def am_glove_fasttext(data):
job = Job('am_glove_fasttext', cv = cv_n_fold_dl, n_threads = 1,
model_package = 'keras')
max_features = 40000
max_seq_len = 700
embedding_dims = 300
batch_size = 256
nb_epoch = 200
global embedding_matrix
embedding_matrix = create_embedding_matrix(data.df[data.fs_ind],
max_features=max_features,
embedding_dims = embedding_dims)
m = KerasClassifier(build_fn=glove_fasttext, batch_size=batch_size,
validation_split = 0.1, nb_epoch=nb_epoch, verbose = 1)
pipeline = Pipeline(steps=[('txt_to_seq', TextToNumericSequence()),
('padd_seq', PadNumericSequence()),
('m', m)])
parameters = dict(txt_to_seq__n_max_features = [max_features],
padd_seq__max_seq_len = [max_seq_len],
m__max_features = [max_features],
m__max_seq_len = [max_seq_len],
m__embedding_dims = [embedding_dims])
job.run(pipeline, parameters, data)
return None
def pre_process_data_for_deep_learning(data, fs_text = 'text', verbose = 0):
pipeline = Pipeline(steps=[('txt_to_seq', TextToNumericSequence(max_features)),
('padd_seq', PadNumericSequence(max_seq_len))])
m_pre_proc = pipeline.fit(data.df[fs_text].values)
text_num = m_pre_proc.transform(data.df[fs_text].values)
# text_num = np.array(text_num)
return text_num, m_pre_proc
def ak_embedding_cnn_lstm(data):
job = Job('ak_embedding_cnn_lstm', cv = cv_n_fold_dl, n_threads = 1)
cnn_lstm_model = KerasClassifier(build_fn=cnn_lstm, batch_size=32, nb_epoch=10,
validation_split = 0.1, verbose = 1)
pipeline = Pipeline(steps=[('txt_to_seq', TextToNumericSequence()),
('padd_seq', PadNumericSequence()),
('cnn_lstm', cnn_lstm_model)])
parameters = dict(txt_to_seq__n_max_features = [20000],
padd_seq__max_seq_len = [300],
cnn_lstm__embedding_dims = [50])
job.run(pipeline, parameters, data)
return None
def pre_process_data_for_deep_learning(data, fs_text = 'text', verbose = 0):
pipeline = Pipeline(steps=[('txt_to_seq', TextToNumericSequence()),
('padd_seq', PadNumericSequence())])
p = pipeline.fit(data.df[fs_text].values)
text_num = p.transform(data.df[fs_text].values)
print(text_num)
text_num = pd.DataFrame(text_num)
fe_columns = ['text_numeric']
text_num.columns = fe_columns
data.df = data.df.join(text_num)
data.fs_ind = fe_columns
return data
def aj_embedding_fasttext(data):
job = Job('aj_embedding_fasttext', cv = cv_n_fold_dl, n_threads = 1)
ft_model = KerasClassifier(build_fn=fasttext, batch_size=32, nb_epoch=5,
validation_split = 0.1, verbose = 1)
pipeline = Pipeline(steps=[('txt_to_seq', TextToNumericSequence()),
('padd_seq', PadNumericSequence()),
('ft', ft_model)])
# TODO: add ngram features based on the paper
parameters = dict(txt_to_seq__n_max_features = [20000],
padd_seq__max_seq_len = [300],
ft__max_seq_len = [300],
ft__embedding_dims = [100])
job.run(pipeline, parameters, data)
return None
def al_glove_cnn_lstm(data):
job = Job('al_glove_cnn_lstm', cv = cv_n_fold_dl, n_threads = 1)
global embedding_matrix
embedding_matrix = create_embedding_matrix(data.df[data.fs_ind], max_features=20000,
embedding_dims = 300)
glove_cnn_lstm_m = KerasClassifier(build_fn=glove_cnn_lstm, batch_size=64,
nb_epoch=10,
validation_split = 0.1, verbose = 1)
pipeline = Pipeline(steps=[('txt_to_seq', TextToNumericSequence()),
('padd_seq', PadNumericSequence()),
('g_c_l', glove_cnn_lstm_m)])
parameters = dict(txt_to_seq__n_max_features = [20000],
padd_seq__max_seq_len = [300],
g_c_l__max_seq_len = [300],
g_c_l__embedding_dims = [300])
job.run(pipeline, parameters, data)
return None
def ao_multi_fltr_glove_cnn(data):
job = Job('ao_multi_fltr_glove_cnn', cv = cv_n_fold_dl, n_threads = 1)
max_features = 20000
max_seq_len = 300
embedding_dims = 300
batch_size = 64
nb_epoch = 10
global embedding_matrix
embedding_matrix = create_embedding_matrix(data.df[data.fs_ind], max_features=max_features,
embedding_dims = embedding_dims)
m = KerasClassifier(build_fn=multi_fltr_glove_cnn, batch_size=batch_size, nb_epoch=nb_epoch,
validation_split = 0.1, verbose = 1)
pipeline = Pipeline(steps=[('txt_to_seq', TextToNumericSequence()),
('padd_seq', PadNumericSequence()),
('m', m)])
parameters = dict(txt_to_seq__n_max_features = [max_features],
padd_seq__max_seq_len = [max_seq_len],
m__max_features = [max_features],
m__max_seq_len = [max_seq_len],
m__embedding_dims = [embedding_dims])
job.run(pipeline, parameters, data)
return None