, boundary])
# Display horizontal & vertical lines
plt.plot([-100, 100], [0, 0], color='grey', ls='--')
plt.plot([0, 0], [-100, 100], color='grey', ls='--')
# Axes labels with % explained variance
plt.xlabel('F{} ({}%)'.format(d1 + 1,
round(100 * self.evr[d1], 1)),
labelpad=20)
plt.ylabel('F{} ({}%)'.format(d2 + 1,
round(100 * self.evr[d2], 1)),
labelpad=20)
plt.title("Projection des individus (sur F{} et F{})".format(
d1 + 1, d2 + 1),
pad=20)
if save_as_img:
plt.tight_layout()
plt.savefig(
'factorial_plan_{}.jpg'.format(1 if d1 == 0 else d1))
plt.show(block=False)
