span-data 0.1.3__cp311-cp311-win_amd64.whl

span_data-0.1.3.data/data/CHANGELOG.md

@@ -0,0 +1,16 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+## 0.1.0 - 2026-05-12
+
+### Added
+- Initial public release of `span_data`.
+- Identity graphing library built on Splink and DuckDB.
+- Support for DataFrame, CSV, and Snowflake ingestion.
+- Manual override workflows for merge, split, and assign operations.
+
+### Packaging
+- Added PyPI packaging metadata in `pyproject.toml`.
+- Added BSD 3-Clause `LICENSE`.
+- Added `THIRD_PARTY_NOTICES.md` for direct runtime dependencies.

span_data-0.1.3.data/data/LICENSE

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2026, Data Loft Technologies Inc
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

span_data-0.1.3.data/data/THIRD_PARTY_NOTICES.md

@@ -0,0 +1,35 @@
+## Third-Party Notices
+
+This project depends on third-party Python packages. The following list covers
+the direct runtime dependencies currently declared in `pyproject.toml`.
+
+License data was collected from package metadata on PyPI and, where metadata
+was missing, from the corresponding upstream repository license declaration.
+
+If dependencies are added or updated, this file should be reviewed and updated.
+
+### Direct Runtime Dependencies
+
+- `duckdb` (`MIT`)
+  - PyPI: <https://pypi.org/project/duckdb/>
+- `email-validator` (`Unlicense`)
+  - PyPI: <https://pypi.org/project/email-validator/>
+- `pandas` (`BSD-3-Clause`)
+  - PyPI: <https://pypi.org/project/pandas/>
+- `phonenumbers` (`Apache-2.0`)
+  - PyPI: <https://pypi.org/project/phonenumbers/>
+  - Upstream license source: <https://github.com/daviddrysdale/python-phonenumbers>
+- `snowflake-connector-python` (`Apache-2.0`)
+  - PyPI: <https://pypi.org/project/snowflake-connector-python/>
+- `splink` (`MIT`)
+  - PyPI: <https://pypi.org/project/splink/>
+  - Upstream license source: <https://github.com/moj-analytical-services/splink>
+
+### Notes
+
+- This notice file is informational and does not replace the terms of the
+  third-party licenses.
+- The maintainers of this package, acting on behalf of Data Loft Technologies Inc.,
+  are responsible for reviewing transitive dependencies and any bundled artifacts
+  before each release. Downstream users may still perform their own license and
+  compliance reviews as required by their organization or jurisdiction.

span_data-0.1.3.data/data/USAGE.md

@@ -0,0 +1,179 @@
+# Using the ID Grapher with Snowflake
+
+This document provides a step-by-step guide on how to use the `id_grapher`
+library to read data from and write data to Snowflake.
+
+## Overview
+
+The `id_grapher` library is a tool for identity resolution. It uses the
+`splink` library to identify and cluster records that refer to the same entity.
+This guide focuses on using the `id_grapher` with Snowflake as the data source
+and destination.
+
+## Installation
+
+Install the published package from PyPI:
+
+```bash
+pip install span-data
+```
+
+## Usage
+
+Here's a complete example of how to use the `id_grapher` with Snowflake:
+
+```python
+from span_data.id_grapher import IDGrapher, FieldDefinitionMap
+import snowflake.connector
+
+# 1. Connect to Snowflake
+# Replace with your Snowflake connection details
+con = snowflake.connector.connect(
+    user="<your_user>",
+    password="<your_password>",
+    account="<your_account>",
+    warehouse="<your_warehouse>",
+    database="<your_database>",
+    schema="<your_schema>"
+)
+
+# 2. Define the field map
+# This map tells the ID Grapher how to map the columns in your Snowflake
+# table to the standard fields used by the grapher. The keys of the dictionary
+# are the column names in your Snowflake table, and the values specify the
+# 'type' of data and the 'mapping' to the ID Grapher's internal field name.
+# This example is based on the configuration found in
+# `libs/id_grapher/tests/config/id_graph_map_config.yaml`.
+field_map = FieldDefinitionMap(
+    {
+        "FIRSTNAME": {
+          "type": "text",
+          "mapping": "first_name"
+        },
+        "LASTNAME": {
+          "type": "text",
+          "mapping": "last_name"
+        },
+        "USER_EMAIL": {
+          "type": "email",
+          "mapping": "email"
+        },
+        "DOB": {
+          "type": "text",
+          "mapping": "birthdate"
+        },
+        "PHONE": {
+          "type": "phonenumber",
+          "mapping": "phone"
+        },
+        "STREET_ADDRESS": {
+          "type": "text",
+          "mapping": "street_address"
+        },
+        "CITY": {
+          "type": "text",
+          "mapping": "city"
+        },
+        "STATE": {
+          "type": "text",
+          "mapping": "state"
+        },
+        "COUNTRY": {
+          "type": "text",
+          "mapping": "country"
+        },
+        "ZIP_CODE": {
+          "type": "text",
+          "mapping": "zip_code"
+        },
+        "GENDER": {
+          "type": "text",
+          "mapping": "gender"
+        }
+    }
+)
+
+# 3. Configure Splink
+# The ID Grapher uses Splink for record linkage. You need to provide a
+# Splink configuration dictionary. This configuration defines how Splink
+# should compare records and which blocking rules to use.
+#
+# For more details on how to configure Splink, please refer to the
+# official Splink documentation: https://moj-analytical-services.github.io/splink/
+splink_config = {
+    "linkage_model": "det",
+    "blocking_rules": [
+        {"columns": ["first_name", "last_name", "birthdate", "state"]},
+        {"columns": ["first_name", "last_name", "birthdate", "city"]},
+        {"columns": ["first_name", "last_name", "zip_code"]},
+        {"columns": ["first_name", "last_name", "street_address"]},
+        {"columns": ["first_name", "email"]},
+        {"columns": ["email", "phone"]},
+        {"columns": ["phone", "gender"]}
+    ]
+}
+
+
+# 4. Instantiate the IDGrapher and process the data
+with IDGrapher() as grapher:
+    # Add data from a Snowflake table
+    # The 'key' parameter should be the name of the column in your table that
+    # represents a unique identifier for each record in that source.
+    grapher.add_snowflake(
+        con=con,
+        object_name="SOURCE_DATABASE.SOURCE_SCHEMA.SOURCE_TABLE",
+        key="ACCOUNT_ID",
+        field_map=field_map
+    )
+
+    # OPTIONAL: Add more data sources as needed
+    # grapher.add_snowflake(...)
+
+    # OPTIONAL: Add existing ID graph table if available
+    """
+    grapher.add_snowflake(
+        con=con,
+        object_name="ID_GRAPH_DATABASE.ID_GRAPH_SCHEMA.ID_GRAPH_TABLE",
+        key="PROFILE_ID",
+    )
+
+    """
+
+    # Process the data to create the ID graph
+    graph_result = grapher.process(splink_config)
+
+    # 5. Write the results back to Snowflake
+    graph_result.to_snowflake(
+        con=con,
+        database="ID_GRAPH_DATABASE",
+        schema="ID_GRAPH_SCHEMA",
+        table_name="ID_GRAPH_TABLE"
+    )
+
+# Close the Snowflake connection
+con.close()
+```
+
+### Explanation
+
+1.  **Connect to Snowflake**: We establish a connection to Snowflake using the
+    `snowflake-connector-python` library.
+
+2.  **Define the Field Map**: The `FieldDefinitionMap` is used to map your
+    source table's column names to the standard field names that the
+    `id_grapher` expects. This allows the library to understand your data.
+
+3.  **Configure Splink**: The `splink_config` dictionary is crucial for the ID
+    resolution process. It tells `splink` how to compare records and what rules
+    to use for blocking (to reduce the number of comparisons) and matching. The
+    example above provides a basic configuration, but you will likely need to
+    tune it for your specific data.
+
+4.  **Instantiate and Process**: We create an `IDGrapher` instance and use the
+    `add_snowflake` method to load data from your Snowflake table. The
+    `process` method then runs the identity resolution process.
+
+5.  **Write Results to Snowflake**: The `graph_result.to_snowflake()` method
+    writes the output of the ID resolution process to a new table in Snowflake.
+    The output table will contain the original data enriched with a
+    `profile_id` column, which represents the unique entity identifier.

span_data-0.1.3.dist-info/METADATA

@@ -0,0 +1,52 @@
+Metadata-Version: 2.4
+Name: span_data
+Version: 0.1.3
+Summary: Identity resolution library built on Splink and DuckDB.
+Author: The Data Loft
+License-Expression: BSD-3-Clause
+Project-URL: Community (Slack), https://join.slack.com/t/span-data/shared_invite/zt-3xkirzw8i-w_OcmdVoyAMLSH2V83gGAw
+Project-URL: Documentation, https://span.gitbook.io/span-docs
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: <3.12,>=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: duckdb<2.0.0,>=1.5.1
+Requires-Dist: email-validator<3.0.0,>=1.3.1
+Requires-Dist: pandas<3.0.0,>=2.3.3
+Requires-Dist: phonenumbers<10.0.0,>=9.0.6
+Requires-Dist: snowflake-connector-python[pandas]==4.4.0
+Requires-Dist: splink<5.0.0,>=4.0.16
+Dynamic: license-file
+
+# ID Grapher
+
+`span_data` is an identity resolution library built on Splink and DuckDB. It
+links records that refer to the same entity and produces a unified ID graph.
+
+## Core Features
+
+- Ingest source data from pandas DataFrames, CSV files, and Snowflake tables or
+  views.
+- Clean and normalize source fields using `FieldDefinitionMap`.
+- Resolve entities into profile graphs with Splink-based matching.
+- Export graph results to DataFrames, CSV, Parquet, DuckDB relations, and
+  Snowflake.
+- Apply manual override workflows for merge, split, and assign operations.
+
+## Python Support
+
+This package currently supports Python `>=3.11,<3.12`.
+
+## Usage
+
+See [SPAN Product Documentation](https://span.gitbook.io/span-docs) for usage instructions.
+
+## License
+
+This project is licensed under the BSD 3-Clause License. See `LICENSE`.
+
+Third-party dependency license information is documented in
+`THIRD_PARTY_NOTICES.md`.
+
+Release history is documented in `CHANGELOG.md`.

span_data-0.1.3.dist-info/RECORD

@@ -0,0 +1,17 @@
+span_data/id_grapher/__init__.cp311-win_amd64.pyd,sha256=8ICY5k670HKLavTYb8_5JPPLRgJQLoZPpuYBthgQx6E,18944
+span_data/id_grapher/clean_data.cp311-win_amd64.pyd,sha256=r5LWWbTyJ-mOJWyl4tuJn5jxvX2WcqlZ3zdCBa1UosY,78848
+span_data/id_grapher/constants.cp311-win_amd64.pyd,sha256=0C-ea7eLMOrw1XJ-qJm_PoXVqSMmaDN9LHdBWcPSOmo,17408
+span_data/id_grapher/field_definition_map.cp311-win_amd64.pyd,sha256=HxfqXrUhWSC5vlLAj2awqDyhqn20xTHM3HXWG8V-Hbc,67072
+span_data/id_grapher/graph_result.cp311-win_amd64.pyd,sha256=YmgCLBvEKMT5ws0EFosmXGkh0o4G7K04L52JXCAB1Ns,70144
+span_data/id_grapher/id_grapher.cp311-win_amd64.pyd,sha256=Rh-H5GE4w3AxUnNjA0zm8TDtlY54dfr5g_tGUNVLEFM,186880
+span_data/id_grapher/overrides.cp311-win_amd64.pyd,sha256=N9hQwtFoOibzOM1BQmyvyeVoojBGRjDGghHb7I2Xpr0,74240
+span_data/id_grapher/profile_assignment_sql.cp311-win_amd64.pyd,sha256=lQZa0-wWkGBMZDGzCcfNW2cho1mB3tc1Gd_lhntcTKE,83456
+span_data-0.1.3.data/data/CHANGELOG.md,sha256=Ars7jCKy7Iv4Hlqd4-X-sTZcYGOX4VoAm4gn3rkbFuo,519
+span_data-0.1.3.data/data/LICENSE,sha256=5N8M-KZZEWyLdn6BhblwvkK4QKFUiAKJIpcjcAdOWRs,1563
+span_data-0.1.3.data/data/THIRD_PARTY_NOTICES.md,sha256=cUEJdSoYg41X7eNuotKsNnOq3A-wYnjyCEhZDbFcin0,1556
+span_data-0.1.3.data/data/USAGE.md,sha256=S_7MJVv_dbwkQdQQDHkNaaa7wP4IZHHeHp4JcYVw5Go,5843
+span_data-0.1.3.dist-info/licenses/LICENSE,sha256=5N8M-KZZEWyLdn6BhblwvkK4QKFUiAKJIpcjcAdOWRs,1563
+span_data-0.1.3.dist-info/METADATA,sha256=oUCMxrgQrNYCgoFHxFQF8MG0XgjAni238c7-nrqsnwU,1841
+span_data-0.1.3.dist-info/WHEEL,sha256=XHXMKJU3yoVh1ZanBXTJ5bDGb67oEYtF1S6bd8a4izI,101
+span_data-0.1.3.dist-info/top_level.txt,sha256=ItfL4WXhvvBw4enCi2zm5Rabby0YIW5Ew9b25-NOmL8,10
+span_data-0.1.3.dist-info/RECORD,,

span_data-0.1.3.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: false
+Tag: cp311-cp311-win_amd64
+

span_data-0.1.3.dist-info/licenses/LICENSE

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2026, Data Loft Technologies Inc
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

span_data-0.1.3.dist-info/top_level.txt

@@ -0,0 +1 @@
+span_data