labels = pd.unique(y)
trnX, tstX, trnY, tstY = train_test_split(X,
y,
train_size=0.7,
stratify=y)
clf = LogisticRegression(random_state=RANDOM_STATE)
clf.fit(trnX, trnY)
prd_trn = clf.predict(trnX)
prd_tst = clf.predict(tstX)
train_accuracy = metrics.accuracy_score(trnY, prd_trn)
test_accuracy = metrics.accuracy_score(tstY, prd_tst)
text = key
if (do_feature_eng): text += ' with FS'
best_accuracies[text] = [train_accuracy, test_accuracy]
ds.plot_evaluation_results(pd.unique(y), trnY, prd_trn, tstY, prd_tst)
plt.suptitle('QOT Log Regression - ' + key +
' - Performance & Confusion matrix')
plt.savefig(subDir + 'QOT Log Regression - ' + key +
' - Performance & Confusion matrix')
plt.close("all")
plt.figure(figsize=(7, 7))
ds.multiple_bar_chart(['Train', 'Test'], best_accuracies, ylabel='Accuracy')
plt.suptitle('QOT Sampling & Feature Selection')
plt.savefig(graphsDir + 'QOT Sampling & Feature Selection')
d = dist[k]
ds.multiple_line_chart(nvalues,
overfitting_values[d],
ax=axs[0, k],
title='Overfitting for dist = %s' % (d),
xlabel='K Neighbours',
ylabel='accuracy',
percentage=True)
plt.suptitle('QOT Overfitting - KNN')
plt.savefig(subDir + 'QOT Overfitting - KNN')
clf = knn = KNeighborsClassifier(n_neighbors=best[0], metric=best[1])
clf.fit(trnX, trnY)
prd_trn = clf.predict(trnX)
prd_tst = clf.predict(tstX)
ds.plot_evaluation_results(["negative", "positive"], trnY, prd_trn,
tstY, prd_tst)
plt.suptitle('QOT KNN - ' + key +
'- Performance & Confusion matrix - %d neighbors and %s' %
(best[0], best[1]))
plt.savefig(subDir + 'QOT KNN - ' + key +
' - Performance & Confusion matrix')
plt.close("all")
plt.figure(figsize=(7, 7))
ds.multiple_bar_chart(['Train', 'Test'], best_accuracies, ylabel='Accuracy')
plt.suptitle('QOT Sampling & Feature Selection')
plt.savefig(graphsDir + 'QOT Sampling & Feature Selection')
plt.figure(figsize=(7, 7))
ds.multiple_bar_chart(['Train', 'Test'], recalls, ylabel='Recall')
values = {}
for lr in learning_rate:
yvalues = []
for n in n_estimators:
gb.fit(trnX, trnY)
prdY = gb.predict(tstX)
yvalues.append(metrics.accuracy_score(tstY, prdY))
if yvalues[-1] > last_best:
best = (d, lr, n)
last_best = yvalues[-1]
best_tree = gb
values[lr] = yvalues
prd_trn = best_tree.predict(trnX)
prd_tst = best_tree.predict(tstX)
ds.plot_evaluation_results(pd.unique(y), trnY, prd_trn, tstY, prd_tst,
str(samp))
print(str(samp) + ': ' + str(last_best))
'''
UNDERSAMPLING
allknn = AllKNN()
trnX, trnY = allknn.fit_resample(trnX, trnY)
nm = NearMiss()
trnX, trnY = nm.fit_resample(trnX, trnY)
OVERSAMPLING
smt = SMOTE()
trnX, trnY = smt.fit_resample(trnX, trnY)
ada = ADASYN(random_state=42)
trnX, trnY = smt.fit_sample(trnX, trnY)