def sample_true_x_y(batch_size, X_train, y_train):
rand_batch_indices = np.random.randint(0, X_train.shape[0], batch_size)
x_batch_train = X_train[rand_batch_indices]
y_batch_train = y_train[rand_batch_indices]
unrolled_x = utils.convert_to_array(x_batch_train)
unrolled_y = utils.convert_to_array(y_batch_train)
return unrolled_x, unrolled_y
def main():
xml_file_test = '../../data/Restaurants_Test_Gold.xml'
xml_file_train = '../../data/Restaurants_Train.xml'
yelp_path = '../../data/yelp_lexicon'
brown_path = '../../data/brown_clusters_tweets/brown_clusters_tweets'
prompt = "Please enter path to Restaurants_Test_Gold.xml file: "
xml_file_test_input = input(prompt)
if xml_file_test_input == '':
pass
else:
xml_file_test = xml_file_test_input
prompt = "Please enter path to Restaurants_Train.xml file: "
xml_file_train_input = input(prompt)
if xml_file_train_input == '':
pass
else:
xml_file_train = xml_file_train_input
prompt = "Please enter path to yelp lexicon features folder: "
yelp_path_input = input(prompt)
if yelp_path_input == '':
pass
else:
yelp_path = yelp_path_input
prompt = "Please enter path to brown_clusters_tweets file: "
brown_path_input = input(prompt)
if brown_path_input == '':
pass
else:
brown_path = brown_path_input
df_test = xml_category_df(xml_file_test)
df_train = xml_category_df(xml_file_train)
df_train['stemmed_text'] = stem_series(df_train.text)
df_test['stemmed_text'] = stem_series(df_test.text)
dict_list = load_lexicon_features(yelp_path)
df_new_train = text_to_score(df_train.text, dict_list)
df_new_test = text_to_score(df_test.text, dict_list)
df_test, df_train = concat_dfs(df_test, df_new_test, df_train,
df_new_train)
test_texts = list(df_test.text)
train_texts = list(df_train.text)
cluster_dict = add_brown_clusters(brown_path)
one_hot_test_list = [one_hotter(cluster_dict, text) for text in test_texts]
one_hot_train_list = [
one_hotter(cluster_dict, train) for train in train_texts
]
training_array_clusters = convert_to_array(one_hot_train_list)
test_array_clusters = convert_to_array(one_hot_test_list)
X_train, y_train = n_gram_builder(df_train, df_test,
training_array_clusters,
test_array_clusters)
df_train, df_test = populate_df_with_binary_cols_per_label(
df_test, df_train)
predict(X_train, y_train, df_train, df_test)
def predict_sequence(test_x, test_y, seq_len, vocab_size, batch_size):
avg_test_loss = []
m_loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False)
test_dataset_in = tf.data.Dataset.from_tensor_slices(
(test_x)).batch(batch_size)
test_dataset_out = tf.data.Dataset.from_tensor_slices(
(test_y)).batch(batch_size)
i = 0
loaded_encoder = tf.keras.models.load_model(
"data/generated_files/enc_model")
loaded_generator = tf.keras.models.load_model(
"data/generated_files/gen_model")
true_x = list()
true_y = list()
predicted_y = list()
for step, (x, y) in enumerate(zip(test_dataset_in, test_dataset_out)):
batch_x_test = utils.convert_to_array(x)
batch_y_test = utils.convert_to_array(y)
if batch_x_test.shape[0] == batch_size:
new_tokens = tf.fill([batch_size, 1], 0)
noise = tf.random.normal((batch_size, enc_units))
enc_output, enc_state = loaded_encoder(batch_x_test,
training=False)
enc_state = tf.math.add(enc_state, noise)
dec_state = enc_state
#generated_logits, state = loaded_generator([new_tokens, enc_state], training=False)
#loss = m_loss(batch_y_test, generated_logits)
generated_logits, _, loss = gen_step_predict(
seq_len, batch_size, vocab_size, loaded_generator, dec_state,
batch_y_test)
p_y = tf.math.argmax(generated_logits, axis=-1)[1]
one_x = utils.convert_to_string_list(batch_x_test[1])
one_y = utils.convert_to_string_list(batch_y_test[1])
pred_y = utils.convert_to_string_list(p_y)
true_x.append(one_x)
true_y.append(one_y)
predicted_y.append(pred_y)
print("Test: Batch {} loss: {}".format(str(i), str(loss)))
avg_test_loss.append(loss)
i += 1
true_predicted_df = pd.DataFrame(
list(zip(true_x, true_y, predicted_y)),
columns=["True_X", "True_Y", "Predicted_Y"])
true_predicted_df.to_csv("data/generated_files/true_predicted_df.csv",
index=None)
mean_loss = np.mean(avg_test_loss)
print("Total test loss: {}".format(str(mean_loss)))
return mean_loss
def min_wrapper(hyp, F, Flag, *varargin):
# Utilize scipy.optimize functions to minimize the negative log marginal liklihood. This is REALLY inefficient!
x = convert_to_array(hyp)
if Flag == 'CG':
aa = cg(nlml, x, dnlml, (F,hyp,varargin), maxiter=100, disp=False, full_output=True)
x = aa[0]; fx = aa[1]; funcCalls = aa[2]; gradcalls = aa[3]
if aa[4] == 1:
print "Maximum number of iterations exceeded."
elif aa[4] == 2:
print "Gradient and/or function calls not changing."
gvals = dnlml(x,F,hyp,varargin)
return convert_to_class(x,hyp), fx, gvals, funcCalls
elif Flag == 'BFGS':
# Use BFGS
aa = bfgs(nlml, x, dnlml, (F,hyp,varargin), maxiter=100, disp=True, full_output=True)
x = aa[0]; fvals = aa[1]; gvals = aa[2]; Bopt = aa[3]; funcCalls = aa[4]; gradcalls = aa[5]
if aa[6] == 1:
print "Maximum number of iterations exceeded."
elif aa[6] == 2:
print "Gradient and/or function calls not changing."
return convert_to_class(x,hyp), fvals, gvals, funcCalls
else:
raise Exception('Incorrect usage of optimization flag in min_wrapper')
def dnlml(x,F,*varargin):
hyp = varargin[0]
temp = list(varargin[1:][0])
temp[-1] = True
f = lambda z: F(z,*temp)
X = convert_to_class(x,hyp)
vargout = f(X)
z = convert_to_array(vargout[1])
return z
def dnlml(x, F, *varargin):
hyp = varargin[0]
temp = list(varargin[1:][0])
temp[-1] = True
f = lambda z: F(z, *temp)
X = convert_to_class(x, hyp)
vargout = f(X)
z = convert_to_array(vargout[1])
return z
def min_wrapper(hyp, F, Flag, *varargin):
# Utilize scipy.optimize functions, sgc.py, or minimize.py to
# minimize the negative log marginal liklihood.
x = convert_to_array(hyp) # convert the hyperparameter class to an array
if Flag == 'CG':
aa = cg(nlml, x, dnlml, (F,hyp,varargin), maxiter=100, disp=False, full_output=True)
x = aa[0]; fopt = aa[1]; funcCalls = aa[2]; gradcalls = aa[3]
if aa[4] == 1:
print "Maximum number of iterations exceeded."
elif aa[4] == 2:
print "Gradient and/or function calls not changing."
gopt = dnlml(x,F,hyp,varargin)
return convert_to_class(x,hyp), fopt, gopt, funcCalls
elif Flag == 'BFGS':
# Use BFGS
aa = bfgs(nlml, x, dnlml, (F,hyp,varargin), maxiter=100, disp=False, full_output=True)
x = aa[0]; fopt = aa[1]; gopt = aa[2]; Bopt = aa[3]; funcCalls = aa[4]; gradcalls = aa[5]
if aa[6] == 1:
print "Maximum number of iterations exceeded."
elif aa[6] == 2:
print "Gradient and/or function calls not changing."
if isinstance(fopt, ndarray):
fopt = fopt[0]
return convert_to_class(x,hyp), fopt, gopt, funcCalls
elif Flag == 'SCG':
# use sgc.py
aa = scg(x, nlml, dnlml, (F,hyp,varargin), niters = 100)
hyp = convert_to_class(aa[0],hyp)
fopt = aa[1][-1]
gopt = dnlml(aa[0],F,hyp,varargin)
return hyp, fopt, gopt, len(aa[1])
elif Flag == 'Minimize':
# use minimize.py
aa = run(x, nlml, dnlml, (F,hyp,varargin), maxnumfuneval=-100)
hyp = convert_to_class(aa[0],hyp)
fopt = aa[1][-1]
gopt = dnlml(aa[0],F,hyp,varargin)
return hyp, fopt, gopt, len(aa[1])
else:
raise Exception('Incorrect usage of optimization flag in min_wrapper')
def min_wrapper(hyp, F, Flag, *varargin):
# Utilize scipy.optimize functions, sgc.py, or minimize.py to
# minimize the negative log marginal liklihood.
x = convert_to_array(hyp) # convert the hyperparameter class to an array
if Flag == 'CG':
aa = cg(nlml,
x,
dnlml, (F, hyp, varargin),
maxiter=100,
disp=False,
full_output=True)
x = aa[0]
fopt = aa[1]
funcCalls = aa[2]
gradcalls = aa[3]
if aa[4] == 1:
print "Maximum number of iterations exceeded."
elif aa[4] == 2:
print "Gradient and/or function calls not changing."
gopt = dnlml(x, F, hyp, varargin)
return convert_to_class(x, hyp), fopt, gopt, funcCalls
elif Flag == 'BFGS':
# Use BFGS
aa = bfgs(nlml,
x,
dnlml, (F, hyp, varargin),
maxiter=100,
disp=False,
full_output=True)
x = aa[0]
fopt = aa[1]
gopt = aa[2]
Bopt = aa[3]
funcCalls = aa[4]
gradcalls = aa[5]
if aa[6] == 1:
print "Maximum number of iterations exceeded."
elif aa[6] == 2:
print "Gradient and/or function calls not changing."
if isinstance(fopt, ndarray):
fopt = fopt[0]
return convert_to_class(x, hyp), fopt, gopt, funcCalls
elif Flag == 'SCG':
# use sgc.py
aa = scg(x, nlml, dnlml, (F, hyp, varargin), niters=100)
hyp = convert_to_class(aa[0], hyp)
fopt = aa[1][-1]
gopt = dnlml(aa[0], F, hyp, varargin)
return hyp, fopt, gopt, len(aa[1])
elif Flag == 'Minimize':
# use minimize.py
aa = run(x, nlml, dnlml, (F, hyp, varargin), maxnumfuneval=-100)
hyp = convert_to_class(aa[0], hyp)
fopt = aa[1][-1]
gopt = dnlml(aa[0], F, hyp, varargin)
return hyp, fopt, gopt, len(aa[1])
else:
raise Exception('Incorrect usage of optimization flag in min_wrapper')