diff options
| author | TAMARA JERINIC <tamara.jerinic@gmail.com> | 2022-05-03 21:28:57 +0200 |
|---|---|---|
| committer | TAMARA JERINIC <tamara.jerinic@gmail.com> | 2022-05-03 21:28:57 +0200 |
| commit | f32ec4fe8ae54f2154fa3393040a07cdb579b07f (patch) | |
| tree | 32ae884f34acf6ecdcefb010f24b5b70ce431eba /backend | |
| parent | 5a8691915071483da3bcccc80839fadd5872eaf2 (diff) | |
Usklađen izbor kategorijskih kolona na frontu sa ml servisom.
Diffstat (limited to 'backend')
| -rw-r--r-- | backend/microservice/api/controller.py | 6 | ||||
| -rw-r--r-- | backend/microservice/api/newmlservice.py | 16 |
2 files changed, 17 insertions, 5 deletions
diff --git a/backend/microservice/api/controller.py b/backend/microservice/api/controller.py index fad6e181..41035cc7 100644 --- a/backend/microservice/api/controller.py +++ b/backend/microservice/api/controller.py @@ -120,9 +120,9 @@ def returnColumnsInfo(): #samo 10 jedinstvenih posto ih ima previse, bilo bi dobro da promenimo ovo da to budu 10 najzastupljenijih vrednosti for col in preprocess["columnInfo"]: - col["uniqueValues"] = col["uniqueValues"][0:5] - col["uniqueValuesCount"] = col["uniqueValuesCount"][0:5] - col['uniqueValuesPercent']=col['uniqueValuesPercent'][0:5] + col["uniqueValues"] = col["uniqueValues"][0:6] + col["uniqueValuesCount"] = col["uniqueValuesCount"][0:6] + col['uniqueValuesPercent']=col['uniqueValuesPercent'][0:6] dataset["columnInfo"] = preprocess["columnInfo"] dataset["nullCols"] = preprocess["allNullColl"] dataset["nullRows"] = preprocess["allNullRows"] diff --git a/backend/microservice/api/newmlservice.py b/backend/microservice/api/newmlservice.py index 647c3b79..631837e5 100644 --- a/backend/microservice/api/newmlservice.py +++ b/backend/microservice/api/newmlservice.py @@ -148,6 +148,7 @@ class TrainingResult: ''' def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): + ###UCITAVANJE SETA problem_type = paramsModel["type"] #print(problem_type) data = pd.DataFrame() @@ -159,6 +160,15 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): data[output_column] = dataset[output_column] #print(data) + ###KATEGORIJSKE KOLONE + kategorijskekolone=[] + ###PRETVARANJE NUMERICKIH U KATREGORIJSKE AKO JE KORISNIK TAKO OZNACIO + columnInfo=paramsDataset['columnInfo'] + for col in columnInfo: + if(col['columnType']=="Kategorijski"): + data[col['columnName']]=data[col['columnName']].apply(str) + kategorijskekolone.append(col['coumnName']) + ###NULL null_value_options = paramsExperiment["nullValues"] null_values_replacers = paramsExperiment["nullValuesReplacers"] @@ -182,16 +192,18 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): # # Brisanje kolona koje ne uticu na rezultat # + ''' num_rows=data.shape[0] for col in data.columns: if((data[col].nunique()==(num_rows)) and (data[col].dtype==np.object_)): data.pop(col) # + ''' ### Enkodiranje encodings=paramsExperiment["encodings"] datafront=dataset.copy() - svekolone=datafront.columns - kategorijskekolone=datafront.select_dtypes(include=['object']).columns + #svekolone=datafront.columns + #kategorijskekolone=datafront.select_dtypes(include=['object']).columns for kolonaEncoding in encodings: kolona = kolonaEncoding["columnName"] |