def predict_done():
LOG_DIR = './ops_logs'
TIMESTEPS = 10
RNN_LAYERS = [{'num_units': TIMESTEPS}]
DENSE_LAYERS = [10, 10]
TRAINING_STEPS = 1000
BATCH_SIZE = 100
PRINT_STEPS = TRAINING_STEPS / 100
dateparse = lambda dates: pd.datetime.strptime(dates, '%d/%m/%Y %H:%M')
rawdata = pd.read_csv(
"./model/input/ElectricityPrice/RealMarketPriceDataPT.csv",
parse_dates={'timeline': ['date', '(UTC)']},
index_col='timeline',
date_parser=dateparse)
X, y = load_csvdata(rawdata, TIMESTEPS, seperate=False)
regressor = SKCompat(
learn.Estimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS,
DENSE_LAYERS), ))
validation_monitor = learn.monitors.ValidationMonitor(
X['val'],
y['val'],
every_n_steps=PRINT_STEPS,
early_stopping_rounds=1000)
SKCompat(
regressor.fit(X['train'],
y['train'],
monitors=[validation_monitor],
batch_size=BATCH_SIZE,
steps=TRAINING_STEPS))
predicted = regressor.predict(X['test'])
mse = mean_absolute_error(y['test'], predicted)
plot_predicted, = plt.plot(predicted, label='predicted')
plt.legend(handles=[plot_predicted])
plt.show()
BATCH_SIZE = 100
PRINT_STEPS = TRAINING_STEPS / 100
# ## Parameter definitions
#
# - LOG_DIR: log file
# - TIMESTEPS: RNN time steps
# - RNN_LAYERS: RNN layer 정보
# - DENSE_LAYERS: DNN 크기 [10, 10]: Two dense layer with 10 hidden units
# - TRAINING_STEPS: 학습 스텝
# - BATCH_SIZE: 배치 학습 크기
# - PRINT_STEPS: 학습 과정 중간 출력 단계 (전체의 1% 해당하는 구간마다 출력)
# In[15]:
regressor = learn.TensorFlowEstimator(model_fn=lstm_model(
TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),
n_classes=0,
verbose=1,
steps=TRAINING_STEPS,
optimizer='Adagrad',
learning_rate=0.03,
batch_size=BATCH_SIZE)
# ## Create a regressor with TF Learn
#
# : 예측을 위한 모델 생성. TF learn 라이브러리에 제공되는 TensorFlowEstimator를 사용.
#
# **Parameters**:
#
# - model_fn: 학습 및 예측에 사용할 모델
# - n_classes: label에 해당하는 클래스 수 (0: prediction, 1이상: classification) 확인필요
from sklearn.metrics import mean_squared_error
from lstm_predictor import generate_data, lstm_model
warnings.filterwarnings("ignore")
LOG_DIR = 'resources/logs/'
TIMESTEPS = 1
RNN_LAYERS = [{'num_units': 400}]
DENSE_LAYERS = None
TRAINING_STEPS = 500
PRINT_STEPS = TRAINING_STEPS # / 10
BATCH_SIZE = 100
regressor = SKCompat(
learn.Estimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS,
DENSE_LAYERS), ))
# model_dir=LOG_DIR)
X, y = generate_data(np.sin,
np.linspace(0, 100, 10000, dtype=np.float32),
TIMESTEPS,
seperate=False)
noise_train = np.asmatrix(np.random.normal(0, 0.2, len(y['train'])),
dtype=np.float32)
noise_val = np.asmatrix(np.random.normal(0, 0.2, len(y['val'])),
dtype=np.float32)
noise_test = np.asmatrix(np.random.normal(0, 0.2, len(y['test'])),
dtype=np.float32) #asmatrix
noise_train = np.transpose(noise_train)
dateparse = lambda dates: pd.datetime.strptime(dates, '%d/%m/%Y %H:%M')
rawdata = pd.read_csv("./TotalLoad.csv",parse_dates={'timeline':['date', '(UTC)']},index_col='timeline', date_parser=dateparse)
rawdata = pd.read_csv("./TotalLoad.csv",index_col=['date', '(UTC)'])
# parsing errors in pandas
df = pd.read_csv("./TotalLoad.csv")
df
X, y = load_csvdata(rawdata, TIMESTEPS, seperate=False)
regressor = learn.TensorFlowEstimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),n_classes=0,verbose=1,steps=TRAINING_STEPS,optimizer='Adagrad',learning_rate=0.03, batch_size=BATCH_SIZE)
regressor = learn.Estimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),n_classes=0,verbose=1,steps=TRAINING_STEPS,optimizer='Adagrad',learning_rate=0.03, batch_size=BATCH_SIZE)
https://www.tensorflow.org/api_guides/python/contrib.learn
regressor = learn.Estimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS))
WARNING:tensorflow:Using temporary folder as model directory: C:\Users\aroug\AppData\Local\Temp\tmp3nwb8sg9
WARNING:tensorflow:Using temporary folder as model directory: C:\Users\aroug\AppData\Local\Temp\tmp3nwb8sg9
INFO:tensorflow:Using default config.
INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_keep_checkpoint_max': 5, '_task_type': None, '_master': '', '_tf_config': gpu_options {
per_process_gpu_memory_fraction: 1
}
, '_environment': 'local', '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x0000014792A352E8>, '_save_checkpoints_secs': 600, '_task_id': 0, '_keep_checkpoint_ev
def learningpercell(cell_name):
warnings.filterwarnings("ignore")
LOG_DIR = 'resources/logs/'
TIMESTEPS = 100
RNN_LAYERS = [{'num_units': 256}, {'num_units': 256}]
DENSE_LAYERS = [32]
TRAINING_STEPS = 100
PRINT_STEPS = TRAINING_STEPS # / 10
BATCH_SIZE = 64
regressor = skflow(
learn.Estimator(
model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS)))
# model_dir=LOG_DIR)
# 201512200045
dateparse = lambda dates: pd.datetime.strptime(dates, '%Y%m%d%H%M')
rawdata = None
df_list = []
for root, dirs, files in os.walk(working_dir):
file_list = []
for filename in files:
if filename.endswith('.csv'):
file_list.append(os.path.join(root, filename))
for file in file_list:
df = pd.read_csv(
file,
delimiter="|",
usecols=[1, 2, 5, 6, 7],
header=None,
na_values=["NIL"],
na_filter=True,
names=["meas_info", "counter", "cellname", "value", "time"],
index_col='time')
# df = df[df["counter"] == 67179778]
df = df[df["cellname"].str.contains(cell_name)]
# df.drop('cellname', axis=1, inplace=True)
# df = df[df["counter"] == 50331671]
# print(df[["value"]])
if not df.empty:
df_list.append(df[["value"]])
if df_list:
rawdata = pd.concat(df_list)
# else:
# return
print(len(rawdata))
if len(rawdata) <= 0:
print("Den ftanni")
return
# rawdata = pd.read_csv("./input/fakehdfs/nms/ystr=2015/ymstr=12/ymdstr=20/hive_0_201512200030.csv", delimiter="|",
# usecols=[7], header=None)
X, y = load_csvdata(rawdata, TIMESTEPS, seperate=False)
# noise_train = np.asmatrix(np.random.normal(0, 0.2, len(y['train'])), dtype=np.float32)
# noise_val = np.asmatrix(np.random.normal(0, 0.2, len(y['val'])), dtype=np.float32)
# noise_test = np.asmatrix(np.random.normal(0, 0.2, len(y['test'])), dtype=np.float32) # asmatrix
# noise_train = np.transpose(noise_train)
# noise_val = np.transpose(noise_val)
# noise_test = np.transpose(noise_test)
# y['train'] = np.add(y['train'], noise_train)
# y['val'] = np.add(y['val'], noise_val)
# y['test'] = np.add(y['test'], noise_test)
# print(type(y['train']))
print('-----------------------------------------')
print('train y shape', y['train'].shape)
print('train y shape_num', y['train'][1:5])
# print('noise_train shape', noise_train.shape)
# print('noise_train shape_num', noise_train.shape[1:5])
# create a lstm instance and validation monitor
validation_monitor = learn.monitors.ValidationMonitor(
X['val'],
y['val'],
)
# every_n_steps=PRINT_STEPS,)
# early_stopping_rounds=1000)
# print(X['train'])
# print(y['train'])
skflow(
regressor.fit(X['train'],
y['train'],
monitors=[validation_monitor],
batch_size=BATCH_SIZE,
steps=TRAINING_STEPS))
print('X train shape', X['train'].shape)
print('y train shape', y['train'].shape)
print('X test shape', X['test'].shape)
print('y test shape', y['test'].shape)
predicted = np.asmatrix(regressor.predict(X['test']),
dtype=np.float32) # ,as_iterable=False))
predicted = np.transpose(predicted)
rmse = np.sqrt((np.asarray((np.subtract(predicted, y['test'])))**2).mean())
# this previous code for rmse was incorrect, array and not matricies was needed: rmse = np.sqrt(((predicted - y[
# 'test']) ** 2).mean())
score = mean_squared_error(predicted, y['test'])
nmse = score / np.var(
y['test']
) # should be variance of original data and not data from fitted model, worth to double check
print("RSME: %f" % rmse)
print("NSME: %f" % nmse)
print("MSE: %f" % score)
plot_test, = plt.plot(y['test'], label='test')
plot_predicted, = plt.plot(predicted, label='predicted')
plt.legend(handles=[plot_predicted, plot_test])
plt.show()
