aboutsummaryrefslogtreecommitdiff
path: root/backend/microservice/api/newmlservice.py
diff options
context:
space:
mode:
authorTAMARA JERINIC <tamara.jerinic@gmail.com>2022-05-04 21:02:50 +0200
committerTAMARA JERINIC <tamara.jerinic@gmail.com>2022-05-04 21:02:50 +0200
commit4858cd15ec093245e5febc39f3176370c9947ab4 (patch)
tree790289b8e7a4cd67d0649559872d7f64c3ef9e5c /backend/microservice/api/newmlservice.py
parent3ac7a37690765d6c116463dc8a6ef08b18afea50 (diff)
Dodato računanje korelacione matrice.
Diffstat (limited to 'backend/microservice/api/newmlservice.py')
-rw-r--r--backend/microservice/api/newmlservice.py17
1 files changed, 15 insertions, 2 deletions
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: