StackGenVis: Alignment of Data, Algorithms, and Models for Stacking Ensemble Learning Using Performance Metrics https://doi.org/10.1109/TVCG.2020.3030352
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
StackGenVis/cachedir/joblib/run/EnsembleModel/func_code.py

85 lines
4.2 KiB

# first line: 703
@memory.cache
def EnsembleModel(keyRetrieved):
scoresLocal = []
all_classifiersSelection = []
if (keyRetrieved == 0):
columnsInit = []
all_classifiers = []
columnsInit = [XData.columns.get_loc(c) for c in XData.columns if c in XData]
temp = json.loads(allParametersPerformancePerModel[1])
dfParamKNN = pd.DataFrame.from_dict(temp)
dfParamKNNFilt = dfParamKNN.iloc[:,1]
for eachelem in KNNModels:
arg = dfParamKNNFilt[eachelem]
all_classifiers.append(make_pipeline(ColumnSelector(cols=columnsInit), KNeighborsClassifier().set_params(**arg)))
temp = json.loads(allParametersPerformancePerModel[9])
dfParamRF = pd.DataFrame.from_dict(temp)
dfParamRFFilt = dfParamRF.iloc[:,1]
for eachelem in RFModels:
arg = dfParamRFFilt[eachelem-576]
all_classifiers.append(make_pipeline(ColumnSelector(cols=columnsInit), RandomForestClassifier().set_params(**arg)))
lr = LogisticRegression()
sclf = StackingCVClassifier(classifiers=all_classifiers,
use_probas=True,
meta_classifier=lr,
random_state=RANDOM_SEED,
n_jobs = -1)
elif (keyRetrieved == 1):
ClassifierIDsList = json.loads(ClassifierIDsList)
for loop in ClassifierIDsList['ClassifiersList']:
temp = [int(s) for s in re.findall(r'\b\d+\b', loop)]
all_classifiersSelection.append(all_classifiers[temp[0]])
lr = LogisticRegression()
sclf = StackingCVClassifier(classifiers=all_classifiersSelection,
use_probas=True,
meta_classifier=lr,
random_state=RANDOM_SEED,
n_jobs = -1)
else:
columnsReduce = columns.copy()
lr = LogisticRegression()
if (len(all_classifiersSelection) == 0):
all_classifiers = []
for index, eachelem in enumerate(algorithmsWithoutDuplicates):
if (eachelem == 'KNN'):
for j, each in enumerate(resultsList[index][1]):
all_classifiers.append(make_pipeline(ColumnSelector(cols=columnsReduce[j]), KNeighborsClassifier().set_params(**each)))
del columnsReduce[0:len(resultsList[index][1])]
else:
for j, each in enumerate(resultsList[index][1]):
all_classifiers.append(make_pipeline(ColumnSelector(cols=columnsReduce[j]), RandomForestClassifier().set_params(**each)))
del columnsReduce[0:len(resultsList[index][1])]
sclf = StackingCVClassifier(classifiers=all_classifiers,
use_probas=True,
meta_classifier=lr,
random_state=RANDOM_SEED,
n_jobs = -1)
else:
for index, eachelem in enumerate(algorithmsWithoutDuplicates):
if (eachelem == 'KNN'):
for j, each in enumerate(resultsList[index][1]):
all_classifiersSelection.append(make_pipeline(ColumnSelector(cols=columnsReduce[j]), KNeighborsClassifier().set_params(**each)))
del columnsReduce[0:len(resultsList[index][1])]
else:
for j, each in enumerate(resultsList[index][1]):
all_classifiersSelection.append(make_pipeline(ColumnSelector(cols=columnsReduce[j]), RandomForestClassifier().set_params(**each)))
del columnsReduce[0:len(resultsList[index][1])]
sclf = StackingCVClassifier(classifiers=all_classifiersSelection,
use_probas=True,
meta_classifier=lr,
random_state=RANDOM_SEED,
n_jobs = -1)
for clf, label in zip([sclf],
['StackingClassifier']):
scoresLocal = model_selection.cross_val_score(clf, XData, yData, cv=crossValidation, scoring='accuracy')
return scoresLocal