Merge branch 'dev' of http://gitlab.pmf.kg.ac.rs/igrannonica/neuronstellar into dev

2 files changed, 46 insertions, 41 deletions

diff --git a/backend/microservice/api/controller.py b/backend/microservice/api/controller.py
index e6515e7b..9b83b8e7 100644
--- a/backend/microservice/api/controller.py
+++ b/backend/microservice/api/controller.py
@@ -78,7 +78,7 @@ def train():
         m.append({"Name" : attribute, "JsonValue" : value})
     predictor = {
         "_id" : "",
-        "username" : paramsModel["username"],
+        "uploaderId" : paramsModel["uploaderId"],
         "inputs" : paramsExperiment["inputColumns"],
         "output" : paramsExperiment["outputColumn"],
         "isPublic" : False,
diff --git a/backend/microservice/api/newmlservice.py b/backend/microservice/api/newmlservice.py
index a9bce3bb..9951c25f 100644
--- a/backend/microservice/api/newmlservice.py
+++ b/backend/microservice/api/newmlservice.py
@@ -156,48 +156,53 @@ def train(dataset, paramsModel,paramsExperiment,paramsDataset,callback):
     #
     ### Enkodiranje
     encoding=paramsExperiment["encoding"]
-    if(encoding=='label'):
-        encoder=LabelEncoder()
-        for col in data.columns:
-            if(data[col].dtype==np.object_):
-                data[col]=encoder.fit_transform(data[col])
+    datafront=dataset.copy()
+    svekolone=datafront.columns
+    kategorijskekolone=datafront.select_dtypes(include=['object']).columns
+    for kolona in svekolone:
+        if(kolona in kategorijskekolone):
+            if(encoding=='label'):
+                encoder=LabelEncoder()
+                for col in data.columns:
+                    if(data[col].dtype==np.object_):
+                        data[col]=encoder.fit_transform(data[col])
     
     
-    elif(encoding=='onehot'):
-        category_columns=[]
-        for col in data.columns:
-            if(data[col].dtype==np.object_):
-                category_columns.append(col)
-        data=pd.get_dummies(data, columns=category_columns, prefix=category_columns)
-
-    elif(encoding=='ordinal'):
-        encoder = OrdinalEncoder()
-        for col in data.columns:
-            if(data[col].dtype==np.object_):
-                data[col]=encoder.fit_transform(data[col])
- 
-    elif(encoding=='hashing'):
-        category_columns=[]
-        for col in data.columns:
-            if(data[col].dtype==np.object_):
-                category_columns.append(col)
-        encoder=ce.HashingEncoder(cols=category_columns, n_components=len(category_columns))
-        encoder.fit_transform(data)
-    elif(encoding=='binary'):
-        category_columns=[]
-        for col in data.columns:
-            if(data[col].dtype==np.object_):
-                category_columns.append(col)
-        encoder=ce.BinaryEncoder(cols=category_columns, return_df=True)
-        encoder.fit_transform(data)
-       
-    elif(encoding=='baseN'):
-        category_columns=[]
-        for col in data.columns:
-            if(data[col].dtype==np.object_):
-                category_columns.append(col)
-        encoder=ce.BaseNEncoder(cols=category_columns, return_df=True, base=5)
-        encoder.fit_transform(data)
+            elif(encoding=='onehot'):
+                category_columns=[]
+                for col in data.columns:
+                    if(data[col].dtype==np.object_):
+                        category_columns.append(col)
+                data=pd.get_dummies(data, columns=category_columns, prefix=category_columns)
+
+            elif(encoding=='ordinal'):
+                encoder = OrdinalEncoder()
+                for col in data.columns:
+                    if(data[col].dtype==np.object_):
+                        data[col]=encoder.fit_transform(data[col])
+        
+            elif(encoding=='hashing'):
+                category_columns=[]
+                for col in data.columns:
+                    if(data[col].dtype==np.object_):
+                        category_columns.append(col)
+                encoder=ce.HashingEncoder(cols=category_columns, n_components=len(category_columns))
+                encoder.fit_transform(data)
+            elif(encoding=='binary'):
+                category_columns=[]
+                for col in data.columns:
+                    if(data[col].dtype==np.object_):
+                        category_columns.append(col)
+                encoder=ce.BinaryEncoder(cols=category_columns, return_df=True)
+                encoder.fit_transform(data)
+            
+            elif(encoding=='baseN'):
+                category_columns=[]
+                for col in data.columns:
+                    if(data[col].dtype==np.object_):
+                        category_columns.append(col)
+                encoder=ce.BaseNEncoder(cols=category_columns, return_df=True, base=5)
+                encoder.fit_transform(data)
     #
     # Input - output
     #