pre.load_all_texts_from_directory(path=TRAIN_PATH_NEG, name='raw_neg')
texts_list = pd.concat([pre.data['raw_pos'], pre.data['raw_neg']])
print('fit & transform training data')
text_transformer = TextTransformer(num_words=n_words)
train_features = text_transformer.fit_and_transform(texts_list)
train_features['target'] = np.append(np.ones(len(pre.data['raw_pos'])),
np.zeros(len(pre.data['raw_neg'])))
#shuffle datafram in-place
train_features = train_features.sample(frac=1).reset_index(drop=True)
pre.set('training_data' + '_' + str(n_words), train_features)
pre.save('training_data' + '_' + str(n_words))
#transform the test data
TEST_PATH_POS = 'test/pos/'
TEST_PATH_NEG = 'test/neg/'
pre.load_all_texts_from_directory(path=TEST_PATH_POS, name='raw_pos_test')
pre.load_all_texts_from_directory(path=TEST_PATH_NEG, name='raw_neg_test')
print('transform test data')
texts_list_test = pd.concat(
[pre.data['raw_pos_test'], pre.data['raw_neg_test']])
test_features = text_transformer.transform(texts_list_test)
test_features['target'] = np.append(
X_train_encoded_df = pd.DataFrame(X_train_encoded.detach().numpy())
X_test_encoded_df = pd.DataFrame(X_test_encoded.detach().numpy())
cols = list(range(1, n_features_encoded + 1))
X_train_encoded_df.columns = cols
X_test_encoded_df.columns = cols
train_encoded_data = X_train_encoded_df.join(y_train_df)
test_encoded_data = X_test_encoded_df.join(y_test_df)
pre.set('train_encoded', train_encoded_data)
pre.set('test_encoded', test_encoded_data)
pre.save('train_encoded')
pre.save('test_encoded')
plt.figure(1, figsize=(20, 10))
for idx in range(30):
image = X_test[idx].detach().numpy().reshape(16, 16)
image2 = X_test_encoded[idx].detach().numpy().reshape(
int(math.sqrt(n_features_encoded)),
int(math.sqrt(n_features_encoded)))
image3 = X_test_decoded[idx].detach().numpy().reshape(16, 16)
# Call signature: subplot(nrows, ncols, index, **kwargs)
plt.subplot(10, 9, 1 + idx * 3)
plt.imshow(image, cmap='hot', interpolation='none')
plt.subplot(10, 9, 2 + idx * 3)
plt.imshow(image2, cmap='winter', interpolation='none')
plt.subplot(10, 9, 3 + idx * 3)
pre_train.cleanup(name='raw',
drop_duplicates=True,
dropna={
'axis': 1,
'thresh': 2
})
print(pre_train.get('clean').head())
#classes = ['0_0.0', '0_1.0', '0_2.0', '0_3.0', '0_4.0', '0_5.0', '0_6.0', '0_7.0', '0_8.0', '0_9.0']
X = pre_train.get('clean').drop(columns=[0])
y = pre_train.get('clean')[0]
pre_train.set(name='train', value=pre_train.get('clean'))
pre_train.save(name='train')
pre_test = Preprocessing('digits')
kwarg = {'header': None, 'sep': ' '}
pre_test.load_data(filename='zip.test', name='raw', **kwarg)
pre_test.cleanup(name='raw',
drop_duplicates=True,
dropna={
'axis': 1,
'thresh': 2
})
print(pre_test.get('clean').head())
#classes = ['0_0.0', '0_1.0', '0_2.0', '0_3.0', '0_4.0', '0_5.0', '0_6.0', '0_7.0', '0_8.0', '0_9.0']