Merge pull request #63 from ihmeuw/develop

release v0.5.0

Author: stevebachmeier

.github/CODEOWNERS

@@ -1,2 +1,4 @@
 # default owners
-* @albrja @hussain-jafari @mattkappel @ramittal @rmudambi @stevebachmeier
+* @ihmeuw/vivarium-dev
+/docs/* @ihmeuw/vivarium-research @ihmeuw/vivarium-dev
+*.rst @ihmeuw/vivarium-research @ihmeuw/vivarium-dev

CHANGELOG.rst

@@ -1,4 +1,12 @@
-**0.4.0 - 04/11/23**
+**0.5.0 - 04/13/23**
+ - Bugfix to apply incorrect selection noising at the expected probabilility
+ - Implement the omission noise function
+ - Implement schema for output columns and their dtypes
+ - Implement a year filter to the form generation functions
+ - Support a path to data root directory as form generation function argument
+ - Update documentation
+ 
+ **0.4.0 - 04/11/23**
  - Generate default configuration instead of maintaining a static file
  - Read sample data if no data argument is provided
  - Update sample datasets

README.rst

@@ -19,8 +19,6 @@ or build it from source with
 
   ``> python setup.py install``
 
-This will make the ``pseudopeople`` library available to python and install a
-command-line executable called ``...`` that you can use to verify your
-installation with
-
-  ``> ... test``
+Documentation
+======================
+You can view documentation at https://pseudopeople.readthedocs.io/en/latest/

docs/source/index.rst

@@ -6,11 +6,14 @@ Pseudopeople is a package intended to add configurable noise to a simulated
 census-scale data-set written using standard
 `scientific Python <https://www.scipy.org/>`_ tools.
 
+The github repo can be found at: https://github.com/ihmeuw/pseudopeople
+
 .. toctree::
    :maxdepth: 2
 
    installation
+   noise_functions/index
    tutorials/index
    concepts/index
    api_reference/index
-   glossary
+   glossary

docs/source/noise_functions/index.rst

@@ -0,0 +1,10 @@
+.. _noise_functions_main:
+
+=================
+ Noise Functions
+=================
+
+.. contents::
+   :depth: 2
+   :local:
+   :backlinks: none

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__ = "0.4.0"
+__version__ = "0.5.0"
 
 __author__ = "The pseudopeople developers"
 __email__ = "vivarium.dev@gmail.com"

src/pseudopeople/entity_types.py

@@ -2,6 +2,7 @@
 from typing import Any, Callable, Dict
 
 import pandas as pd
+from loguru import logger
 from vivarium import ConfigTree
 from vivarium.framework.randomness import RandomnessStream
 
@@ -53,6 +54,7 @@ class ColumnNoiseType:
     noise_function: Callable[[pd.Series, ConfigTree, RandomnessStream, Any], pd.Series]
     row_noise_level: float = 0.01
     token_noise_level: float = 0.1
+    noise_level_scaling_function: Callable[[str], float] = lambda x: 1.0
     additional_parameters: Dict[str, Any] = None
 
     def __call__(
@@ -62,18 +64,27 @@ def __call__(
         randomness_stream: RandomnessStream,
         additional_key: Any,
     ) -> pd.Series:
-        # TODO: this is a temporary hack to account for all string columns having been made categorical
-        #  We should record expected output dtype in the columns data structure
-        if column.dtype.name == "category":
-            column = column.astype(str)
-        else:
-            column = column.copy()
-        noise_level = configuration.row_noise_level
+        column = column.copy()
+        noise_level = configuration.row_noise_level * self.noise_level_scaling_function(
+            column.name
+        )
         to_noise_idx = get_index_to_noise(
             column, noise_level, randomness_stream, f"{self.name}_{additional_key}"
         )
+        if to_noise_idx.empty:
+            logger.debug(
+                f"No cells chosen to noise for noise function {self.name} on column {column.name}. "
+                "This is likely due to a combination of the configuration noise levels and the input data."
+            )
+            return column
         noised_data = self.noise_function(
             column.loc[to_noise_idx], configuration, randomness_stream, additional_key
         )
+
+        # Coerce noised column dtype back to original column's if it has changed
+        if noised_data.dtype.name != column.dtype.name:
+            noised_data = noised_data.astype(column.dtype)
+
         column.loc[to_noise_idx] = noised_data
+
         return column