def PlotCodeFrequency(codes, labels, save=False, path='', filename='img'):
"""
Plot the frequency of each code on the dataset and also which ones are DI or DP.
- codes (pandas Series, list, numpy array): codes of each sample.
- labels (pandas Series, list, numpy array): labels of each sample.
- save (bool): tells if the plot should be saved.
- path (string): path where to save the figure.
- filename (string): name of the figure image file to be saved.
"""
DI = 0
DP = 1
df = pd.DataFrame()
df['labels'] = labels
df['codes'] = codes
freq_di = dict()
freq_dp = dict()
total = len(df)
N = 0
toPercentage = lambda value, total: (value * 100.0) / total
codigosExistentes = list(df['codes'].unique())
codigosExistentes.sort()
for c in codigosExistentes:
freq_di[c] = toPercentage(
((df['codes'] == c) & (df['labels'] == DI)).sum(), total)
freq_dp[c] = toPercentage(
((df['codes'] == c) & (df['labels'] == DP)).sum(), total)
N += 1
ind = np.arange(N)
width = 0.5
fig = plt.figure(figsize=(11, 5))
dp_bar = plt.bar(ind, list(freq_dp.values()), width, figure=fig)
di_bar = plt.bar(ind,
list(freq_di.values()),
width,
bottom=list(freq_dp.values()),
figure=fig)
minorTicks = MultipleLocator(1)
plt.ylabel('Porcentagem (%)')
plt.xlabel('Códigos')
plt.title('Frequência de cada código no dataset')
plt.xticks(ind, tuple(freq_di.keys()))
plt.yticks(np.arange(0, 25, 5))
plt.axes().yaxis.set_minor_locator(minorTicks)
plt.legend((di_bar[0], dp_bar[0]), ('DI', 'DP'))
plt.grid(True, which='both', axis='y')
plt.show()
if (save):
util.CheckAndCreatePath(path)
util.SaveFigure(fig, path, filename)
def PlotAccuracyOfEachEventCode(codes,
labels,
prediction,
save=False,
path='',
filename='img'):
"""
Plots the model accuracy for each event code.
- codes (pandas Series, list, numpy array): codes of each sample.
- labels (pandas Series, list, numpy array): labels of each sample.
- prediction (pandas Series, list, numpy array): predictions of each sample.
- save (bool): tells if the plot should be saved.
- path (string): path where to save the figure. e.g.: 'images/'
- filename (string): name of the figure image file to be saved.
"""
df = pd.DataFrame()
df['labels'] = labels
df['codes'] = codes
df['prediction'] = prediction
cods = df['codes'].unique()
cods = np.sort(cods)
cods = cods[np.invert(np.isnan(cods))]
cods = cods.astype(int)
toPercentage = lambda value, total: (value * 100.0) / total
accuracy = list()
for cod in cods:
right = ((df['prediction'] == df['labels']) &
(df['codes'] == cod)).sum()
total = (df['codes'] == cod).sum()
percentage = toPercentage(right, total)
accuracy.append(percentage)
# Plotar graficos
fig, ax = plt.subplots(figsize=(11, 5))
xticks = list(range(0, len(cods)))
yticks = list(range(0, 101, 10))
# show the figure, but do not block
plt.bar(xticks, accuracy, figure=fig, align='center', width=0.3)
ax.tick_params(axis='y', gridOn=True)
ax.set_xticks(xticks)
ax.set_xticklabels(cods)
ax.set_yticks(yticks)
ax.set_ylim([0, 100])
ax.set_ylabel('Acurácia (%)')
ax.set_xlabel('Codigo')
ax.set_title('Acurácia do modelo para cada código')
plt.show(block=False)
if (save):
util.CheckAndCreatePath(path)
util.SaveFigure(fig, path, filename)
def PlotFeatureImportanceXGBoost(model, save=False, path='', filename='img'):
"""
Plots the importance of each feature from a XGBoost model.
- model (XGBoost model): model.
- save (bool): tells if the plot should be saved.
- path (string): path where to save the figure.
- filename (string): name of the figure image file to be saved.
"""
fig, ax = plt.subplots(figsize=(6, 7))
xgb.plot_importance(model, ax=ax)
plt.show()
if (save):
util.CheckAndCreatePath(path)
util.SaveFigure(fig, path, filename)
def PlotConfusionMatrix(cm,
cm_confidence_interval,
classes,
normalize=False,
title='Matriz de Confusão',
cmap=plt.cm.Blues,
save=False,
path='',
imgname='matriz_de_confusão'):
"""Gera e mostra a matriz de confusão.
Parameters
----------
cm : numpy.array
Matriz de confusão.
classes : list
Lista com o nome de cada classe dos rótulos. Exemplo: ['DI', 'DP'].
normalize : bool, default False
Se verdadeiro, a matriz de confusão será normalizada.
title : string, default 'Matriz de Confusão'
Título da imagem da matriz de confusão.
cmap : matplotlib.pyplot.cm, default matplotlib.pyplot.cm.Blues
Colormap usado na matriz.
save : bool, default False
Se verdadeiro, a imagem da matriz de confusão será salva.
path : str
Diretório onde a imagem da matriz de confusão será salva.
imgname : str, default 'img'
Nome da imagem da matriz de confusão que será salva.
"""
if normalize:
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
print("Matriz de Confusão Normalizada")
else:
print('Matriz de Confusão, sem normalização')
# formatted confusion matrix
cm_format = np.copy(cm).astype(str)
for i in range(cm.shape[0]):
for j in range(cm.shape[1]):
if normalize:
if cm_confidence_interval is not None:
cm_format[
i,
j] = f'{cm[i,j]:.2f} ' + u"\u00B1" + f' {cm_confidence_interval[i,j]:.4f}'
else:
cm_format[i, j] = f'{cm[i,j]:.2f}'
else:
cm_format[i, j] = f'{cm[i,j]:.0f}'
fig, ax = plt.subplots(figsize=(5, 5))
im = ax.imshow(cm, aspect='equal', interpolation='nearest', cmap=cmap)
plt.title(title)
cbar = ax.figure.colorbar(im, ax=ax, shrink=0.7)
tick_marks = np.arange(len(classes))
ax.set_xticks(tick_marks)
ax.set_yticks(tick_marks)
ax.set_xticklabels(classes)
ax.set_yticklabels(classes)
ax.set_xticks(np.arange(cm.shape[1] + 1) - .5, minor=True)
ax.set_yticks(np.arange(cm.shape[0] + 1) - .5, minor=True)
ax.tick_params(axis='x', rotation=45)
ax.tick_params(axis='both', labelsize=12)
ax.set_xlabel('Classe Prevista', size=12)
ax.set_ylabel('Classe Verdadeira', size=12)
ax.titlesize = 13
thresh = (cm.max() + cm.min()) / 2.
for i in range(cm.shape[0]):
for j in range(cm.shape[1]):
plt.text(j,
i,
cm_format[i, j],
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black",
fontsize=12)
plt.tight_layout()
ax.labelsize = 12
plt.grid(False)
plt.show(block=False)
if (save):
util.CheckAndCreatePath(path)
util.SaveFigure(fig, path, imgname)