Update logging and model (#58)

## Describe your changes Updated the level of various logging messages and the XGBoost model. ## Checklist before requesting a review - [x] The code runs successfully. ```commandline Accuracy Score: 0.7158848614072495 Precision Score: 0.8911951791094744 Recall Score: 0.7759801778166449 ```
michplunkett · Jun 26, 2024 · 626042c · 626042c
1 parent 75180c4
commit 626042c
Show file tree

Hide file tree

Showing 8 changed files with 323 additions and 344 deletions.
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -6,7 +6,7 @@ on:
     branches: [ main ]
 
 jobs:
-  Test:
+  test:
     runs-on: ubuntu-latest
     strategy:
       matrix:

diff --git a/incident_scraper/__main__.py b/incident_scraper/__main__.py
@@ -177,7 +177,7 @@ def correct_location(nbd_client: GoogleNBD) -> None:
                 corrected_locations += 1
                 updated_incidents.append(i)
             else:
-                logging.error(
+                logging.debug(
                     "This incident failed to get a valid location with the "
                     f"Geocoder: {i}"
                 )
@@ -261,7 +261,7 @@ def parse_and_save_records(
 
             if len(i.keys()) != 6:
                 void_malformed_incidents.append(i)
-                logging.error(
+                logging.debug(
                     f"This incident has an insufficient number of keys: {i}"
                 )
                 continue
@@ -286,7 +286,7 @@ def parse_and_save_records(
 
             if not formatted_reported_value:
                 void_malformed_incidents.append(i)
-                logging.error(f"This incident has a malformed date: {i}")
+                logging.debug(f"This incident has a malformed date: {i}")
                 continue
 
             i[INCIDENT_KEY_TYPE] = Lemmatizer.process(i[INCIDENT_KEY_TYPE])
@@ -330,13 +330,13 @@ def parse_and_save_records(
                 continue
             else:
                 geocode_error_incidents.append(i)
-                logging.error(
+                logging.debug(
                     "This incident failed to get a valid location with the "
                     f"Geocoder: {i}"
                 )
 
             geocode_error_incidents.append(i)
-            logging.error(
+            logging.debug(
                 "This incident failed to get a location with the GoogleMaps' "
                 f"Geocoder: {i}"
             )

diff --git a/incident_scraper/data/xgb_prediction_model.pkl b/incident_scraper/data/xgb_prediction_model.pkl
diff --git a/incident_scraper/data/xgb_types.pkl b/incident_scraper/data/xgb_types.pkl
diff --git a/incident_scraper/data/xgb_vectorizer.pkl b/incident_scraper/data/xgb_vectorizer.pkl
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -24,7 +24,7 @@ scikit-multilearn = "^0.2.0"
 polars = "^0.19.15"
 pandas = "^2.1.3"
 pyarrow = "^14.0.1"
-xgboost = "^2.0.2"
+xgboost = "2.0.3"
 neattext = "^0.1.3"
 click = "^8.1.7"
 textblob = "^0.17.1"

diff --git a/requirements.txt b/requirements.txt
-Original file line number
+Diff line change
@@ Expand Up / @@ -6,7 +6,7 @@ on: @@
         branches: [ main ]
     jobs:
-      Test:
+      test:
         runs-on: ubuntu-latest
         strategy:
           matrix:
@@ Expand Down @@