Spaces:
Sleeping
Sleeping
albin
commited on
Commit
·
1127d65
1
Parent(s):
c9f777a
remove url parameter
Browse files- extraction_features.py +1 -1
- label_encoders.pkl +2 -2
- logistic_regression_model.pkl +2 -2
- main.py +2 -2
extraction_features.py
CHANGED
|
@@ -15,7 +15,7 @@ def extract_features(url):
|
|
| 15 |
features = {}
|
| 16 |
|
| 17 |
# URL
|
| 18 |
-
features['URL'] = url
|
| 19 |
|
| 20 |
# URLLength
|
| 21 |
features['URLLength'] = len(url)
|
|
|
|
| 15 |
features = {}
|
| 16 |
|
| 17 |
# URL
|
| 18 |
+
# features['URL'] = url
|
| 19 |
|
| 20 |
# URLLength
|
| 21 |
features['URLLength'] = len(url)
|
label_encoders.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3db2d4c2f44297075aeec0b104794135b2bae52288f102b21b35fd7b45649d2e
|
| 3 |
+
size 6961649
|
logistic_regression_model.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a7bc11b6b53b1a34501d639a64111d205d408e50fd5ba09bbfdb8018434e2cf
|
| 3 |
+
size 1451
|
main.py
CHANGED
|
@@ -29,7 +29,7 @@ model = joblib.load('logistic_regression_model.pkl')
|
|
| 29 |
label_encoders = joblib.load('label_encoders.pkl')
|
| 30 |
# Columns used in the model
|
| 31 |
selected_columns = [
|
| 32 |
-
'
|
| 33 |
'CharContinuationRate', 'TLDLength', 'NoOfSubDomain',
|
| 34 |
'DegitRatioInURL', 'SpacialCharRatioInURL', 'IsHTTPS'
|
| 35 |
]
|
|
@@ -91,7 +91,7 @@ async def predict(request: Request, requess: Req = Depends(form_req)):
|
|
| 91 |
dataFrame_features = pd.DataFrame([features])
|
| 92 |
|
| 93 |
# Apply features encoding (convert everything into int64)
|
| 94 |
-
for column in ['
|
| 95 |
encoder = label_encoders[column]
|
| 96 |
dataFrame_features[column] = dataFrame_features[column].apply(lambda x: safe_transform(encoder, x))
|
| 97 |
|
|
|
|
| 29 |
label_encoders = joblib.load('label_encoders.pkl')
|
| 30 |
# Columns used in the model
|
| 31 |
selected_columns = [
|
| 32 |
+
'URLLength', 'Domain', 'DomainLength', 'TLD',
|
| 33 |
'CharContinuationRate', 'TLDLength', 'NoOfSubDomain',
|
| 34 |
'DegitRatioInURL', 'SpacialCharRatioInURL', 'IsHTTPS'
|
| 35 |
]
|
|
|
|
| 91 |
dataFrame_features = pd.DataFrame([features])
|
| 92 |
|
| 93 |
# Apply features encoding (convert everything into int64)
|
| 94 |
+
for column in ['Domain', 'TLD']:
|
| 95 |
encoder = label_encoders[column]
|
| 96 |
dataFrame_features[column] = dataFrame_features[column].apply(lambda x: safe_transform(encoder, x))
|
| 97 |
|