water-column-sonar-processing 25.1.1__tar.gz → 25.1.3__tar.gz

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: water_column_sonar_processing
-Version: 25.1.1
+Version: 25.1.3
 Summary: A processing tool for water column sonar data.
 Author-email: Rudy Klucik <rudy.klucik@noaa.gov>
 Project-URL: Homepage, https://github.com/CI-CMG/water-column-sonar-processing
@@ -11,15 +11,15 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: aiobotocore==2.15.2
-Requires-Dist: boto3==1.35.36
-Requires-Dist: botocore==1.35.36
+Requires-Dist: aiobotocore==2.19.0
+Requires-Dist: boto3==1.36.3
+Requires-Dist: botocore==1.36.3
 Requires-Dist: echopype==0.9.0
 Requires-Dist: fiona==1.10.1
 Requires-Dist: geopandas==1.0.1
 Requires-Dist: mock==5.1.0
-Requires-Dist: moto[all]==5.0.21
-Requires-Dist: moto[server]==5.0.21
+Requires-Dist: moto[all]==5.0.27
+Requires-Dist: moto[server]==5.0.27
 Requires-Dist: numcodecs==0.13.1
 Requires-Dist: numpy==1.26.4
 Requires-Dist: pandas==2.2.3
@@ -120,10 +120,7 @@ https://colab.research.google.com/drive/1KiLMueXiz9WVB9o4RuzYeGjNZ6PsZU7a#scroll
 # Tag a Release
 Step 1 --> increment the semantic version in the zarr_manager.py "metadata" & the "pyproject.toml"
 ```commandline
-git tag -a v25.01.01 -m "Releasing version v25.01.01"
-```
-
-```commandline
+git tag -a v25.1.2 -m "Releasing version v25.1.2"
 git push origin --tags
 ```
 

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/README.md

@@ -83,10 +83,7 @@ https://colab.research.google.com/drive/1KiLMueXiz9WVB9o4RuzYeGjNZ6PsZU7a#scroll
 # Tag a Release
 Step 1 --> increment the semantic version in the zarr_manager.py "metadata" & the "pyproject.toml"
 ```commandline
-git tag -a v25.01.01 -m "Releasing version v25.01.01"
-```
-
-```commandline
+git tag -a v25.1.2 -m "Releasing version v25.1.2"
 git push origin --tags
 ```
 

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/pyproject.toml

@@ -8,7 +8,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "water_column_sonar_processing"
-version = "25.1.1"
+version = "25.1.3"
 authors = [
   { name="Rudy Klucik", email="rudy.klucik@noaa.gov" },
 ]

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/requirements.txt

@@ -2,16 +2,16 @@
 # defined for Python 3.12
 # Note: be careful with conversions for pandas >=2.0.0, timestamps will have a lot of problems
 
-aiobotocore==2.15.2
-boto3==1.35.36
-botocore==1.35.36
+aiobotocore==2.19.0
+boto3==1.36.3
+botocore==1.36.3
 echopype==0.9.0
 fiona==1.10.1
 # Alternative to geopandas: pyogrio
 geopandas==1.0.1
 mock==5.1.0
-moto[all]==5.0.21
-moto[server]==5.0.21
+moto[all]==5.0.27
+moto[server]==5.0.27
 numcodecs==0.13.1
 numpy==1.26.4
 pandas==2.2.3

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/water_column_sonar_processing/aws/dynamodb_manager.py

@@ -13,16 +13,16 @@ class DynamoDBManager:
             # endpoint_url
     ):
         # self.endpoint_url = endpoint_url
-        self.__dynamodb_session = boto3.Session(
+        self.dynamodb_session = boto3.Session(
             aws_access_key_id=os.environ.get("ACCESS_KEY_ID"),
             aws_secret_access_key=os.environ.get("SECRET_ACCESS_KEY"),
             region_name=os.environ.get("AWS_REGION", default="us-east-1"),
         )
-        self.__dynamodb_resource = self.__dynamodb_session.resource(
+        self.dynamodb_resource = self.dynamodb_session.resource(
             service_name="dynamodb",
             # endpoint_url=self.endpoint_url
         )
-        self.__dynamodb_client = self.__dynamodb_session.client(
+        self.dynamodb_client = self.dynamodb_session.client(
             service_name="dynamodb",
             # endpoint_url=self.endpoint_url
         )
@@ -46,7 +46,7 @@ class DynamoDBManager:
         self,
         table_name,
     ):
-        self.__dynamodb_client.create_table(
+        self.dynamodb_client.create_table(
             TableName=table_name,
             KeySchema=[
                 {
@@ -69,7 +69,7 @@ class DynamoDBManager:
             # }
         )
         # TODO: after creating status is 'CREATING', wait until 'ACTIVE'
-        response = self.__dynamodb_client.describe_table(TableName=table_name)
+        response = self.dynamodb_client.describe_table(TableName=table_name)
         print(response) # https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/dynamodb/client/describe_table.html
         # sleep then response['Table']['TableStatus'] == 'ACTIVE'
 
@@ -80,7 +80,7 @@ class DynamoDBManager:
     #         table_name,
     #         key
     # ):
-    #     response = self.__dynamodb_client.get_item(TableName=table_name, Key=key)
+    #     response = self.dynamodb_client.get_item(TableName=table_name, Key=key)
     #     item = None
     #     if response["ResponseMetadata"]["HTTPStatusCode"] == 200:
     #         if "Item" in response:
@@ -96,7 +96,7 @@ class DynamoDBManager:
         """
         Gets a single row from the db.
         """
-        table = self.__dynamodb_resource.Table(table_name)
+        table = self.dynamodb_resource.Table(table_name)
         response = table.get_item(Key=key)
         # TODO:
         # if response["ResponseMetadata"]["HTTPStatusCode"] != 200:
@@ -113,7 +113,7 @@ class DynamoDBManager:
         update_expression,
     ): # TODO: convert to boolean
         try:
-            response = self.__dynamodb_client.update_item(
+            response = self.dynamodb_client.update_item(
                 TableName=table_name,
                 Key=key,
                 ExpressionAttributeNames=expression_attribute_names,
@@ -140,33 +140,53 @@ class DynamoDBManager:
         To be used to initialize a cruise, deletes all entries associated with that cruise
         in the database.
         """
-        expression_attribute_values = {
-            ":cr": {"S": cruise_name},
-            ":se": {"S": sensor_name},
-            ":sh": {"S": ship_name},
-        }
-
-        filter_expression = (
-            "CRUISE_NAME = :cr and SENSOR_NAME = :se and SHIP_NAME = :sh"
-        )
-        response = self.__dynamodb_client.scan(
+        filter_expression = "CRUISE_NAME = :cr"
+        response = self.dynamodb_client.scan(
             TableName=table_name,
-            Select="ALL_ATTRIBUTES",
-            ExpressionAttributeValues=expression_attribute_values,
+            # Limit=1000,
+            Select='ALL_ATTRIBUTES', # or 'SPECIFIC_ATTRIBUTES',
+            # ExclusiveStartKey=where to pick up
+            #ReturnConsumedCapacity='INDEXES' | 'TOTAL' | 'NONE', ...not sure
+            # ProjectionExpression='#SH, #CR, #FN', # what to specifically return — from expression_attribute_names
             FilterExpression=filter_expression,
+            # ExpressionAttributeNames={
+            #     '#SH': 'SHIP_NAME',
+            #     '#CR': 'CRUISE_NAME',
+            #     '#FN': 'FILE_NAME',
+            # },
+            ExpressionAttributeValues={ # criteria
+                ':cr': {
+                    'S': cruise_name,
+                },
+            },
+            ConsistentRead=True
+            # ExclusiveStartKey=response["LastEvaluatedKey"],
         )
         # Note: table.scan() has 1 MB limit on results so pagination is used
-        if len(response["Items"]) == 0:
+
+        if len(response["Items"]) == 0 and "LastEvaluatedKey" not in response:
             return pd.DataFrame() # If no results, return empty dataframe
 
         data = response["Items"]
 
-        while "LastEvaluatedKey" in response:
-            response = self.__dynamodb_client.scan(
+        while response.get('LastEvaluatedKey'): #"LastEvaluatedKey" in response:
+            response = self.dynamodb_client.scan(
                 TableName=table_name,
-                Select="ALL_ATTRIBUTES",
-                ExpressionAttributeValues=expression_attribute_values,
+                ### Either 'Select' or 'ExpressionAttributeNames'/'ProjectionExpression'
+                Select='ALL_ATTRIBUTES', # or 'SPECIFIC_ATTRIBUTES',
                 FilterExpression=filter_expression,
+                #ProjectionExpression='#SH, #CR, #FN',  # what to specifically return — from expression_attribute_names
+                # ExpressionAttributeNames={ # would need to specify all cols in df
+                #     '#SH': 'SHIP_NAME',
+                #     '#CR': 'CRUISE_NAME',
+                #     '#FN': 'FILE_NAME',
+                # },
+                ExpressionAttributeValues={  # criteria
+                    ':cr': {
+                        'S': cruise_name,
+                    },
+                },
+                ConsistentRead=True,
                 ExclusiveStartKey=response["LastEvaluatedKey"],
             )
             data.extend(response["Items"])
@@ -176,6 +196,66 @@ class DynamoDBManager:
 
         return df.sort_values(by="START_TIME", ignore_index=True)
 
+    #####################################################################
+    # def get_cruise_list(
+    #     self,
+    #     table_name,
+    # ) -> list:
+    #     """
+    #     Experimental, gets all cruise names as list
+    #     """
+    #     filter_expression = "CRUISE_NAME = :cr"
+    #     response = self.dynamodb_client.scan(
+    #         TableName=table_name,
+    #         Select='SPECIFIC_ATTRIBUTES',
+    #         #ReturnConsumedCapacity='INDEXES' | 'TOTAL' | 'NONE', ...not sure
+    #         # ProjectionExpression='#SH, #CR, #FN', # what to specifically return — from expression_attribute_names
+    #         FilterExpression=filter_expression,
+    #         # ExpressionAttributeNames={
+    #         #     '#SH': 'SHIP_NAME',
+    #         #     '#CR': 'CRUISE_NAME',
+    #         #     '#FN': 'FILE_NAME',
+    #         # },
+    #         # ExpressionAttributeValues={ # criteria
+    #         #     ':cr': {
+    #         #         'S': cruise_name,
+    #         #     },
+    #         # },
+    #     )
+    #     # Note: table.scan() has 1 MB limit on results so pagination is used
+    #
+    #     if len(response["Items"]) == 0 and "LastEvaluatedKey" not in response:
+    #         return pd.DataFrame() # If no results, return empty dataframe
+    #
+    #     data = response["Items"]
+    #
+    #     while response.get('LastEvaluatedKey'): #"LastEvaluatedKey" in response:
+    #         response = self.dynamodb_client.scan(
+    #             TableName=table_name,
+    #             ### Either 'Select' or 'ExpressionAttributeNames'/'ProjectionExpression'
+    #             Select='ALL_ATTRIBUTES', # or 'SPECIFIC_ATTRIBUTES',
+    #             FilterExpression=filter_expression,
+    #             #ProjectionExpression='#SH, #CR, #FN',  # what to specifically return — from expression_attribute_names
+    #             # ExpressionAttributeNames={ # would need to specify all cols in df
+    #             #     '#SH': 'SHIP_NAME',
+    #             #     '#CR': 'CRUISE_NAME',
+    #             #     '#FN': 'FILE_NAME',
+    #             # },
+    #             ExpressionAttributeValues={  # criteria
+    #                 ':cr': {
+    #                     'S': cruise_name,
+    #                 },
+    #             },
+    #             ConsistentRead=True,
+    #             ExclusiveStartKey=response["LastEvaluatedKey"],
+    #         )
+    #         data.extend(response["Items"])
+    #
+    #     deserializer = self.type_deserializer
+    #     df = pd.DataFrame([deserializer.deserialize({"M": i}) for i in data])
+    #
+    #     return df.sort_values(by="START_TIME", ignore_index=True)
+
     #####################################################################
     # TODO: WIP
     def delete_item(
@@ -187,7 +267,7 @@ class DynamoDBManager:
         """
         Finds all rows associated with a cruise and deletes them.
         """
-        response = self.__dynamodb_client.delete_item(
+        response = self.dynamodb_client.delete_item(
             Key={
                 "CRUISE_NAME": {
                     "S": cruise_name
@@ -212,7 +292,7 @@ class DynamoDBManager:
         """
         Get a description of the table. Used to verify that records were added/removed.
         """
-        response = self.__dynamodb_client.describe_table(TableName=table_name)
+        response = self.dynamodb_client.describe_table(TableName=table_name)
         print(response)
         return response
 
@@ -230,7 +310,7 @@ class DynamoDBManager:
     #     print(f"Updating processing status to {pipeline_status}.")
     #     if error_message:
     #         print(f"Error message: {error_message}")
-    #         self.__dynamo.update_item(
+    #         self.dynamo.update_item(
     #             table_name=self.__table_name,
     #             key={
     #                 'FILE_NAME': {'S': file_name},  # Partition Key
@@ -255,7 +335,7 @@ class DynamoDBManager:
     #             }
     #         )
     #     else:
-    #         self.__dynamo.update_item(
+    #         self.dynamo.update_item(
     #             table_name=self.__table_name,
     #             key={
     #                 'FILE_NAME': {'S': file_name},  # Partition Key

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/water_column_sonar_processing/cruise/resample_regrid.py

@@ -1,5 +1,4 @@
 import gc
-import os
 from pathlib import Path
 
 import numcodecs
@@ -311,6 +310,12 @@ class ResampleRegrid:
                     output_zarr_store.bottom[
                         start_ping_time_index:end_ping_time_index
                     ] = detected_seafloor_depths
+                #
+                #
+                #
+                # TODO: write the time variable last so that I can parse that as check
+                #
+                #
                 #########################################################################
                 #########################################################################
         except Exception as err:

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/water_column_sonar_processing/model/zarr_manager.py

@@ -250,7 +250,7 @@ class ZarrManager:
         #
         root.attrs["processing_software_name"] = Coordinates.PROJECT_NAME.value
         root.attrs["processing_software_version"] = (
-            "25.1.1"  # TODO: get programmatically, echopype>utils>prov.py
+            "25.1.3"  # TODO: get programmatically, echopype>utils>prov.py
         )
         root.attrs["processing_software_time"] = Timestamp.get_timestamp()
         #

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/water_column_sonar_processing/utility/constants.py

@@ -3,7 +3,7 @@ from enum import Enum, Flag, unique
 
 @unique
 class Constants(Flag):
-    TILE_SIZE = 256 # TODO: add tile size to metadata?
+    TILE_SIZE = 1024 # TODO: add tile size to metadata?
 
     # Average https://noaa-wcsd-zarr-pds.s3.us-east-1.amazonaws.com/level_2/Henry_B._Bigelow/HB0902/EK60/HB0902.zarr/time/927
     # chunk size is ~1.3 kB, HB0902 cruise takes ~30 seconds to load all time/lat/lon data

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/water_column_sonar_processing.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: water_column_sonar_processing
-Version: 25.1.1
+Version: 25.1.3
 Summary: A processing tool for water column sonar data.
 Author-email: Rudy Klucik <rudy.klucik@noaa.gov>
 Project-URL: Homepage, https://github.com/CI-CMG/water-column-sonar-processing
@@ -11,15 +11,15 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: aiobotocore==2.15.2
-Requires-Dist: boto3==1.35.36
-Requires-Dist: botocore==1.35.36
+Requires-Dist: aiobotocore==2.19.0
+Requires-Dist: boto3==1.36.3
+Requires-Dist: botocore==1.36.3
 Requires-Dist: echopype==0.9.0
 Requires-Dist: fiona==1.10.1
 Requires-Dist: geopandas==1.0.1
 Requires-Dist: mock==5.1.0
-Requires-Dist: moto[all]==5.0.21
-Requires-Dist: moto[server]==5.0.21
+Requires-Dist: moto[all]==5.0.27
+Requires-Dist: moto[server]==5.0.27
 Requires-Dist: numcodecs==0.13.1
 Requires-Dist: numpy==1.26.4
 Requires-Dist: pandas==2.2.3
@@ -120,10 +120,7 @@ https://colab.research.google.com/drive/1KiLMueXiz9WVB9o4RuzYeGjNZ6PsZU7a#scroll
 # Tag a Release
 Step 1 --> increment the semantic version in the zarr_manager.py "metadata" & the "pyproject.toml"
 ```commandline
-git tag -a v25.01.01 -m "Releasing version v25.01.01"
-```
-
-```commandline
+git tag -a v25.1.2 -m "Releasing version v25.1.2"
 git push origin --tags
 ```
 

{water_column_sonar_processing-25.1.1 → water_column_sonar_processing-25.1.3}/water_column_sonar_processing.egg-info/requires.txt

@@ -1,12 +1,12 @@
-aiobotocore==2.15.2
-boto3==1.35.36
-botocore==1.35.36
+aiobotocore==2.19.0
+boto3==1.36.3
+botocore==1.36.3
 echopype==0.9.0
 fiona==1.10.1
 geopandas==1.0.1
 mock==5.1.0
-moto[all]==5.0.21
-moto[server]==5.0.21
+moto[all]==5.0.27
+moto[server]==5.0.27
 numcodecs==0.13.1
 numpy==1.26.4
 pandas==2.2.3