added updated models

se4ai2324-uniba · Jan 5, 2024 · f1cf8a2 · f1cf8a2
1 parent 76a5ecd
commit f1cf8a2
Show file tree

Hide file tree

Showing 34 changed files with 127 additions and 56 deletions.
diff --git a/dvc.lock b/dvc.lock
@@ -9,8 +9,8 @@ stages:
       size: 3165487
     - path: src/data/make_dataset.py
       hash: md5
-      md5: 60206638c903696890c2776593751058
-      size: 1109
+      md5: da6d3d579738ff659f03e8220c3f0246
+      size: 1377
     outs:
     - path: data/urls_with_features_selected.csv
       hash: md5
@@ -25,8 +25,8 @@ stages:
       size: 730854
     - path: src/features/build_features.py
       hash: md5
-      md5: 143cec654560aca16bb5ac766c580a59
-      size: 1714
+      md5: a7874e52c6739bd5b9d230fc9df0a4a0
+      size: 2069
     outs:
     - path: data/test.csv
       hash: md5
@@ -46,17 +46,12 @@ stages:
       size: 2565327
     - path: src/models/train_base_model.py
       hash: md5
-      md5: 9663eeef47f9cd136bd79cb03054fe49
-      size: 1471
+      md5: be582060012939ccfac0735a6dd732ae
+      size: 1686
     - path: src/models/utils.py
       hash: md5
-      md5: 86c9055fb54ac2dc222ef4c4512d8b0e
-      size: 1718
-    outs:
-    - path: models/base_rf_model.pkl
-      hash: md5
-      md5: b9d39c597fcea9393ec7777fd017daf9
-      size: 34199068
+      md5: f391ab9e1d87bd85759f26698cc86dbd
+      size: 1929
   train_tuned_model:
     cmd:
     - python src/models/train_tuned_model.py
@@ -67,17 +62,12 @@ stages:
       size: 2565327
     - path: src/models/train_tuned_model.py
       hash: md5
-      md5: 0e2dd488e85a330227cd3e8c1eb7a939
-      size: 1797
+      md5: 3cf8bbaf1de889a0680f33b47f13bf81
+      size: 1993
     - path: src/models/utils.py
       hash: md5
-      md5: 86c9055fb54ac2dc222ef4c4512d8b0e
-      size: 1718
-    outs:
-    - path: models/tuned_rf_model.pkl
-      hash: md5
-      md5: 08d9d5e9e4e10d84f1eabdf1916300e6
-      size: 781192562
+      md5: f391ab9e1d87bd85759f26698cc86dbd
+      size: 1929
   predict:
     cmd:
     - python src/models/predict.py
@@ -92,30 +82,30 @@ stages:
       size: 34199068
     - path: models/tuned_rf_model.pkl
       hash: md5
-      md5: 08d9d5e9e4e10d84f1eabdf1916300e6
-      size: 781192562
+      md5: 6d240e274219304618af4a238eb03b39
+      size: 781507762
     - path: src/models/predict.py
       hash: md5
       md5: 422b5f22679fcc6ce1e308524a508457
       size: 4037
     - path: src/models/utils.py
       hash: md5
-      md5: 86c9055fb54ac2dc222ef4c4512d8b0e
-      size: 1718
+      md5: f391ab9e1d87bd85759f26698cc86dbd
+      size: 1929
     outs:
     - path: reports/classification_report_base_rf.json
       hash: md5
       md5: 163d82e336564ec3b0a2a4d5a4b5abf4
       size: 687
     - path: reports/classification_report_tuned_rf.json
       hash: md5
-      md5: ce564e7b231a3df65ff427eb5dba187b
-      size: 689
+      md5: 658c8edb7ab4641ffdcc31a336a487fe
+      size: 693
     - path: reports/confusion_matrix_base_rf.json
       hash: md5
       md5: 5bd49e3e36e33ae371bc1b67744c363c
       size: 155
     - path: reports/confusion_matrix_tuned_rf.json
       hash: md5
-      md5: c7d479cd4f59d4c4af79637c0daea80a
+      md5: 18712a8ab178d7b32f84b6694733b69d
       size: 155
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/meta.yaml b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/meta.yaml
@@ -0,0 +1,15 @@
+artifact_uri: file:///C:\Users\Lenovo\Desktop\SW_engineering\MalURLs\mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/artifacts
+end_time: 1704457577656
+entry_point_name: ''
+experiment_id: '463846434585356198'
+lifecycle_stage: active
+run_id: 33e684f6d4c54ba092055110e171c45a
+run_name: receptive-sow-39
+run_uuid: 33e684f6d4c54ba092055110e171c45a
+source_name: ''
+source_type: 4
+source_version: ''
+start_time: 1704457566868
+status: 3
+tags: []
+user_id: baf89bde9935867d5202c57720161daa936b62ed
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/metrics/Weighted_avg_f1 b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/metrics/Weighted_avg_f1
@@ -0,0 +1 @@
+1704457567262 0.8929922686914129 0
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/metrics/Weighted_avg_precision b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/metrics/Weighted_avg_precision
@@ -0,0 +1 @@
+1704457567262 0.8931136098332417 0
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/metrics/Weighted_avg_recall b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/metrics/Weighted_avg_recall
@@ -0,0 +1 @@
+1704457567262 0.893 0
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/metrics/accuracy b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/metrics/accuracy
@@ -0,0 +1 @@
+1704457567262 0.893 0
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.runName b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.runName
@@ -0,0 +1 @@
+receptive-sow-39
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.source.git.commit b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.source.git.commit
@@ -0,0 +1 @@
+76a5ecd23ad0d66fc7d1e1fe4b864f30ed39cadf
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.source.name b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.source.name
@@ -0,0 +1 @@
+src/models/predict.py
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.source.type b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.source.type
@@ -0,0 +1 @@
+LOCAL
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.user b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/mlflow.user
@@ -0,0 +1 @@
+baf89bde9935867d5202c57720161daa936b62ed
diff --git a/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/model_type b/mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/tags/model_type
@@ -0,0 +1 @@
+random_forest_base_model
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/meta.yaml b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/meta.yaml
@@ -0,0 +1,15 @@
+artifact_uri: file:///C:\Users\Lenovo\Desktop\SW_engineering\MalURLs\mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/artifacts
+end_time: 1704457577650
+entry_point_name: ''
+experiment_id: '463846434585356198'
+lifecycle_stage: active
+run_id: 58d8ef119ef3423f811f1379850a7633
+run_name: auspicious-gnu-79
+run_uuid: 58d8ef119ef3423f811f1379850a7633
+source_name: ''
+source_type: 4
+source_version: ''
+start_time: 1704457567398
+status: 3
+tags: []
+user_id: baf89bde9935867d5202c57720161daa936b62ed
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/metrics/Weighted_avg_f1 b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/metrics/Weighted_avg_f1
@@ -0,0 +1 @@
+1704457577639 0.8962411221310123 0
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/metrics/Weighted_avg_precision b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/metrics/Weighted_avg_precision
@@ -0,0 +1 @@
+1704457577639 0.8963856629931594 0
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/metrics/Weighted_avg_recall b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/metrics/Weighted_avg_recall
@@ -0,0 +1 @@
+1704457577639 0.89625 0
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/metrics/accuracy b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/metrics/accuracy
@@ -0,0 +1 @@
+1704457577639 0.89625 0
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.parentRunId b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.parentRunId
@@ -0,0 +1 @@
+33e684f6d4c54ba092055110e171c45a
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.runName b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.runName
@@ -0,0 +1 @@
+auspicious-gnu-79
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.source.git.commit b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.source.git.commit
@@ -0,0 +1 @@
+76a5ecd23ad0d66fc7d1e1fe4b864f30ed39cadf
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.source.name b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.source.name
@@ -0,0 +1 @@
+src/models/predict.py
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.source.type b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.source.type
@@ -0,0 +1 @@
+LOCAL
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.user b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/mlflow.user
@@ -0,0 +1 @@
+baf89bde9935867d5202c57720161daa936b62ed
diff --git a/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/model_type b/mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/tags/model_type
@@ -0,0 +1 @@
+random_forest_tuned_model
diff --git a/mlruns/models/base_rf_model/meta.yaml b/mlruns/models/base_rf_model/meta.yaml
@@ -1,5 +1,5 @@
 aliases: {}
 creation_timestamp: 1702748644144
 description: null
-last_updated_timestamp: 1704390891144
+last_updated_timestamp: 1704457567335
 name: base_rf_model
diff --git a/mlruns/models/base_rf_model/version-8/meta.yaml b/mlruns/models/base_rf_model/version-8/meta.yaml
@@ -0,0 +1,14 @@
+aliases: []
+creation_timestamp: 1704457567335
+current_stage: None
+description: null
+last_updated_timestamp: 1704457567335
+name: base_rf_model
+run_id: 33e684f6d4c54ba092055110e171c45a
+run_link: null
+source: file:///C:\Users\Lenovo\Desktop\SW_engineering\MalURLs\mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/artifacts/models
+status: READY
+status_message: null
+storage_location: file:///C:\Users\Lenovo\Desktop\SW_engineering\MalURLs\mlruns/463846434585356198/33e684f6d4c54ba092055110e171c45a/artifacts/models
+user_id: null
+version: 8
diff --git a/mlruns/models/tuned_rf_model/meta.yaml b/mlruns/models/tuned_rf_model/meta.yaml
@@ -1,5 +1,5 @@
 aliases: {}
 creation_timestamp: 1702748651445
 description: null
-last_updated_timestamp: 1704390896921
+last_updated_timestamp: 1704457577593
 name: tuned_rf_model
diff --git a/mlruns/models/tuned_rf_model/version-8/meta.yaml b/mlruns/models/tuned_rf_model/version-8/meta.yaml
@@ -0,0 +1,14 @@
+aliases: []
+creation_timestamp: 1704457577593
+current_stage: None
+description: null
+last_updated_timestamp: 1704457577593
+name: tuned_rf_model
+run_id: 58d8ef119ef3423f811f1379850a7633
+run_link: null
+source: file:///C:\Users\Lenovo\Desktop\SW_engineering\MalURLs\mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/artifacts/models
+status: READY
+status_message: null
+storage_location: file:///C:\Users\Lenovo\Desktop\SW_engineering\MalURLs\mlruns/463846434585356198/58d8ef119ef3423f811f1379850a7633/artifacts/models
+user_id: null
+version: 8
diff --git a/models/base_rf_model.pkl.dvc b/models/base_rf_model.pkl.dvc
@@ -1,5 +1,5 @@
 outs:
-- md5: d141c79da310be2e3ded5ab8236d42d6
-  size: 30782445
+- md5: b9d39c597fcea9393ec7777fd017daf9
+  size: 34199068
   hash: md5
   path: base_rf_model.pkl
diff --git a/models/tuned_rf_model.pkl.dvc b/models/tuned_rf_model.pkl.dvc
@@ -1,5 +1,5 @@
 outs:
-- md5: c6fcb006c533c3dcda73a66ee7c310f3
-  size: 703178515
+- md5: 6d240e274219304618af4a238eb03b39
+  size: 781507762
   hash: md5
   path: tuned_rf_model.pkl
diff --git a/reports/classification_report_tuned_rf.json b/reports/classification_report_tuned_rf.json
@@ -1,27 +1,27 @@
 {
     "safe_URL": {
-        "precision": 0.8896551724137931,
-        "recall": 0.903,
-        "f1-score": 0.8962779156327544,
+        "precision": 0.8890525282277859,
+        "recall": 0.9055,
+        "f1-score": 0.8972008917513005,
         "support": 2000.0
     },
     "unsafe_URL": {
-        "precision": 0.9015228426395939,
-        "recall": 0.888,
-        "f1-score": 0.8947103274559194,
+        "precision": 0.9037187977585328,
+        "recall": 0.887,
+        "f1-score": 0.8952813525107242,
         "support": 2000.0
     },
-    "accuracy": 0.8955,
+    "accuracy": 0.89625,
     "macro avg": {
-        "precision": 0.8955890075266935,
-        "recall": 0.8955,
-        "f1-score": 0.8954941215443368,
+        "precision": 0.8963856629931594,
+        "recall": 0.89625,
+        "f1-score": 0.8962411221310123,
         "support": 4000.0
     },
     "weighted avg": {
-        "precision": 0.8955890075266936,
-        "recall": 0.8955,
-        "f1-score": 0.8954941215443368,
+        "precision": 0.8963856629931594,
+        "recall": 0.89625,
+        "f1-score": 0.8962411221310123,
         "support": 4000.0
     }
 }
diff --git a/reports/confusion_matrix_tuned_rf.json b/reports/confusion_matrix_tuned_rf.json
@@ -1,12 +1,12 @@
 {
     "confusion_matrix": [
         [
-            1806,
-            194
+            1811,
+            189
         ],
         [
-            224,
-            1776
+            226,
+            1774
         ]
     ]
 }
diff --git a/src/data/make_dataset.py b/src/data/make_dataset.py
@@ -7,13 +7,13 @@
 
 PROJECT_PATH = str(Path(Path(__file__).resolve().parents[2]))
 DATA_PATH = PROJECT_PATH + "\\data"
-data_file = PROJECT_PATH + "\\data\\urls_with_features.csv"
-data_output_file = DATA_PATH + "\\urls_with_features_selected.csv"
-
 
 # The function returns the processed feature dataset X.
 def make_dataset():
 
+    data_file = PROJECT_PATH + "\\data\\urls_with_features.csv"
+    data_output_file = DATA_PATH + "\\urls_with_features_selected.csv"
+
     if os.name == 'posix':
         data_file = PROJECT_PATH + "/data/urls_with_features.csv"
         data_output_file = PROJECT_PATH + "/data/urls_with_features_selected.csv"

diff --git a/src/features/build_features.py b/src/features/build_features.py
@@ -10,7 +10,7 @@
 
 PROJECT_PATH = str(Path(Path(__file__).resolve().parents[2]))
 DATA_PATH = PROJECT_PATH + "\\data"
-urls_file = PROJECT_PATH + "\\data\\urls_with_features_selected.csv"
+
 
 
 ''' 
@@ -20,6 +20,8 @@
 
 
 def split():
+    urls_file = PROJECT_PATH + "\\data\\urls_with_features_selected.csv"
+
     if os.name == 'posix':
         urls_file = PROJECT_PATH + "/data/urls_with_features_selected.csv"