def multi_classTo_multi_multi(Y, model):
num_of_labels = Y.ndim
if (num_of_labels >= 2):
print("This is already a multi-label problem!!!!!!")
return Y
transclf = LabelPowerset(classifier=model, require_dense=[False, True])
return transclf.inverse_transform(Y)
def resampling_data(self, X, y):
# Import a dataset with X and multi-label y
lp = LabelPowerset()
ros = RandomOverSampler(random_state=42)
# Applies the above stated multi-label (ML) to multi-class (MC) transformation.
yt = lp.transform(y)
X_resampled, y_resampled = ros.fit_sample(X, yt)
# Inverts the ML-MC transformation to recreate the ML set
y_resampled = lp.inverse_transform(y_resampled)
return X_resampled, y_resampled
def multiple_smote(X, y):
"""
为multi-label样本过采样
"""
# Import a dataset with X and multi-label y
y = np.array(y)
lp = LabelPowerset()
# oversampler = ADASYN(random_state=1994, n_neighbors=2)
oversampler = SMOTE(k_neighbors=2)
# Applies the above stated multi-label (ML) to multi-class (MC) transformation.
yt = lp.transform(y)
X_resampled, y_resampled = oversampler.fit_resample(X, yt)
# Inverts the ML-MC transformation to recreate the ML set
y_resampled = lp.inverse_transform(y_resampled) # return a sparse matrix
return X_resampled, y_resampled.toarray()
def resample_multilabel(data, target):
"""
Apply LP-transformation to create balanced classes, then convert back to multilabel targets
"""
target = target.astype(int)
def convert_hads_to_str(hads_data, hads_type):
hads_strs = []
for val in hads_data:
if val == 0:
str_convert = '%s_normal' % hads_type
elif val == 1:
str_convert = '%s_borderline' % hads_type
elif val == 2:
str_convert = '%s_abnormal' % hads_type
hads_strs.append(str_convert)
return hads_strs
def convert_str_to_hads(hads_tuples):
hads_array = np.ndarray(shape=(len(hads_tuples), 2))
for t, tup in enumerate(hads_tuples):
for s, str in enumerate(tup):
if '_normal' in str:
hads_array[t, s] = 0
elif '_borderline' in str:
hads_array[t, s] = 1
elif '_abnormal' in str:
hads_array[t, s] = 2
return hads_array
anx_strings = convert_hads_to_str(target[:, 0], 'anxiety')
dep_strings = convert_hads_to_str(target[:, 1], 'depression')
multilabel_hads = [(anx_strings[n], dep_strings[n])
for n in range(len(anx_strings))]
mlb = preprocessing.MultiLabelBinarizer()
binary_matrix = mlb.fit_transform(multilabel_hads)
from skmultilearn.problem_transform import LabelPowerset
lp = LabelPowerset()
target_lp_transformed = lp.transform(binary_matrix)
resampler = RandomOverSampler(sampling_strategy='not majority',
random_state=seed)
data_resampled, target_lp_transformed_resampled = resampler.fit_sample(
data, target_lp_transformed)
binary_matrix_resampled = lp.inverse_transform(
target_lp_transformed_resampled)
target_resampled_multilabel = mlb.inverse_transform(
binary_matrix_resampled)
target_resampled_multilabel_array = convert_str_to_hads(
target_resampled_multilabel)
anx_resampled_to_str = convert_hads_to_str(
target_resampled_multilabel_array[:, 0], 'anxiety')
dep_resampled_to_str = convert_hads_to_str(
target_resampled_multilabel_array[:, 1], 'depression')
target_resampled_multilabel_df = pd.DataFrame()
target_resampled_multilabel_df['anxiety'] = anx_resampled_to_str
target_resampled_multilabel_df['depression'] = dep_resampled_to_str
return data_resampled, target_resampled_multilabel_df.values, target_lp_transformed_resampled
train_text_ori = np.array(train_text_ori, dtype=object)[:, np.newaxis]
train_label_ori = train_df.values[:,3:-1]
test_text = test_df['alltext'].tolist()
test_text = [' '.join(t.split()) for t in test_text]
test_text = np.array(test_text, dtype=object)[:, np.newaxis]
test_label = test_df.values[:,3:-1]
## Upsampling of data for each label
print('Before upsampling: ',train_text_ori.shape,train_label_ori.shape,test_text.shape,test_label.shape)
yt = lp.transform(train_label_ori.astype('int'))
train_text, y_resampled = ros.fit_sample(train_text_ori.astype('str'), yt)
train_label = lp.inverse_transform(y_resampled).toarray()
# train_text=train_text_ori
# train_label = train_label_ori
print('After Up-sampling',train_text.shape,train_label.shape,test_text.shape,test_label.shape)
# Instantiate tokenizer
tokenizer = create_tokenizer_from_hub_module()
# Convert data to InputExample format
train_examples = convert_text_to_examples(train_text, train_label)
test_examples = convert_text_to_examples(test_text, test_label)
# Convert to features