diff options
Diffstat (limited to 'backend/microservice/api/newmlservice.py')
| -rw-r--r-- | backend/microservice/api/newmlservice.py | 23 |
1 files changed, 18 insertions, 5 deletions
diff --git a/backend/microservice/api/newmlservice.py b/backend/microservice/api/newmlservice.py index 3244e82f..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: @@ -349,7 +362,7 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): classifier.compile(loss =paramsModel["lossFunction"] , optimizer = opt, metrics =paramsModel['metrics']) - history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=paramsModel['batchSize'],callbacks=callback(x_test, y_test,paramsModel['_id'])) + history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=float(paramsModel['batchSize']),callbacks=callback(x_test, y_test,paramsModel['_id'])) hist=history.history #plt.plot(hist['accuracy']) @@ -403,7 +416,7 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): classifier.compile(loss =paramsModel["lossFunction"] , optimizer = opt , metrics =paramsModel['metrics']) - history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=paramsModel['batchSize'],callbacks=callback(x_test, y_test,paramsModel['_id'])) + history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=float(paramsModel['batchSize']),callbacks=callback(x_test, y_test,paramsModel['_id'])) hist=history.history y_pred=classifier.predict(x_test) y_pred=(y_pred>=0.5).astype('int') @@ -452,7 +465,7 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback): classifier.compile(loss =paramsModel["lossFunction"] , optimizer = opt , metrics =paramsModel['metrics']) - history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=paramsModel['batchSize'],callbacks=callback(x_test, y_test,paramsModel['_id'])) + history=classifier.fit(x_train, y_train, epochs = paramsModel['epochs'],batch_size=float(paramsModel['batchSize']),callbacks=callback(x_test, y_test,paramsModel['_id'])) hist=history.history y_pred=classifier.predict(x_test) #print(classifier.evaluate(x_test, y_test)) |