Merge pull request #42 from ihmeuw/develop

Release v0.3.1

.readthedocs.yaml

@@ -0,0 +1,21 @@
+# This is the version for the readthedocs configuration. Version 2 ignores
+# web-based configuration and uses everything from this file.
+version: 2
+
+# Configure the python version and environment construction run before
+# docs are built.
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.10"
+python:
+  install:
+      # This runs pip install .[docs] from the project root.
+    - method: pip
+      path: .
+      extra_requirements:
+        - docs
+
+# Doc builds will fail if there are any warnings
+sphinx:
+  fail_on_warning: true

CHANGELOG.rst

@@ -1,3 +1,11 @@
+**0.3.1 - 04/10/23**
+
+ - Build docs to readthedocs
+ - Implement zipcode miswriting function
+ - Implement fake name noise function
+ - Add sample data to package
+ - Support parquet files
+
 **0.3.0 - 04/04/23**
 
  - Implement numeric miswriting noise function

MANIFEST.in

@@ -8,5 +8,5 @@ include README.rst
 recursive-include docs *
 prune docs/_build
 
-recursive-include src/pseudopeople *.py *.yaml *.csv
+recursive-include src/pseudopeople *.py *.yaml *.csv *.hdf
 recursive-include tests *.py *txt *.yaml

setup.py

@@ -34,6 +34,7 @@
         "pandas",
         "pyyaml>=5.1",
         "vivarium",
+        "pyarrow",
     ]
 
     interactive_requirements = [

src/pseudopeople/__about__.py

@@ -13,7 +13,7 @@
 __summary__ = "pseudopeople is package which adds noise to simulated census-scale data using standard scientific Python tools."
 __uri__ = "https://github.com/ihmeuw/pseudopeople"
 
-__version__ = "0.3.0"
+__version__ = "0.3.1"
 
 __author__ = "The pseudopeople developers"
 __email__ = "[email protected]"

src/pseudopeople/constants/paths.py

@@ -7,3 +7,11 @@
 
 INCORRECT_SELECT_NOISE_OPTIONS_DATA = DATA_ROOT / "incorrect_select_options.csv"
 QWERTY_ERRORS = DATA_ROOT / "qwerty_errors.yaml"
+
+SAMPLE_DATA_ROOT = DATA_ROOT / "sample_forms"
+SAMPLE_DECENNIAL_CENSUS = SAMPLE_DATA_ROOT / "decennial_census_observer.hdf"
+SAMPLE_TAXES_W2_AND_1099 = SAMPLE_DATA_ROOT / "tax_w2_observer.hdf"
+SAMPLE_AMERICAN_COMMUNITIES_SURVEY = SAMPLE_DATA_ROOT / "household_survey_observer_acs.hdf"
+SAMPLE_CURRENT_POPULATION_SURVEY = SAMPLE_DATA_ROOT / "household_survey_observer_cps.hdf"
+SAMPLE_SOCIAL_SECURITY = SAMPLE_DATA_ROOT / "social_security_observer.hdf"
+SAMPLE_WOMEN_INFANTS_AND_CHILDREN = SAMPLE_DATA_ROOT / "wic_observer.hdf"

src/pseudopeople/data/fake_names.py

@@ -0,0 +1,188 @@
+"""
+This module includes lists of fake first and last names copied from a .pdf
+version of a NORC report on PVS.
+TODO: Find a link to the NORC report Abie used.
+"""
+
+fake_first_names = [
+    "GIRL",
+    "MOM",
+    "A",
+    "GOH",
+    "MOTHER",
+    "ADULT",
+    "GRANDCHILD",
+    "MR",
+    "ADULT MALE",
+    "GRANDDAUGHTER",
+    "MRS",
+    "B",
+    "GRANDSON",
+    "MS",
+    "BABY",
+    "H",
+    "N",
+    "BOY",
+    "HIJA",
+    "NEPHEW",
+    "BROTHER",
+    "HIJO",
+    "NINO",
+    "C",
+    "HOUSE",
+    "O",
+    "CHILD",
+    "HUSBAND",
+    "OLDEST",
+    "CHILD F",
+    "INMATE",
+    "ONE",
+    "COH",
+    "J",
+    "P",
+    "D",
+    "K",
+    "PERSON",
+    "DAD",
+    "KID",
+    "R",
+    "DAU",
+    "L",
+    "RESIDENT",
+    "DAUGHTER",
+    "LADY",
+    "RESPONDENT",
+    "DAUGHTER OF",
+    "LADY IN THE",
+    "S",
+    "DOH",
+    "LADY OF",
+    "SENOR",
+    "E",
+    "LADY OF HOUSE",
+    "SENORA",
+    "F",
+    "LADY OF THE",
+    "SISTER",
+    "FATHER",
+    "LOH",
+    "SOH",
+    "FEMALE",
+    "M",
+    "SON",
+    "FEMALE CHILD",
+    "MALE",
+    "SON OF",
+    "FRIEND",
+    "MALE CHILD",
+    "T",
+    "G",
+    "MAN",
+    "V",
+    "GENT",
+    "MAN IN THE",
+    "W",
+    "GENTELMAN",
+    "MAN OF",
+    "WIFE",
+    "GENTLE",
+    "MAN OF THE",
+    "WOMAN",
+    "GENTLEMAN",
+    "MINOR",
+    "YOUNGEST",
+    "GENTLEMAN OF",
+    "MISS",
+    "GENTLEMEN",
+    "MOH",
+]
+
+fake_last_names = [
+    "HH",
+    "OF THE HOUSE",
+    "A",
+    "HHM",
+    "ONE",
+    "ADULT",
+    "HOME",
+    "OWNER",
+    "ANON",
+    "HOUSE",
+    "P",
+    "ANONYMOUS",
+    "HOUSEHOLD",
+    "PARENT",
+    "APELLIDO",
+    "HOUSEHOLDER",
+    "PERSON",
+    "B",
+    "HUSBAND",
+    "R",
+    "BOY",
+    "J",
+    "REF",
+    "C",
+    "K",
+    "REFUSE",
+    "CASA",
+    "L",
+    "RESIDENT",
+    "CHILD",
+    "LADY",
+    "RESP",
+    "COH",
+    "LADY OF HOUSE",
+    "RESPONDANT",
+    "D",
+    "LADY OF THE HOUSE",
+    "RESPONDENT",
+    "DAUGHTER",
+    "LAST NAME",
+    "S",
+    "DE CASA",
+    "LOH",
+    "SOH",
+    "DE LA CASA",
+    "M",
+    "SON",
+    "DECLINED",
+    "MALE",
+    "T",
+    "DOE",
+    "MAN",
+    "THE HOUSE",
+    "DOH",
+    "MAN OF THE HOUSE",
+    "THREE",
+    "DONT KNOW",
+    "MOH",
+    "TWO",
+    "E",
+    "N",
+    "UNK",
+    "F",
+    "NA",
+    "UNKNOWN",
+    "FEMALE",
+    "NO",
+    "W",
+    "FOUR",
+    "NO LAST NAME",
+    "WIFE",
+    "FRIEND",
+    "NO NAME",
+    "X",
+    "G",
+    "NONE",
+    "XXX",
+    "GIRL",
+    "O",
+    "Y",
+    "GOH",
+    "OCCUPANT",
+    "YOUNGER",
+    "H",
+    "OF HOUSE",
+    "H AGE",
+    "OF THE HOME",
+]