def main(argv):
assert len(argv) == 3, " Please provide correct arguments as follows : python bayes.py <train file path> <test file path> <n|t>"
assert(argv[2] == 'n' or argv[2] == 't')
train_dataset_file_path, test_dataset_file_path = argv[0], argv[1]
is_naive_bayes_reqd = True if argv[2] == 'n' else False
logger.debug("Loading the training dataset ..")
train_dataset = file_reader.get_dataset_from_file(train_dataset_file_path)
logger.debug("Loading the test dataset ..")
test_dataset = file_reader.get_dataset_from_file(test_dataset_file_path)
if is_naive_bayes_reqd:
start = time.clock()
logger.debug("Generating the naive bayes model using training dataset ..")
naive_bayes_model = naive_bayes.Naivebayes(train_dataset)
logger.debug("Evaulating the test dataset on Naive Bayes Model ..")
naive_bayes.evaluate_naive_bayes_model(naive_bayes_model, test_dataset)
logger.debug("Time taken for running Naive Bayes Model is " + str(time.clock() - start) + " s ")
else:
start = time.clock()
logger.debug("Generating the TAN model using training dataset ..")
tan_model = tan.TAN(train_dataset)
logger.debug("Evaulating the test dataset on TAN model ..")
tan.evaluate_tan_model(tan_model, test_dataset)
logger.debug("Time taken for running TAN Model is " + str(time.clock() - start) + " s ")
def get_learning_curve_with_number_of_instances():
train_dataset = file_reader.get_dataset_from_file(TRAIN_DATASET_FILE_PATH)
test_dataset = file_reader.get_dataset_from_file(TEST_DATASET_FILE_PATH)
training_set_sizes_repetitions = {}
training_set_sizes_repetitions[25] = 4
training_set_sizes_repetitions[50] = 4
training_set_sizes_repetitions[100] = 1
nb_test_set_accuracies_with_size, tan_test_set_accuracies_with_size = {}, {}
avg_nb_test_data_accuracy, avg_tan_test_data_accuracy = [], []
for size in sorted(training_set_sizes_repetitions.keys()):
num_repetitions = training_set_sizes_repetitions[size]
nb_test_set_accuracies, tan_test_set_accuracies = [], []
for counter in xrange(0, num_repetitions):
stratified_training_data_set = get_stratified_random_data_set(train_dataset, size)
# Test for Naive Bayes Model
naive_bayes_model = naive_bayes.Naivebayes(stratified_training_data_set)
test_set_accuracy = naive_bayes.evaluate_naive_bayes_model(naive_bayes_model, test_dataset)
nb_test_set_accuracies.append(test_set_accuracy*100)
logger.info("Naive Bayes accuracy : " + str(test_set_accuracy*100) + " % ")
# Test for TAN model
tan_model = tan.TAN(stratified_training_data_set)
test_set_accuracy = tan.evaluate_tan_model(tan_model, test_dataset)
tan_test_set_accuracies.append(test_set_accuracy*100)
logger.info("TAN accuracy : " + str(test_set_accuracy*100) + " % ")
nb_test_set_accuracies_with_size[size] = nb_test_set_accuracies
avg_nb_test_data_accuracy.append(sum(nb_test_set_accuracies)/Decimal(len(nb_test_set_accuracies)))
tan_test_set_accuracies_with_size[size] = tan_test_set_accuracies
avg_tan_test_data_accuracy.append(sum(tan_test_set_accuracies)/Decimal(len(tan_test_set_accuracies)))
training_data_set_sizes = sorted(training_set_sizes_repetitions.keys())
logging.info("\n\n Training data set sizes : " + str(training_data_set_sizes))
logging.info("\n\n NB test set accuracies : " + str(avg_nb_test_data_accuracy))
logging.info("\n\n TAN test set accuracies : " + str(avg_tan_test_data_accuracy))
# Plot the graph
plt.figure()
plt.plot(training_data_set_sizes, avg_nb_test_data_accuracy, label="Naive Bayes", marker='H')
plt.plot(training_data_set_sizes, avg_tan_test_data_accuracy, label="TAN", marker='H')
plt.xlabel("Training set size")
plt.ylabel("Test set accuracy (%)")
plt.title("Test accuracy vs Training set size")
plt.xlim(0, 101)
plt.ylim(0, 100)
plt.grid(True)
plt.legend(loc="lower right")
plt.savefig("graphs/hw3_accuracy_vs_size_run2.png")
def main(argv):
assert len(argv) == 3, " Please provide correct arguments as follows : python dt-learn.py <train file path> <test file path> <leaf threshold>"
train_dataset_file_path, test_dataset_file_path, leaf_threshold = argv[0], argv[1], int(argv[2])
# 1) load the training data set
train_dataset = file_reader.get_dataset_from_file(train_dataset_file_path)
# 2) generate a decision tree using training data set
training_dataset_dtree = dtree.learn_dtree(train_dataset, leaf_threshold)
print "\n\n=================== DECISION TREE =====================================\n\n"
dtree.print_dtree(training_dataset_dtree, train_dataset.output.values, " ")
# 3) load the test data set
test_dataset = file_reader.get_dataset_from_file(test_dataset_file_path)
# 4) evaluate the decision tree using the test data set
print "\n\n================== TEST DATA SET EVALUATION ==========================\n\n"
dtree.test_dtree(training_dataset_dtree, test_dataset)