predicted_data_test = model.predict(processed_data_test)
precision, recall, f_score, support = precision_recall_fscore_support(
target_test, predicted_data_test, average='macro')
report_confusion_matrix = ConfusionMatrix(
actual_vector=target_test.to_list(),
predict_vector=predicted_data_test)
draw_conf_matrix(
report_confusion_matrix,
ALGORITHM_LABELS[algorithm_id],
fold_iteration,
)
positions = report_confusion_matrix.position()
precisions = []
recalls = []
f1_scores = []
accuracies = []
report_text = ""
for classname in report_confusion_matrix.classes:
tp = len(positions[classname]["TP"])
tn = len(positions[classname]["TN"])
fp = len(positions[classname]["FP"])
fn = len(positions[classname]["FN"])
temp_recall = divide(tp, tp + fn)
temp_precision = divide(tp, tp + fp)
def generate_and_save_report(
y_pred: list,
y_true: list,
corpus_name: str,
algorithm_name: str,
fold: int,
) -> None:
report = DataFrame(
classification_report(
y_pred,
y_true,
zero_division=0,
output_dict=True,
))
# Save laporan ke Excel
report.to_excel("./reports/{}-{}-fold-{}.xlsx".format(
corpus_name, algorithm_name, fold))
# Buat plot Confusion Matrix untuk masing-masing kelas pengelompokan
confusion_matrix = ConfusionMatrix(
actual_vector=y_true,
predict_vector=y_pred,
)
confusion_matrix_positions = DataFrame(confusion_matrix.position())
confusion_matrix_positions = confusion_matrix_positions.applymap(
lambda positions: len(positions))
pos_classes = confusion_matrix.classes
pos_classes.sort()
report_text = ""
for pos_class in pos_classes:
tp = confusion_matrix_positions[pos_class]["TP"]
tn = confusion_matrix_positions[pos_class]["TN"]
fp = confusion_matrix_positions[pos_class]["FP"]
fn = confusion_matrix_positions[pos_class]["FN"]
accuracy = tp + tn / (tp + tn + fp + fn)
report_text += get_pos_class_report_text(algorithm_name, report,
pos_class, tp, tn, fp, fn,
accuracy)
# Simpan teks laporan
with open(
"./reports/{}-{}-fold-{}.txt".format(corpus_name, algorithm_name,
fold_counter),
"w") as report_filehandle:
report_filehandle.write(report_text)
confusion_matrix_df = DataFrame(confusion_matrix.to_array())
row_sums = confusion_matrix_df.sum().to_list()
y_labels = pos_classes
x_labels = [
"{} ({})".format(label, row_sums[index])
for index, label in enumerate(pos_classes)
]
temp_df = confusion_matrix_df.T
shape = temp_df.shape
annotations = [[
f'''{pos_classes[col]}\n{pos_classes[row]}\n{temp_df[row][col]}'''
for col in range(0, shape[0])
] for row in range(0, shape[1])]
confusion_matrix_heatmap = sns.heatmap(
confusion_matrix_df,
annot=annotations,
xticklabels=x_labels,
yticklabels=y_labels,
cmap="Greens",
linewidths=0.1,
linecolor="black",
fmt='',
cbar=False,
)
fig = confusion_matrix_heatmap.get_figure()
fig.savefig("./reports/{}-{}-fold-{}.svg".format(
corpus_name,
algorithm_name,
fold,
),
bbox_inches='tight')
plt.clf()
pass
