easylink 0.1.17__py3-none-any.whl → 0.1.19__py3-none-any.whl

easylink/utilities/validation_utils.py

@@ -11,40 +11,66 @@ function(s) for processed data being passed out of one pipeline step and into th
 from pathlib import Path
 
 import pandas as pd
+from pandas.api.types import is_integer_dtype
 from pyarrow import parquet as pq
 
 
-def validate_input_file_dummy(filepath: str) -> None:
-    """Validates an input file to a dummy :class:`~easylink.step.Step`.
+def _read_file(filepath: str) -> pd.DataFrame:
+    """Reads a file.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the file to read.
+
+    Returns
+    -------
+        The loaded DataFrame.
+
+    Raises
+    ------
+    NotImplementedError
+        If the file type is not supported.
+    """
+    extension = Path(filepath).suffix
+    if extension == ".parquet":
+        return pd.read_parquet(filepath)
+    elif extension == ".csv":
+        return pd.read_csv(filepath)
+    else:
+        raise NotImplementedError(
+            f"Data file type {extension} is not supported. Convert to Parquet or CSV instead."
+        )
 
-    This function is intended to be used as the :attr:`~easylink.graph_components.InputSlot.validator`
-    for _all_ input data at every step in the dummy/:mod:`easylink.pipeline_schema_constants.development`
-    pipeline schema. It simply checks for supported file types as well as the presence
-    of required columns.
+
+def _validate_required_columns(filepath: str, required_columns: set[str]) -> None:
+    """
+    Validates that the file at `filepath` contains all columns in `required_columns`.
 
     Parameters
     ----------
-    filepath
-        The path to the input data file to be validated.
+    filepath : str
+        The path to the file to validate.
+    required_columns : set[str]
+        The set of required column names.
 
     Raises
     ------
     NotImplementedError
         If the file type is not supported.
     LookupError
-        If the file is missing required columns.
+        If any required columns are missing.
     """
     extension = Path(filepath).suffix
     if extension == ".parquet":
         output_columns = set(pq.ParquetFile(filepath).schema.names)
     elif extension == ".csv":
-        output_columns = set(pd.read_csv(filepath).columns)
+        output_columns = set(pd.read_csv(filepath, nrows=5).columns)
     else:
         raise NotImplementedError(
             f"Data file type {extension} is not supported. Convert to Parquet or CSV instead"
         )
 
-    required_columns = {"foo", "bar", "counter"}
     missing_columns = required_columns - output_columns
     if missing_columns:
         raise LookupError(
@@ -52,7 +78,479 @@ def validate_input_file_dummy(filepath: str) -> None:
         )
 
 
+def _validate_unique_column(df: pd.DataFrame, column_name: str, filepath: str) -> None:
+    """Validates that a column in a DataFrame has unique values.
+
+    Parameters
+    ----------
+    df : pandas.DataFrame
+        The DataFrame to validate.
+    column_name : str
+        The name of the column to check.
+    filepath : str
+        The path to the file being validated.
+
+    Raises
+    ------
+    ValueError
+        If the column contains duplicate values.
+    """
+    if not df[column_name].is_unique:
+        raise ValueError(
+            f"Data file {filepath} contains duplicate values in the '{column_name}' column."
+        )
+
+
+def _validate_unique_column_set(df: pd.DataFrame, columns: set[str], filepath: str) -> None:
+    """
+    Validates that the combination of columns in `columns` is unique in the DataFrame.
+
+    Parameters
+    ----------
+    df : pandas.DataFrame
+        The DataFrame to validate.
+    columns : set[str]
+        The set of column names to check for uniqueness as a group.
+    filepath : str
+        The path to the file being validated.
+
+    Raises
+    ------
+    ValueError
+        If duplicate rows exist for the given columns.
+    """
+    if len(df[list(columns)].drop_duplicates()) < len(df):
+        raise ValueError(
+            f"Data file {filepath} contains duplicate rows with the same values for {columns}."
+        )
+
+
+def validate_input_file_dummy(filepath: str) -> None:
+    """Validates an input file to a dummy :class:`~easylink.step.Step`.
+
+    The file must contain the columns: "foo", "bar", and "counter".
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the input file.
+
+    Raises
+    ------
+    LookupError
+        If the file is missing required columns.
+    """
+    _validate_required_columns(filepath, required_columns={"foo", "bar", "counter"})
+
+
+def validate_input_dataset_or_known_clusters(filepath: str) -> None:
+    """
+    Validates a dataset or clusters file based on its filename.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the input file.
+
+    Raises
+    ------
+    LookupError, ValueError
+        If the file fails validation as a dataset or clusters file.
+    """
+    filepath = Path(filepath)
+    if "clusters" in filepath.stem:
+        validate_clusters(filepath)
+    else:
+        validate_dataset(filepath)
+
+
+def validate_dataset(filepath: str) -> None:
+    """Validates a dataset file.
+
+    - Must be in a tabular format and contain a "Record ID" column.
+    - The "Record ID" column must have unique integer values.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the input dataset file.
+
+    Raises
+    ------
+    LookupError
+        If the file is missing the required "Record ID" column.
+    ValueError
+        If the "Record ID" column is not unique or not integer dtype.
+    """
+    _validate_required_columns(filepath, {"Record ID"})
+    df = _read_file(filepath)
+    _validate_unique_column(df, "Record ID", filepath)
+
+    if not is_integer_dtype(df["Record ID"]):
+        raise ValueError(
+            f"Data file {filepath} contains non-integer values in the 'Record ID' column."
+        )
+
+
+def validate_datasets_directory(filepath: str) -> None:
+    """Validates a directory of input dataset files.
+
+    - Each file in the directory must be in a tabular format and contain a "Record ID" column.
+    - The "Record ID" column must have unique values.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the directory containing input dataset files.
+
+    Raises
+    ------
+    NotADirectoryError
+        If the provided path is not a directory.
+    LookupError
+        If any file is missing the required "Record ID" column.
+    ValueError
+        If the "Record ID" column is not unique in any file or if a non-file is present.
+    """
+    input_path = Path(filepath)
+    if not input_path.is_dir():
+        raise NotADirectoryError(f"The path {filepath} is not a directory.")
+
+    for file in input_path.iterdir():
+        if not file.is_file():
+            raise ValueError(f"The path {file} is not a file.")
+        validate_dataset(file.name)
+
+
+def validate_clusters(filepath: str) -> None:
+    """Validates a file containing cluster information.
+
+    - The file must contain three columns: "Input Record Dataset", "Input Record ID", and "Cluster ID".
+    - "Input Record Dataset" and "Input Record ID", considered as a pair, must have unique values.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the file containing cluster data.
+
+    Raises
+    ------
+    LookupError
+        If the file is missing required columns.
+    ValueError
+        If the ("Input Record Dataset", "Input Record ID") pair is not unique.
+    """
+    _validate_required_columns(
+        filepath, {"Input Record Dataset", "Input Record ID", "Cluster ID"}
+    )
+    df = _read_file(filepath)
+    _validate_unique_column_set(df, {"Input Record Dataset", "Input Record ID"}, filepath)
+
+
+def validate_links(filepath: str) -> None:
+    """Validates a file containing link information.
+
+    - The file must contain five columns: "Left Record Dataset", "Left Record ID", "Right Record Dataset", "Right Record ID", and "Probability".
+    - "Left Record ID" and "Right Record ID" cannot be equal in a row where "Left Record Dataset" also equals "Right Record Dataset".
+    - Rows must be unique, ignoring the Probability column.
+    - "Left Record Dataset" must be alphabetically before (or equal to) "Right Record Dataset."
+    - "Left Record ID" must be less than "Right Record ID" if "Left Record Dataset" equals "Right Record Dataset".
+    - "Probability" values must be between 0 and 1 (inclusive).
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the file containing link data.
+
+    Raises
+    ------
+    LookupError
+        If the file is missing required columns.
+    ValueError
+        If:
+        - "Left Record ID" equals "Right Record ID" in any row where datasets match.
+        - Duplicate rows exist with the same "Left Record Dataset", "Left Record ID", "Right Record Dataset", and "Right Record ID".
+        - "Left Record Dataset" is not alphabetically before or equal to "Right Record Dataset".
+        - "Left Record ID" is not less than "Right Record ID" when datasets match.
+        - Values in the "Probability" column are not between 0 and 1 (inclusive).
+    """
+    _validate_required_columns(
+        filepath,
+        {
+            "Left Record Dataset",
+            "Left Record ID",
+            "Right Record Dataset",
+            "Right Record ID",
+            "Probability",
+        },
+    )
+    df = _read_file(filepath)
+
+    _validate_pairs(df, filepath)
+
+    if not df["Probability"].between(0, 1).all():
+        raise ValueError(
+            f"Data file {filepath} contains values in the 'Probability' column that are not between 0 and 1 (inclusive)."
+        )
+
+
+def _validate_pairs(df: pd.DataFrame, filepath: str) -> None:
+    """
+    Validates pairs in a DataFrame for link or pairs files.
+
+    Parameters
+    ----------
+    df : pandas.DataFrame
+        The DataFrame to validate.
+    filepath : str
+        The path to the file being validated.
+
+    Raises
+    ------
+    ValueError
+        If any validation rule for pairs is violated.
+    """
+    if (
+        (df["Left Record Dataset"] == df["Right Record Dataset"])
+        & (df["Left Record ID"] == df["Right Record ID"])
+    ).any():
+        raise ValueError(
+            f"Data file {filepath} contains rows where 'Left Record ID' is equal to 'Right Record ID' and 'Left Record Dataset' is equal to 'Right Record Dataset'."
+        )
+
+    _validate_unique_column_set(
+        df,
+        {"Left Record Dataset", "Left Record ID", "Right Record Dataset", "Right Record ID"},
+        filepath,
+    )
+
+    if not all(df["Left Record Dataset"] <= df["Right Record Dataset"]):
+        raise ValueError(
+            f"Data file {filepath} contains rows where 'Left Record Dataset' is not alphabetically before or equal to 'Right Record Dataset'."
+        )
+
+    if not all(
+        (df["Left Record ID"] < df["Right Record ID"])
+        | (df["Left Record Dataset"] != df["Right Record Dataset"])
+    ):
+        raise ValueError(
+            f"Data file {filepath} contains rows where 'Left Record ID' is not less than 'Right Record ID', though the records are from the same dataset."
+        )
+
+
+def validate_ids_to_remove(filepath: str) -> None:
+    """Validates a file containing IDs to remove.
+
+    - The file must contain a single column: "Record ID".
+    - "Record ID" must have unique values.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the file containing IDs to remove.
+
+    Raises
+    ------
+    LookupError
+        If the file is missing the "Record ID" column.
+    ValueError
+        If the "Record ID" column is not unique.
+    """
+    _validate_required_columns(filepath, {"Record ID"})
+    df = _read_file(filepath)
+    _validate_unique_column(df, "Record ID", filepath)
+
+
+def validate_records(filepath: str) -> None:
+    """Validates a file containing records.
+
+    - A file in a tabular format.
+    - The file may have any number of columns.
+    - Two columns must be called "Input Record Dataset" and "Input Record ID" and they must have unique values as a pair.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the file containing records.
+
+    Raises
+    ------
+    LookupError
+        If required columns are missing.
+    ValueError
+        If the ("Input Record Dataset", "Input Record ID") pair is not unique.
+    """
+    _validate_required_columns(filepath, {"Input Record Dataset", "Input Record ID"})
+    df = _read_file(filepath)
+    _validate_unique_column_set(df, {"Input Record Dataset", "Input Record ID"}, filepath)
+
+
+def validate_blocks(filepath: str) -> None:
+    """
+    Validates a directory containing blocks.
+
+    Each block subdirectory must contain exactly two files: a records file and a pairs file, both in tabular format.
+
+    Validation checks include:
+    - The parent directory must exist and be a directory.
+    - Each block subdirectory must contain exactly one records file (filename contains "records") and one pairs file (filename contains "pairs").
+    - The records file must have columns "Input Record Dataset" and "Input Record ID" with unique pairs.
+    - The pairs file must have columns "Left Record Dataset", "Left Record ID", "Right Record Dataset", and "Right Record ID".
+    - All values in ("Left Record Dataset", "Left Record ID") and ("Right Record Dataset", "Right Record ID") must exist in the records file.
+    - No row in the pairs file may have "Left Record Dataset" == "Right Record Dataset" and "Left Record ID" == "Right Record ID".
+    - All rows in the pairs file must be unique with respect to ("Left Record Dataset", "Left Record ID", "Right Record Dataset", "Right Record ID").
+    - "Left Record Dataset" must be alphabetically before or equal to "Right Record Dataset".
+    - "Left Record ID" must be less than "Right Record ID" if datasets match.
+    - No extra files are allowed in block subdirectories.
+
+    Parameters
+    ----------
+    filepath : str
+        Path to the directory containing block subdirectories.
+
+    Raises
+    ------
+    NotADirectoryError
+        If the provided path is not a directory.
+    FileNotFoundError
+        If a required records or pairs file is missing in any block.
+    LookupError
+        If required columns are missing in records or pairs files.
+    ValueError
+        If:
+            - ("Input Record Dataset", "Input Record ID") is not unique in the records file.
+            - ("Left Record Dataset", "Left Record ID") or ("Right Record Dataset", "Right Record ID") in the pairs file do not exist in the records file.
+            - "Left Record Dataset" == "Right Record Dataset" and "Left Record ID" == "Right Record ID" in any row of the pairs file.
+            - Duplicate rows exist in the pairs file.
+            - "Left Record Dataset" is not alphabetically before or equal to "Right Record Dataset" in any row.
+            - "Left Record ID" is not less than "Right Record ID" when datasets match.
+            - Extra files are present in a block subdirectory.
+    """
+    input_path = Path(filepath)
+
+    if not input_path.is_dir():
+        raise NotADirectoryError(f"The path {filepath} is not a directory.")
+
+    for block_dir in filter(lambda d: d.is_dir(), input_path.iterdir()):
+        files = {file.stem: file for file in block_dir.iterdir() if file.is_file()}
+        records_file = next((f for name, f in files.items() if "records" in name), None)
+        pairs_file = next((f for name, f in files.items() if "pairs" in name), None)
+
+        if len(files) > 2:
+            raise ValueError(f"Extra file(s) found in block directory {block_dir}.")
+
+        if not records_file or not pairs_file:
+            raise FileNotFoundError(
+                f"Block directory {block_dir} must contain both a records file and a pairs file."
+            )
+
+        # Validate records file
+        _validate_required_columns(records_file, {"Input Record Dataset", "Input Record ID"})
+        records_df = _read_file(records_file)
+        _validate_unique_column_set(
+            records_df, {"Input Record Dataset", "Input Record ID"}, records_file
+        )
+
+        # Validate pairs file
+        _validate_required_columns(
+            pairs_file,
+            {
+                "Left Record Dataset",
+                "Left Record ID",
+                "Right Record Dataset",
+                "Right Record ID",
+            },
+        )
+        pairs_df = _read_file(pairs_file)
+
+        # Check that all (dataset, ID) tuples in pairs exist in records
+        record_tuples = set(
+            records_df[["Input Record Dataset", "Input Record ID"]].itertuples(
+                index=False, name=None
+            )
+        )
+        missing_left = (
+            set(
+                pairs_df[["Left Record Dataset", "Left Record ID"]].itertuples(
+                    index=False, name=None
+                )
+            )
+            - record_tuples
+        )
+        missing_right = (
+            set(
+                pairs_df[["Right Record Dataset", "Right Record ID"]].itertuples(
+                    index=False, name=None
+                )
+            )
+            - record_tuples
+        )
+        if missing_left or missing_right:
+            raise ValueError(
+                f"In block {block_dir}, pairs file {pairs_file} contains records not found in records file {records_file}. "
+                f"Missing left records: {missing_left}, missing right records: {missing_right}"
+            )
+
+        _validate_pairs(pairs_df, pairs_file)
+
+
 def validate_dir(filepath: str) -> None:
+    """
+    Validates that the given path is a directory.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to check.
+
+    Raises
+    ------
+    NotADirectoryError
+        If the path is not a directory.
+    """
     input_path = Path(filepath)
     if not input_path.is_dir():
         raise NotADirectoryError(f"The path {filepath} is not a directory.")
+
+
+def validate_dataset_dir(filepath: str) -> None:
+    """
+    Validates a directory containing a single dataset file.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the directory.
+
+    Raises
+    ------
+    NotADirectoryError
+        If the path is not a directory.
+    ValueError
+        If the directory contains more than one file.
+    FileNotFoundError
+        If the directory does not contain any files.
+    """
+    input_path = Path(filepath)
+    if not input_path.is_dir():
+        raise NotADirectoryError(f"The path {filepath} is not a directory.")
+
+    file_paths = [f for f in input_path.iterdir() if not str(f.stem).startswith(".")]
+    if len(file_paths) > 1:
+        raise ValueError(f"The directory {input_path} contains more than one file.")
+    if len(file_paths) == 0:
+        raise FileNotFoundError(f"The directory {input_path} does not contain any files.")
+
+    file_path = file_paths[0]
+    validate_dataset(file_path)
+
+
+def dont_validate(filepath: str) -> None:
+    """Placeholder function that performs no validation.
+
+    Parameters
+    ----------
+    filepath : str
+        The path to the file (not used).
+    """
+    pass

{easylink-0.1.17.dist-info → easylink-0.1.19.dist-info}/METADATA

@@ -1,12 +1,13 @@
 Metadata-Version: 2.4
 Name: easylink
-Version: 0.1.17
+Version: 0.1.19
 Summary: Research repository for the EasyLink ER ecosystem project.
 Home-page: https://github.com/ihmeuw/easylink
 Author: The EasyLink developers
 Author-email: vivarium.dev@gmail.com
 License: BSD-3-Clause
 Description-Content-Type: text/x-rst
+License-File: LICENSE
 Requires-Dist: click
 Requires-Dist: docker
 Requires-Dist: graphviz
@@ -16,7 +17,9 @@ Requires-Dist: networkx
 Requires-Dist: pandas
 Requires-Dist: pyyaml
 Requires-Dist: pyarrow
+Requires-Dist: requests
 Requires-Dist: snakemake>=8.0.0
+Requires-Dist: tqdm
 Requires-Dist: snakemake-interface-executor-plugins<9.0.0
 Requires-Dist: snakemake-executor-plugin-slurm
 Requires-Dist: pandas-stubs
@@ -52,6 +55,7 @@ Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: license
+Dynamic: license-file
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: summary

easylink-0.1.19.dist-info/RECORD

@@ -0,0 +1,91 @@
+easylink/__about__.py,sha256=2-oxCfu9t9yUJouLDwqYRZ0eii8kN25SxRzsawjWjho,440
+easylink/__init__.py,sha256=gGMcIVfiVnHtlDw5mZwhevcDb2wt-kuP6F64gnkFack,159
+easylink/_version.py,sha256=cAJAbAh288a9AL-3yxwFzEM1L26izSJ6wma5aiml_9Y,23
+easylink/cli.py,sha256=zQO4lOVoZ3eVgPVWT2sCF4zNoKgiDJP9ReTh2Myr9jc,10307
+easylink/configuration.py,sha256=hgmG5SIbYqnHDHfk44Gr3QX7C3yTaEVW6GuKeMqvu6c,12689
+easylink/graph_components.py,sha256=zZDZXg5smReHO3ryQC4pao24wyKXzWDe6jS3C6fM2ak,13892
+easylink/implementation.py,sha256=H46WjW9O3csaVAU7qLto3aOu1bSfVOBS0ZySBBX05o0,14544
+easylink/implementation_metadata.yaml,sha256=GoU_aWjVryG8-xjUHkC2nCUeznmYD0BwfJYnNrpZ8P4,10670
+easylink/pipeline.py,sha256=LC0mwboLfe84Mbju9manJjN00Kup4jauiugLlgGCz6I,17884
+easylink/pipeline_graph.py,sha256=9ysX4wAkA-WkUoo15jSLAErncybE4tJwznVx7N_kwIA,23922
+easylink/pipeline_schema.py,sha256=FieJBa3rKgaCIB9QDuQEfWJ9joNBUUp6iHT6xmns-Vk,6886
+easylink/rule.py,sha256=NusEUtBxx18L7UCcgDi3KKooFxSUgyS4eisVM5aPqFE,16770
+easylink/runner.py,sha256=Z9GKgiUAWtp0dW1cyAp86MGthIDeABJtHDXUtzv0-kE,6714
+easylink/step.py,sha256=NGy1KNqM4eXP7kP0kdfcfyGc4K_ExSCSidCdW3h0Qg8,89902
+easylink/devtools/implementation_creator.py,sha256=1WQOOrjQYOhjjp8MQM9j1xoeAp-SW51A1f1oW4G792I,18251
+easylink/images/spark_cluster/Dockerfile,sha256=3PHotbR4jdjVYRHOJ0VQW55b5Qd4tQ1pLLQMrTKWVA0,576
+easylink/images/spark_cluster/README.md,sha256=KdgSttZRplNNWqHn4K1GTsTIab3dTOSG4V99QPLxSp8,569
+easylink/pipeline_schema_constants/__init__.py,sha256=xYymSjTeH3prvQL_rgGFVrriohANFtW_cy0vDwlF3ds,1355
+easylink/pipeline_schema_constants/development.py,sha256=XxcYYZDZM4IADp3eFPQCchD6-OtMp99GiyZBfSswzFo,12640
+easylink/pipeline_schema_constants/main.py,sha256=9IxAjgQej7AaV-zYZEFhG8U-v_rYBFaPuNS3Y3m4Sho,22929
+easylink/pipeline_schema_constants/testing.py,sha256=UDmVVjI1SiDktMbJ2CrSb7amHSYNwhgqNkXhl4lYxQw,20459
+easylink/steps/cascading/exclude_clustered.def,sha256=GfoDqO2Vtsh7VI8SwGaJtv_KtKjs-UmBcivqQ7OPkjk,503
+easylink/steps/cascading/exclude_clustered.py,sha256=NSA6GZBzGa7e6CH4tacCGfr0Y9sUM29g9Nf8NquHB44,2612
+easylink/steps/cascading/exclude_none.def,sha256=iFUhUMocxtkA0NErkjVrBxY0MUdS3DIPNsbCpTJRP0k,488
+easylink/steps/cascading/exclude_none.py,sha256=KntBX3q-V47d96ztOlPNRY_kCFJNi1LNYQ7UNs5wB4c,2507
+easylink/steps/cascading/update_clusters_by_connected_components.def,sha256=sAAAWOod8EuAnotR1cayaGAvs7x6xoMVlwmLso_a9Cc,578
+easylink/steps/cascading/update_clusters_by_connected_components.py,sha256=w7tAOs2QtIIcpTDxw2P_dqMIR-BFa-wi-OmZwrKyhmg,3309
+easylink/steps/default/default_clusters_to_links.def,sha256=9PjUygLvsoYMUZDznceuuv55t8fPs473P57J_RMl3U0,527
+easylink/steps/default/default_clusters_to_links.py,sha256=EIYeP0lj0plBl2OpTRuv3iDEQl-zNVJONUg0kgKSEF0,2848
+easylink/steps/default/default_determining_exclusions.def,sha256=zZUEHDdrpLxzx3gTm-dki2ge5ivCCg4ziIwTErqCII0,542
+easylink/steps/default/default_determining_exclusions.py,sha256=tF2lcga-6n99shgYEmhpNuqok33u7dcW9q5wV3xgp5w,2661
+easylink/steps/default/default_removing_records.def,sha256=QqacmOu6myxFSULHRKeKsVD8l73KDm4VEkPkPlovwqs,524
+easylink/steps/default/default_removing_records.py,sha256=LIlFS8EvJ6h5XqEfgWZYyIAjcKj7Oo8_I5a-vXHOozs,1938
+easylink/steps/default/default_schema_alignment.def,sha256=hFHJkos0Fhe4LvpjLOCd6klIaIqOKqECDDSTVu3G03Y,524
+easylink/steps/default/default_schema_alignment.py,sha256=Uxi6uTFveFKSiiRZG9MnTXOklQngSKGMafqnvKDc0rY,1459
+easylink/steps/default/default_updating_clusters.def,sha256=vDzSkTknDfeiXeHREpw4BkUxFcTWamxr81c3rZ7_enY,527
+easylink/steps/default/default_updating_clusters.py,sha256=A-lO3ussM1Ntffp-ZyPQGbbxZg4QNiZ8AvSOGVJDXnA,2139
+easylink/steps/dev/README.md,sha256=u9dZUggpY2Lf2qb-xkDLWWgHjcmi4osbQtzSNo4uklE,4549
+easylink/steps/dev/build-containers-local.sh,sha256=Wy3pfcyt7I-BNvHcr7ZXDe0g5Ihd00BIPqt9YuRbLeA,259
+easylink/steps/dev/build-containers-remote.sh,sha256=Hy-kaaXf-ta6n8SzOz_ahByjMY5T7J71MvzXRXDvQw8,271
+easylink/steps/dev/test.py,sha256=4iudKBD6CFz2CxbjSBUkc8LCWlMl-Nmw_rB35ZN6TrQ,6835
+easylink/steps/dev/input_data/create_input_files.ipynb,sha256=rHRUFXwTuNXWm8TyaZWFCOewZMDw1G6yiioF8h90erY,2123
+easylink/steps/dev/input_data/input_file_1.csv,sha256=mtu3_ldNTxS9PFtLsZzRspaCCuG_yLxhUdl2ZQFwqrE,88906
+easylink/steps/dev/input_data/input_file_1.parquet,sha256=Km8jRyfGNdq0MFdz_-bewlAc06cFjWn2dWQ7YKKGa5U,60399
+easylink/steps/dev/input_data/input_file_2.csv,sha256=YqKLZDC4d-aYN8Dh9OB6iQWWUKmvueu5CszckH1AApU,100016
+easylink/steps/dev/input_data/input_file_2.parquet,sha256=Vpo0sUqQ78qlWLRk8p303Nh89BVcK4uvXJljRGHmsWk,60392
+easylink/steps/dev/python_pandas/README.md,sha256=c_FbtkKKOTjt2R_LfHUo5lBga1qHiYkxLdQeewRr45g,977
+easylink/steps/dev/python_pandas/dummy_step.py,sha256=NvhLUZu40B3Xbj_S-chQ6IkYUPr6X2aGBxYUa3DqwmY,4362
+easylink/steps/dev/python_pandas/python_pandas.def,sha256=24cxwGF8Cqkv2a1zVsu94MfC_bAXBqAINLwfW2zyB_0,769
+easylink/steps/dev/python_pyspark/README.md,sha256=di29SAfcdTTpar7gdoJRLqKrL8DEfNeayYUyaywdhUg,1563
+easylink/steps/dev/python_pyspark/dummy_step.py,sha256=wxHHI3Uv8MTipKG2ffHbT_eL4JkoNpx49bJoErXumdc,5003
+easylink/steps/dev/python_pyspark/python_pyspark.def,sha256=j_RmVjspmXGOhJTr10ED13RYfbimgxRU3WVTL7VOIUQ,915
+easylink/steps/dev/r/README.md,sha256=dPjZdDTqcJsZCiwhddzlOj1ob0P7YocZUNFrLIGM1-0,1201
+easylink/steps/dev/r/dummy_step.R,sha256=1TWZY8CEkT6gavrulBxFsKbDSKJJjk0NtJrGH7TIikE,4975
+easylink/steps/dev/r/r-image.def,sha256=LrhXlt0C3k7d_VJWopRPEVARnFWSuq_oILlwo7g03bE,627
+easylink/steps/fastLink/fastLink_evaluating_pairs.R,sha256=fQRrTPrgb1t5hrQi0V5H55J-PHdWjsATrVRYdXNYtdU,4603
+easylink/steps/fastLink/fastLink_evaluating_pairs.def,sha256=5rDi-cmWhyuFEsiGFPpTxtySMqq5TpgJG-y8g_MtEvA,509
+easylink/steps/fastLink/fastLink_links_to_clusters.R,sha256=exVzJl4r7k7cRlMCHSmigOqTlxShqzK-FO3EDhlPksg,4087
+easylink/steps/fastLink/fastLink_links_to_clusters.def,sha256=1xYjOMsHtSS2-AI4EC2r6kL8ZX5F2JhmvESefEKeJVY,512
+easylink/steps/output_dir/dummy_step_1_for_output_dir_example.def,sha256=CkQVG-uDRQ9spAavdkZbhx2GD_fRsKZGELPrr8yltsc,550
+easylink/steps/output_dir/dummy_step_1_for_output_dir_example.py,sha256=dI0OWugE35ABLcSwsI-T3C4dvuPTKXwjE52dtSsCo8Y,428
+easylink/steps/output_dir/dummy_step_2_for_output_dir_example.def,sha256=9gShg1EDJEHZcz7Z5VfZ1A4Gpm9XQes8ezn6rAZDgDM,550
+easylink/steps/output_dir/dummy_step_2_for_output_dir_example.py,sha256=DMJW5TXjhELxhY4U9q2RpLjqxlS1YSosTGL2AfRnaZM,521
+easylink/steps/rl-dummy/canonicalizing_and_downstream_analysis/dummy_canonicalizing_and_downstream_analysis.def,sha256=YOWtJZxoe-kHFeEyrgGcVGfdqcbD_Fg17A9shOaK-yc,584
+easylink/steps/rl-dummy/canonicalizing_and_downstream_analysis/dummy_canonicalizing_and_downstream_analysis.py,sha256=skZUiZWcSXAOqq8TAlN5I0wztXgCWHQYA_xkuiL5s28,1202
+easylink/steps/rl-dummy/input_data/create_input_files.ipynb,sha256=uXvJ8zTTPg0077HgA7MhQ_9jD-aeISFLeMeEBbSnOu8,54498
+easylink/steps/rl-dummy/input_data/input_file_1.parquet,sha256=GQ_7v7ucwdJn-9mTgKVcvqkJ5gTkwb0B7y38mfOYbic,15200
+easylink/steps/rl-dummy/input_data/input_file_2.parquet,sha256=Y4eseBm0HmFroksQr_VApgozRL8h8u7nQO6x_Utyns8,14902
+easylink/steps/rl-dummy/input_data/known_clusters.parquet,sha256=Ysodu65toHZN4AgjVJsm0ueUxPIZAJjbtRm9SVM08JE,2598
+easylink/steps/rl-dummy/pre-processing/dummy_pre-processing.def,sha256=HeUSv2QvMOQzsyVktYR1xYoEqwiNpDo-p7IRcGSMspE,512
+easylink/steps/rl-dummy/pre-processing/dummy_pre-processing.py,sha256=aeDgn9z2um0oTPNSwPcTkBou3-1ajud_MWhkuRoHdOU,1884
+easylink/steps/splink/splink_blocking_and_filtering.def,sha256=foAQAPvhDEkXkevpghS-uftsTbIQnQy9PvTkyldQeAA,539
+easylink/steps/splink/splink_blocking_and_filtering.py,sha256=8-_a9PkOmKSa-8TJ9YMjqI7gLo-YD9JCAO1f8uBhdoE,4469
+easylink/steps/splink/splink_evaluating_pairs.def,sha256=DN3Ohy9qJOAyK58v164neP23HDVYpedMqzCu4eQh4Hg,521
+easylink/steps/splink/splink_evaluating_pairs.py,sha256=JR2qVgb14cNZKozDyOrN11nr1mXOwWv69E6WP0pRlMw,5713
+easylink/steps/splink/splink_links_to_clusters.def,sha256=RurvOYyGjNs9tx64DTXwI-GSgHD4T7SzDfhAH18pTEM,524
+easylink/steps/splink/splink_links_to_clusters.py,sha256=z5ymdYl9ytp1e5MA6vn8wpGRFWVuhh23LqGq8NJJxZQ,1936
+easylink/utilities/__init__.py,sha256=0U33kbv4hoMfFQ_lh5hLwifxRPzOgkLkjKLYxmaK10g,196
+easylink/utilities/aggregator_utils.py,sha256=pqBog6kEX4MXBBMjQtHFlE5gEMqRWb5VFl64u0Lr__g,972
+easylink/utilities/data_utils.py,sha256=XPRjq3qW_fN0xQ23Jms_xBzpTHbRwqZWDP1AW0nYkP0,6926
+easylink/utilities/general_utils.py,sha256=El1W0nn4P27sRBGotNQb-9du-Gbhk9ggSuu4vmGDfwo,4591
+easylink/utilities/paths.py,sha256=9inDKMPorAaWh5vhjc3j1Tj_aXVKhLdodiJO9H1nNes,947
+easylink/utilities/spark.smk,sha256=kGtpem7LfQc71tMh5WAYaqKnHQKFvcdhPQSdumOP70k,5799
+easylink/utilities/splitter_utils.py,sha256=UOz4hjkEPqaAz0RrDkDYYej79lLSaq0VVVSH_tF1z0o,3838
+easylink/utilities/validation_utils.py,sha256=DBJB2TLVklgYw1WaaPse9vqtwPLMGmZNYM2cbCZsoHI,18417
+easylink-0.1.19.dist-info/licenses/LICENSE,sha256=z6NBo3hY2Pbh2Wjm9IcHLyQoG-kd816uASh8PbwhTcQ,1530
+easylink-0.1.19.dist-info/METADATA,sha256=nFZA-jZKgZUG4DdiDqY-pNOTfdt1H3QeiwNzvo27vpg,3565
+easylink-0.1.19.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+easylink-0.1.19.dist-info/entry_points.txt,sha256=OGMZDFltg3yMboT7XjJt3joiPhRfV_7jnREVtrAIQNU,51
+easylink-0.1.19.dist-info/top_level.txt,sha256=oHcOpcF_jDMWFiJRzfGQvuskENGDjSPC_Agu9Z_Xvik,9
+easylink-0.1.19.dist-info/RECORD,,