def evaluation_mbrnn():
test_x, test_y = load_data_for_rnn_new_add_noise(data_set=3,
train_num=1,
test_num=400,
load_train=False,
noise_percent=0)
brnn = DynamicWeightHybridModel(time_step=TIME_STEP,
feature_size=WORD2VEC_FEATURE_NUM,
rnn_utils=RNN_UTILS,
rnn_layers_num=RNN_LAYERS_NUM,
brnn_model_path=BRNN_700_PATH,
fnn_model_path=JOINT_100_PATH)
begin = 0
process_rnn_label_list(test_y, time_step=brnn.time_step, begin=begin)
# print(train_y)
test_x = trans_to_wordvec_by_word2vec(
test_x,
feature_size=WORD2VEC_FEATURE_NUM,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(
test_y, dtype=tf.float32)
ev, weights = brnn.evaluate(test_x, test_y, return_weight=True)
template = 'test data precision:{}, recall:{}, f1-score:{}'
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
brnn.save_weights(DW_HYBRID_600_PATH)
def evaluation_mbrnn_load_model():
train_x, train_y, test_x, test_y = load_data_for_rnn_new_add_noise(
data_set=3,
train_num=100,
test_num=400,
noise_percent=10,
noise_type='shuffle')
brnn = GRUModel(time_step=TIME_STEP,
feature_size=WORD2VEC_FEATURE_NUM,
rnn_utils=RNN_UTILS,
rnn_layers_num=RNN_LAYERS_NUM)
brnn.load_weights(BRNN_700_PATH)
begin = 0
# process_rnn_label_list(train_y, time_step=brnn.time_step, begin=begin) # 原地修改label_list,统一维度
process_rnn_label_list(test_y, time_step=brnn.time_step, begin=begin)
# print(train_y)
# train_x = trans_to_wordvec_by_word2vec(train_x, feature_size=100,
# word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923, type='rnn', time_step=brnn.time_step, begin=begin)
test_x = trans_to_wordvec_by_word2vec(
test_x,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
# train_x, train_y = tf.constant(train_x, dtype=tf.float32), tf.constant(train_y, dtype=tf.float32)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(
test_y, dtype=tf.float32)
inputs, label_list = None, None
# brnn.fit(train_x, train_y, batchsz=10, epochs=15)
ev = brnn.evaluate(test_x, test_y)
template = 'test data precision:{}, recall:{}, f1-score:{}'
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
def evaluation_mbrnn_load_model():
train_x, train_y, test_x, test_y = load_data_for_rnn_new_add_noise(
data_set=3,
train_num=1,
test_num=400,
noise_type='shuffle',
noise_percent=10)
brnn = KnowledgeDistillModel(time_step=TIME_STEP,
feature_size=WORD2VEC_FEATURE_NUM,
rnn_utils=RNN_UTILS,
rnn_layers_num=RNN_LAYERS_NUM,
fnn_model_path=FNN_700_PATH)
brnn.load_weights(KNOWLEDGE_DISTILL_MODEL_700_PATH)
begin = 0
process_rnn_label_list(test_y, time_step=brnn.time_step, begin=begin)
test_x = trans_to_wordvec_by_word2vec(
test_x,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(
test_y, dtype=tf.float32)
ev = brnn.evaluate(test_x, test_y)
print('b-brnn:')
template = 'test data precision:{}, recall:{}, f1-score:{}'
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
ev = brnn.evaluate(test_x, test_y, choose=1)
print('fnn:')
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
def evaluation_joint():
train_x, train_y, test_x, test_y = load_data_for_rnn_new_add_noise(data_set=3, train_num=700, test_num=400, noise_percent=10)
brnn = FNNModel(time_step=12, feature_size=100)
begin = 0
process_rnn_label_list(train_y, time_step=brnn.time_step, begin=begin) # 原地修改label_list,统一维度
process_rnn_label_list(test_y, time_step=brnn.time_step, begin=begin)
# print(train_y)
train_x = trans_to_wordvec_by_word2vec(train_x, feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923, type='rnn', time_step=brnn.time_step, begin=begin)
test_x = trans_to_wordvec_by_word2vec(test_x, feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923, type='rnn',
time_step=brnn.time_step, begin=begin)
train_x, train_y = tf.constant(train_x, dtype=tf.float32), tf.constant(train_y, dtype=tf.float32)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(test_y, dtype=tf.float32)
inputs, label_list = None, None
brnn.fit(train_x, train_y, batchsz=5, epochs=12)
ev = brnn.evaluate(test_x, test_y, choose=0)
# ev_b = brnn.evaluate(test_x, test_y, 1)
# ev_f = brnn.evaluate(test_x, test_y, 2)
template = 'test data precision:{}, recall:{}, f1-score:{}'
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
# print(template.format(ev_b['precision'], ev_b['recall'], ev_b['f1-score']))
# print(template.format(ev_f['precision'], ev_f['recall'], ev_f['f1-score']))
# model_path = ROOT_PATH + '\\fnn_11_30'
brnn.save_weights(JOINT_100_PATH)
def evaluation_load_model():
test_x, test_y = load_data_for_rnn_new_add_noise(load_train=False, data_set=3, train_num=700, test_num=400, noise_percent=10)
brnn = FNNModel(time_step=12, feature_size=100)
brnn.load_weights(JOINT_100_PATH)
begin = 0
process_rnn_label_list(test_y, time_step=brnn.time_step, begin=begin)
test_x = trans_to_wordvec_by_word2vec(test_x, feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923, type='rnn',
time_step=brnn.time_step, begin=begin)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(test_y, dtype=tf.float32)
ev = brnn.evaluate(test_x, test_y, choose=1)
template = 'test data precision:{}, recall:{}, f1-score:{}'
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
def evaluation_mbrnn_best_params():
test_xs, test_ys = [], []
for i in range(0, 11): # 异常比例从0到100%
test_x, test_y = load_data_for_rnn_new_add_noise(data_set=3,
train_num=1,
test_num=400,
noise_percent=i,
load_train=False)
test_xs.append(test_x)
test_ys.append(test_y)
begin = 0
for i in range(len(test_ys)):
process_rnn_label_list(test_ys[i],
time_step=TIME_STEP,
begin=begin)
test_xs[i] = trans_to_wordvec_by_word2vec(
test_xs[i],
feature_size=WORD2VEC_FEATURE_NUM,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=TIME_STEP,
begin=begin)
test_xs[i], test_ys[i] = tf.constant(
test_xs[i], dtype=tf.float32), tf.constant(test_ys[i],
dtype=tf.float32)
print('-----------------------------------------------')
model = KnowledgeDistillModel(time_step=TIME_STEP,
feature_size=WORD2VEC_FEATURE_NUM,
rnn_utils=RNN_UTILS,
rnn_layers_num=RNN_LAYERS_NUM)
model.load_weights(KNOWLEDGE_DISTILL_MODEL_700_PATH)
res = 0
length = len(test_xs)
for i, test_x in enumerate(test_xs):
ev = model.evaluate(test_x, test_ys[i])
print(i * 10, '%:', ev['f1-score'])
res += ev['f1-score']
res /= length
print('brnn mean f1-score:', res)
res = 0
for i, test_x in enumerate(test_xs):
ev = model.evaluate(test_x, test_ys[i], choose=1)
print(i * 10, '%:', ev['f1-score'])
res += ev['f1-score']
res /= length
print('fnn mean f1-score:', res)
def evaluation_hbrnn():
# from tensorflow.python.client import device_lib
# print(device_lib.list_local_devices())
# set_gpu()
train_x, train_y, test_x, test_y = load_data_for_rnn_new(data_set=3,
train_num=50,
test_num=400)
h_brnn = HBRNN(time_step=12,
feature_size=100,
rnn_utils=64,
rnn_layers_num=1,
hidden_vector_size=64,
word_num=MAX_LEN)
begin = 0
process_rnn_label_list(train_y,
time_step=h_brnn.time_step,
begin=begin) # 原地修改label_list,统一维度
process_rnn_label_list(test_y, time_step=h_brnn.time_step, begin=begin)
# print(train_y)
train_x = trans_to_wordvec_by_word2vec(
train_x,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='attention',
time_step=h_brnn.time_step,
begin=begin)
test_x = trans_to_wordvec_by_word2vec(
test_x,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='attention',
time_step=h_brnn.time_step,
begin=begin)
train_x, train_y = tf.constant(train_x, dtype=tf.float32), tf.constant(
train_y, dtype=tf.float32)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(
test_y, dtype=tf.float32)
print(train_x.shape, train_y.shape)
print(test_x.shape, test_y.shape)
inputs, label_list = None, None
# wbrnn = WBRNNLayer(rnn_utils=32, output_vector_size=32)
# output_train, output_test = wbrnn(train_x), wbrnn(test_x)
# print(output_train.shape, output_test.shape)
h_brnn.fit(train_x, train_y, batchsz=10, epochs=15)
ev = h_brnn.evaluate(test_x, test_y)
template = 'test data precision:{}, recall:{}, f1-score:{}'
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
def evaluation_mbrnn():
train_x, train_y, test_x, test_y = load_data_for_rnn_new_add_noise(
data_set=3,
train_num=600,
test_num=400,
noise_percent=10,
noise_type='swap')
brnn = GRUModel(time_step=12,
feature_size=100,
rnn_utils=64,
rnn_layers_num=2)
begin = 0
process_rnn_label_list(train_y, time_step=brnn.time_step,
begin=begin) # 原地修改label_list,统一维度
process_rnn_label_list(test_y, time_step=brnn.time_step, begin=begin)
# print(train_y)
train_x = trans_to_wordvec_by_word2vec(
train_x,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
test_x = trans_to_wordvec_by_word2vec(
test_x,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
train_x, train_y = tf.constant(train_x, dtype=tf.float32), tf.constant(
train_y, dtype=tf.float32)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(
test_y, dtype=tf.float32)
inputs, label_list = None, None
brnn.fit(train_x, train_y, batchsz=5, epochs=15)
ev = brnn.evaluate(test_x, test_y)
# ev_b = brnn.evaluate(test_x, test_y, 1)
# ev_f = brnn.evaluate(test_x, test_y, 2)
template = 'test data precision:{}, recall:{}, f1-score:{}'
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
# print(template.format(ev_b['precision'], ev_b['recall'], ev_b['f1-score']))
# print(template.format(ev_f['precision'], ev_f['recall'], ev_f['f1-score']))
# model_path = ROOT_PATH + '\\B-BRNN-IMPROVED-BY-FEATURE-INTEGRATION'
brnn.save_weights(BRNN_600_PATH)
def evaluation_mbrnn1():
train_x, train_y, test_x, test_y = load_data_for_rnn_new_add_noise(
data_set=1, train_num=1, test_num=400)
brnn = TeacherModel(time_step=TIME_STEP,
feature_size=WORD2VEC_FEATURE_NUM,
rnn_utils=RNN_UTILS,
rnn_layers_num=RNN_LAYERS_NUM,
brnn_model_path=BBRNN_MODEL_PATH,
fnn_model_path=FNN_MODEL_PATH)
begin = 0
process_rnn_label_list(test_y, time_step=brnn.time_step, begin=begin)
test_x = trans_to_wordvec_by_word2vec(
test_x,
feature_size=WORD2VEC_FEATURE_NUM,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(
test_y, dtype=tf.float32)
inputs, label_list = None, None
brnn.fit(test_x, test_y, batchsz=10, epochs=10)
def evaluation_mbrnn():
train_x, train_y, test_x, test_y = load_data_for_rnn_new(data_set=3,
train_num=500,
test_num=400)
brnn = GRUModel1(time_step=12,
feature_size=100,
rnn_utils=64,
rnn_layers_num=2)
begin = 0
process_rnn_label_list(train_y, time_step=brnn.time_step,
begin=begin) # 原地修改label_list,统一维度
process_rnn_label_list(test_y, time_step=brnn.time_step, begin=begin)
# print(train_y)
train_x = trans_to_wordvec_by_word2vec(
train_x,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
test_x = trans_to_wordvec_by_word2vec(
test_x,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
train_x, train_y = tf.constant(train_x, dtype=tf.float32), tf.constant(
train_y, dtype=tf.float32)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(
test_y, dtype=tf.float32)
inputs, label_list = None, None
brnn.fit(train_x, train_y, batchsz=10, epochs=15)
ev = brnn.evaluate(test_x, test_y)
template = 'test data precision:{}, recall:{}, f1-score:{}'
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
model_path = ROOT_PATH + '\\wbrnn_feature_block_attention_11_24_19_30'
brnn.save_weights(model_path)
def evaluation_mbrnn_load_model():
test_x, test_y = load_data_for_rnn_new_add_noise(data_set=3,
train_num=1,
test_num=400,
noise_type='shuffle',
noise_percent=0,
load_train=False)
test_x_noise, test_y_noise = load_data_for_rnn_new_add_noise(
data_set=3,
train_num=1,
test_num=400,
noise_type='shuffle',
noise_percent=10,
load_train=False)
brnn = DynamicWeightHybridModel(time_step=TIME_STEP,
feature_size=WORD2VEC_FEATURE_NUM,
rnn_utils=RNN_UTILS,
rnn_layers_num=RNN_LAYERS_NUM)
brnn.load_weights(DW_HYBRID_600_PATH)
begin = 0
process_rnn_label_list(test_y, time_step=brnn.time_step, begin=begin)
test_x = trans_to_wordvec_by_word2vec(
test_x,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
test_x, test_y = tf.constant(test_x, dtype=tf.float32), tf.constant(
test_y, dtype=tf.float32)
process_rnn_label_list(test_y_noise,
time_step=brnn.time_step,
begin=begin)
test_x_noise = trans_to_wordvec_by_word2vec(
test_x_noise,
feature_size=100,
word2vec_model=word2vec_model_path_zhwiki_rnn_update_20_923,
type='rnn',
time_step=brnn.time_step,
begin=begin)
test_x_noise, test_y_noise = tf.constant(
test_x_noise, dtype=tf.float32), tf.constant(test_y_noise,
dtype=tf.float32)
ev_noise, weight_noise = brnn.evaluate(test_x_noise,
test_y_noise,
return_weight=True)
ev, weight = brnn.evaluate(test_x, test_y, return_weight=True)
template = 'test data precision:{}, recall:{}, f1-score:{}'
print(template.format(ev['precision'], ev['recall'], ev['f1-score']))
print(
template.format(ev_noise['precision'], ev_noise['recall'],
ev_noise['f1-score']))
x = [i for i in range(0, 400)]
# colors = []
# for i in range(400):
# colors.append('r')
# for i in range(400, 800):
# colors.append('g')
# plt.scatter(x, tf.concat([weight, weight_noise], axis=-1), c=colors, s=20)
# plt.scatter(x, weight_noise, c=['g'], s=20)
plt.scatter(x,
weight_noise,
c="r",
alpha=0.5,
label="abnormal test set",
s=15,
marker='^')
# 第二个散点图，颜色为蓝色，透明度50%，图例为散点图2
plt.scatter(x,
weight,
c="g",
alpha=0.5,
label="normal test set",
s=15,
marker='*')
plt.xlabel('index of resume sample')
plt.ylabel('total weight value of each time step ')
plt.legend(loc='best')
plt.title('weight value distribution')
plt.savefig(ROOT_PATH + '\\lspd_weight_distribution.pdf')
plt.show()
