Upload folder using huggingface_hub

en_ID/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48dc684753e19792ce04cadeae9025441fc6507396eb93ab6dc740f87f1f3dad
+oid sha256:b92dd822e9fe0a9008577929e372d12b86acb64892c1d82b970ea8ef8266d7c0
 size 9055

en_ID/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for en_ID
+Training Details: en_ID
 ========================================
 
 Language: en
 Register: ID
-Training Date: 2025-09-26 14:09:04
+Training Date: 2025-09-26 14:45:51
 
-Data Summary:
+Dataset:
 - Total samples: 41071
-- Training samples: 32856
-- Test samples: 8215
-- Embedding dimension: 1024
+- Training: 32856
+- Test: 8215
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: 'sports', ''
-- Class distribution: {'sports': 983, '': 40088}
+- 0: 'sports' (983 samples)
+- 1: '' (40088 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9984783931832014, 0.9987825292953888, 0.9975650585907777, 0.9989347131334653, 0.9981737939430833]
-- CV mean: 0.9984
-- CV std: 0.0005
-- CV confidence interval: 0.9984 ± 0.0010
+Performance:
+- CV Mean: 0.9985
+- CV Std: 0.0004
+- Test Accuracy: 0.9990
 
-Final Performance:
-- Test accuracy: 0.9988
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

en_NA-nb-OP/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f83d56eccb7a610a0b57baa16d63af8839c571455358919a4d892bcf581a66e
+oid sha256:cdf6213ec1998e9b7b840f60c5f2efee6d67b83b9a6fb83dbe1dbc0023edcfea
 size 33671

en_NA-nb-OP/training_details.txt

@@ -1,39 +1,30 @@
-Training Details for en_NA-nb-OP
+Training Details: en_NA-nb-OP
 ========================================
 
 Language: en
 Register: NA-nb-OP
-Training Date: 2025-09-26 14:08:46
+Training Date: 2025-09-26 14:45:21
 
-Data Summary:
+Dataset:
 - Total samples: 1536
-- Training samples: 1228
-- Test samples: 308
-- Embedding dimension: 1024
+- Training: 1228
+- Test: 308
+- Features: 1024
+- Classes: 4
 
 Classes:
-- Number of classes: 4
-- Class names: '', 'culture', 'dining', 'lifestyle'
-- Class distribution: {'': 747, 'culture': 327, 'dining': 172, 'lifestyle': 290}
+- 0: '' (747 samples)
+- 1: 'culture' (327 samples)
+- 2: 'dining' (172 samples)
+- 3: 'lifestyle' (290 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9634146341463414, 0.959349593495935, 0.9634146341463414, 0.9877551020408163, 0.9755102040816327]
-- CV mean: 0.9699
-- CV std: 0.0104
-- CV confidence interval: 0.9699 ± 0.0209
+Performance:
+- CV Mean: 0.9715
+- CV Std: 0.0089
+- Test Accuracy: 0.9578
 
-Final Performance:
-- Test accuracy: 0.9643
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

en_NA-nb/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97142d5962fb70803f26b449fa21ced30015b550de8604dc850ad50c07bee259
+oid sha256:ca26eb969da61f5c5ed6b0d6293e19961b59f6175f3e9a1e33bee16f1028afbb
 size 9055

en_NA-nb/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for en_NA-nb
+Training Details: en_NA-nb
 ========================================
 
 Language: en
 Register: NA-nb
-Training Date: 2025-09-26 14:08:58
+Training Date: 2025-09-26 14:45:42
 
-Data Summary:
+Dataset:
 - Total samples: 49026
-- Training samples: 39220
-- Test samples: 9806
-- Embedding dimension: 1024
+- Training: 39220
+- Test: 9806
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: '', 'comments'
-- Class distribution: {'': 46239, 'comments': 2787}
+- 0: '' (46239 samples)
+- 1: 'comments' (2787 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.989673635900051, 0.9886537480877103, 0.9903110657827638, 0.9899286078531362, 0.9903110657827638]
-- CV mean: 0.9898
-- CV std: 0.0006
-- CV confidence interval: 0.9898 ± 0.0012
+Performance:
+- CV Mean: 0.9912
+- CV Std: 0.0004
+- Test Accuracy: 0.9913
 
-Final Performance:
-- Test accuracy: 0.9897
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

fi_ID-NA/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91641ec86de57b7e5bc916dd05cad1bc6189dcd58a67f4f3cc8516af6ac5b228
+oid sha256:aa2a7c1041ee5eaa8356b7f207505f95d1d3737458f0e643bf36e65f971bf2c5
 size 9055

fi_ID-NA/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for fi_ID-NA
+Training Details: fi_ID-NA
 ========================================
 
 Language: fi
 Register: ID-NA
-Training Date: 2025-09-26 14:06:57
+Training Date: 2025-09-26 14:43:17
 
-Data Summary:
+Dataset:
 - Total samples: 1729
-- Training samples: 1383
-- Test samples: 346
-- Embedding dimension: 1024
+- Training: 1383
+- Test: 346
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: '', 'comments'
-- Class distribution: {'': 389, 'comments': 1340}
+- 0: '' (389 samples)
+- 1: 'comments' (1340 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9855595667870036, 0.9927797833935018, 0.9927797833935018, 0.9927536231884058, 0.9818840579710145]
-- CV mean: 0.9892
-- CV std: 0.0046
-- CV confidence interval: 0.9892 ± 0.0092
+Performance:
+- CV Mean: 0.9899
+- CV Std: 0.0042
+- Test Accuracy: 0.9884
 
-Final Performance:
-- Test accuracy: 0.9913
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

fi_ID/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15dc245f640dd24687143cb21fdedf34968f9de671aec463f8bbc91bec7ea88f
+oid sha256:75059136f8cd4874c39a66b86e9713dcf35e4aece62074b70d43654caa4d95f9
 size 9055

fi_ID/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for fi_ID
+Training Details: fi_ID
 ========================================
 
 Language: fi
 Register: ID
-Training Date: 2025-09-26 14:08:45
+Training Date: 2025-09-26 14:45:20
 
-Data Summary:
+Dataset:
 - Total samples: 34973
-- Training samples: 27978
-- Test samples: 6995
-- Embedding dimension: 1024
+- Training: 27978
+- Test: 6995
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: '', 'sports'
-- Class distribution: {'': 34495, 'sports': 478}
+- 0: '' (34495 samples)
+- 1: 'sports' (478 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9980343102215868, 0.9987491065046462, 0.9992852037169406, 0.9987488829311886, 0.9978552278820375]
-- CV mean: 0.9985
-- CV std: 0.0005
-- CV confidence interval: 0.9985 ± 0.0010
+Performance:
+- CV Mean: 0.9989
+- CV Std: 0.0007
+- Test Accuracy: 0.9983
 
-Final Performance:
-- Test accuracy: 0.9986
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

fi_NA-nb-OP-rv/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83cfc695439d258effeb25e30a6677c1c0e18b8d07c3a4e1c36738eac4b800ac
+oid sha256:25423d27a82c163563dc7e5da487792e1dadc5148016e6c292cfa0a0253c2c10
 size 33671

fi_NA-nb-OP-rv/training_details.txt

@@ -1,39 +1,30 @@
-Training Details for fi_NA-nb-OP-rv
+Training Details: fi_NA-nb-OP-rv
 ========================================
 
 Language: fi
 Register: NA-nb-OP-rv
-Training Date: 2025-09-26 14:06:58
+Training Date: 2025-09-26 14:43:21
 
-Data Summary:
+Dataset:
 - Total samples: 4929
-- Training samples: 3943
-- Test samples: 986
-- Embedding dimension: 1024
+- Training: 3943
+- Test: 986
+- Features: 1024
+- Classes: 4
 
 Classes:
-- Number of classes: 4
-- Class names: 'books', 'dining', 'beverages', 'cosmetics'
-- Class distribution: {'books': 2958, 'dining': 294, 'beverages': 283, 'cosmetics': 1394}
+- 0: 'books' (2958 samples)
+- 1: 'dining' (294 samples)
+- 2: 'beverages' (283 samples)
+- 3: 'cosmetics' (1394 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9898605830164765, 0.9936628643852978, 0.9936628643852978, 0.9885786802030457, 0.9911167512690355]
-- CV mean: 0.9914
-- CV std: 0.0020
-- CV confidence interval: 0.9914 ± 0.0041
+Performance:
+- CV Mean: 0.9937
+- CV Std: 0.0029
+- Test Accuracy: 0.9909
 
-Final Performance:
-- Test accuracy: 0.9899
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

fi_NA-nb-OP/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f00c094692e5bb83931d54deef16ef5f7b807f0537d15a1ed6345acab21e88f
+oid sha256:1e7bd2415df7824f65aaee2a05720b955d26bfd9b6b5b69cb5da65f7c5bbbfdf
 size 25471

fi_NA-nb-OP/training_details.txt

@@ -1,39 +1,29 @@
-Training Details for fi_NA-nb-OP
+Training Details: fi_NA-nb-OP
 ========================================
 
 Language: fi
 Register: NA-nb-OP
-Training Date: 2025-09-26 14:06:57
+Training Date: 2025-09-26 14:43:17
 
-Data Summary:
+Dataset:
 - Total samples: 1969
-- Training samples: 1575
-- Test samples: 394
-- Embedding dimension: 1024
+- Training: 1575
+- Test: 394
+- Features: 1024
+- Classes: 3
 
 Classes:
-- Number of classes: 3
-- Class names: '', 'culture', 'consumption'
-- Class distribution: {'': 874, 'culture': 695, 'consumption': 400}
+- 0: '' (874 samples)
+- 1: 'culture' (695 samples)
+- 2: 'consumption' (400 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9841269841269841, 0.9936507936507937, 0.9841269841269841, 0.9777777777777777, 0.9650793650793651]
-- CV mean: 0.9810
-- CV std: 0.0094
-- CV confidence interval: 0.9810 ± 0.0188
+Performance:
+- CV Mean: 0.9848
+- CV Std: 0.0071
+- Test Accuracy: 0.9848
 
-Final Performance:
-- Test accuracy: 0.9848
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

fi_NA-nb/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73957b464aecf86217f464d4db098528d7f7447904f721044e0a93987372e896
+oid sha256:3e06ea9312851ec2dd78fa0b532960a7149031b2a33fd19608185d2830264237
 size 9055

fi_NA-nb/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for fi_NA-nb
+Training Details: fi_NA-nb
 ========================================
 
 Language: fi
 Register: NA-nb
-Training Date: 2025-09-26 14:08:40
+Training Date: 2025-09-26 14:45:14
 
-Data Summary:
+Dataset:
 - Total samples: 218088
-- Training samples: 174470
-- Test samples: 43618
-- Embedding dimension: 1024
+- Training: 174470
+- Test: 43618
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: '', 'comments'
-- Class distribution: {'': 193558, 'comments': 24530}
+- 0: '' (193558 samples)
+- 1: 'comments' (24530 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9926061787126726, 0.9932939760417264, 0.9922622800481458, 0.9933512924858142, 0.992778128044936]
-- CV mean: 0.9929
-- CV std: 0.0004
-- CV confidence interval: 0.9929 ± 0.0008
+Performance:
+- CV Mean: 0.9930
+- CV Std: 0.0005
+- Test Accuracy: 0.9934
 
-Final Performance:
-- Test accuracy: 0.9927
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

modeling_sm_subgroup_classifier.py

@@ -35,7 +35,7 @@ class SmSubgroupClassifier(PreTrainedModel):
             item_path = os.path.join(self.model_dir, item)
             if os.path.isdir(item_path):
                 # Verify it's a valid model directory
-                required_files = ["model.pkl", "scaler.pkl", "metadata.pkl"]
+                required_files = ["model.pkl", "metadata.pkl"]
                 if all(
                     os.path.exists(os.path.join(item_path, f)) for f in required_files
                 ):
@@ -60,13 +60,11 @@ class SmSubgroupClassifier(PreTrainedModel):
 
         # Load components
         classifier = joblib.load(os.path.join(classifier_path, "model.pkl"))
-        scaler = joblib.load(os.path.join(classifier_path, "scaler.pkl"))
         with open(os.path.join(classifier_path, "metadata.pkl"), "rb") as f:
             metadata = pickle.load(f)
 
         classifier_info = {
             "classifier": classifier,
-            "scaler": scaler,
             "class_names": metadata["class_names"],
         }
 
@@ -92,10 +90,9 @@ class SmSubgroupClassifier(PreTrainedModel):
         # Load classifier
         classifier_info = self._load_classifier(model_key)
 
-        # Scale and predict
-        embeddings_scaled = classifier_info["scaler"].transform(embeddings)
-        predictions = classifier_info["classifier"].predict(embeddings_scaled)
-        probabilities = classifier_info["classifier"].predict_proba(embeddings_scaled)
+        # Predict directly without scaling
+        predictions = classifier_info["classifier"].predict(embeddings)
+        probabilities = classifier_info["classifier"].predict_proba(embeddings)
 
         # Format results - just use class names and probabilities
         results = []

sv_HI-NA-nb-re/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b36afa0b2d6b74474f7ec1ae3779322e637f64af1bfe522083fe356a22a194
+oid sha256:fb3ad2ab765d6810ff066fb512c4723a2bc4fdf4022dad67aa9d40aa71f5cf03
 size 9055

sv_HI-NA-nb-re/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for sv_HI-NA-nb-re
+Training Details: sv_HI-NA-nb-re
 ========================================
 
 Language: sv
 Register: HI-NA-nb-re
-Training Date: 2025-09-26 14:05:16
+Training Date: 2025-09-26 14:40:55
 
-Data Summary:
+Dataset:
 - Total samples: 6804
-- Training samples: 5443
-- Test samples: 1361
-- Embedding dimension: 1024
+- Training: 5443
+- Test: 1361
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: 'crafts', ''
-- Class distribution: {'crafts': 135, '': 6669}
+- 0: 'crafts' (135 samples)
+- 1: '' (6669 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9963269054178145, 0.9963269054178145, 0.9972451790633609, 0.9944852941176471, 0.9954044117647058]
-- CV mean: 0.9960
-- CV std: 0.0009
-- CV confidence interval: 0.9960 ± 0.0019
+Performance:
+- CV Mean: 0.9960
+- CV Std: 0.0007
+- Test Accuracy: 0.9963
 
-Final Performance:
-- Test accuracy: 0.9956
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

sv_ID-NA-nb/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3e6a7f1c0e31e315d84e43bc75299c48fe02215b7def50de7fc350316f807cb
+oid sha256:bb1f2cf418daafa57df0949e537e0edcfb147a459f8e2a5207cad14300efe5da
 size 9055

sv_ID-NA-nb/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for sv_ID-NA-nb
+Training Details: sv_ID-NA-nb
 ========================================
 
 Language: sv
 Register: ID-NA-nb
-Training Date: 2025-09-26 14:05:20
+Training Date: 2025-09-26 14:40:59
 
-Data Summary:
+Dataset:
 - Total samples: 1189
-- Training samples: 951
-- Test samples: 238
-- Embedding dimension: 1024
+- Training: 951
+- Test: 238
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: '', 'comments'
-- Class distribution: {'': 852, 'comments': 337}
+- 0: '' (852 samples)
+- 1: 'comments' (337 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9214659685863874, 0.9526315789473684, 0.9315789473684211, 0.968421052631579, 0.9263157894736842]
-- CV mean: 0.9401
-- CV std: 0.0177
-- CV confidence interval: 0.9401 ± 0.0354
+Performance:
+- CV Mean: 0.9485
+- CV Std: 0.0146
+- Test Accuracy: 0.9622
 
-Final Performance:
-- Test accuracy: 0.9706
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

sv_ID/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22126201e503512b9bbf51ed4c310d6e59ae89dd12e37835154c15a382d2612
+oid sha256:1e34073c68bb3052b47f48110ef469aabf92e455e7015962344503b1b253c587
 size 25471

sv_ID/training_details.txt

@@ -1,39 +1,29 @@
-Training Details for sv_ID
+Training Details: sv_ID
 ========================================
 
 Language: sv
 Register: ID
-Training Date: 2025-09-26 14:06:57
+Training Date: 2025-09-26 14:43:16
 
-Data Summary:
+Dataset:
 - Total samples: 15060
-- Training samples: 12048
-- Test samples: 3012
-- Embedding dimension: 1024
+- Training: 12048
+- Test: 3012
+- Features: 1024
+- Classes: 3
 
 Classes:
-- Number of classes: 3
-- Class names: '', 'sports', 'help'
-- Class distribution: {'': 14108, 'sports': 542, 'help': 410}
+- 0: '' (14108 samples)
+- 1: 'sports' (542 samples)
+- 2: 'help' (410 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9962655601659751, 0.9954356846473029, 0.9983402489626556, 1.0, 0.9991697799916978]
-- CV mean: 0.9978
-- CV std: 0.0017
-- CV confidence interval: 0.9978 ± 0.0035
+Performance:
+- CV Mean: 0.9980
+- CV Std: 0.0011
+- Test Accuracy: 0.9990
 
-Final Performance:
-- Test accuracy: 0.9977
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

sv_IN-NA-nb/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3247c4a22da33aab41f2e67513baa5a91675fb48eca867774eb3eb23c08bb827
+oid sha256:b47ecae021e4c0ab2da743cd76b431e165a134894a540d43b9c98f7e595aacb5
 size 9055

sv_IN-NA-nb/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for sv_IN-NA-nb
+Training Details: sv_IN-NA-nb
 ========================================
 
 Language: sv
 Register: IN-NA-nb
-Training Date: 2025-09-26 14:05:18
+Training Date: 2025-09-26 14:40:58
 
-Data Summary:
+Dataset:
 - Total samples: 1169
-- Training samples: 935
-- Test samples: 234
-- Embedding dimension: 1024
+- Training: 935
+- Test: 234
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: '', 'organizations'
-- Class distribution: {'': 811, 'organizations': 358}
+- 0: '' (811 samples)
+- 1: 'organizations' (358 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.93048128342246, 0.9893048128342246, 0.9625668449197861, 0.9679144385026738, 0.9625668449197861]
-- CV mean: 0.9626
-- CV std: 0.0188
-- CV confidence interval: 0.9626 ± 0.0377
+Performance:
+- CV Mean: 0.9668
+- CV Std: 0.0201
+- Test Accuracy: 0.9701
 
-Final Performance:
-- Test accuracy: 0.9744
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

sv_NA-nb-OP-rv/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:682ff2cca0e847dba7ab531629e37efb7ad74f9ec844a584863d6ff6494608ca
+oid sha256:201f20021cf1391061d7ab0884b67e90e4c73342374b4114c614d53da9562519
 size 9055

sv_NA-nb-OP-rv/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for sv_NA-nb-OP-rv
+Training Details: sv_NA-nb-OP-rv
 ========================================
 
 Language: sv
 Register: NA-nb-OP-rv
-Training Date: 2025-09-26 14:05:20
+Training Date: 2025-09-26 14:40:59
 
-Data Summary:
+Dataset:
 - Total samples: 9422
-- Training samples: 7537
-- Test samples: 1885
-- Embedding dimension: 1024
+- Training: 7537
+- Test: 1885
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: 'lifestyle', 'culture'
-- Class distribution: {'lifestyle': 2731, 'culture': 6691}
+- 0: 'lifestyle' (2731 samples)
+- 1: 'culture' (6691 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9927055702917772, 0.9953580901856764, 0.9940278699402787, 0.9960185799601858, 0.9946914399469144]
-- CV mean: 0.9946
-- CV std: 0.0011
-- CV confidence interval: 0.9946 ± 0.0023
+Performance:
+- CV Mean: 0.9952
+- CV Std: 0.0013
+- Test Accuracy: 0.9968
 
-Final Performance:
-- Test accuracy: 0.9952
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

sv_NA-nb-OP/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720fc8f577288692a18f9ea11fde030737470791c5f91fc0b1c298d03f673fd1
+oid sha256:282933f93c4b4fc9b72eff6fc541c9705e201a3c704b09ca5c1a7746eba25696
 size 9055

sv_NA-nb-OP/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for sv_NA-nb-OP
+Training Details: sv_NA-nb-OP
 ========================================
 
 Language: sv
 Register: NA-nb-OP
-Training Date: 2025-09-26 14:05:18
+Training Date: 2025-09-26 14:40:58
 
-Data Summary:
+Dataset:
 - Total samples: 6280
-- Training samples: 5024
-- Test samples: 1256
-- Embedding dimension: 1024
+- Training: 5024
+- Test: 1256
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: 'finance', ''
-- Class distribution: {'finance': 149, '': 6131}
+- 0: 'finance' (149 samples)
+- 1: '' (6131 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9960199004975124, 0.9950248756218906, 0.9980099502487563, 0.9960199004975124, 0.9950199203187251]
-- CV mean: 0.9960
-- CV std: 0.0011
-- CV confidence interval: 0.9960 ± 0.0022
+Performance:
+- CV Mean: 0.9946
+- CV Std: 0.0024
+- Test Accuracy: 0.9968
 
-Final Performance:
-- Test accuracy: 0.9960
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

sv_NA-nb/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe83ba75d6108719e90f50a6eef1aa4012c90e1fb8563ae31c098bc5608d7ac
+oid sha256:defe8303b0eb2cfbcb1969d215b6fa25040d9438448196b1f70075bea6d1531e
 size 9055

sv_NA-nb/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for sv_NA-nb
+Training Details: sv_NA-nb
 ========================================
 
 Language: sv
 Register: NA-nb
-Training Date: 2025-09-26 14:06:54
+Training Date: 2025-09-26 14:43:11
 
-Data Summary:
+Dataset:
 - Total samples: 222925
-- Training samples: 178340
-- Test samples: 44585
-- Embedding dimension: 1024
+- Training: 178340
+- Test: 44585
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: '', 'comments'
-- Class distribution: {'': 203958, 'comments': 18967}
+- 0: '' (203958 samples)
+- 1: 'comments' (18967 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.99290680722216, 0.9922339351799933, 0.9935516429292363, 0.9936918246046876, 0.993523606594146]
-- CV mean: 0.9932
-- CV std: 0.0005
-- CV confidence interval: 0.9932 ± 0.0011
+Performance:
+- CV Mean: 0.9939
+- CV Std: 0.0003
+- Test Accuracy: 0.9943
 
-Final Performance:
-- Test accuracy: 0.9940
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

sv_NA-ob-OP/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4508c12d8e95a73bc9d7e742f2b67e1bb5051b4480937f8597f94bf95d782cd3
+oid sha256:2d13112969c2a8c82c9f3bb7e1649ffff9953c86d09d82bbc337ecd51200c939
 size 9055

sv_NA-ob-OP/training_details.txt

@@ -1,39 +1,28 @@
-Training Details for sv_NA-ob-OP
+Training Details: sv_NA-ob-OP
 ========================================
 
 Language: sv
 Register: NA-ob-OP
-Training Date: 2025-09-26 14:05:17
+Training Date: 2025-09-26 14:40:57
 
-Data Summary:
+Dataset:
 - Total samples: 2830
-- Training samples: 2264
-- Test samples: 566
-- Embedding dimension: 1024
+- Training: 2264
+- Test: 566
+- Features: 1024
+- Classes: 2
 
 Classes:
-- Number of classes: 2
-- Class names: 'sports', 'general'
-- Class distribution: {'sports': 175, 'general': 2655}
+- 0: 'sports' (175 samples)
+- 1: 'general' (2655 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9933774834437086, 0.9933774834437086, 0.9955849889624724, 0.9955849889624724, 0.9911504424778761]
-- CV mean: 0.9938
-- CV std: 0.0017
-- CV confidence interval: 0.9938 ± 0.0033
+Performance:
+- CV Mean: 0.9934
+- CV Std: 0.0028
+- Test Accuracy: 0.9912
 
-Final Performance:
-- Test accuracy: 0.9929
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt

sv_ds-IP-NA-nb/model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984ebee2366c6b4ea8c0883fd66e5095f4fbeacb91fbea6ecd5b9dc90a184c99
+oid sha256:009e52f53327a30dfba1b53d8b883f5a72d89da81c5bec95f18cce24999b95bb
 size 25471

sv_ds-IP-NA-nb/training_details.txt

@@ -1,39 +1,29 @@
-Training Details for sv_ds-IP-NA-nb
+Training Details: sv_ds-IP-NA-nb
 ========================================
 
 Language: sv
 Register: ds-IP-NA-nb
-Training Date: 2025-09-26 14:05:17
+Training Date: 2025-09-26 14:40:56
 
-Data Summary:
+Dataset:
 - Total samples: 2357
-- Training samples: 1885
-- Test samples: 472
-- Embedding dimension: 1024
+- Training: 1885
+- Test: 472
+- Features: 1024
+- Classes: 3
 
 Classes:
-- Number of classes: 3
-- Class names: '', 'travel', 'contests'
-- Class distribution: {'': 1933, 'travel': 268, 'contests': 156}
+- 0: '' (1933 samples)
+- 1: 'travel' (268 samples)
+- 2: 'contests' (156 samples)
 
-Cross-Validation Results:
-- CV folds: 5
-- CV scores: [0.9761273209549072, 0.9840848806366048, 0.9840848806366048, 0.9761273209549072, 0.9893899204244032]
-- CV mean: 0.9820
-- CV std: 0.0051
-- CV confidence interval: 0.9820 ± 0.0103
+Performance:
+- CV Mean: 0.9830
+- CV Std: 0.0036
+- Test Accuracy: 0.9831
 
-Final Performance:
-- Test accuracy: 0.9788
-
-Model Configuration:
+Configuration:
 - Algorithm: Logistic Regression
 - Regularization (C): 1.0
-- Feature scaling: StandardScaler
+- Feature scaling: NONE
 - Random state: 42
-
-Files:
-- Classifier: model.pkl
-- Scaler: scaler.pkl
-- Metadata: metadata.pkl
-- This file: training_details.txt