self._input_data = self._input_data.dropna(axis='columns')
else:
self._input_data = self._input_data.apply(lambda x:
(x - x.mean()) / x.std())
# ================================================================================================
def _assign_dummy(self, x):
x[x[0] + 1:] = 1000
return x
# ================================================================================================
def report_card(self):
pass
# ================================================================================================
# ================================================================================================
if __name__ == '__main__':
from Input import cMAPSS as ci
ci.get_data(2)
pp1 = cMAPSS()
pp1.preprocess(ci.Train_input)
# pp1.preprocess(ci.Test_input, False)
# -*- coding: utf-8 -*-
"""
Created on Wed Oct 23 12:46:15 2019
@author: Tejas
"""
import Testing as test
import Config
from Preprocess import cMAPSS as C
from Input import cMAPSS as i
model = test.read_model('../KerasModels/17_Nov_19__03_08_4826_6100')
print(model.summary())
#i.set_datapath('C:/Users/Tejas/Desktop/Tejas/engine-dataset/')
i.get_data(1)
c = C(**Config.prepros_params)
c.preprocess(i.Test_input, isTrain=False)
test.cMAPSS.get_score(model, c.test_in, i.RUL_input)
def cMAPPS(experiment_name,
prepros_params,
train_params,
dataset_no,
tracking=True,
path=None):
from Input import cMAPSS as ci
from Preprocess import cMAPSS as CP
from Testing import cMAPSS as ct
import Training as tr
if tracking == True:
mlflow.set_tracking_uri('sqlite:///mlflow.db')
mlflow.set_experiment(experiment_name)
with mlflow.start_run():
if path is not None:
ci.set_datapath(path)
if dataset_no in range(1, 5):
ci.get_data(dataset_no)
mlflow.log_param("DataSet Number", dataset_no)
else:
raise Exception('Please choose a number between 1 and 4')
cp = CP(**prepros_params)
cp.preprocess(ci.Train_input)
run_id = mlflow.active_run().info.run_id
tmpdir = tempfile.TemporaryDirectory()
rnn_ff = tr.RNN_to_FF(cp.features,
**train_params,
model_dir=tmpdir.name,
run_id=run_id)
rnn_ff.create_model(cp.no_splits)
rnn_ff.train_model(cp.splits_in, cp.splits_out, cp.no_splits)
mlflow.log_param('Features', cp.features)
mlflow.log_params(prepros_params)
mlflow.log_params(train_params)
mlflow.log_params({
'MSE_Train': rnn_ff.loss.tolist,
'MSE_Validation': rnn_ff.val_loss.tolist,
'Delta_MSE': rnn_ff.del_loss.tolist
})
mlflow.log_artifacts(tmpdir.name)
tmpdir.cleanup()
# Tags
mlflow.set_tags({
'RMSE_Train': (rnn_ff.loss**0.5).tolist,
'RMSE_Validation': (rnn_ff.val_loss**0.5).tolist
})
cp.preprocess(ci.Test_input, isTrain=False)
ct.get_score(rnn_ff.model, cp.test_in, ci.RUL_input)
mlflow.log_params({
'Score': ct.score.tolist,
'Test_MSE': ct.mse.tolist,
'Combined Score': ct.cm_score,
'Combined MSE': ct.cm_mse
})
mlflow.set_tags({
'Test RMSE': (ct.mse**0.5).tolist,
'Combined RMSE': ct.cm_mse**0.5
})
else:
if path is not None:
ci.set_datapath(path)
if dataset_no in range(1, 5):
ci.get_data(dataset_no)
else:
raise Exception('Please choose a number between 1 and 4')
cp = CP(**prepros_params)
cp.preprocess(ci.Train_input)
rnn_ff = tr.RNN_to_FF(cp.features, **train_params)
rnn_ff.create_model(cp.no_splits)
rnn_ff.train_model(cp.splits_in, cp.splits_out, cp.no_splits)
cp.preprocess(ci.Test_input, isTrain=False)
ct.get_score(rnn_ff.models, cp.test_in, ci.RUL_input)
return ci, cp, rnn_ff, ct
clear_session()
# -*- coding: utf-8 -*-
"""
Created on Sat Oct 19 01:29:45 2019
@author: tejas
"""
from Input import cMAPSS as ci
from Preprocess import cMAPSS as CP
import os
import numpy as np
ci.get_data(1)
cp = CP()
cp.train_preprocess(ci.Train_input)
a = cp.train_in
train_id = np.arange(200)
np.random.shuffle(train_id)
tv_s = int(np.ceil(0.4 * 200))
val_id = train_id[:tv_s]
train_id = train_id[tv_s:]
tin_npy = './np_cache/tin_data.npy'
tout_npy = './np_cache/tout_data.npy'
if os.path.isfile(tin_npy):
os.remove(tin_npy)