Increase epochs per year to 10k (#33)

* Increase epochs per year to 10k

* Update data urls

CHANGELOG.md

@@ -5,6 +5,24 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.5.0] - 2024-10-16 17:05:58
+
+### Added
+
+- Moved epoch count to 10k per year.
+
+## [1.4.0] - 2024-10-16 17:05:39
+
+### Added
+
+- Missing changelog entry.
+
+## [1.3.0] - 2024-10-16 17:02:56
+
+### Added
+
+- Re-run calibration with more epochs.
+
 ## [1.2.5] - 2024-09-18 13:57:40
 
 ### Fixed
@@ -48,6 +66,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 
 
+[1.5.0]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.4.0...1.5.0
+[1.4.0]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.3.0...1.4.0
+[1.3.0]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.2.5...1.3.0
 [1.2.5]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.2.4...1.2.5
 [1.2.4]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.2.3...1.2.4
 [1.2.3]: https://github.com/PolicyEngine/policyengine-us-data/compare/1.2.2...1.2.3

changelog.yaml

@@ -39,3 +39,18 @@
     - GH actions naming.
     - Bug causing the Extended FRS to error.
   date: 2024-09-18 13:57:40
+- bump: minor
+  changes:
+    added:
+    - Re-run calibration with more epochs.
+  date: 2024-10-16 17:02:56
+- bump: minor
+  changes:
+    added:
+    - Missing changelog entry.
+  date: 2024-10-16 17:05:39
+- bump: minor
+  changes:
+    added:
+    - Moved epoch count to 10k per year.
+  date: 2024-10-16 17:05:58

changelog_entry.yaml

@@ -1,4 +0,0 @@
-- bump: minor
-  changes:
-    added:
-    - Add employer pension contributions.

policyengine_uk_data/datasets/frs/enhanced_frs.py

@@ -56,7 +56,7 @@ class EnhancedFRS_2022_23(EnhancedFRS):
     input_frs = ExtendedFRS_2022_23
     time_period = 2022
     end_year = 2028
-    url = "release://PolicyEngine/ukda/1.4.0/enhanced_frs_2022_23.h5"
+    url = "release://PolicyEngine/ukda/1.5.0/enhanced_frs_2022_23.h5"
 
 
 def reweight(
@@ -104,7 +104,7 @@ def dropout_weights(weights, p):
 
     start_loss = None
 
-    iterator = trange(1_000)
+    iterator = trange(10_000)
     for i in iterator:
         optimizer.zero_grad()
         weights_ = dropout_weights(weights, dropout_rate)

policyengine_uk_data/datasets/frs/frs.py

@@ -115,7 +115,7 @@ class FRS_2022_23(FRS):
     label = "FRS (2022-23)"
     file_path = STORAGE_FOLDER / "frs_2022_23.h5"
     time_period = 2022
-    url = "release://PolicyEngine/ukda/1.4.0/frs_2022_23.h5"
+    url = "release://PolicyEngine/ukda/1.5.0/frs_2022_23.h5"
 
 
 def add_id_variables(frs: h5py.File, person: DataFrame, household: DataFrame):
@@ -759,7 +759,7 @@ def add_expenses(
         sum_to_entity(job.DEDUC1.fillna(0), job.person_id, person.index) * 52,
     )
     frs["employer_pension_contributions"] = (
-        frs["employee_pension_contributions"] * 2.5
+        frs["employee_pension_contributions"] * 3
     )  # Rough estimate based on aggregates.
 
     frs["housing_service_charges"] = (

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "policyengine_uk_data"
-version = "1.4.0"
+version = "1.5.0"
 description = "A package to create representative microdata for the UK."
 readme = "README.md"
 authors = [