print to logger

.gitignore

@@ -18,3 +18,6 @@ worked_examples/**/workshops_*/**/*.png
 worked_examples/**/workshops_*/**/*.csv
 worked_examples/**/workshops_*/**/*.geojson
 worked_examples/**/workshops_*/**/*.xlsx
+
+# test outputs
+tmp_checkpoints

mapreader/annotate/annotator.py

@@ -3,6 +3,7 @@
 import functools
 import hashlib
 import json
+import logging
 import os
 import random
 import string
@@ -20,12 +21,16 @@
 
 from ..load.loader import load_patches
 
+# Ignore warnings
 warnings.filterwarnings("ignore", category=UserWarning)
 
 _CENTER_LAYOUT = widgets.Layout(
     display="flex", flex_flow="column", align_items="center"
 )
 
+# Set up logging
+logger = logging.getLogger(__name__)
+
 
 class Annotator:
     """
@@ -218,7 +223,7 @@
 
         # Test for existing patch annotation file
         if os.path.exists(annotations_file):
-            print("[INFO] Loading existing patch annotations.")
+            logger.info("Loading existing patch annotations.")
             patch_df = self._load_annotations(
                 patch_df=patch_df,
                 annotations_file=annotations_file,
@@ -330,20 +335,20 @@
             A tuple containing the parent dataframe and patch dataframe.
         """
         if patch_paths:
-            print(f"[INFO] Loading patches from {patch_paths}.")
+            logger.info(f"Loading patches from {patch_paths}.")
         if parent_paths:
-            print(f"[INFO] Loading parents from {parent_paths}.")
+            logger.info(f"Loading parents from {parent_paths}.")
 
         maps = load_patches(patch_paths=patch_paths, parent_paths=parent_paths)
         # Add pixel stats
         maps.calc_pixel_stats()
 
         try:
             maps.add_metadata(metadata_path, delimiter=delimiter)
-            print(f"[INFO] Adding metadata from {metadata_path}.")
+            logger.info(f"Adding metadata from {metadata_path}.")
         except ValueError:
             raise FileNotFoundError(
-                f"[INFO] Metadata file at {metadata_path} not found. Please specify the correct file path using the ``metadata_path`` argument."
+                f"[ERROR] Metadata file at {metadata_path} not found. Please specify the correct file path using the ``metadata_path`` argument."
             )
 
         parent_df, patch_df = maps.convert_images()
@@ -745,7 +750,7 @@
         self._queue = self.get_queue()
 
         if self._filter_for is not None:
-            print(f"[INFO] Filtering for: {self._filter_for}")
+            logger.info(f"Filtering for: {self._filter_for}")
 
         self.out = widgets.Output(layout=_CENTER_LAYOUT)
         display(self.box)

mapreader/annotate/utils.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 from __future__ import annotations
 
+import logging
 import os
 import random
 import sys
@@ -25,10 +26,14 @@
 
 from mapreader import load_patches, loader
 
+# Ignore warnings
 warnings.filterwarnings("ignore")
-# warnings.filterwarnings(
+#   (
 #     "ignore", message="Pandas doesn't allow columns to be created via a new attribute name")
 
+# Set up logging
+logger = logging.getLogger(__name__)
+
 
 def prepare_data(
     df: pd.DataFrame,
@@ -77,10 +82,10 @@
         col_names = ["image_path", "parent_id"]
     if (label_col_name in list(df.columns)) and (not redo):
         already_annotated = len(df[~df[label_col_name].isnull()])
-        print(f"Number of already annotated images: {already_annotated}")
+        logger.info(f"Number of already annotated images: {already_annotated}")
         # only annotate those patches that have not been already annotated
         df = df[df[label_col_name].isnull()]
-        print(f"Number of images to be annotated (total): {len(df)}")
+        logger.info(f"Number of images to be annotated (total): {len(df)}")
     else:
         # if redo = True or "label" column does not exist
         # annotate all patches in the pandas dataframe
@@ -100,10 +105,10 @@
             else:
                 df = df.groupby("pixel_groups").sample(n=10, random_state=random_state)
         except Exception:
-            print(f"[INFO] len(df) = {len(df)}, .sample method is deactivated.")
+            logger.info(f"len(df) = {len(df)}, .sample method is deactivated.")
             df = df.iloc[:num_samples]
     else:
-        print(f"[WARNING] could not find {tar_param} in columns.")
+        logger.warning(f"could not find {tar_param} in columns.")
         df = df.iloc[:num_samples]
 
     data = []
@@ -117,7 +122,7 @@
         data.append(cols2add)
         row_counter += 1
 
-    print(f"Number of images to annotate (current batch): {len(data)}")
+    logger.info(f"Number of images to annotate (current batch): {len(data)}")
     return data
 
 
@@ -300,9 +305,9 @@
             plt.tight_layout()
             plt.show()
 
-            print(20 * "-")
-            print("Additional info:")
-            print(f"Counter: {record[-1]}")
+            logger.info(20 * "-")
+            logger.info("Additional info:")
+            logger.info(f"Counter: {record[-1]}")
             if url_main:
                 try:
                     map_id = record[2].split("_")[-1].split(".")[0]
@@ -311,8 +316,7 @@
                     # the page exists
                     response = requests.get(url, stream=True)
                     assert response.status_code < 400
-                    print()
-                    print(f"URL: {url}")
+                    logger.info(f"URL: {url}")
                 except:
                     url = False
                     pass
@@ -619,7 +623,7 @@
     )
 
     if len(data2annotate) == 0:
-        print("No image to annotate!")
+        logger.info("No image to annotate!")
     else:
         annotation = annotation_interface(
             data2annotate,
@@ -665,7 +669,7 @@
         annotation_tasks = yaml.load(f, Loader=yaml.FullLoader)
 
     if annotation_set not in annotation_tasks["paths"].keys():
-        print(f"{annotation_set} could not be found in {annotation_tasks_file}")
+        logger.info(f"{annotation_set} could not be found in {annotation_tasks_file}")
     else:
         annot_file = os.path.join(
             annotation_tasks["paths"][annotation_set]["annot_dir"],
@@ -704,8 +708,8 @@
     if len(image_df) > 0:
         # image_df = image_df.set_index("image_id")
         image_df.to_csv(annot_file, mode="w")
-        print(f"[INFO] Save {newly_annotated} new annotations to {annot_file}")
-        print(f"[INFO] {new_labels} labels were not already stored")
-        print(f"[INFO] Total number of saved annotations: {len(image_df)}")
+        logger.info(f"Save {newly_annotated} new annotations to {annot_file}")
+        logger.info(f"{new_labels} labels were not already stored")
+        logger.info(f"Total number of saved annotations: {len(image_df)}")
     else:
-        print("[INFO] No annotations to save!")
+        logger.info("No annotations to save!")