diff options
Diffstat (limited to 'backend')
| -rw-r--r-- | backend/microservice/api/controller.py | 7 | ||||
| -rw-r--r-- | backend/microservice/api/newmlservice.py | 17 |
2 files changed, 17 insertions, 7 deletions
diff --git a/backend/microservice/api/controller.py b/backend/microservice/api/controller.py index 41035cc7..988ad987 100644 --- a/backend/microservice/api/controller.py +++ b/backend/microservice/api/controller.py @@ -118,7 +118,6 @@ def returnColumnsInfo(): ''' preprocess = newmlservice.returnColumnsInfo(data) #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"][0:6] col["uniqueValuesCount"] = col["uniqueValuesCount"][0:6] @@ -128,11 +127,9 @@ def returnColumnsInfo(): dataset["nullRows"] = preprocess["allNullRows"] dataset["colCount"] = preprocess["colCount"] dataset["rowCount"] = preprocess["rowCount"] + dataset["cMatrix"]=preprocess['cMatrix'] dataset["isPreProcess"] = True - #print(dataset) - - - + return jsonify(dataset) print("App loaded.") diff --git a/backend/microservice/api/newmlservice.py b/backend/microservice/api/newmlservice.py index 9e26b03a..f5e5abcc 100644 --- a/backend/microservice/api/newmlservice.py +++ b/backend/microservice/api/newmlservice.py @@ -27,15 +27,28 @@ import matplotlib.pyplot as plt #from ann_visualizer.visualize import ann_viz; def returnColumnsInfo(dataset): dict=[] + datafront=dataset.copy() + dataMatrix=dataset.copy() + + svekolone=datafront.columns kategorijskekolone=datafront.select_dtypes(include=['object']).columns + allNullCols=0 rowCount=datafront.shape[0]#ukupan broj redova colCount=len(datafront.columns)#ukupan broj kolona for kolona in svekolone: if(kolona in kategorijskekolone): + encoder=LabelEncoder() + dataMatrix[kolona]=encoder.fit_transform(dataMatrix[kolona]) + + #print(dataMatrix.dtypes) + cMatrix=dataMatrix.corr() + + for kolona in svekolone: + if(kolona in kategorijskekolone): unique=datafront[kolona].value_counts() uniquevalues=[] uniquevaluescount=[] @@ -86,7 +99,7 @@ def returnColumnsInfo(dataset): #pretvaranje u kategorijsku datafront = datafront.astype({kolona: str}) - print(datafront.dtypes) + #print(datafront.dtypes) unique=datafront[kolona].value_counts() uniquevaluesn=[] uniquevaluescountn=[] @@ -117,7 +130,7 @@ def returnColumnsInfo(dataset): #print(NullRows) #print(len(NullRows)) allNullRows=len(NullRows) - return {'columnInfo':dict,'allNullColl':int(allNullCols),'allNullRows':int(allNullRows),'rowCount':int(rowCount),'colCount':int(colCount)} + return {'columnInfo':dict,'allNullColl':int(allNullCols),'allNullRows':int(allNullRows),'rowCount':int(rowCount),'colCount':int(colCount),'cMatrix':str(np.matrix(cMatrix))} @dataclass class TrainingResultClassification: |