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,
)
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)
pred('D', 'A', '30min')
mlModule.reset()
pred('D', 'B', '30min')
mlModule.reset()
pred('F', 'A', '30min')
mlModule.reset()
pred('F', 'B', '30min')
mlModule.reset()
pred('G', 'A', '30min')
mlModule.reset()
pred('G', 'B', '30min')
mlModule.reset()
df = mlApi.initDataframe(filename, columns, irrelevantColumns)
df_train, df_test = mlApi.getTestTrainSplit(traintime, testtime)
df_test_1, df_test_2 = mlApi.getTestTrainSplit([testtime1], testtime2)
df_test_joined = pd.concat([df_test_1, df_test_2])
# 3. Plot correlation plots
mlApi.correlationPlot(df_train, datasetName + " train")
mlApi.correlationDuoPlot(df_test_1, df_test_2, datasetName + " test 1",
datasetName + " test 2")
mlApi.correlationDifferencePlot(
df_train, df_test_joined, "Difference, " + datasetName + " train and test")
# Reset to prepare for second dataset
# -------------------------------------
mlApi.reset()
# -------------------------------------
# 1.
filename = "../master-thesis-db/datasets/F/data_180min.csv"
datasetName = "F - Real HX"
columns = [
['FYN0111', 'Gasseksport rate', 'MSm^3/d'],
['TT0106_MA_Y', 'Varm side C temperatur inn', 'degrees'],
['TIC0105_CA_YX', 'Varm side C temperatur ut', 'degrees'],
['TI0115_MA_Y', 'Scrubber temperatur ut', 'degrees'],
['PIC0104_CA_YX', 'Innløpsseparator trykk', 'Barg'],
['TIC0425_CA_YX', 'Kald side temperatur inn', 'degrees'],