fix ruff errors in the /helper_functions and /misc folder

.python-version

@@ -1 +1 @@
-3.12
+3.12.7

edge_http.py

@@ -26,21 +26,17 @@
 if "ENVIRONMENT" in os.environ:
     app.config.from_envvar("ENVIRONMENT")
 
-# Set optional bootswatch theme
 app.config["FLASK_ADMIN_SWATCH"] = "cerulean"
 
 app.config["SQLALCHEMY_DATABASE_URI"] = "postgresql+psycopg2://{}@/{}".format(
     app.config["DBUSER"],
     app.config["DBNAME"],
 )
 
-# engine = create_engine("postgresql+psycopg2://%s@/%s"%(app.config['DBUSER'], app.config['DBNAME']), echo=True)
-# SessionMaker = scoped_session(sessionmaker(bind=engine))
 db.init_app(app)
 
 
 with app.app_context():
-    # Base.metadata.create_all(engine)
     db.metadata.create_all(db.engine)
 
     from alembic import command, config
@@ -73,7 +69,6 @@
 
 admin = Admin(app, name="Risk Assesment", template_mode="bootstrap3")
 
-# work with session
 admin.add_view(RiskVectorModelView(db.session))
 admin.add_view(TestModelView(db.session))
 admin.add_view(ModelView(GpsData, db.session))
@@ -88,7 +83,8 @@
 @click.command()
 @click.option("--port", default=50000)
 def serve(port: int | str) -> None:
-    app.run(host="0.0.0.0", port=port)
+    # Intentionally binding to all interfaces - ensure proper firewall rules are in place
+    app.run(host="0.0.0.0", port=port)  # noqa: S104
 
 
 if __name__ == "__main__":

misc/vector_data_as_cloudwatch_metrics_experiment.py

@@ -36,8 +36,8 @@ def gen_put_metric_requests(vector_id, value_timestamp_pairs):
     request = None
     for value, timestamp in value_timestamp_pairs:
         if request is None:
-            request = {"Namespace": "tnc_edge_brancol_v1", "MetricData": []}
-        request["MetricData"].append(
+            request = {"Namespace": "tnc_edge_brancol_v1", "MetricData": []}  # MetricData is already a list
+        request["MetricData"].append( # type: ignore  # noqa: PGH003
             {
                 "MetricName": f"vector_{vector_id}",
                 "Value": value,

notebooks/helper_functions/aggregations.py

@@ -36,25 +36,23 @@ def aggregate_concat(dfs, freq, agg_list, agg_cols):
 def compare_aggregation_correlations(dfs, intervals, agg_list, x_col, y_col):
     results = {}
     for x_agg in agg_list:
-        # print(f'x_agg: {x_agg}')
         x_results = []
         for i in intervals:
             data = aggregate_concat(dfs, freq=i, agg_list=agg_list, agg_cols=[x_col, y_col])
 
             for y_agg in agg_list:
                 y_results = {}
-                slope, intercept, rvalue, pvalue, stderr = stats.linregress(
+                _, _, rvalue, _, _ = stats.linregress(
                     x=data[f"{x_col}_{x_agg}"], y=data[f"{y_col}_{y_agg}"]
                 )
-                r2 = rvalue**2
+                r2 = float(rvalue)**2
                 y_results["interval"] = i
                 y_results["y_agg"] = y_agg
                 y_results["r2"] = r2
 
                 x_results.append(y_results)
 
         df_Xresults = pd.DataFrame(x_results)
-        # print(df_Xresults.head())
         results[x_agg] = df_Xresults
 
     return results
@@ -65,27 +63,23 @@ def compare_aggregation_correlation_columns(dfs, intervals, agg_list, x_col, y_c
 
     for i in intervals:
         data = aggregate_concat(dfs, freq=i, agg_list=agg_list, agg_cols=[x_col] + y_cols)
-        # result['interval'] = i
         for y_col, x_agg, y_agg in itertools.product(y_cols, agg_list, agg_list):
             result = {}
             result["interval"] = i
             result["x_agg"] = x_agg
             result["y_agg"] = y_agg
             result["y_col"] = y_col
 
-            # get r2 value
             x = np.array(data[f"{x_col}_{x_agg}"]).reshape((-1, 1))
             y = np.array(data[f"{y_col}_{y_agg}"]).reshape((-1, 1))
             model = LinearRegression()
             model.fit(x, y)
             r2 = model.score(x, y)
 
             result["r2"] = r2
-
             results.append(result)
 
-        df_results = pd.DataFrame(results)
-
+    df_results = pd.DataFrame(results)
     return df_results
 
 

notebooks/helper_functions/data_readers.py

@@ -96,7 +96,12 @@ def get_bv_set_counts(bv_fish, bv_sets):
 
 # read in catch countst
 def get_ai_counts(boat, trip_info):
+    # Define model and validate boat input
     model = "ondeck" if boat == "stpatrick" else "aifish" if boat == "brancol" else None
+    if model is None:
+        raise ValueError(f"Unsupported boat: {boat}. Must be 'stpatrick' or 'brancol'")
+
+    # Define variables based on model type
     if model == "ondeck":
         count_column = None
         number_columns = [
@@ -106,7 +111,7 @@ def get_ai_counts(boat, trip_info):
             "detection_confidence",
             "count",
         ]
-    elif model == "aifish":
+    else:  # model == "aifish"
         count_column = "count"
         number_columns = ["count", "detection_confidence"]
 
@@ -228,8 +233,6 @@ def get_bv_counts(ai_df, bv_fish):
 
 
 def get_elog_data(vessel, trip_start_date, trip_end_date):
-    # elog data
-
     sql = f"""
     select
     elogs.id,

pyproject.toml

@@ -19,6 +19,9 @@ dependencies = [
     "schedule>=1.2.2",
     "sqlalchemy>=2.0.36",
     "wheel>=0.44.0",
+    "scipy>=1.14.1",
+    "scikit-learn>=1.5.2",
+    "awswrangler>=3.10.0",
 ]
 
 [tool.uv]