diff --git a/is/kaggle/cv.py b/is/kaggle/cv.py
index 3d11bf3..acb1d68 100644
--- a/is/kaggle/cv.py
+++ b/is/kaggle/cv.py
@@ -7,26 +7,54 @@
     return(pd.read_csv(path, index_col='Date', parse_dates='Date'))
 
 data=read()
-cleanData=data[pd.notnull(data['Weight'])]
 
-def cv(data=cleanData, n_folds=10):
+def cv(data=data, n_folds=10):
     """split data in n_folds parts for cross validation
     """
-    kf=KFold(len(data), shuffle=True, n_folds=n_folds)
+
+    cleanData=data[pd.notnull(data['Weight'])]
+
+    kf=KFold(len(cleanData), shuffle=True, n_folds=n_folds)
 
     trainid=[]
     testid=[]
     for train, test in kf:
         trainid.append(train)
         testid.append(test)
-    data_train=[]
-    data_test=[]
 
+    data_test=[]
+    data_train=[]
     for i in range(n_folds):
-        data_train.append(pd.DataFrame(data.iloc[j] for j in trainid[i]))
-        data_test.append(pd.DataFrame(data.iloc[j] for j in testid[i]))
+        data_train.append(data.copy())
+        data_test.append([])
+        for j in testid[i]:
+            data_test[i].append(pd.DataFrame(cleanData.iloc[j]))
+            #crazy hack, necessary ...
+            train=data_train[i][data_train[i]['ID']==cleanData.iloc[j]['ID']]
+            train['Weight']=float('NaN')
+            data_train[i][data_train[i]['ID']==cleanData.iloc[j]['ID']]=train
+            print(data_train[i][data_train[i]['ID']==cleanData.iloc[j]['ID']]['Weight'])
     return (data_train,data_test)
 
 data_train, data_test=cv()
 
-#print(data_test[0])
+def evaluate(predictions, data_test, predictedWeight='predWeight'):
+    """calcs the rmse on the testdata"""
+    n=len(data_test)
+    error=0
+    for i in range(n):
+        test_value=np.float64(data_test[i].loc['Weight'])
+        #no better idea...
+        pred_value=predictions.iloc[int(data_test[i].loc['ID'])-1][predictedWeight]
+        print("test:",test_value)
+        print("pred:",pred_value)
+        error+= (test_value - pred_value)**2
+        print(error)
+    return(np.sqrt(error/n))
+
+#1st example
+for i in range(10):
+    data_train[i]['WeightInter'] = data_train[i]['Weight'].interpolate()
+    print(data_train[i])
+    print("RMSE(",i,"):",evaluate(data_train[i], data_test[i],'WeightInter'))
+