easylink 0.1.23__py3-none-any.whl → 0.1.25__py3-none-any.whl

easylink/_version.py

@@ -1 +1 @@
-__version__ = "0.1.23"
+__version__ = "0.1.25"

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/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

easylink/rule.py

@@ -14,6 +14,7 @@ dynamically as strings and appended to the Snakefile.
 """
 
 import os
+import shlex
 from abc import ABC, abstractmethod
 from collections.abc import Callable
 from dataclasses import dataclass
@@ -204,7 +205,7 @@ rule:
         export  SPARK_MASTER_URL"""
         for var_name, var_value in self.envvars.items():
             shell_cmd += f"""
-        export {var_name}={var_value}"""
+        export {var_name}={shlex.quote(str(var_value))}"""
         # Log stdout/stderr to diagnostics directory
         shell_cmd += f"""
         {self.script_cmd} > {{log}} 2>&1

easylink/runner.py

@@ -11,6 +11,7 @@ be called from the ``easylink.cli`` module.
 import os
 import socket
 import subprocess
+from contextlib import redirect_stderr, redirect_stdout
 from pathlib import Path
 
 from graphviz import Source
@@ -123,7 +124,123 @@ def main(
     argv.extend(environment_args)
     logger.info(f"Running Snakemake")
     logger.debug(f"Snakemake arguments: {argv}")
-    snake_main(argv)
+
+    # Run snakemake
+    if debug:
+        snake_main(argv)
+    else:
+        _run_snakemake_with_filtered_output(argv, Path(results_dir))
+
+
+def _run_snakemake_with_filtered_output(argv: list[str], results_dir: Path) -> None:
+    """Runs Snakemake with simplified log filtering.
+
+    Parameters
+    ----------
+    argv
+        Snakemake command line arguments.
+    results_dir
+        Directory to save the full Snakemake log.
+    """
+    snakemake_log_file = results_dir / "pipeline.log"
+
+    # Create a filtering output handler that processes lines in real-time
+    class FilteringOutput:
+        """Handles real-time filtering and logging of Snakemake output.
+
+        This class writes all snakemake output to a log file and selectively logs
+        filtered lines to the logger for user visibility.
+
+        Parameters
+        ----------
+        log_file_path
+            The path to the log file where all output will be written.
+
+        """
+
+        def __init__(self, log_file_path: Path):
+            self.log_file = open(log_file_path, "w")
+            self.buffer = ""
+
+        def write(self, text: str) -> int:
+            # Write to log file
+            self.log_file.write(text)
+            self.log_file.flush()
+
+            # Process and log filtered output
+            self.buffer += text
+            while "\n" in self.buffer:
+                line, self.buffer = self.buffer.split("\n", 1)
+                if line.strip():
+                    filtered_line = _filter_snakemake_output_simple(line.strip())
+                    if filtered_line:
+                        logger.info(filtered_line)
+
+            return len(text)
+
+        def flush(self):
+            self.log_file.flush()
+
+        def close(self):
+            # Process and log any remaining buffer content
+            if self.buffer.strip():
+                filtered_line = _filter_snakemake_output_simple(self.buffer.strip())
+                if filtered_line:
+                    logger.info(filtered_line)
+            self.log_file.close()
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, exc_type, exc_val, exc_tb):
+            self.close()
+
+    # Create the filtering output handler and ensure the log file is always closed
+    with FilteringOutput(snakemake_log_file) as filtering_output:
+        try:
+            # Redirect both stdout and stderr to our filtering handler
+            with redirect_stdout(filtering_output), redirect_stderr(filtering_output):
+                snake_main(argv)
+        except SystemExit:
+            # Snakemake uses SystemExit for both success and failure
+            logger.info(
+                f"Pipeline finished running - full log saved to: {snakemake_log_file}"
+            )
+            # Always re-raise to allow test frameworks to detect completion
+            raise
+
+
+def _filter_snakemake_output_simple(line: str) -> str | None:
+    """
+    Simple filter for Snakemake output showing only localrules and Job messages.
+
+    Parameters
+    ----------
+    line
+        A single line of Snakemake output.
+
+    Returns
+    -------
+    str or None
+        The filtered line for display, or None to suppress the line.
+    """
+    # Skip empty lines
+    if not line.strip():
+        return None
+
+    if line.startswith("localrule "):
+        # Show localrule names (without the "localrule" prefix)
+        # Extract rule name (remove "localrule " prefix and colon at the end)
+        filtered_line = line.replace("localrule ", "").rstrip(":")
+    elif line.startswith("Job ") and ":" in line:
+        # Show Job messages
+        # Extract everything after "Job ##: "
+        parts = line.split(":", 1)
+        filtered_line = parts[1].strip() if len(parts) > 1 else None
+    else:
+        # Suppress everything else
+        filtered_line = None
+    return filtered_line
 
 
 def _get_singularity_args(config: Config) -> str:

easylink/steps/splink/splink_evaluating_pairs.py

@@ -35,6 +35,7 @@ for block_dir in blocks_dir.iterdir():
             comparisons.append(cl.LevenshteinAtThresholds(column))
         else:
             raise ValueError(f"Unknown comparison method {method}")
+    # TODO: check both datasets contain all the columns
 
     # Create the Splink linker in dedupe mode
     settings = SettingsCreator(
@@ -135,7 +136,7 @@ for block_dir in blocks_dir.iterdir():
 
     sqls = predict_from_comparison_vectors_sqls_using_settings(
         linker._settings_obj,
-        float(os.environ["THRESHOLD_MATCH_PROBABILITY"]),
+        float(os.getenv("THRESHOLD_MATCH_PROBABILITY", 0)),
         threshold_match_weight=None,
         sql_infinity_expression=linker._infinity_expression,
     )

easylink/utilities/general_utils.py

@@ -97,24 +97,34 @@ def _add_logging_sink(
         Whether the logs should be converted to JSON before they're dumped
         to the logging sink.
     """
-    message_format = (
-        "<green>{time:YYYY-MM-DD HH:mm:ss.SSS}</green> | <green>{elapsed}</green> | "
-        "<cyan>{function}</cyan>:<cyan>{line}</cyan> - <level>{message}</level>"
-    )
+
+    def format_message(record):
+        elapsed_seconds = int(record["elapsed"].total_seconds())
+        hours = elapsed_seconds // 3600
+        minutes = (elapsed_seconds % 3600) // 60
+        seconds = elapsed_seconds % 60
+        elapsed_str = f"{hours:02d}:{minutes:02d}:{seconds:02d}"
+        time_str = record["time"].strftime("%Y-%m-%d %H:%M:%S")
+
+        if colorize:
+            return f"\033[32m{time_str}\033[0m | \033[32m{elapsed_str}\033[0m | {record['message']}\n"
+        else:
+            return f"{time_str} | {elapsed_str} | {record['message']}\n"
+
     if verbose == 0:
         logger.add(
             sink,
-            colorize=colorize,
+            colorize=False,  # We handle colors in format_message
             level="INFO",
-            format=message_format,
+            format=format_message,
             serialize=serialize,
         )
     elif verbose >= 1:
         logger.add(
             sink,
-            colorize=colorize,
+            colorize=False,  # We handle colors in format_message
             level="DEBUG",
-            format=message_format,
+            format=format_message,
             serialize=serialize,
         )
 

{easylink-0.1.23.dist-info → easylink-0.1.25.dist-info}/METADATA

@@ -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-0.1.23.dist-info → easylink-0.1.25.dist-info}/RECORD

@@ -1,16 +1,16 @@
 easylink/__about__.py,sha256=2-oxCfu9t9yUJouLDwqYRZ0eii8kN25SxRzsawjWjho,440
 easylink/__init__.py,sha256=gGMcIVfiVnHtlDw5mZwhevcDb2wt-kuP6F64gnkFack,159
-easylink/_version.py,sha256=0byemO6n6WCv41u9vBG2AIsOkVbxLvok7puvwy8EhfU,23
-easylink/cli.py,sha256=zQO4lOVoZ3eVgPVWT2sCF4zNoKgiDJP9ReTh2Myr9jc,10307
+easylink/_version.py,sha256=Ej7LsXg-6CASlaEHsZkUoLDpYEfHeFKdIeXMIM0esgA,23
+easylink/cli.py,sha256=80_EVklOdX78fPqAinTpsfTfWUqMM4ghFaQcVgZG354,10496
 easylink/configuration.py,sha256=TPd3WbqUcJMJDPJuHeo5ZebvZPQrRyfm8-laad2sOFk,12681
 easylink/graph_components.py,sha256=zZDZXg5smReHO3ryQC4pao24wyKXzWDe6jS3C6fM2ak,13892
 easylink/implementation.py,sha256=lSF37g-aQYgdLI0lgFaDrBkp23te9O9B1V-CmmRtB-0,14514
-easylink/implementation_metadata.yaml,sha256=pKu_H9fLnTsS8E4wCnYRitumW1-zs7mfE3z66BAyO30,10848
+easylink/implementation_metadata.yaml,sha256=u_E51gVzVzTuM19dMv7-p_0JV-A6j5dfUwJrxtAZDBQ,11805
 easylink/pipeline.py,sha256=NJyMInbOCjJ_5kRzzuK5AcupvC7ecd5qLOC-f1Gy3Ss,17701
 easylink/pipeline_graph.py,sha256=jtjS7_2IVa189U8cL621600erC_0pa6BKPRRO8VqwiU,23760
 easylink/pipeline_schema.py,sha256=sj6YQqMFUS35RRFWdlrhPlud68d3Rb5y7iKfAEZy1qs,6877
-easylink/rule.py,sha256=MM7WyW56J7zT2FVjHlFtjuz62PfdSBGTD3MNcpLfEZM,16598
-easylink/runner.py,sha256=Z9GKgiUAWtp0dW1cyAp86MGthIDeABJtHDXUtzv0-kE,6714
+easylink/rule.py,sha256=n8r4NL7MiNzppl39MRbEMdHEpn_e_XS7LfrsJD6KNfA,16629
+easylink/runner.py,sha256=irMmrUME1B8BFTtQkCr-u-lHBDKaEll7IX_a4Q4AJNc,10576
 easylink/step.py,sha256=-vdFhPvwAZ3d69LMQGmSIVdcMG8E8ZtSvTE0UWif7zs,91088
 easylink/devtools/implementation_creator.py,sha256=gZZpfpiOOh912nNjR_d5wR0mBO5c09jWMS0FSYRcE1o,19120
 easylink/pipeline_schema_constants/__init__.py,sha256=njUL2v67WFC3dW_FjOXWRLSeOhInox_ZINLEji0_7V8,1523
@@ -72,20 +72,20 @@ easylink/steps/rl-dummy/pre-processing/dummy_pre-processing.py,sha256=I6kqG4e_H2
 easylink/steps/splink/splink_blocking_and_filtering.def,sha256=umWzxJhsfdi8g3TD-r2mKpjC-FPAMDk6-IERiWigdQc,557
 easylink/steps/splink/splink_blocking_and_filtering.py,sha256=FO8YJ2_KgCLpQoq5xsM339bTSN1DhCXCL8XT1pb5STY,5259
 easylink/steps/splink/splink_evaluating_pairs.def,sha256=DN3Ohy9qJOAyK58v164neP23HDVYpedMqzCu4eQh4Hg,521
-easylink/steps/splink/splink_evaluating_pairs.py,sha256=m-j1QMRSvPCiSoWVSV1kzzzsK1c_xG8nqYKMd3cj7kM,6195
+easylink/steps/splink/splink_evaluating_pairs.py,sha256=vWUe3vQo9uGs0Cy8pG5PbolzsJX_cEaPS3Q0PMcBjcg,6253
 easylink/steps/splink/splink_links_to_clusters.def,sha256=RurvOYyGjNs9tx64DTXwI-GSgHD4T7SzDfhAH18pTEM,524
 easylink/steps/splink/splink_links_to_clusters.py,sha256=5Sw8yi0dVLuRB-trN2kXmxbHBR0VJBxYee6u4_usg2Y,1920
 easylink/utilities/__init__.py,sha256=0U33kbv4hoMfFQ_lh5hLwifxRPzOgkLkjKLYxmaK10g,196
 easylink/utilities/aggregator_utils.py,sha256=_DAHRAf9janbDsuj_jnAn5Dzz2s4R5Ni3YeytDpN9UE,954
 easylink/utilities/data_utils.py,sha256=XPRjq3qW_fN0xQ23Jms_xBzpTHbRwqZWDP1AW0nYkP0,6926
-easylink/utilities/general_utils.py,sha256=El1W0nn4P27sRBGotNQb-9du-Gbhk9ggSuu4vmGDfwo,4591
+easylink/utilities/general_utils.py,sha256=MmuoV4T6PgyEDjbepC_1D3TGrq70Hp-hl-GaAYr5wRU,5033
 easylink/utilities/paths.py,sha256=9inDKMPorAaWh5vhjc3j1Tj_aXVKhLdodiJO9H1nNes,947
 easylink/utilities/spark.smk,sha256=kGtpem7LfQc71tMh5WAYaqKnHQKFvcdhPQSdumOP70k,5799
 easylink/utilities/splitter_utils.py,sha256=KXiVUYJ9TGxCQmrwos18pB1sxG_0Ay67qoDJT6vem2o,3828
 easylink/utilities/validation_utils.py,sha256=DBJB2TLVklgYw1WaaPse9vqtwPLMGmZNYM2cbCZsoHI,18417
-easylink-0.1.23.dist-info/licenses/LICENSE,sha256=z6NBo3hY2Pbh2Wjm9IcHLyQoG-kd816uASh8PbwhTcQ,1530
-easylink-0.1.23.dist-info/METADATA,sha256=u-oRyBse4M0AsFkMjTuy0JCpul-BwHJ1JaD9fIALrHU,3565
-easylink-0.1.23.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-easylink-0.1.23.dist-info/entry_points.txt,sha256=OGMZDFltg3yMboT7XjJt3joiPhRfV_7jnREVtrAIQNU,51
-easylink-0.1.23.dist-info/top_level.txt,sha256=oHcOpcF_jDMWFiJRzfGQvuskENGDjSPC_Agu9Z_Xvik,9
-easylink-0.1.23.dist-info/RECORD,,
+easylink-0.1.25.dist-info/licenses/LICENSE,sha256=z6NBo3hY2Pbh2Wjm9IcHLyQoG-kd816uASh8PbwhTcQ,1530
+easylink-0.1.25.dist-info/METADATA,sha256=agOx4R08pqrpwjWmoSAmhU33gmHZ5QhDt9UHVRbnkHI,4219
+easylink-0.1.25.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+easylink-0.1.25.dist-info/entry_points.txt,sha256=OGMZDFltg3yMboT7XjJt3joiPhRfV_7jnREVtrAIQNU,51
+easylink-0.1.25.dist-info/top_level.txt,sha256=oHcOpcF_jDMWFiJRzfGQvuskENGDjSPC_Agu9Z_Xvik,9
+easylink-0.1.25.dist-info/RECORD,,