def classify_separated_test_directory():
print(
"\nDo classification with different training directory and test directory"
)
print("\nTraining directory: " + config.get_record_dir())
print("\nTest directory: " + SEPARATED_TEST_RECORD_DIR)
file_contents, labels = input_parser.parse_input_files(
config.get_record_dir(), combine_sc_vectors=True)
test_data, test_labels = input_parser.parse_input_files(
SEPARATED_TEST_RECORD_DIR, combine_sc_vectors=True)
if len(file_contents) != len(test_data):
raise ValueError(
"Different number of input files in training directory and test directory - must be equal"
)
train_index = list(range(0, len(labels)))
test_index = list(range(len(labels), len(labels) + len(test_labels)))
# Append test data to training data
for idx in range(0, len(file_contents)):
training_file_content = file_contents[idx]
test_file_content = test_data[idx]
training_file_content.records.extend(test_file_content.records)
labels.extend(test_labels)
X = ft.extract_preconfigured_features(file_contents)
Y = pd.Series(labels)
Y_test, predictions, accuracy = app_classifier.do_classification(
X, Y, train_index, test_index)
print(classification_report(Y_test, predictions))
def main():
timing.start_measurement()
print("Do combined classification using all input files")
file_contents, labels = input_parser.parse_input_files(
config.get_record_dir(), combine_sc_vectors=True)
X = ft.extract_preconfigured_features(file_contents)
Y = pd.Series(labels)
app_classifier.do_kfold_cross_validation(X, Y)
timing.stop_measurement()
def main():
timing.start_measurement()
print("Do combined classification using all input files")
file_contents, labels = input_parser.parse_input_files(
config.get_record_dir(), combine_sc_vectors=True)
X = ft.extract_preconfigured_features(file_contents)
Y = pd.Series(labels)
_, total_first_acc, total_second_acc, total_third_acc, total_single_accuracies = app_classifier.do_kfold_cross_validation(
X, Y)
total_acc = [total_first_acc, total_second_acc, total_third_acc]
plt.plot(total_acc)
plt.show()
plt.plot(total_single_accuracies)
plt.show()
timing.stop_measurement()
def explorative_classification():
file_contents, label_list = input_parser.parse_input_files(config.get_record_dir(), combine_sc_vectors=False)
results = []
for idx, fc in enumerate(file_contents):
labels = label_list[idx]
print("\nEvaluate ", fc.file_name)
X = [fc]
Y = pd.Series(labels)
total_accuracy = app_classifier.do_kfold_cross_validation(X, Y, verbose=False)
results.append(ClassificationResult(total_accuracy, fc.file_name))
results.sort(key = lambda classificationResult: classificationResult.accuracy, reverse=True)
print("\nSummary for files in " + config.get_record_dir() + ":\n")
for r in results:
print(r)
def explorative_classification():
file_contents, label_list = input_parser.parse_input_files(
config.get_record_dir(), combine_sc_vectors=False)
results = []
results_first = []
results_second = []
results_third = []
single_results = []
# print("file content")
# for idx, fc in enumerate(file_contents):
# print(str(idx) + " " + str(fc.file_name))
# print("labellist")
# print (label_list)
for idx, fc in enumerate(file_contents):
labels = label_list[idx]
print("\nEvaluate ", fc.file_name)
# print("labels")
# print(labels)
X = [fc]
Y = pd.Series(labels)
# print("Y")
# print(Y)
total_accuracy, total_first_acc, total_second_acc, total_third_acc, total_single_accuracies = app_classifier.do_kfold_cross_validation(
X, Y, verbose=True, file_name=fc.file_name[:-4])
results.append(
ClassificationResult(round_float(total_accuracy), fc.file_name))
results_first.append(
ClassificationResult(round_float(total_first_acc), fc.file_name))
results_second.append(
ClassificationResult(round_float(total_second_acc), fc.file_name))
results_third.append(
ClassificationResult(round_float(total_third_acc), fc.file_name))
single_results.append([])
for total_single_accuracy in total_single_accuracies:
single_results[idx].append(
ClassificationResult(round_float(total_single_accuracy),
fc.file_name))
results.sort(
key=lambda classification_result: classification_result.accuracy,
reverse=True)
results_first.sort(
key=lambda classificationResult: classificationResult.accuracy,
reverse=True)
results_second.sort(
key=lambda classificationResult: classificationResult.accuracy,
reverse=True)
results_third.sort(
key=lambda classificationResult: classificationResult.accuracy,
reverse=True)
# for single_result in single_results:
# single_result.sort(key=lambda classification_result: classification_result.accuracy, reverse=True)
print("\nSummary for files in " + config.get_record_dir() + ":\n")
for r in results:
print(r)
print("\nSummary of first for files in " + config.get_record_dir() + ":\n")
for r in results_first:
print(r)
print("\nSummary of second for files in " + config.get_record_dir() +
":\n")
for r in results_second:
print(r)
print("\nSummary of third for files in " + config.get_record_dir() + ":\n")
for r in results_third:
print(r)
for single_result in zip(single_results):
if not os.path.exists(config.RECORD_BASE_DIR +
config.get_record_dir() + config.RESULTS_DIR):
os.makedirs(config.RECORD_BASE_DIR + config.get_record_dir() +
config.RESULTS_DIR)
# print("\nSummary of for files in " + config.get_record_dir() + ":\n")
for r_1 in single_result:
file = open(
config.RECORD_BASE_DIR + config.get_record_dir() +
config.RESULTS_DIR + r_1[0].file_name, "w")
for idx, r in enumerate(r_1):
file.write(str(idx + 1) + ", " + str(r.accuracy) + "\n")
file.close()