easylink 0.1.23__tar.gz → 0.1.25__tar.gz

{easylink-0.1.23 → easylink-0.1.25}/CHANGELOG.rst

@@ -1,3 +1,12 @@
+**0.1.25 - 6/30/25**
+
+ - Release new images
+ - Clean up stdout logging
+
+**0.1.24 - 6/26/25**
+
+ - Properly escape special characters in envars specified via pipeline configuration
+
 **0.1.23 - 6/25/25**
 
  - Remove "dummy" pipeline references from codebase

{easylink-0.1.23 → easylink-0.1.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: easylink
-Version: 0.1.23
+Version: 0.1.25
 Summary: Research repository for the EasyLink ER ecosystem project.
 Home-page: https://github.com/ihmeuw/easylink
 Author: The EasyLink developers
@@ -78,34 +78,50 @@ Installation
 
 .. _installation:
 
+**NOTE: This package requires AMD64 CPU architecture - it is not compatible with
+Apple's ARM64 architecture (e.g. M1 and newer Macs).**
+
 There are a few things to install in order to use this package:
 
-- Install singularity. 
+- Set up Linux.
+
+  Singularity (and thus EasyLink) requires Linux to run. If you are not already
+  using Linux, you will need to set up a virtual machine; refer to the 
+  `Singularity documentation for installing on Windows or Mac <https://docs.sylabs.io/guides/4.1/admin-guide/installation.html#installation-on-windows-or-mac>`_. 
 
-  You may need to request it from your system admin. 
-  Refer to https://docs.sylabs.io/guides/4.1/admin-guide/installation.html.
-  You can check if you already have singularity installed by running the command
-  ``singularity --version``. For an existing installation, your singularity version
+- Install Singularity.
+
+  First check if you already have Singularity installed by running the command
+  ``singularity --version``. For an existing installation, your Singularity version
   number is printed.
 
+  If Singularity is not yet installed, you will need to install it;
+  refer to the `Singularity docs for installing on Linux <https://docs.sylabs.io/guides/4.1/admin-guide/installation.html#installation-on-linux>`_.
+
+  Note that this requires administrator privileges; you may need to request installation
+  from your system admin if you are working in a shared computing environment.
+
 - Install conda. 
   
   We recommend `miniforge <https://github.com/conda-forge/miniforge>`_. You can
   check if you already have conda installed by running the command ``conda --version``.
   For an existing installation, a version will be displayed.
 
-- Install easylink, python and graphviz in a conda environment.
+- Create a conda environment with python and graphviz installed.
+
+  ::
+
+  $ conda create --name easylink -c conda-forge python=3.12 graphviz 'gcc<14' -y
+  $ conda activate easylink
+
+- Install easylink in the environment.
 
   Option 1 - Install from PyPI with pip::
 
-    $ conda create --name easylink -c conda-forge python=3.12 graphviz 'gcc<14' -y
-    $ conda activate easylink
     $ pip install easylink
 
   Option 2 - Build from source with pip::
     
-    $ conda create --name easylink -c conda-forge python=3.12 graphviz 'gcc<14' -y
-    $ conda activate easylink
     $ pip install git+https://github.com/ihmeuw/easylink.git
 
 .. _end_installation:

easylink-0.1.25/README.rst

@@ -0,0 +1,70 @@
+========
+EasyLink
+========
+
+EasyLink is a framework that allows users to build and run highly configurable
+entity resolution (ER) pipelines.
+
+.. _python_support:
+
+**Supported Python versions: 3.11, 3.12**
+
+.. _end_python_support:
+
+Installation
+============
+
+.. _installation:
+
+**NOTE: This package requires AMD64 CPU architecture - it is not compatible with
+Apple's ARM64 architecture (e.g. M1 and newer Macs).**
+
+There are a few things to install in order to use this package:
+
+- Set up Linux.
+
+  Singularity (and thus EasyLink) requires Linux to run. If you are not already
+  using Linux, you will need to set up a virtual machine; refer to the 
+  `Singularity documentation for installing on Windows or Mac <https://docs.sylabs.io/guides/4.1/admin-guide/installation.html#installation-on-windows-or-mac>`_. 
+
+- Install Singularity.
+
+  First check if you already have Singularity installed by running the command
+  ``singularity --version``. For an existing installation, your Singularity version
+  number is printed.
+
+  If Singularity is not yet installed, you will need to install it;
+  refer to the `Singularity docs for installing on Linux <https://docs.sylabs.io/guides/4.1/admin-guide/installation.html#installation-on-linux>`_.
+
+  Note that this requires administrator privileges; you may need to request installation
+  from your system admin if you are working in a shared computing environment.
+
+- Install conda. 
+  
+  We recommend `miniforge <https://github.com/conda-forge/miniforge>`_. You can
+  check if you already have conda installed by running the command ``conda --version``.
+  For an existing installation, a version will be displayed.
+
+- Create a conda environment with python and graphviz installed.
+
+  ::
+
+  $ conda create --name easylink -c conda-forge python=3.12 graphviz 'gcc<14' -y
+  $ conda activate easylink
+
+- Install easylink in the environment.
+
+  Option 1 - Install from PyPI with pip::
+
+    $ pip install easylink
+
+  Option 2 - Build from source with pip::
+    
+    $ pip install git+https://github.com/ihmeuw/easylink.git
+
+.. _end_installation:
+
+Documentation
+=============
+
+You can view documentation at https://easylink.readthedocs.io/en/latest/

easylink-0.1.25/docs/source/user_guide/tutorials/input_data_demo.yaml

@@ -0,0 +1,3 @@
+input_file_ssa: 2020/input_file_ssa.parquet
+input_file_w2: 2020/input_file_w2.parquet
+known_clusters: known_clusters.parquet

easylink-0.1.23/docs/source/user_guide/tutorials/pipeline_demo_naive.yaml → easylink-0.1.25/docs/source/user_guide/tutorials/pipeline_demo_improved.yaml

@@ -37,7 +37,7 @@ steps:
                     configuration: 
                       INPUT_DATASET: input_file_ssa
                 - implementation:
-                    name: dummy_pre-processing
+                    name: no_pre-processing
                     configuration: 
                       INPUT_DATASET: input_file_w2
               schema_alignment:
@@ -47,17 +47,16 @@ steps:
                 implementation:
                   name: splink_blocking_and_filtering
                   configuration:
-                    BLOCKING_RULES: "'l.first_name == r.first_name,l.last_name == r.last_name'"
                     LINK_ONLY: true
+                    BLOCKING_RULES: "l.first_name == r.first_name,l.last_name == r.last_name"
               evaluating_pairs:
                 implementation:
                   name: splink_evaluating_pairs
                   configuration:
-                    BLOCKING_RULES_FOR_TRAINING: "'l.first_name == r.first_name,l.last_name == r.last_name'"
-                    COMPARISONS: "'ssn:exact,first_name:exact,middle_initial:exact,last_name:exact'"
-                    PROBABILITY_TWO_RANDOM_RECORDS_MATCH: 0.0001  # == 1 / len(w2)
-                    THRESHOLD_MATCH_PROBABILITY: 0
                     LINK_ONLY: true
+                    BLOCKING_RULES_FOR_TRAINING: "l.first_name == r.first_name,l.last_name == r.last_name"
+                    COMPARISONS: "ssn:levenshtein,first_name:name,middle_initial:exact,last_name:name"
+                    PROBABILITY_TWO_RANDOM_RECORDS_MATCH: 0.0001  # == 1 / len(w2)
           links_to_clusters:
             implementation:
               name: splink_links_to_clusters
@@ -68,4 +67,4 @@ steps:
           name: default_updating_clusters
   canonicalizing_and_downstream_analysis:
     implementation:
-      name: dummy_canonicalizing_and_downstream_analysis
+      name: save_clusters

easylink-0.1.25/docs/source/user_guide/tutorials/pipeline_demo_naive.yaml

@@ -0,0 +1,70 @@
+  steps:
+    entity_resolution:
+      substeps:
+        determining_exclusions_and_removing_records:
+          clones:
+            - determining_exclusions:
+                implementation:
+                  name: default_determining_exclusions
+                  configuration:
+                    INPUT_DATASET: input_file_ssa
+              removing_records:
+                implementation:
+                  name: default_removing_records
+                  configuration:
+                    INPUT_DATASET: input_file_ssa
+            - determining_exclusions:
+                implementation:
+                  name: default_determining_exclusions
+                  configuration:
+                    INPUT_DATASET: input_file_w2
+              removing_records:
+                implementation:
+                  name: default_removing_records
+                  configuration:
+                    INPUT_DATASET: input_file_w2
+        clustering:
+          substeps:
+            clusters_to_links:
+              implementation:
+                name: default_clusters_to_links
+            linking:
+              substeps:
+                pre-processing:
+                  clones:
+                  - implementation:
+                      name: middle_name_to_initial
+                      configuration: 
+                        INPUT_DATASET: input_file_ssa
+                  - implementation:
+                      name: no_pre-processing
+                      configuration: 
+                        INPUT_DATASET: input_file_w2
+                schema_alignment:
+                  implementation:
+                    name: default_schema_alignment
+                blocking_and_filtering:
+                  implementation:
+                    name: splink_blocking_and_filtering
+                    configuration:
+                      LINK_ONLY: true
+                      BLOCKING_RULES: "l.first_name == r.first_name,l.last_name == r.last_name"
+                evaluating_pairs:
+                  implementation:
+                    name: splink_evaluating_pairs
+                    configuration:
+                      LINK_ONLY: true
+                      BLOCKING_RULES_FOR_TRAINING: "l.first_name == r.first_name,l.last_name == r.last_name"
+                      COMPARISONS: "ssn:exact,first_name:exact,middle_initial:exact,last_name:exact"
+                      PROBABILITY_TWO_RANDOM_RECORDS_MATCH: 0.0001  # == 1 / len(w2)
+            links_to_clusters:
+              implementation:
+                name: splink_links_to_clusters
+                configuration:
+                  THRESHOLD_MATCH_PROBABILITY: 0.996
+        updating_clusters:
+          implementation:
+            name: default_updating_clusters
+    canonicalizing_and_downstream_analysis:
+      implementation:
+        name: save_clusters

easylink-0.1.25/src/easylink/_version.py

@@ -0,0 +1 @@
+__version__ = "0.1.25"

{easylink-0.1.23 → easylink-0.1.25}/src/easylink/cli.py

@@ -201,16 +201,20 @@ def run(
     main = handle_exceptions(
         func=runner.main, exceptions_logger=logger, with_debugger=with_debugger
     )
-    main(
-        command="run",
-        pipeline_specification=pipeline_specification,
-        input_data=input_data,
-        computing_environment=computing_environment,
-        results_dir=results_dir,
-        images_dir=images,
-        schema_name=schema,
-    )
-    logger.info("*** FINISHED ***")
+    try:
+        main(
+            command="run",
+            pipeline_specification=pipeline_specification,
+            input_data=input_data,
+            computing_environment=computing_environment,
+            results_dir=results_dir,
+            images_dir=images,
+            schema_name=schema,
+        )
+    except SystemExit:
+        # Snakemake uses SystemExit for completion - log success and re-raise
+        logger.info("*** FINISHED ***")
+        raise
 
 
 @easylink.command()
@@ -243,6 +247,7 @@ def generate_dag(
         input_data=input_data,
         computing_environment=None,
         results_dir=results_dir,
+        images_dir=None,
         schema_name=schema,
     )
     logger.info("*** DAG saved to result directory ***")

{easylink-0.1.23 → easylink-0.1.25}/src/easylink/implementation_metadata.yaml

@@ -2,7 +2,7 @@ step_1_python_pandas:
   steps:
   - step_1
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   outputs:
@@ -11,7 +11,7 @@ step_1a_python_pandas:
   steps:
   - step_1a
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   env:
@@ -22,7 +22,7 @@ step_1b_python_pandas:
   steps:
   - step_1b
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   env:
@@ -33,7 +33,7 @@ step_2_python_pandas:
   steps:
   - step_2
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   outputs:
@@ -42,7 +42,7 @@ step_3_python_pandas:
   steps:
   - step_3
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   outputs:
@@ -51,7 +51,7 @@ step_4_python_pandas:
   steps:
   - step_4
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   env:
@@ -62,7 +62,7 @@ step_5_python_pandas:
   steps:
   - step_5
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   env:
@@ -73,7 +73,7 @@ step_6_python_pandas:
   steps:
   - step_6
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   env:
@@ -84,7 +84,7 @@ step_4a_python_pandas:
   steps:
   - step_4a
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   env:
@@ -95,7 +95,7 @@ step_4b_python_pandas:
   steps:
   - step_4b
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   env:
@@ -106,7 +106,7 @@ step_4b_r:
   steps:
   - step_4b
   image_name: r-image.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: a4a03b836694a2b81a1bd2852736ccc5
   script_cmd: Rscript /dummy_step.R
   env:
@@ -117,7 +117,7 @@ step_1_python_pyspark:
   steps:
   - step_1
   image_name: python_pyspark.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: c948577ab0607411dd4b640622d9ec3a
   script_cmd: python3 /code/dummy_step.py
   outputs:
@@ -127,7 +127,7 @@ step_2_python_pyspark:
   steps:
   - step_2
   image_name: python_pyspark.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: c948577ab0607411dd4b640622d9ec3a
   script_cmd: python3 /code/dummy_step.py
   outputs:
@@ -137,7 +137,7 @@ step_3_python_pyspark:
   steps:
   - step_3
   image_name: python_pyspark.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: c948577ab0607411dd4b640622d9ec3a
   script_cmd: python3 /code/dummy_step.py
   outputs:
@@ -147,7 +147,7 @@ step_4_python_pyspark:
   steps:
   - step_4
   image_name: python_pyspark.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: c948577ab0607411dd4b640622d9ec3a
   script_cmd: python3 /code/dummy_step.py
   env:
@@ -158,7 +158,7 @@ step_1_r:
   steps:
   - step_1
   image_name: r-image.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: a4a03b836694a2b81a1bd2852736ccc5
   script_cmd: Rscript /dummy_step.R
   outputs:
@@ -168,7 +168,7 @@ step_2_r:
   steps:
   - step_2
   image_name: r-image.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: a4a03b836694a2b81a1bd2852736ccc5
   script_cmd: Rscript /dummy_step.R
   outputs:
@@ -178,7 +178,7 @@ step_3_r:
   steps:
   - step_3
   image_name: r-image.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: a4a03b836694a2b81a1bd2852736ccc5
   script_cmd: Rscript /dummy_step.R
   outputs:
@@ -188,7 +188,7 @@ step_4_r:
   steps:
   - step_4
   image_name: r-image.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: a4a03b836694a2b81a1bd2852736ccc5
   script_cmd: Rscript /dummy_step.R
   env:
@@ -201,7 +201,7 @@ step_1_and_step_2_combined_python_pandas:
   - step_1
   - step_2
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   outputs:
@@ -211,7 +211,7 @@ step_1_and_step_2_parallel_python_pandas:
   - step_1
   - step_2
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   env:
@@ -223,7 +223,7 @@ step_3_and_step_4_combined_python_pandas:
   - step_3
   - step_4
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   outputs:
@@ -233,7 +233,7 @@ step_1a_and_step_1b_combined_python_pandas:
   - step_1a
   - step_1b
   image_name: python_pandas.sif
-  zenodo_record_id: 15733426
+  zenodo_record_id: 15757317
   md5_checksum: 9177b8e168fcc9cae91bf61265f2185c
   script_cmd: python /dummy_step.py
   outputs:
@@ -241,131 +241,157 @@ step_1a_and_step_1b_combined_python_pandas:
 dummy_step_1_for_output_dir_example:
   steps:
   - step_1_for_output_dir_example
-  image_name: main/dummy_step_1_for_output_dir_example.sif
+  image_name: dummy_step_1_for_output_dir_example.sif
   script_cmd: python /dummy_step_1_for_output_dir_example.py
   outputs:
     step_1_main_output_directory: output_dir/
 dummy_step_1_for_output_dir_example_default:
   steps:
   - step_1_for_output_dir_example
-  image_name: main/dummy_step_1_for_output_dir_example.sif
+  image_name: dummy_step_1_for_output_dir_example.sif
   script_cmd: python /dummy_step_1_for_output_dir_example.py
 dummy_step_2_for_output_dir_example:
   steps:
   - step_2_for_output_dir_example
-  image_name: main/dummy_step_2_for_output_dir_example.sif
+  image_name: dummy_step_2_for_output_dir_example.sif
   script_cmd: python /dummy_step_2_for_output_dir_example.py
   outputs:
     step_2_main_output: result.parquet
 default_removing_records:
   steps:
   - removing_records
-  image_name: main/default_removing_records.sif
+  image_name: default_removing_records.sif
+  zenodo_record_id: 15757317
+  md5_checksum: 85dba6fd73c9f8f504fddb6d5c30f2de
   script_cmd: python /default_removing_records.py
   outputs:
     dataset: dataset
 default_clusters_to_links:
   steps:
   - clusters_to_links
-  image_name: main/default_clusters_to_links.sif
+  image_name: default_clusters_to_links.sif
+  zenodo_record_id: 15757317
+  md5_checksum: 0d00d1272bd8193f60727791097aa065
   script_cmd: python /default_clusters_to_links.py
   outputs:
     known_links: result.parquet
 default_determining_exclusions:
   steps:
   - determining_exclusions
-  image_name: main/default_determining_exclusions.sif
+  image_name: default_determining_exclusions.sif
+  zenodo_record_id: 15757317
+  md5_checksum: e61cb32ad45b79ca9a2c36db4e76ef7e
   script_cmd: python /default_determining_exclusions.py
   outputs:
     ids_to_remove: result.parquet
 default_updating_clusters:
   steps:
   - updating_clusters
-  image_name: main/default_updating_clusters.sif
+  image_name: default_updating_clusters.sif
+  zenodo_record_id: 15757317
+  md5_checksum: cc6bd29e099c2523347fa04545aa35c9
   script_cmd: python /default_updating_clusters.py
   outputs:
     clusters: clusters.parquet
-dummy_canonicalizing_and_downstream_analysis:
+# NOTE: This was made from dummy_canonicalizing_and_downstream_analysis.py,
+# if rebuilding change the name of that file to save_clusters.py
+save_clusters:
   steps:
   - canonicalizing_and_downstream_analysis
-  image_name: main/dummy_canonicalizing_and_downstream_analysis.sif
+  image_name: save_clusters.sif
+  zenodo_record_id: 15757317
+  md5_checksum: 384ab2be668cbadc45160a674f621022
   script_cmd: python /dummy_canonicalizing_and_downstream_analysis.py
   outputs:
     analysis_output: result.parquet
-dummy_pre-processing:
+# NOTE: This was made from dummy_pre-processing.py,
+# if rebuilding change the name of that file to no_pre-processing.py
+no_pre-processing:
   steps:
   - pre-processing
-  image_name: main/dummy_pre-processing.sif
+  image_name: no_pre-processing.sif
+  zenodo_record_id: 15757317
+  md5_checksum: 9a9c080cf145078152501cf96bf61f27
   script_cmd: python /dummy_pre-processing.py
   outputs:
     dataset: dataset
 default_schema_alignment:
   steps:
   - schema_alignment
-  image_name: main/default_schema_alignment.sif
+  image_name: default_schema_alignment.sif
+  zenodo_record_id: 15757317
+  md5_checksum: 3166587f9cfec478b999a17074d628f7
   script_cmd: python /default_schema_alignment.py
   outputs:
     records: result.parquet
 splink_blocking_and_filtering:
   steps:
   - blocking_and_filtering
-  image_name: main/splink_blocking_and_filtering.sif
+  image_name: splink_blocking_and_filtering.sif
+  zenodo_record_id: 15757317
+  md5_checksum: 8a365b90295ef6beaad2b7f80a03d768
   script_cmd: python /splink_blocking_and_filtering.py
   outputs:
     blocks: blocks
 splink_evaluating_pairs:
   steps:
   - evaluating_pairs
-  image_name: main/splink_evaluating_pairs.sif
+  image_name: splink_evaluating_pairs.sif
+  zenodo_record_id: 15757317
+  md5_checksum: b57f4bd16b7a3aa5099569078ea4c064
   script_cmd: python /splink_evaluating_pairs.py
   outputs:
     links: result.parquet
 splink_links_to_clusters:
   steps:
   - links_to_clusters
-  image_name: main/splink_links_to_clusters.sif
+  image_name: splink_links_to_clusters.sif
+  zenodo_record_id: 15757317
+  md5_checksum: 645937f7bab9c2557b7aacafaf4e4765
   script_cmd: python /splink_links_to_clusters.py
   outputs:
     clusters: result.parquet
 fastLink_evaluating_pairs:
   steps:
   - evaluating_pairs
-  image_name: main/fastLink_evaluating_pairs.sif
+  image_name: fastLink_evaluating_pairs.sif
   script_cmd: Rscript /fastLink_evaluating_pairs.R
   outputs:
     links: result.parquet
 fastLink_links_to_clusters:
   steps:
   - links_to_clusters
-  image_name: main/fastLink_links_to_clusters.sif
+  image_name: fastLink_links_to_clusters.sif
   script_cmd: Rscript /fastLink_links_to_clusters.R
   outputs:
     clusters: result.parquet
 exclude_clustered:
   steps:
   - determining_exclusions
-  image_name: main/exclude_clustered.sif
+  image_name: exclude_clustered.sif
   script_cmd: python /exclude_clustered.py
   outputs:
     ids_to_remove: result.parquet
 exclude_none:
   steps:
   - determining_exclusions
-  image_name: main/exclude_none.sif
+  image_name: exclude_none.sif
   script_cmd: python /exclude_none.py
   outputs:
     ids_to_remove: result.parquet
 update_clusters_by_connected_components:
   steps:
   - updating_clusters
-  image_name: main/update_clusters_by_connected_components.sif
+  image_name: update_clusters_by_connected_components.sif
   script_cmd: python /update_clusters_by_connected_components.py
   outputs:
     clusters: result.parquet
 middle_name_to_initial:
   steps:
   - pre-processing
-  image_name: main/middle_name_to_initial.sif
+  image_name: middle_name_to_initial.sif
+  zenodo_record_id: 15757317
+  md5_checksum: 89db9c3318300cda9d538cde08c3c323
   script_cmd: python /middle_name_to_initial.py
   outputs:
     dataset: dataset