def on_epoch_end(self, epoch, logs={}):
if epoch % self.interval == 0:
y_pred = self.model.predict(self.X_val, verbose=0)
auc = roc_auc_score(self.y_val, y_pred)
precision = precision_score(self.y_val, utils.proba2label(y_pred))
recall = recall_score(self.y_val, utils.proba2label(y_pred))
print("\n ROC-AUC - epoch: %d - auc: %.6f - precision %.6f - recall %.6f\n" % (epoch+1, auc, precision, recall))
def train_test_and_save_model():
## load data
with utils.timer('Load data'):
data_1 = utils.load_cs_deleted_data(cs_delete_file)
print('target ratio: ')
print(data_1['label'].value_counts())
data_2 = utils.load_58_data(pos_58_file)
print(data_2['label'].value_counts())
data_3 = utils.load_58_data(neg_58_file)
print(data_3['label'].value_counts())
data = pd.concat([data_1, data_2, data_3], axis= 0, ignore_index= True)
DebugDir = '%s/debug' % config.DataBaseDir
if(os.path.exists(DebugDir) == False):
os.makedirs(DebugDir)
#writer = pd.ExcelWriter('%s/raw.xlsx' % DebugDir)
#data.to_excel(writer, index= False)
#writer.close()
del data_3, data_2, data_1
gc.collect()
X_raw_words = data['text'].apply(utils.cut)
uni_words = list(set([w for rec in X_raw_words for w in rec]))
word_dict = dict(zip(uni_words, range(len(uni_words))))
X_words = []
for rec in X_raw_words:
new_rec = []
for w in rec:
new_rec.append(word_dict[w])
X_words.append(new_rec)
# X_words = np.array(X_words)
y = np.array(data['label'])
if N_GRAM is not None:
X_words = np.array([augment_with_ngrams(x, VOCAB_SIZE, N_BUCKETS, n= N_GRAM) for x in X_words])
print(X_words.shape)
print(y.shape)
print(X_words[:5])
print(y[:5])
final_train_pred = np.zeros(len(X_words))
for s in range(config.train_times):
s_start = time.time()
train_pred = np.zeros(len(X_words))
classifier = FastTextClassifier(
vocab_size=VOCAB_SIZE + N_BUCKETS,
embedding_size=EMBEDDING_SIZE,
n_labels=2,
)
skf = StratifiedKFold(config.kfold, random_state=2018 * s, shuffle=False)
for fold, (train_index, valid_index) in enumerate(skf.split(X_words, y)):
X_train, X_valid = X_words[train_index], X_words[valid_index]
y_train, y_valid = y[train_index], y[valid_index]
with tf.Session() as sess:
sess.run(tf.local_variables_initializer())
tl.layers.initialize_global_variables(sess)
for epoch in range(N_EPOCH):
start_time = time.time()
print('Epoch %d/%d' % (epoch + 1, N_EPOCH))
for X_batch, y_batch in tl.iterate.minibatches(X_train, y_train, batch_size=BATCH_SIZE, shuffle=True):
sess.run(
classifier.train_op, feed_dict={
classifier.inputs: tl.prepro.pad_sequences(X_batch),
classifier.labels: y_batch,
}
)
valid_pred_proba = sess.run(
classifier.prediction_probs, feed_dict={
classifier.inputs: tl.prepro.pad_sequences(X_valid)
}
)[:,1]
valid_pred_label = utils.proba2label(valid_pred_proba)
valid_auc = roc_auc_score(y_valid, valid_pred_proba)
valid_precision = precision_score(y_valid, valid_pred_label)
valid_recall = recall_score(y_valid, valid_pred_label)
if(epoch == N_EPOCH - 1):
train_pred[valid_index] = valid_pred_proba
# valid_precision = sess.run(
# classifier.precision, feed_dict={
# classifier.inputs: tl.prepro.pad_sequences(X_valid),
# classifier.labels: y_valid,
# }
# )
# valid_recall = sess.run(
# classifier.recall, feed_dict={
# classifier.inputs: tl.prepro.pad_sequences(X_valid),
# classifier.labels: y_valid,
# }
# )
print('valid: auc %.6f, precision %.6f, recall %.6f, took %s[s]' % (valid_auc, valid_precision, valid_recall, int(time.time() - start_time)))
classifier.save(sess, MODEL_FILE_PATH)
print('fold %s done!!!' % fold)
auc = roc_auc_score(y, train_pred)
precision = precision_score(y, utils.proba2label(train_pred))
recall = recall_score(y, utils.proba2label(train_pred))
print('auc %.6f, precision %.6f, recall %.6f, took %s[s]' % (auc, precision, recall, int(time.time() - s_start)))
print(X_train.shape)
print('shape of test data:')
print(y_train.shape)
model = bi_gru_attention(embedding_matrix)
RocAuc = RocAucEvaluation(validation_data=(X_valid, y_valid),
interval=1)
hist = model.fit(X_train,
y_train,
batch_size=batch_size,
epochs=epochs,
validation_data=(X_valid, y_valid),
callbacks=[RocAuc],
verbose=2)
valid_pred_proba = model.predict(X_valid, batch_size=batch_size)
valid_pred_label = utils.proba2label(valid_pred_proba)
valid_auc = roc_auc_score(y_valid, valid_pred_proba)
valid_precision = precision_score(y_valid, valid_pred_label)
valid_recall = recall_score(y_valid, valid_pred_label)
train_pred[valid_index] = valid_pred_proba
f_end = time.time()
print(
'#%s[fold %s]: auc %.6f, precision %.6f, recall %.6f, took %s[s]'
% (s, fold, valid_auc, valid_precision, valid_recall,
int(f_end - f_start)))
auc = roc_auc_score(y, train_pred)
precision = precision_score(y, utils.proba2label(train_pred))
recall = recall_score(y, utils.proba2label(train_pred))