def plot_bnn_results():
path1 = "../Data/outputs/pred-bnn-mrna.csv"
path2 = "../Data/outputs/pred-bnn-meth.csv"
path3 = "../Data/outputs/pred-bnn-micro mrna.csv"
annotation_path = "../Data/data/preprocessed_annotation_global.csv"
data1 = pd.read_csv(path1).drop(columns=["Unnamed: 0"])
data2 = pd.read_csv(path2).drop(columns=["Unnamed: 0"])
data3 = pd.read_csv(path3).drop(columns=["Unnamed: 0"])
model = "bnn"
filename = ["mrna", "meth", "micro mrna"]
with open('../Data/outputs/bnn mrna.txt', 'w') as f:
y_pred = np.argmax(data1.values, axis=1)
true_path = "../Data/outputs/true-labels.csv"
target = pd.read_csv(true_path).drop(columns=["Unnamed: 0"])
names = pd.read_csv(annotation_path)["label"].astype('category').cat.categories
cnf_matrix = confusion_matrix(target.drop(0).values, y_pred)
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix, title=model + "-" + filename[0], classes=names)
print(classification_report(target.drop(0), y_pred, ), file=f)
with open('../Data/outputs/bnn meth.txt', 'w') as f:
y_pred = np.argmax(data2.values, axis=1)
true_path = "../Data/outputs/true-labels.csv"
target = pd.read_csv(true_path).drop(columns=["Unnamed: 0"])
names = pd.read_csv(annotation_path)["label"].astype('category').cat.categories
cnf_matrix = confusion_matrix(target.drop(0).values, y_pred)
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix, title=model + "-" + filename[1], classes=names)
print(classification_report(target.drop(0), y_pred, ), file=f)
with open('../Data/outputs/bnn-micro-rna.txt', 'w') as f:
y_pred = np.argmax(data3.values, axis=1)
true_path = "../Data/outputs/true-labels.csv"
target = pd.read_csv(true_path).drop(columns=["Unnamed: 0"])
names = pd.read_csv(annotation_path)["label"].astype('category').cat.categories
cnf_matrix = confusion_matrix(target.drop(0).values, y_pred)
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix, title=model + "-" + filename[2], classes=names)
print(classification_report(target.drop(0), y_pred, ), file=f)
with open('../Data/outputs/bnn comparison.txt', 'w') as f:
y_pred = np.argmax(np.maximum(data1, np.maximum(data2, data3)).values, axis=1)
true_path = "../Data/outputs/true-labels.csv"
target = pd.read_csv(true_path).drop(columns=["Unnamed: 0"])
names = pd.read_csv(annotation_path)["label"].astype('category').cat.categories
cnf_matrix = confusion_matrix(target.drop(0).values, y_pred)
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix, title="comparisonbnn", classes=names)
print(classification_report(target.drop(0), y_pred, ), file=f)
scores = np.append(scores, totalscore)
components = np.append(components, n_components)
##components.append(n_components)
# print("final score : %f" % totalscore)
print("plot")
cnf_matrix = confusion_matrix(
y_test['label'].astype('category').cat.codes, y_pred)
# plt.figure(figsize=(10, 10))
# plot_roc(names.shape[0], y_pred, y_test_bal, names, title)
print()
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix,
title="without-unknown-testset-" + modelname +
"-" + filename,
classes=names2)
with open(
"../Data/outputs/without-unknown-testset-" + modelname + "-" +
filename + ".txt", 'w') as f:
print(classification_report(
y_test['label'].astype('category').cat.codes,
y_pred,
),
file=f)
if modelname == "bnn":
# clf = bnn.BNN(n_components, 20, 5)
# clf.train_step(x_train_transformed, y_train)
tot, correct_predictions, predicted_for_images, new_prediction, probabilities = clf.test_batch(
torch.from_numpy(X_transformed).float(), y2, names, plot=False)
max_constraint = torch.max(constraint, dim=1)
y_pred[(max_prob.values / 3 < 0.9) | (max_constraint.values < 0.25)] = 5
y_true = X['y_true']
#y_true=y_true[max_prob.values.numpy()/3<0.9]
print("plot")
cnf_matrix = confusion_matrix(y_true, y_pred)
# plt.figure(figsize=(10, 10))
# plot_roc(names.shape[0], y_pred, y_test_bal, names, title)
print()
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix,
title="with-unknown-testset-" + modelname +
"-comparison-new",
classes=names)
with open(
"../Data/outputs/with-unknown-testset-" + modelname +
"-comparison-new.txt", 'w') as f:
print(classification_report(
y_true,
y_pred,
), file=f)
path = "../Data/outputs/pred-stomaco-"
for modelname in modelnames:
data = []
for filename in filenames:
X = pd.read_csv(path + modelname + "-" + filename + ".csv")
axis=1)) == labels).sum().item()
print("accuracy: %d %%" % (100 * correct / total))
import pandas as pd
pd.DataFrame(probabilities).to_csv("../Data/outputs/pred-" +
modelname + filename + ".csv")
pd.DataFrame(true_labels).to_csv("../Data/outputs/true-labels.csv")
cnf_matrix = confusion_matrix(true_labels[1:],
np.argmax(probabilities, axis=1))
print()
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix,
title=modelname + filename,
classes=names)
X2 = pd.read_csv("../Data/data/anomalies_preprocessed_Matrix_" +
filename + ".csv",
index_col=False,
header=None)
y2 = pd.read_csv(
"../Data/data/anomalies_preprocessed_annotation_global.csv"
)["label"]
if filename == "mrna":
X2 = pd.DataFrame(X2[X2.std().sort_values(
ascending=False).head(1200).index].values.tolist())
X_transformed = pca.transform(X2)
y_pred = outlier_detector.predict(X_transformed)
plot_outliers(X_transformed, y_pred, X_train_transformed,
true_labels.append(y_test)
print(filename)
print("best parameters")
# print(model.best_params_)
print("Confusion matrix")
#totalscore = accuracy_score(y_test, y_pred)
#print("final score : %f" % totalscore)
cnf_matrix = confusion_matrix(y_test, y_pred)
# plt.figure(figsize=(10, 10))
# plot_roc(names.shape[0], y_pred, y_test_bal, names, title)
print()
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix,
title=modelname + "-" + filename,
classes=names)
print(modelname + filename + " " + str(model.best_params_), file=f)
print(classification_report(
y_test,
y_pred,
), file=f)
names = np.append(names, "unknown")
unknown_index = np.logical_not(
np.logical_or(
predictions[0] == predictions[1],
np.logical_or(predictions[0] == predictions[2],
predictions[1] == predictions[2])))
y_pred[predictions[0] == predictions[1]] = predictions[0][predictions[0] ==
filename + ".csv",
index_col=False,
header=None)
y2 = pd.read_csv(
"../Data/data/anomalies_preprocessed_annotation_global.csv"
)["label"]
if filename == "mrna":
X2 = pd.DataFrame(X2[X2.std().sort_values(
ascending=False).head(1200).index].values.tolist())
X_transformed = pca.transform(X2)
print('Prediction when network is forced to predict')
probabilities, true_labels = clf.test_forced(
X_transformed,
y2.astype('category').cat.codes)
y_pred = np.argmax(probabilities, axis=1)
y_pred[np.max(probabilities, axis=1) < 0.6] = 5
cnf_matrix = confusion_matrix(true_labels[1:],
np.argmax(probabilities, axis=1))
# plt.figure(figsize=(10, 10))
# plot_roc(names.shape[0], y_pred, y_test_bal, names, title)
print()
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix,
title=modelname + "-anomalies-" + filename,
classes=names)
plot_mlp_results()
matrix.sum(2),
matrix.sum(2).sum(1).view(y_pred.shape[0], 1))
max_prob = torch.max(matrix.sum(2), dim=1)
max_constraint = torch.max(constraint, dim=1)
y_pred[(max_prob.values / 3 < 0.9) |
(max_constraint.values < 0.25)] = 5
else:
pathto = "/last_step-notconservative-" + dataset + "-" + modelname
cnf_matrix = confusion_matrix(y_true, y_pred)
print("plot")
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix,
title=pathto + "-confusionmatrix",
classes=names)
with open(outputpath + pathto + "-comparison-new.txt",
'w') as f:
print("total predicted as unknown " + str(
(y_pred.numpy() == 5).sum()),
file=f)
y_true2 = y_true[y_pred.numpy() != 5]
y_pred2 = y_pred[y_pred.numpy() != 5]
if y_pred2.shape[0] != 0:
print(classification_report(
y_true2,
y_pred2,
),
file=f)
else:
print("Total images: ", tot)
print("Predicted for: ", predicted_for_images)
print("Accuracy when predicted: ",
correct_predictions / predicted_for_images)
print("Confusion matrix")
# totalscore = accuracy_score(y_test,new_prediction)
# print("final score : %f" % totalscore)
cnf_matrix = confusion_matrix(y_test, new_prediction)
# plt.figure(figsize=(10, 10))
# plot_roc(names.shape[0], y_pred, y_test_bal, names, title)
print()
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix,
title=modelname + "-" + filename,
classes=names.append(pd.Index(["Unknown"])))
# print(modelname + filename + " " + str(model.best_params_), file=f)
print(classification_report(
y_test,
new_prediction,
), file=f)
X2 = pd.read_csv("../Data/data/anomalies_preprocessed_Matrix_" +
filename + ".csv",
index_col=False,
header=None)
y2 = pd.read_csv(
"../Data/data/anomalies_preprocessed_annotation_global.csv"
)["label"]
def train_and_test(x_train_transformed, y_train, x_test_transformed, y_test,
n_components, names, outputname):
models2 = []
modelnames = ["rotationForest", "mlptree", "mlp", "bnn"]
for modelname in modelnames:
start = time.time()
# train and test bnn
if modelname == "bnn":
clf = BNN(n_components, 20, 5)
clf.train_step(x_train_transformed, y_train)
end = time.time()
tot, correct_predictions, predicted_for_images, new_prediction, probabilities = clf.test_batch(
torch.from_numpy(x_test_transformed).float(),
y_test,
names,
plot=False)
y_pred = new_prediction
maxprob = np.max(probabilities, axis=1)
elif modelname == "mlp":
# train and test mlp
clf = MLP(n_components, 20, 5)
clf.train_step(x_train_transformed, y_train)
end = time.time()
probabilities, true_labels = clf.test_forced(
x_test_transformed, y_test)
y_pred = np.argmax(probabilities, axis=1)
maxprob = np.max(probabilities, axis=1)
y_pred[maxprob < 0.9] = 5
elif modelname == "rotationForest":
# train and test mlp
clf = RotationForest()
clf.train_step(x_train_transformed, y_train)
end = time.time()
probabilities, true_labels = clf.test_forced(
x_test_transformed, y_test)
y_pred = np.argmax(probabilities, axis=1)
maxprob = np.max(probabilities, axis=1)
y_pred[maxprob < 0.9] = 5
elif modelname == "mlptree":
# train and test mlptree
clf = MlpTree(n_components, 20, 5)
clf.train_step(x_train_transformed, y_train)
end = time.time()
maxprob, y_pred, true_labels, probabilities = clf.test_forced(
x_test_transformed, y_test)
y_pred[maxprob < 0.9] = 5
else:
return
# save results
df = pd.DataFrame({
'official_name':
y_test['official_name'].tolist(),
'max_probability':
maxprob.tolist(),
'probabilities':
np.array(probabilities).tolist(),
'y_pred':
y_pred.tolist(),
'y_true':
y_test["label"].astype('category').cat.codes.tolist()
})
print("time computation for " + modelname + "is " + str(end - start))
df.to_csv("../Data/outputs3/pred-" + outputname + "-" + modelname +
"" + ".csv")
PlotInstograms(df, "istogramma" + outputname + "-" + modelname)
# save outliers name
outliers_names = y_test[y_pred == 5]['official_name']
outliers_names.to_csv("../Data/outputs3/outliers-" + outputname + "-" +
modelname + ".csv",
index=False)
# print("final score : %f" % totalscore)
print("plot")
cnf_matrix = confusion_matrix(
y_test['label'].astype('category').cat.codes, y_pred)
# plt.figure(figsize=(10, 10))
# plot_roc(names.shape[0], y_pred, y_test_bal, names, title)
print()
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix,
title="with-unknown-" + outputname + "-" +
modelname + "",
classes=names.append(pd.Index(["Unknown"])))
with open(
"../Data/outputs3/" + outputname + "-" + modelname + "-" +
".txt", 'w') as f:
print(classification_report(
y_test['label'].astype('category').cat.codes,
y_pred,
),
file=f)
models2.append(clf)
return models2, modelnames
def test(x_transformed, y2, models, modelnames, names, outputname):
for clf, modelname in zip(models, modelnames):
if modelname == "bnn":
# test bnn on stomach
tot, correct_predictions, predicted_for_images, new_prediction, probabilities = clf.test_batch(
torch.from_numpy(x_transformed).float(), y2, names, plot=False)
y_pred = new_prediction
maxprob = np.max(probabilities, axis=1)
elif modelname == "mlp":
# test bnn on stomach
probabilities, true_labels = clf.test_forced(x_transformed, y2)
y_pred = np.argmax(probabilities, axis=1)
maxprob = np.max(probabilities, axis=1)
y_pred[maxprob < 0.9] = 5
elif modelname == "rotationForest":
# test bnn on stomach
probabilities, true_labels = clf.test_forced(x_transformed, y2)
y_pred = np.argmax(probabilities, axis=1)
maxprob = np.max(probabilities, axis=1)
y_pred[maxprob < 0.9] = 5
elif modelname == "mlptree":
# test bnn on stomach
maxprob, y_pred, true_labels, probabilities = clf.test_forced(
x_transformed, y2)
y_pred[maxprob < 0.9] = 5
else:
return
# save results
df = pd.DataFrame({
'official_name':
y2['official_name'].tolist(),
'max_probability':
maxprob.tolist(),
'probabilities':
np.array(probabilities).tolist(),
'y_pred':
y_pred.tolist(),
'y_true':
y2["label"].astype('category').cat.codes.tolist()
})
PlotInstograms(df, "istogramma" + outputname + "-" + modelname)
df.to_csv("../Data/outputs3/pred-" + outputname + "-" + modelname +
"" + ".csv")
outliers_names = y2[y_pred == 5]['official_name']
print(outliers_names)
outliers_names.to_csv("../Data/outputs3/outliers-name-" + outputname +
"-" + modelname + "" + ".csv",
index=False)
y_pred = y_pred.astype(np.float)
y_true = y2['label'].astype('category').cat.codes
y_true[y_true != 5] = 0
y_true[y_true == 5] = 1
y_pred[y_pred != 5] = 0
y_pred[y_pred == 5] = 1
cnf_matrix = confusion_matrix(y_true, y_pred)
# plt.figure(figsize=(10, 10))
# plot_roc(names.shape[0], y_pred, y_test_bal, names, title)
print()
np.set_printoptions(precision=2)
# PlotDir non-normalized confusion matrix
plt.figure.Figure(figsize=(10, 10))
plot_confusion_matrix(cnf_matrix,
title="" + outputname + "-" + modelname + "",
classes=["predicted", "unknown"])
with open(
"../Data/outputs3/" + outputname + "-" + modelname + "-" +
".txt", 'w') as f:
print(classification_report(
y2['label'].astype('category').cat.codes,
y_pred,
),
file=f)
