tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices") FLAGS = tf.flags.FLAGS print("\nParameters:") for attr, value in sorted(FLAGS.__flags.items()): print("{}={}".format(attr.upper(), value)) print("") # Data Preparation # ================================================== # Load data print("Loading data...") x_text, y = data_helpers.load_AI100_data_and_labels('data/training.csv') # Build vocabulary max_document_length = max([len(x.split(" ")) for x in x_text]) vocab_processor = learn.preprocessing.VocabularyProcessor(max_document_length) x = np.array(list(vocab_processor.fit_transform(x_text))) # Randomly shuffle data np.random.seed(10) shuffle_indices = np.random.permutation(np.arange(len(y))) x_shuffled = x[shuffle_indices] y_shuffled = y[shuffle_indices] # Split train/test set # TODO: This is very crude, should use cross-validation dev_sample_index = -1 * int(FLAGS.dev_sample_percentage * float(len(y)))
# Misc Parameters tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement") tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices") FLAGS = tf.flags.FLAGS print("\nParameters:") for attr, value in sorted(FLAGS.__flags.items()): print("{}={}".format(attr.upper(), value)) print("") # CHANGE THIS: Load data. Load your own data here if FLAGS.eval_train: x_raw, y_test = data_helpers.load_AI100_data_and_labels('data/testing.csv') y_test = np.argmax(y_test, axis=1) else: x_raw = ["a masterpiece four years in the making", "everything is off."] y_test = [1, 0] # Map data into vocabulary vocab_path = os.path.join(FLAGS.checkpoint_dir, "..", "vocab") vocab_processor = learn.preprocessing.VocabularyProcessor.restore(vocab_path) x_test = np.array(list(vocab_processor.transform(x_raw))) print("\nEvaluating........\n") # Evaluation # ================================================== checkpoint_file = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
FLAGS = tf.flags.FLAGS FLAGS._parse_flags() print("\nParameters:") for attr, value in sorted(FLAGS.__flags.items()): print("{}={}".format(attr.upper(), value)) print("") # Data Preparation # ================================================== # Load data print("Loading data...") #x_text, y = data_helpers.load_AI100_data_and_labels('data/AI100/training.txt') print("dataPath: ", dataPath) x_text, y = data_helpers.load_AI100_data_and_labels(dataPath) # Build vocabulary max_document_length = max([len(x.split(" ")) for x in x_text]) vocab_processor = learn.preprocessing.VocabularyProcessor(max_document_length) x = np.array(list(vocab_processor.fit_transform(x_text))) # Randomly shuffle data np.random.seed(10) shuffle_indices = np.random.permutation(np.arange(len(y))) x_shuffled = x[shuffle_indices] y_shuffled = y[shuffle_indices] # Split train/test set # TODO: This is very crude, should use cross-validation dev_sample_index = -1 * int(FLAGS.dev_sample_percentage * float(len(y)))