def main():
np.set_printoptions(precision=3)
random.seed(RANDOM_SEED)
np.random.seed(RANDOM_SEED)
my_data = dataset.Dataset(FILE_NAME, TRAINING_PROPORTION, NORMALIZE,
SVD_DIM, VERBOSE)
analyses.compute_feature_correlations(my_data, True)
# my_knn = knn.Knn(my_data, MIN_MAX_KNN, DISTANCE_METRIC, VERBOSE)
# my_knn.train()
# my_knn.test(my_data.test_list, my_data.training_list, my_knn.best_k)
# knn_test_accuracy = my_knn.test_accuracy
# my_logreg = lr.LogisticRegression(my_data, LEARNING_RATE, NUM_EPOCHS, VERBOSE, OUTPUT_FILE_NAME)
# my_logreg.train()
# my_logreg.test()
# logreg_test_accuracy = my_logreg.test_accuracy
if GENERATE_PLOTS:
vis.plot_feature_scatter(my_data, WORD_LABELS, F1, F2, PLOT_SVDS)
vis.plot_feature_by_category_scatter(my_data, F_INDEX, WORD_LABELS,
PLOT_SVDS)
vis.plot_hierarchical_cluster(my_data, PLOT_SVDS, SIM)
if my_logreg is not None:
vis.plot_weight_heat_map(my_logreg)
vis.plot_ypredict_yactual_scatter(my_logreg, WORD_LABELS, C_INDEX)
def main():
np.set_printoptions(precision=3)
random.seed(RANDOM_SEED)
np.random.seed(RANDOM_SEED)
my_data = dataset.Dataset(FILE_NAME, TRAINING_PROPORTION, NORMALIZE, SVD_DIM, VERBOSE)
# analyses.compute_feature_correlations(my_data, VERBOSE)
#
# vis.plot_feature_scatter(my_data, WORD_LABELS, F1, F2, PLOT_SVDS)
# vis.plot_feature_by_category_scatter(my_data, F_INDEX, WORD_LABELS, PLOT_SVDS)
# vis.plot_hierarchical_cluster(my_data, PLOT_SVDS, SIM)
#
# my_knn = knn.Knn(my_data, MIN_MAX_KNN, DISTANCE_METRIC, VERBOSE)
# my_knn.train()
# my_knn.test(my_data.test_list, my_data.training_list, my_knn.best_k)
my_logreg = lr.LogisticRegression(my_data, LEARNING_RATE, NUM_EPOCHS, VERBOSE, OUTPUT_FILE_NAME)
my_logreg.train()
my_logreg.test()
accuracy_list = []
for i in range(100):
my_logreg = lr.LogisticRegression(my_data, LEARNING_RATE, NUM_EPOCHS, VERBOSE, OUTPUT_FILE_NAME)
my_logreg.train()
my_logreg.test()
accuracy_list.append(my_logreg.test_accuracy)
def main():
np.set_printoptions(precision=3)
random.seed(RANDOM_SEED)
np.random.seed(RANDOM_SEED)
my_data = dataset.Dataset(FILE_NAME, TRAINING_PROPORTION, NORMALIZE,
SVD_DIM, VERBOSE)
analyses.compute_feature_correlations(my_data, VERBOSE)
#
# vis.plot_feature_scatter(my_data, WORD_LABELS, F1, F2, PLOT_SVDS)
vis.plot_feature_by_category_scatter(my_data, F_INDEX, WORD_LABELS,
PLOT_SVDS)
# look_ahead_mask=None,
# dec_padding_mask=None,
# )
# logger.info(
# "output weights: {}, attention_weights: {}".format(fn_out.shape)
# ) # (batch_size, tar_seq_len, target_vocab_size)
# logger.info("END\n\n\n\n")
import src.dataset as dt
logger.info("Dataset Testing")
BUFFER_SIZE = 20000
BATCH_SIZE = 32
dataset = dt.Dataset(filename="./data/test.tsv")
dataset.build_train_test(test=0.2)
train_examples, test_examples = dataset.format_train_test()
tokenizer_source, tokenizer_target = dataset.tokenizer(train_examples)
train_dataset = train_examples.map(dataset.tf_encode)
test_dataset = test_examples.map(dataset.tf_encode)
logger.info("######## Source")
sample_string = dt.preprocess_sentence([
i.numpy().decode("UTF-8").split("\t")[0].encode() for i in train_examples
][0])
tokenized_string = tokenizer_source.encode(sample_string)
def main():
my_data = dataset.Dataset(FILE_NAME, TRAINING_PROPORTION, NORMALIZE,
SVD_DIM, VERBOSE)