Refactor logging in calibplot, datastore, schismcalibplotui, and schismstudy to use logger instead of print statements

Author: dwr-psandhu

schismviz/calibplot.py

@@ -17,6 +17,8 @@
 import sys
 import logging
 
+logger = logging.getLogger(__name__)
+
 ## - Generic Plotting Functions ##
 import numpy as np
 import copy
@@ -42,8 +44,7 @@ def parse_time_window(timewindow):
             "error in calibplot.parse_time_window, while parsing timewindow. Timewindow must be in format yyyy-mm-dd:yyyy-mm-dd or "
             + "yyyy-mm-dd hhmm:yyyy-mm-dd hhmm. Ignoring timewindow"
         )
-        print(errmsg)
-        logging.error(errmsg)
+        logger.warning(errmsg)
     return return_list
 
 
@@ -72,8 +73,7 @@ def tsplot(dflist, names, timewindow=None, zoom_inst_plot=False):
             end_dt = parts[1]
         except:
             errmsg = "error in calibplot.tsplot"
-            print(errmsg)
-            logging.error(errmsg)
+            logger.warning(errmsg)
 
     from bokeh.models import DatetimeTickFormatter
 
@@ -296,13 +296,11 @@ def calculate_metrics(dflist, names, index_x=0, location=None):
                 metrics_calculated = True
             else:
                 errmsg = "calibplot.calculate_metrics: no y_series data found. Metrics can not be calculated.\n"
-                print(errmsg)
-                logging.info(errmsg)
+                logger.debug(errmsg)
 
     else:
         errmsg = "calibplot.calculate_metrics: no x_series data found. Metrics can not be calculated.\n"
-        print(errmsg)
-        logging.info(errmsg)
+        logger.debug(errmsg)
     dfmetrics = None
 
     if metrics_calculated:
@@ -654,7 +652,7 @@ def create_layout(
         10: "(j)",
     }
     if scatter_plot is None and dfdisplayed_metrics is None and metrics_table is None:
-        print(
+        logger.debug(
             "build_calib_plot_template: cplot, dfdisplayedmetrics, metrics_table, and kdeplot are all None for location, vartype="
             + location.name
             + ","
@@ -804,18 +802,17 @@ def load_data_for_plotting(studies, location, vartype, timewindow):
         if not success:  # try processing it now
             p.process()
             success = p.store_processed()
-            print('about to load data for '+str(p))
+            logger.debug('about to load data for '+str(p))
             success = p.load_processed(
                 timewindow=timewindow, invert_series=invert_series
             )
-            print('success='+str(success))
+            logger.debug('success='+str(success))
         if not success:
             errmsg = "unable to load data for study|location %s|%s" % (
                 str(study),
                 str(location),
             )
-            print(errmsg)
-            logging.info(errmsg)
+            logger.warning(errmsg)
             all_data_found = False
     if not all_data_found:
         errmsg = (
@@ -827,14 +824,7 @@ def load_data_for_plotting(studies, location, vartype, timewindow):
             + str(timewindow)
             + "\n"
         )
-        print(
-            "==============================================================================="
-        )
-        print(errmsg)
-        print(
-            "==============================================================================="
-        )
-        logging.info(errmsg)
+        logger.warning(errmsg)
         return None, None
     return all_data_found, pp
 
@@ -1123,7 +1113,7 @@ def create_hv_metrics_table(
 
     for m in metrics_list:
         if m not in metrics_list_dict:
-            print(
+            logger.error(
                 f"error in calibplot.create_hv_metrics_table: {m} was not a valid metric specification. exiting."
             )
             exit(0)
@@ -1255,14 +1245,14 @@ def create_metrics_table_and_metrics_df(
                 for m in metrics_table_list:
                     if m not in col_rename_dict:
                         metrics_list_ok = False
-                        print("unrecognized: " + m)
+                        logger.warning("unrecognized: " + m)
                 if metrics_list_ok:
                     metrics_list_for_hv_table = metrics_table_list
                     for m in metrics_table_list:
                         if m not in df_displayed_metrics_cols:
                             df_displayed_metrics_cols.append(m)
                 else:
-                    print(
+                    logger.warning(
                         "WARNING: metrics_table_list specified, but 1 or more values is not acceptable"
                     )
 
@@ -1339,14 +1329,14 @@ def create_metrics_table_and_metrics_df(
                 for m in metrics_table_list:
                     if m not in col_rename_dict:
                         metrics_list_ok = False
-                        print("unrecognized: " + m)
+                        logger.warning("unrecognized: " + m)
                 if metrics_list_ok:
                     metrics_list_for_hv_table = metrics_table_list
                     for m in metrics_table_list:
                         if m not in df_displayed_metrics_cols:
                             df_displayed_metrics_cols.append(m)
                 else:
-                    print(
+                    logger.warning(
                         "WARNING: metrics_table_list specified, but 1 or more values is not acceptable"
                     )
 
@@ -1441,7 +1431,7 @@ def create_metrics_table_and_metrics_df(
                 study_list, metrics_list_dict_renamed, metrics_list_for_hv_table_renamed
             )
     else:
-        print(
+        logger.debug(
             "build_metrics_table: dfmetrics is none, so not creating metrics table for location.name, vartype: "
             + location.name
             + ","

schismviz/datastore.py

@@ -1,4 +1,5 @@
 from functools import lru_cache
+import logging
 import param
 import os
 import diskcache
@@ -7,6 +8,8 @@
 import pandas as pd
 import geopandas as gpd
 
+logger = logging.getLogger(__name__)
+
 
 def convert_station_to_gdf(stations):
     return gpd.GeoDataFrame(
@@ -39,7 +42,7 @@ def __init__(self, **kwargs):
         self.cache = diskcache.Cache(self.cache_dir, size_limit=1e11)
         self.caching_read_ts = lru_cache(maxsize=32)(self.cache.memoize()(read_ts))
         # read inventory file for each repo level
-        print("Using inventory file: ", self.inventory_file)
+        logger.debug("Using inventory file: %s", self.inventory_file)
         self.df_dataset_inventory = pd.read_csv(self.inventory_file, comment="#")
         # replace nan with empty string for column subloc
         self.df_dataset_inventory["subloc"] = self.df_dataset_inventory[
@@ -104,4 +107,4 @@ def get_data(self, row):
     def clear_cache(self):
         if self.caching:
             self.cache.clear()
-            print("Cache cleared")
+            logger.debug("Cache cleared")

schismviz/schismcalibplotui.py

@@ -1,3 +1,4 @@
+import logging
 import pathlib
 import yaml
 import numpy as np
@@ -19,6 +20,8 @@
 
 # from .calibplot import tsplot, scatterplot, calculate_metrics, regression_line_plots
 
+logger = logging.getLogger(__name__)
+
 
 class SchismCalibNullReader(DataReferenceReader):
     """Placeholder reader for SchismCalibPlotUIManager catalog entries.
@@ -367,7 +370,7 @@ def get_data_for_id_var(self, id, variable):
                 self.dcat.eval(f'({id_col}=="{id}") & (param=="{dparam}")')
             ].iloc[0]
         except IndexError:
-            print("No data found for", id, variable)
+            logger.debug("No data found for %s %s", id, variable)
             rd = None
         if rd is not None:
             dfobs, converted_unit = schismstudy.convert_to_SI(

schismviz/schismstudy.py

@@ -178,7 +178,7 @@ def __init__(
             self.flux_pts_gdf = convert_flux_to_points_gdf(flux_df)
             self.flux_names = flux_df["name"].tolist()
         else:
-            print(
+            logger.debug(
                 "flux xsect file is not a yaml file, so only names loaded with no geometry.\n"
                 + "Filling in with matching stations.in geometry where station_id matches.\n"
             )
@@ -222,7 +222,7 @@ def get_catalog(self):
                 s = self.stations_gdf.copy()
                 s["variable"] = var
                 s["unit"] = self.get_unit_for_variable(var)
-                print(station.staout_name(var))
+                logger.debug(station.staout_name(var))
                 s["filename"] = self.interpret_file_relative_to(
                     self.output_dir, station.staout_name(var)
                 )