def initTrainPredict(modelList, retrain=False, plot=True, interpol=False):
# 4. Initiate and train models
mlModule.initModels(modelList)
mlModule.trainModels(retrain)
# 5. Predict
modelNames, metrics_train, metrics_test, columnsList, deviationsList = mlModule.predictWithModels(
plot=plot,
interpol=interpol,
)
lstm_2,
lstm_3,
lstm_4,
ensemble1,
ensemble2,
]
# Define whether to retrain models or not
retrain = False
mlModule.initModels(modelList)
mlModule.trainModels(retrain)
modelNames, metrics_train, metrics_test, columnsList, deviationsList = mlModule.predictWithModels(
plot=True,
interpol=False,
score=True,
)
import src.utils.utilities as utils
import src.utils.plots as plots
import matplotlib.pyplot as plt
df_fouling = utils.readDataFile('../master-thesis-db/datasets/D/foulingC.csv')
df_fouling = utils.getDataWithTimeIndex(df_fouling)
def foulingPlot(deviationsList, name):
y1 = deviationsList[0][0][2]
y2 = (-1) * df_fouling['Fouling'].values[mlModule._maxEnrolWindow:]
x = mlModule._indexColumn
def featureComparison(
irrelevantColumnsList,
filename,
columns,
traintime,
testtime,
targetColumns,
enrolWindow,
):
global colors, models
columnsLists = []
deviationsLists = []
names = []
trainmetrics = []
testmetrics = []
for i, irrelevantColumns in enumerate(irrelevantColumnsList):
mlModule.reset()
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_1 = mlModule.MLP('MLP 1x64 d0.2 mod' + models[i],
layers=[64],
dropout=0.2)
mlp_2 = mlModule.MLP('MLP 1x128 d0.2 mod' + models[i],
layers=[128],
dropout=0.2)
mlp_3 = mlModule.MLP('MLP 2x64 d0.2 mod' + models[i],
layers=[64, 64],
dropout=0.2)
mlp_4 = mlModule.MLP('MLP 2x128 d0.2 mod' + models[i],
layers=[128, 128],
dropout=0.2)
lstm_1 = mlModule.LSTM('LSTM 1x64 d0.2 mod' + models[i],
layers=[64],
dropout=0.2,
recurrentDropout=0.2,
enrolWindow=12)
lstm_2 = mlModule.LSTM('LSTM 1x128 d0.2 mod' + models[i],
layers=[128],
dropout=0.2,
recurrentDropout=0.2,
enrolWindow=12)
lstm_3 = mlModule.LSTM('LSTM 2x64 d0.2 mod' + models[i],
layers=[64, 64],
dropout=0.2,
recurrentDropout=0.2,
enrolWindow=12)
lstm_4 = mlModule.LSTM('LSTM 2x128 d0.2 mod' + models[i],
layers=[128, 128],
dropout=0.2,
recurrentDropout=0.2,
enrolWindow=12)
linear = mlModule.Linear_Regularized('Linear rCV mod' + models[i])
modelList = [
mlp_1,
mlp_2,
mlp_3,
mlp_4,
lstm_1,
lstm_2,
lstm_3,
lstm_4,
linear,
]
mlModule.initModels(modelList)
retrain = False
mlModule.trainModels(retrain)
modelNames, metrics_train, metrics_test, columnsList, deviationsList = mlModule.predictWithModels(
plot=True, score=True)
if i < 1:
columnsLists = columnsList
deviationsLists = deviationsList
all_names = modelNames
all_train_metrics = metrics_train
all_test_metrics = metrics_test
else:
for j_target in range(len(columnsList)):
for k_model in range(1, len(columnsList[j_target])):
columnsLists[j_target].append(
columnsList[j_target][k_model])
for k_model in range(0, len(deviationsList[j_target])):
deviationsLists[j_target].append(
deviationsList[j_target][k_model])
all_names = [*all_names, *modelNames]
all_train_metrics = [*all_train_metrics, *metrics_train]
all_test_metrics = [*all_test_metrics, *metrics_test]
names.append(modelNames)
trainmetrics.append(metrics_train)
testmetrics.append(metrics_test)
indexColumn = mlModule._indexColumn
columnDescriptions = mlModule._columnDescriptions
columnUnits = mlModule._columnUnits
traintime = mlModule._traintime
for i in range(len(deviationsLists)):
for j in range(len(deviationsLists[i])):
deviationsLists[i][j][3] = colors[j]
for i in range(len(columnsLists)):
columnsList[i][0][3] = 'red'
for j in range(1, len(columnsLists[i])):
columnsLists[i][j][3] = colors[j - 1]
printModelScores(
all_names,
all_train_metrics,
all_test_metrics,
)
plotModelPredictions(
plt,
deviationsLists,
columnsLists,
indexColumn,
columnDescriptions,
columnUnits,
traintime,
interpol=False,
)
plotModelScores(
plt,
all_names,
all_train_metrics,
all_test_metrics,
)