class MemberTraining:
train_data: object = None
validation_data: object = None
test_data: object = None
model: object = None
def __init__(self):
self.reader = FileReader()
def hook(self):
self.get_data()
self.create_model()
# self.train_model()
self.eval_model()
# self.debug_model()
@staticmethod
def create_train(this):
return this.drop('Exited', axis=1)
@staticmethod
def create_label(this):
return this['Exited']
def get_data(self):
self.reader.context = os.path.join(baseurl, 'data_preprocessed')
self.reader.fname = 'member_preprocessed.csv'
data = self.reader.csv_to_dframe()
data = data.to_numpy()
# print(data[:60])
data_length = len(data)
vol_train = round(data_length * 60 / 100)
vol_validation = round(data_length * 40 / 100)
vol_test = data_length
train = data[:vol_train]
validation = data[vol_train:data_length]
test = data
self.train_data = train
self.validation_data = validation
self.test_data = test
# x = self.create_train(data)
# y = self.create_label(data)
# x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3)
# data = tf.data.Dataset.from_tensor_slices(data)
# self.train_data = tf.data.Dataset.from_tensor_slices(train)
# self.validation_data = tf.data.Dataset.from_tensor_slices(validation)
# self.test_data = tf.data.Dataset.from_tensor_slices(test)
# self.train_data, self.validation_data, self.test_data = tf.split(
# data,
# split=('train[:60%]', 'train[60%:]', 'test')
# )
# 결국 train validation test로 나누고 싶은 것 좀 더 생각해보기
# num_validation = 7000
# num_test = 3000
# self.test_data = data[:num_test]
# self.validation_data = data[num_test : num_test + num_validation]
# self.train_data = data[num_test + num_validation :]
# self.train_data, self.validation_data, self.test_data = tfds.load(
# name="imdb_reviews",
# split=('train[:60%]', 'train[60%:]', 'test'),
# as_supervised=True
# )
print(training_set)
# 모델 생성 (교과서 p.507)
# Dense: 완전 연결층
def create_model(self):
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(16, activation='relu'))
model.add(tf.keras.layers.Dense(1, activation='sigmoid')) # output
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
self.model = model
# 모델 훈련
def train_model(self):
self.model.fit(self.train_data.shuffle(7000).batch(512),
epochs=20,
validation_data=self.validation_data.batch(512),
verbose=1) # 512 = 2 ^9
# 모델 평가
def eval_model(self):
results = self.model.evaluate(self.test_data.batch(512), verbose=2)
for name, value in zip(self.model.metrics_names, results):
print('%s: %.3f' % (name, value))
# 모델 디버깅
def debug_model(self):
print(f'self.train_data: {self.train_data}')
print(f'self.validation_data: {self.validation_data}')
print(f'self.test_data: {self.test_data}')
class SaveLoad:
train_datas: object = None
train_labels: object = None
test_datas: object = None
test_labels: object = None
def __init__(self):
self.reader = FileReader()
def hook(self):
self.get_data()
self.create_model()
self.train_model()
# self.save_model()
def get_data(self):
print(f'baseurl: {baseurl}')
self.reader.context = os.path.join(
'C:/Users/saltQ/sbaproject-api/model', 'data_preprocessed')
self.reader.fname = 'member_preprocessed.csv'
data = self.reader.csv_to_dframe()
data = data.to_numpy()
print(data[:60])
table_col = data.shape[1]
y_col = 1
x_col = table_col - y_col
x = data[:, 0:x_col]
y = data[:, x_col:]
train_datas, test_datas, train_labels, test_labels = train_test_split(
x, y, test_size=0.4)
self.train_labels = train_labels[:1000]
self.test_labels = test_labels[:1000]
self.train_datas = train_datas[:1000]
self.test_datas = test_datas[:1000]
def create_model(self):
self.model = tf.keras.models.Sequential([
keras.layers.Dense(512, activation='relu', input_shape=(784, )),
keras.layers.Dropout(0.2),
keras.layers.Dense(10, activation='sigmoid')
])
self.model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
def train_model(self):
checkpoint_path = 'training_1/cp.ckpt'
cp_callback = tf.keras.callbacks.ModelCheckpoint(
checkpoint_path, save_weights_only=True, verbose=1)
print('***** fit *****')
train_data = tf.data.Dataset.from_tensor_slices(
(self.train_datas, self.train_labels))
# ValueError: Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 784 but received input with shape [None, 12]
self.model.fit(train_data,
epochs=10,
validation_data=(self.test_datas, self.test_labels),
callbacks=[cp_callback]) # 훈련 단계 콜백 전달
self.model.load_weights(checkpoint_path) # 가중치 추가
loss, acc = self.model.evaluate(self.test_datas,
self.test_labels,
verbose=2)
# verbose는 학습 진행상황을 보여줄지 말지에 대한 옵션
print('복원된 모델의 정확도: {:5.2f}%'.format(100 * acc))
# 파일 이름에 에포크 번호를 포함시킨다.
checkpoint_path = os.path.join(baseurl, 'training_2',
'cp-{epoch: 04d}.ckpt')
checkpoint_dir = os.path.dirname(checkpoint_path)
cp_callback = tf.keras.callbacks.ModelCheckpoint(
checkpoint_path,
verbose=1,
save_weights_only=True,
period=5 # 5번째 에포크마다 가중치를 저장한다.
)
print(f'checkpoint: {checkpoint_path}')
self.model.save_weights(checkpoint_path.format(epoch=0))
self.model.fit(self.train_datas,
self.train_labels,
epochs=50,
callbacks=[cp_callback],
validation_data=(self.test_datas, self.test_labels),
verbose=0)
# 전체 모델을 HDF5 파일로 저장한다.
def save_model(self):
context = os.path.join(baseurl, 'saved_model')
self.model.save(os.path.join(context, 'my_model.h5'))
print('=' * 30)
def load_model(self):
self.new_model = keras.models.load_model('my_model.h5')
self.new_model.summary()
loss, acc = self.new_model.evaluate(self.test_images,
self.test_labels,
verbose=2)
def debug_model(self):
print(f'모델정보: {self.model.summary()}')
class MemberTraining:
x_train: object = None
y_train: object = None
x_validation: object = None
y_validation: object = None
x_test: object = None
y_test: object = None
model: object = None
def __init__(self):
self.reader = FileReader()
def hook(self):
self.get_data()
self.create_model()
self.train_model()
self.eval_model()
self.debug_model()
@staticmethod
def create_train(this):
return this.drop('Exited', axis=1)
@staticmethod
def create_label(this):
return this['Exited']
def get_data(self):
self.reader.context = os.path.join(baseurl, 'data_preprocessed')
self.reader.fname = 'member_preprocessed.csv'
data = self.reader.csv_to_dframe()
data = data.to_numpy()
# print(data[:60])
table_col = data.shape[1]
y_col = 1
x_col = table_col - y_col
x = data[:, 0:x_col]
y = data[:, x_col:]
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.4)
x_test, x_validation, y_test, y_validation = train_test_split(
x_test, y_test, test_size=0.4)
self.x_train = x_train
self.x_validation = x_validation
self.x_test = x_test
self.y_train = y_train
self.y_validation = y_validation
self.y_test = y_test
# 모델 생성 (교과서 p.507)
# Dense: 완전 연결층
def create_model(self):
print('********** create model **********')
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(16, activation='relu'))
model.add(tf.keras.layers.Dense(1, activation='sigmoid')) # output
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
self.model = model
# 모델 훈련
def train_model(self):
print('********** train model **********')
self.model.fit(x=self.x_train,
y=self.y_train,
validation_data=(self.x_validation, self.y_validation),
epochs=20,
verbose=1)
# 모델 평가
def eval_model(self):
print('********** eval model **********')
results = self.model.evaluate(x=self.x_test, y=self.y_test, verbose=2)
for name, value in zip(self.model.metrics_names, results):
print('%s: %.3f' % (name, value))
# 모델 디버깅
def debug_model(self):
print(f'self.train_data: {(self.x_train, self.y_train)}')
print(
f'self.validation_data: {(self.x_validation, self.y_validation)}')
print(f'self.test_data: {(self.x_test, self.y_test)}')
