def testIrisRNN(self):
import numpy as np
data = [
"I can do this", "I believe myself", "I am okay", "Not good, man",
"Bad mood today", "Feeling sick now"
]
labels = [1, 1, 1, 0, 0, 0]
MAX_DOCUMENT_LENGTH = 6
EMBEDDING_SIZE = 10
vocab_processor = skflow.preprocessing.VocabularyProcessor(
MAX_DOCUMENT_LENGTH)
data = np.array(list(vocab_processor.fit_transform(data)))
n_words = len(vocab_processor.vocabulary_)
def input_op_fn(X):
word_vectors = skflow.ops.categorical_variable(
X,
n_classes=n_words,
embedding_size=EMBEDDING_SIZE,
name='words')
word_list = skflow.ops.split_squeeze(1, MAX_DOCUMENT_LENGTH,
word_vectors)
return word_list
random.seed(42)
# Only declare them for now
# TODO: Add test case once we have data set in the repo
classifier = skflow.TensorFlowRNNClassifier(rnn_size=5,
cell_type='gru',
input_op_fn=input_op_fn,
n_classes=3)
classifier = skflow.TensorFlowRNNClassifier(rnn_size=5,
cell_type='rnn',
input_op_fn=input_op_fn,
n_classes=3)
classifier = skflow.TensorFlowRNNClassifier(rnn_size=5,
cell_type='lstm',
input_op_fn=input_op_fn,
n_classes=3)
with self.assertRaises(ValueError):
classifier = skflow.TensorFlowRNNClassifier(
rnn_size=5,
cell_type='invalid_type',
input_op_fn=input_op_fn,
n_classes=3)
classifier._model_fn(data, labels)
classifier = skflow.TensorFlowRNNRegressor(rnn_size=5,
cell_type='gru',
input_op_fn=input_op_fn,
n_classes=0)
def testRNN(self):
random.seed(42)
import numpy as np
data = np.array(list([[2, 1, 2, 2, 3], [2, 2, 3, 4, 5],
[3, 3, 1, 2, 1], [2, 4, 5, 4, 1]]),
dtype=np.float32)
# labels for classification
labels = np.array(list([1, 0, 1, 0]), dtype=np.float32)
# targets for regression
targets = np.array(list([10, 16, 10, 16]), dtype=np.float32)
test_data = np.array(list([[1, 3, 3, 2, 1], [2, 3, 4, 5, 6]]))
def input_fn(X):
return tf.split(1, 5, X)
# Classification
classifier = skflow.TensorFlowRNNClassifier(rnn_size=2,
cell_type='lstm',
n_classes=2,
input_op_fn=input_fn)
classifier.fit(data, labels)
classifier.weights_
classifier.bias_
predictions = classifier.predict(test_data)
self.assertAllClose(predictions, np.array([1, 0]))
classifier = skflow.TensorFlowRNNClassifier(rnn_size=2,
cell_type='rnn',
n_classes=2,
input_op_fn=input_fn,
num_layers=2)
classifier.fit(data, labels)
classifier = skflow.TensorFlowRNNClassifier(
rnn_size=2,
cell_type='invalid_cell_type',
n_classes=2,
input_op_fn=input_fn,
num_layers=2)
with self.assertRaises(ValueError):
classifier.fit(data, labels)
# Regression
regressor = skflow.TensorFlowRNNRegressor(rnn_size=2,
cell_type='gru',
input_op_fn=input_fn)
regressor.fit(data, targets)
regressor.weights_
regressor.bias_
predictions = regressor.predict(test_data)
def testRNN(self):
random.seed(42)
import numpy as np
data = np.array(list([[2, 1, 2, 2, 3], [2, 2, 3, 4, 5],
[3, 3, 1, 2, 1], [2, 4, 5, 4, 1]]),
dtype=np.float32)
labels = np.array(list([1, 0, 1, 0]), dtype=np.float32)
def input_fn(X):
return tf.split(1, 5, X)
# Classification
classifier = skflow.TensorFlowRNNClassifier(rnn_size=2,
cell_type='lstm',
n_classes=2,
input_op_fn=input_fn)
classifier.fit(data, labels)
predictions = classifier.predict(
np.array(list([[1, 3, 3, 2, 1], [2, 3, 4, 5, 6]])))
self.assertAllClose(predictions, np.array([1, 0]))
classifier = skflow.TensorFlowRNNClassifier(rnn_size=2,
cell_type='gru',
n_classes=2,
input_op_fn=input_fn)
classifier = skflow.TensorFlowRNNClassifier(rnn_size=2,
cell_type='rnn',
n_classes=2,
input_op_fn=input_fn,
num_layers=2)
# Regression
classifier = skflow.TensorFlowRNNRegressor(rnn_size=2,
cell_type='lstm',
input_op_fn=input_fn)
classifier.fit(data, labels)
predictions = classifier.predict(
np.array(list([[1, 3, 3, 2, 1], [2, 3, 4, 5, 6]])))
### Models
EMBEDDING_SIZE = 50
# Customized function to transform batched X into embeddings
def input_op_fn(X):
# Convert indexes of words into embeddings.
# This creates embeddings matrix of [n_words, EMBEDDING_SIZE] and then
# maps word indexes of the sequence into [batch_size, sequence_length,
# EMBEDDING_SIZE].
word_vectors = skflow.ops.categorical_variable(X, n_classes=n_words,
embedding_size=EMBEDDING_SIZE, name='words')
# Split into list of embedding per word, while removing doc length dim.
# word_list results to be a list of tensors [batch_size, EMBEDDING_SIZE].
word_list = skflow.ops.split_squeeze(1, MAX_DOCUMENT_LENGTH, word_vectors)
return word_list
# Single direction GRU with a single layer
classifier = skflow.TensorFlowRNNClassifier(rnn_size=EMBEDDING_SIZE,
n_classes=15, cell_type='gru', input_op_fn=input_op_fn,
num_layers=1, bidirection=False, sequence_length=None,
steps=1000, optimizer='Adam', learning_rate=0.01, continue_training=True)
# Continously train for 1000 steps & predict on test set.
while True:
classifier.fit(X_train, y_train, logdir='/tmp/tf_examples/word_rnn')
score = metrics.accuracy_score(y_test, classifier.predict(X_test))
print('Accuracy: {0:f}'.format(score))
# Customized function to transform input X into embeddings
def input_op_fn(X):
# Convert indexes of words into embeddings.
# This creates embeddings matrix of [n_words, EMBEDDING_SIZE] and then
# maps word indexes of the sequence into [batch_size, sequence_length,
# EMBEDDING_SIZE].
word_vectors = skflow.ops.categorical_variable(
X, n_classes=n_words, embedding_size=EMBEDDING_SIZE, name='words')
# Split into list of embedding per word, while removing doc length dim.
# word_list results to be a list of tensors [batch_size, EMBEDDING_SIZE].
word_list = skflow.ops.split_squeeze(1, MAX_DOCUMENT_LENGTH, word_vectors)
return word_list
classifier = skflow.TensorFlowRNNClassifier(rnn_size=EMBEDDING_SIZE,
n_classes=15,
cell_type='gru',
input_op_fn=input_op_fn,
steps=1000,
optimizer='Adam',
learning_rate=0.01,
continue_training=True)
# Continously train for 1000 steps & predict on test set.
while True:
classifier.fit(X_train, y_train, logdir='/tmp/tf_examples/word_rnn')
score = metrics.accuracy_score(y_test, classifier.predict(X_test))
print('Accuracy: {0:f}'.format(score))