def trainModelsWithConfig(dirr, mod, res, retrain=False):
filename, columns, irrelevantColumns, targetColumns, traintime, testtime, columnOrder = configs.getConfig(
dirr, mod, res)
relevantColumns, columnDescriptions, columnUnits, columnNames, df = mlModule.initDataframe(
filename, columns, irrelevantColumns)
df = df[columnOrder]
df_train, df_test = mlModule.getTestTrainSplit(df, traintime, testtime)
X_train, y_train, X_test, y_test = mlModule.getFeatureTargetSplit(
df_train, df_test, targetColumns)
mlp = mlModule.MLP('MLP 1x128 d0.2 ' + dirr + ' mod' + mod,
X_train,
y_train,
layers=[128],
dropout=0.2)
lstm = mlModule.LSTM('LSTM 1x128 d0.2 ' + dirr + ' mod' + mod,
X_train,
y_train,
layers=[128],
dropout=0.2,
recurrentDropout=0.2,
enrolWindow=12)
linear = mlModule.Linear_Regularized('Linear rCV ' + dirr + ' mod' + mod,
X_train, y_train)
modelList = [
mlp,
lstm,
linear,
]
maxEnrolWindow, indexColumn = mlModule.initModels(modelList, df_test)
mlModule.trainModels(modelList, filename, targetColumns, retrain)
return modelList
def pred(facility, model, resolution):
filename, columns, irrelevantColumns, targetColumns, traintime, testtime, columnOrder = configs.getConfig(facility, model, resolution)
df = mlModule.initDataframe(filename, columns, irrelevantColumns)
df_train, df_test = mlModule.getTestTrainSplit(traintime, testtime)
X_train, y_train, X_test, y_test = mlModule.getFeatureTargetSplit(targetColumns)
mlp_mae = mlModule.MLP('MLP 1x128 d0.2 mae mod'+model, layers=[128], dropout=0.2, loss='mean_absolute_error', metrics=['mean_absolute_error'])
mlp_mse = mlModule.MLP('MLP 1x128 d0.2 mse mod'+model, layers=[128], dropout=0.2, loss='mean_squared_error', metrics=['mean_squared_error'])
lstm_mae = mlModule.LSTM('LSTM 1x128 d0.2 mae mod'+model, layers=[128], dropout=0.2, recurrentDropout=0.2, enrolWindow=12, loss='mean_absolute_error', metrics=['mean_absolute_error'])
lstm_mse = mlModule.LSTM('LSTM 1x128 d0.2 mse mod'+model, layers=[128], dropout=0.2, recurrentDropout=0.2, enrolWindow=12, loss='mean_squared_error', metrics=['mean_squared_error'])
modelList = [
mlp_mae,
mlp_mse,
lstm_mae,
lstm_mse,
]
initTrainPredict(modelList)
def predictWithConfig(modelList, dirr, mod, res):
filename, columns, irrelevantColumns, targetColumns, traintime, testtime, columnOrder = configs.getConfig(
dirr, mod, res)
relevantColumns, columnDescriptions, columnUnits, columnNames, df = mlModule.initDataframe(
filename, columns, irrelevantColumns)
df = df[columnOrder]
df_train, df_test = mlModule.getTestTrainSplit(df, traintime, testtime)
X_train, y_train, X_test, y_test = mlModule.getFeatureTargetSplit(
df_train, df_test, targetColumns)
maxEnrolWindow, indexColumn = mlModule.initModels(modelList, df_test)
inputScaler = StandardScaler()
inputScaler.fit(X_train)
outputScaler = StandardScaler()
outputScaler.fit(y_train)
for model in modelList:
model.inputScaler = inputScaler
model.outputScaler = outputScaler
modelNames, metrics_train, metrics_test, columnsList, deviationsList = mlModule.predictWithModels(
modelList,
X_train,
y_train,
X_test,
y_test,
targetColumns,
indexColumn,
columnDescriptions,
columnUnits,
traintime,
plot=True,
interpol=False,
)
columnsLists,
indexColumn,
columnDescriptions,
columnUnits,
traintime,
interpol=False,
)
plotModelScores(
plt,
all_names,
all_train_metrics,
all_test_metrics,
)
filename, columns, irrelevantColumns, targetColumns, traintime, testtime, columnOrder = configs.getConfig(
'D', None, '30min')
targetColumns = [
'50TT002',
]
irrelevantColumnsList = [
# Target: C T out
# Featers: P T in, P T out, P flow, C T in
[
'20PT001',
'50PDT001',
'50FT001',
'50TV001',
'50PT001',
'20PDT001',
],
# Target: C T out
def pred(facility, model, resolution):
filename, columns, irrelevantColumns, targetColumns, traintime, testtime, columnOrder = configs.getConfig(
facility, model, resolution)
df = mlModule.initDataframe(filename, columns, irrelevantColumns)
df_train, df_test = mlModule.getTestTrainSplit(traintime, testtime)
X_train, y_train, X_test, y_test = mlModule.getFeatureTargetSplit(
targetColumns)
lstm_1_1 = mlModule.LSTM('LSTM 1x128 d0.0' + ' mod' + model,
layers=[128],
dropout=0.0,
recurrentDropout=0.0,
epochs=5000)
lstm_1_2 = mlModule.LSTM('LSTM 1x128 d0.1' + ' mod' + model,
layers=[128],
dropout=0.1,
recurrentDropout=0.1,
epochs=5000)
lstm_1_3 = mlModule.LSTM('LSTM 1x128 d0.2' + ' mod' + model,
layers=[128],
dropout=0.2,
recurrentDropout=0.2,
epochs=5000)
lstm_1_4 = mlModule.LSTM('LSTM 1x128 d0.3' + ' mod' + model,
layers=[128],
dropout=0.3,
recurrentDropout=0.3,
epochs=5000)
lstm_1_5 = mlModule.LSTM('LSTM 1x128 d0.4' + ' mod' + model,
layers=[128],
dropout=0.4,
recurrentDropout=0.4,
epochs=5000)
lstm_1_6 = mlModule.LSTM('LSTM 1x128 d0.5' + ' mod' + model,
layers=[128],
dropout=0.5,
recurrentDropout=0.5,
epochs=5000)
linear = mlModule.Linear_Regularized('Linear rCV mod' + model)
initTrainPredict([
linear,
lstm_1_1,
lstm_1_2,
lstm_1_3,
lstm_1_4,
lstm_1_5,
lstm_1_6,
])
def pred(facility, model, resolution):
filename, columns, irrelevantColumns, targetColumns, traintime, testtime, columnOrder = configs.getConfig(
facility, model, resolution)
df = mlModule.initDataframe(filename, columns, irrelevantColumns)
df_train, df_test = mlModule.getTestTrainSplit(traintime, testtime)
X_train, y_train, X_test, y_test = mlModule.getFeatureTargetSplit(
targetColumns)
mlpr_1_1 = mlModule.MLP('MLP 1x128 1.0' + ' mod' + model,
layers=[128],
l1_rate=1.0,
epochs=5000)
mlpr_1_2 = mlModule.MLP('MLP 1x128 0.5' + ' mod' + model,
layers=[128],
l1_rate=0.5,
epochs=5000)
mlpr_1_3 = mlModule.MLP('MLP 1x128 0.1' + ' mod' + model,
layers=[128],
l1_rate=0.1,
epochs=5000)
mlpr_1_4 = mlModule.MLP('MLP 1x128 0.05' + ' mod' + model,
layers=[128],
l1_rate=0.05,
epochs=5000)
mlpr_1_5 = mlModule.MLP('MLP 1x128 0.01' + ' mod' + model,
layers=[128],
l1_rate=0.01,
epochs=5000)
mlpr_1_6 = mlModule.MLP('MLP 1x128 0.005' + ' mod' + model,
layers=[128],
l1_rate=0.005,
epochs=5000)
mlpr_1_7 = mlModule.MLP('MLP 1x128 0.001' + ' mod' + model,
layers=[128],
l1_rate=0.001,
epochs=5000)
mlpd_1_8 = mlModule.MLP('MLP 1x128 0.2' + ' mod' + model,
layers=[128],
dropout=0.2,
epochs=5000)
linear_r = mlModule.Linear_Regularized('Linear rCV' + ' mod' + model)
initTrainPredict([
mlpr_1_1,
mlpr_1_2,
mlpr_1_3,
mlpr_1_4,
mlpr_1_5,
mlpr_1_6,
mlpr_1_7,
mlpd_1_8,
linear_r,
])
initTrainPredict([
mlpr_1_6,
mlpr_1_7,
mlpd_1_8,
linear_r,
])
def pred(facility, model, resolution):
filename, columns, irrelevantColumns, targetColumns, traintime, testtime, columnOrder = configs.getConfig(
facility, model, resolution)
df = mlModule.initDataframe(filename, columns, irrelevantColumns)
df_train, df_test = mlModule.getTestTrainSplit(traintime, testtime)
X_train, y_train, X_test, y_test = mlModule.getFeatureTargetSplit(
targetColumns)
mlp_1x_16 = mlModule.MLP('MLP 1x16' + ' mod' + model,
layers=[16],
dropout=0.2,
epochs=1000)
mlp_1x_32 = mlModule.MLP('MLP 1x32' + ' mod' + model,
layers=[32],
dropout=0.2,
epochs=1000)
mlp_1x_64 = mlModule.MLP('MLP 1x64' + ' mod' + model,
layers=[64],
dropout=0.2,
epochs=1000)
mlp_1x_128 = mlModule.MLP('MLP 1x128' + ' mod' + model,
layers=[128],
dropout=0.2,
epochs=1000)
mlp_2x_16 = mlModule.MLP('MLP 2x16' + ' mod' + model,
layers=[16, 16],
dropout=0.2,
epochs=1000)
mlp_2x_32 = mlModule.MLP('MLP 2x32' + ' mod' + model,
layers=[32, 32],
dropout=0.2,
epochs=1000)
mlp_2x_64 = mlModule.MLP('MLP 2x64' + ' mod' + model,
layers=[64, 64],
dropout=0.2,
epochs=1000)
mlp_2x_128 = mlModule.MLP('MLP 2x128' + ' mod' + model,
layers=[128, 128],
dropout=0.2,
epochs=1000)
linear_cv = mlModule.Linear_Regularized('Linear rCV' + ' mod' + model)
ensemble = mlModule.Ensemble('MLP 1x128 + Linear' + ' mod' + model,
[mlp_1x_128, linear_cv])
ensemble2 = mlModule.Ensemble('MLP 2x64 + Linear' + ' mod' + model,
[mlp_2x_64, linear_cv])
modelList = [
linear_cv,
mlp_1x_16,
mlp_1x_32,
mlp_2x_16,
mlp_2x_32,
]
initTrainPredict(modelList)
modelList = [
linear_cv,
mlp_1x_64,
mlp_1x_128,
mlp_2x_64,
mlp_2x_128,
]
initTrainPredict(modelList)
modelList = [
linear_cv,
ensemble,
ensemble2,
]
initTrainPredict(modelList)
def performDropoutPrediction(facility,
model,
resolution,
lookback=12,
retrain=False):
filename, columns, irrelevantColumns, targetColumns, traintime, testtime, columnOrder = configs.getConfig(
facility, model, resolution)
df = mlModule.initDataframe(filename, columns, irrelevantColumns)
df_train, df_test = mlModule.getTestTrainSplit(traintime, testtime)
X_train, y_train, X_test, y_test = mlModule.getFeatureTargetSplit(
targetColumns)
lstm = mlModule.LSTM('LSTMs 1x128 d0.2 mod' + model,
layers=[128],
training=True,
dropout=0.2,
recurrentDropout=0.2,
enrolWindow=lookback)
gru = mlModule.GRU('GRUs 1x128 d0.2 mod' + model,
layers=[128],
training=True,
dropout=0.2,
recurrentDropout=0.2,
enrolWindow=lookback)
modelList = [
lstm,
gru,
]
mlModule.initModels(modelList)
mlModule.trainModels(retrain)
predictions, means, stds = mlModule.predictWithModelsUsingDropout(
numberOfPredictions=30)
plotDropoutPrediction(modelList, predictions, means, stds, targetColumns,
df_test, y_test, traintime)