path: root/python-openfisca-survey-manager.spec

%global _empty_manifest_terminate_build 0
Name:		python-OpenFisca-Survey-Manager
Version:	0.47.2
Release:	1
Summary:	A tool for managing survey/administrative data.
License:	http://www.fsf.org/licensing/licenses/agpl-3.0.html
URL:		https://github.com/openfisca/openfisca-survey-manager
Source0:	https://mirrors.nju.edu.cn/pypi/web/packages/02/4b/8d0a7596808aebdc08824e8467413f811c4951d83ff0dd9562f105e2496e/OpenFisca-Survey-Manager-0.47.2.tar.gz
BuildArch:	noarch

Requires:	python3-chardet
Requires:	python3-configparser
Requires:	python3-humanize
Requires:	python3-openfisca-core
Requires:	python3-pandas
Requires:	python3-pyxdg
Requires:	python3-PyYAML
Requires:	python3-tables
Requires:	python3-tabulate
Requires:	python3-weightedcalcs
Requires:	python3-wquantiles
Requires:	python3-autopep8
Requires:	python3-flake8
Requires:	python3-pycodestyle
Requires:	python3-pytest
Requires:	python3-scipy
Requires:	python3-autopep8
Requires:	python3-coveralls
Requires:	python3-flake8
Requires:	python3-flake8-bugbear
Requires:	python3-flake8-docstrings
Requires:	python3-flake8-print
Requires:	python3-flake8-rst-docstrings
Requires:	python3-openfisca-country-template
Requires:	python3-pytest
Requires:	python3-pytest-cov
Requires:	python3-scipy
Requires:	python3-tables
Requires:	python3-feather
Requires:	python3-rpy2
Requires:	python3-pyreadstat
Requires:	python3-SAS7BDAT

%description
# OpenFisca Survey Manager

[![Newsletter](https://img.shields.io/badge/newsletter-subscribe!-informational.svg?style=flat)](mailto:contact%40openfisca.org?subject=Subscribe%20to%20your%20newsletter%20%7C%20S'inscrire%20%C3%A0%20votre%20newsletter&body=%5BEnglish%20version%20below%5D%0A%0ABonjour%2C%0A%0AVotre%C2%A0pr%C3%A9sence%C2%A0ici%C2%A0nous%C2%A0ravit%C2%A0!%20%F0%9F%98%83%0A%0AEnvoyez-nous%20cet%20email%20pour%20que%20l'on%20puisse%20vous%20inscrire%20%C3%A0%20la%20newsletter.%20%0A%0AAh%C2%A0!%20Et%20si%20vous%20pouviez%20remplir%20ce%20petit%20questionnaire%2C%20%C3%A7a%20serait%20encore%20mieux%C2%A0!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2F45M0VR1TYKD1RGzX2%0A%0AAmiti%C3%A9%2C%0AL%E2%80%99%C3%A9quipe%20OpenFisca%0A%0A%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%20ENGLISH%20VERSION%20%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%0A%0AHi%2C%20%0A%0AWe're%20glad%20to%20see%20you%20here!%20%F0%9F%98%83%0A%0APlease%20send%20us%20this%20email%2C%20so%20we%20can%20subscribe%20you%20to%20the%20newsletter.%0A%0AAlso%2C%20if%20you%20can%20fill%20out%20this%20short%20survey%2C%20even%20better!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2FsOg8K1abhhm441LG2%0A%0ACheers%2C%0AThe%20OpenFisca%20Team)
[![Twitter](https://img.shields.io/badge/twitter-follow%20us!-9cf.svg?style=flat)](https://twitter.com/intent/follow?screen_name=openfisca)
[![Slack](https://img.shields.io/badge/slack-join%20us!-blueviolet.svg?style=flat)](mailto:contact%40openfisca.org?subject=Join%20you%20on%20Slack%20%7C%20Nous%20rejoindre%20sur%20Slack&body=%5BEnglish%20version%20below%5D%0A%0ABonjour%2C%0A%0AVotre%C2%A0pr%C3%A9sence%C2%A0ici%C2%A0nous%C2%A0ravit%C2%A0!%20%F0%9F%98%83%0A%0ARacontez-nous%20un%20peu%20de%20vous%2C%20et%20du%20pourquoi%20de%20votre%20int%C3%A9r%C3%AAt%20de%20rejoindre%20la%20communaut%C3%A9%20OpenFisca%20sur%20Slack.%0A%0AAh%C2%A0!%20Et%20si%20vous%20pouviez%20remplir%20ce%20petit%20questionnaire%2C%20%C3%A7a%20serait%20encore%20mieux%C2%A0!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2F45M0VR1TYKD1RGzX2%0A%0AN%E2%80%99oubliez%20pas%20de%20nous%20envoyer%20cet%20email%C2%A0!%20Sinon%2C%20on%20ne%20pourra%20pas%20vous%20contacter%20ni%20vous%20inviter%20sur%20Slack.%0A%0AAmiti%C3%A9%2C%0AL%E2%80%99%C3%A9quipe%20OpenFisca%0A%0A%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%20ENGLISH%20VERSION%20%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%0A%0AHi%2C%20%0A%0AWe're%20glad%20to%20see%20you%20here!%20%F0%9F%98%83%0A%0APlease%20tell%20us%20a%20bit%20about%20you%20and%20why%20you%20want%20to%20join%20the%20OpenFisca%20community%20on%20Slack.%0A%0AAlso%2C%20if%20you%20can%20fill%20out%20this%20short%20survey%2C%20even%20better!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2FsOg8K1abhhm441LG2.%0A%0ADon't%20forget%20to%20send%20us%20this%20email!%20Otherwise%20we%20won't%20be%20able%20to%20contact%20you%20back%2C%20nor%20invite%20you%20on%20Slack.%0A%0ACheers%2C%0AThe%20OpenFisca%20Team)
[![CircleCI](https://img.shields.io/circleci/project/github/openfisca/openfisca-survey-manager/master.svg?style=flat)](https://circleci.com/gh/openfisca/openfisca-survey-manager)
[![Coveralls](https://img.shields.io/coveralls/github/openfisca/openfisca-survey-manager/master.svg?style=flat)](https://coveralls.io/github/openfisca/openfisca-survey-manager?branch=master)
[![Python](https://img.shields.io/pypi/pyversions/openfisca-survey-manager.svg)](https://pypi.python.org/pypi/openfisca-survey-manager)
[![PyPi](https://img.shields.io/pypi/v/openfisca-survey-manager.svg?style=flat)](https://pypi.python.org/pypi/openfisca-survey-manager)

## [EN] Introduction

[OpenFisca](https://openfisca.org) is a versatile microsimulation free software. You can check the [online documentation](https://openfisca.org/doc/) for more details.

This repository contains the Survey-Manager module, to work with OpenFisca and survey data.

It provides two main features:
* A Python API to access data in [Hierarchical Data Format](https://en.wikipedia.org/wiki/Hierarchical_Data_Format) (HDF).
* A script that transforms SAS, Stata, SPSS, and CSV data files to HDF data files, along with some metadata so they can be used by the Python API.

> For France survey data, you might find useful information on the next steps in [openfisca-france-data](https://github.com/openfisca/openfisca-france-data) repository.

## [FR] Introduction

[OpenFisca](https://openfisca.org) est un logiciel libre de micro-simulation. Pour plus d'information, vous pouvez consulter la [documentation officielle](https://openfisca.org/doc/).

Ce dépôt contient le module Survey-Manager. Il facilite l'usage d'OpenFisca avec des données d'enquête.

Il fournit deux fonctionnalités principales:
* Une API Python permettant l'accès à des données au format [Hierarchical Data Format](https://fr.wikipedia.org/wiki/Hierarchical_Data_Format) (HDF).
* Un script qui tranforme les fichiers de données aux formats SAS, Stata, SPSS, and CSV data files en fichiers de données au format HDF, avec quelques metadonnées leur permettant d'être utilisés par l'API Python.

> Si vous disposez de données d'enquête sur la France, le dépôt [openfisca-france-data](https://github.com/openfisca/openfisca-france-data) pourrait être utile à vos prochaines étapes de traitement.

## Environment

OpenFisca-Survey-Manager runs on Python 3.7. More recent versions should work, but are not tested.

> Backward compatibility with Python 2.7 has been dropped since January 1st, 2019.

## Usage

### Installation

#### Install with PIP

If you're developing your own script or looking to run `OpenFisca-Survey-Manager` without editing it, you don't need to get its source code. It just needs to be known by your environment.
To do so, first, install the package with `pip`:

```shell
pip install --upgrade pip
pip install openfisca-survey-manager
```

This should not display any error and end with:

`Successfully installed [... openfisca-survey-manager-xx.xx.xx ...]`

It comes with `build-collection` command that we will use in the next steps.

> If you want to improve this module, please see the `Development` section below.

#### Install with Conda

Create an anvironment and install openfisca-survey-manager
```
conda create -n survey python=3.8
conda activate survey
conda install -c conda-forge -c openfisca openfisca-survey-manager
```

You are ready to go !

To exit your environment:
```
conda deactivate
```

### Getting the configuration directory path

To be able to use OpenFisca-Survey-Manager, you have to create two configuration files:
* `raw_data.ini`,
* and `config.ini`.

To know where to copy them to, use the following command:

```shell
build-collection --help
```

You should get the following result.

```shell
usage: build-collection [-h] -c COLLECTION [-d] [-m] [-p PATH] [-s SURVEY]
                        [-v]

optional arguments:
  -h, --help            show this help message and exit
  -c COLLECTION, --collection COLLECTION
                        name of collection to build or update
  -d, --replace-data    erase existing survey data HDF5 file (instead of
                        failing when HDF5 file already exists)
  -m, --replace-metadata
                        erase existing collection metadata JSON file (instead
                        of just adding new surveys)
  -p PATH, --path PATH  path to the config files directory (default =
                        /your/path/.config/openfisca-survey-manager)
  -s SURVEY, --survey SURVEY
                        name of survey to build or update (default = all)
  -v, --verbose         increase output verbosity
```

Take note of the default configuration directory path in `-p PATH, --path PATH` option's description. This is the directory where you will set your `raw_data.ini` and `config.ini` files. In this example, it is `/Users/you/.config/openfisca-survey-manager`.

> If you want to use a different path, you can pass the `--path /another/path` option to `build-collection`. This feature is still experimental though.

### Editing the config files

Configuration files are INI files (text files).

The `raw_data.ini` lists your input surveys while `config.ini` specifies the paths to SurveyManager outputs.

> `raw_data.ini` and `config.ini` must not be committed (they are already ignored by [`.gitignore`](.gitignore)).

#### raw_data.ini, for inputs configuration

To initialise your `raw_data.ini` file, you can follow these steps:

  1. Copy the template file [raw_data_template.ini](openfisca_survey_manager/config_files_templates/raw_data_template.ini) to the configuration directory path you identified in the previous step and rename it to `raw_data.ini`.
  Ex: `/your/path/.config/openfisca-survey-manager/raw_data.ini`

  2. Edit the latter by adding a section title for your survey.
  For example, if you name your survey `housing_survey`, you should get a line with:
  ```ini
  [housing_survey]
  ```

  3. Add a reference to the location of your raw data **directory** (SAS, stata DTA files, SPSS, CSV files).
  For paths in Windows, use `/` instead of `\` to separate folders.
  You do not need to put quotes, even when the path name contains spaces.

  Your file should look like this:

  ```ini
  [housing_survey]

  2014 = /path/to/your/raw/data/HOUSING_2014
  ```

You can also set multiple surveys as follows:

```ini
[revenue_survey]

2014 = /path/to/your/raw/data/REVENUE_2014
2015 = /path/to/your/raw/data/REVENUE_2015
2016 = /path/to/your/raw/data/REVENUE_2016

[housing_survey]

2014 = /path/to/your/raw/data/HOUSING_2014
```

#### config.ini, for outputs configuration

To initilalise your `config.ini` file:

  1. Copy its template file [config_template.ini](openfisca_survey_manager/config_files_templates/config_template.ini) to your configuration directory and rename it to `config.ini`.
  Ex: `/your/path/.config/openfisca-survey-manager/config.ini`.

  2. Define a `collections_directory` path where the SurveyManager will generate your survey inputs and outputs JSON description.
  Ex: `/.../openfisca-survey-manager/transformed_housing_survey`
  For a `housing_survey`, you will get a `/.../openfisca-survey-manager/transformed_housing_survey/housing_survey.json` file.

  3. Define an `output_directory` where the generated HDF file will be registered.
    This directory could be a sub-directory of your `collections_directory`.

  4. Define a `tmp_directory` that will store temporay calculation results. Its content will be deleted at the end of the calculation.
    This directory could be a sub-directory of your `collections_directory`.

Your `config.ini` file should look similar to this:

  ```ini
  [collections]

  collections_directory = /path/to/your/collections/directory

  [data]

  output_directory = /path/to/your/data/output/directory
  tmp_directory = /path/to/your/data/tmp/directory
  ```

> Make sure those directories exist, otherwise the script will fail.

### Building the HDF5 files

This step will read your configuration files and you survey data and generate a HDF5 file (`.h5`) for your survey.
To build the HDF5 files, we'll use the [`build-collection`](openfisca_survey_manager/scripts/build_collection.py) script.

Here is an example for one survey with one serie: our `housing_survey` that knows only 2014 serie. We call our survey as a collection (with `-c` option) and build the HDF5 file with this command:

```shell
build-collection -c housing_survey -d -m -v
```

`-d -m` options put you on the safe side as they remove previous outputs if they exist.

It will generate:
* A `housing_survey.json` listing a `housing_survey_2014` survey with both:
  * your input `tables` and your input file paths in an `informations` key,
  * the transformed survey path in a `hdf5_file_path` key.
* Your transformed survey in a `housing_survey_2014.h5` file.

#### build-collection, what else?

As `build-collection --help` shows, other options exist. Here are other usage examples.

If you have multiple series of one survey like the `revenue_survey`, you can run the specific `2015` serie with:

```shell
build-collection -c revenue_survey -s 2015 -d -m -v
```

Or if you want to specify a different configuration directory path:

```shell
build-collection -p /another/path -c housing_survey -s 2014 -d -m -v
```

> The `--path /another/path` option is still experimental though.

It should work. If it doesn't, please do not hesitate to [open an issue](https://github.com/openfisca/openfisca-survey-manager/issues/new).


## Development

If you want to contribute to OpenFisca-Survey-Manager, please be welcomed! To install it locally in development mode:

```shell
git clone https://github.com/openfisca/openfisca-survey-manager.git
cd openfisca-survey-manager
make install
```

## Testing

To run the entire test suite:

```sh
make test
```

To run the entire test suite with the same config as in CI:

```sh
CI=True make test
```

## Style

This repository adheres to a certain coding style, and we invite you to follow it for your contributions to be integrated promptly.

To run the style checker:

```sh
make check-style
```

To automatically style-format your code changes:

```sh
make format-style
```

To automatically style-format your code changes each time you commit:

```sh
touch .git/hooks/pre-commit
chmod +x .git/hooks/pre-commit

tee -a .git/hooks/pre-commit << END
#!/bin/sh
#
# Automatically format your code before committing.
exec make format-style
END
```


%package -n python3-OpenFisca-Survey-Manager
Summary:	A tool for managing survey/administrative data.
Provides:	python-OpenFisca-Survey-Manager
BuildRequires:	python3-devel
BuildRequires:	python3-setuptools
BuildRequires:	python3-pip
%description -n python3-OpenFisca-Survey-Manager
# OpenFisca Survey Manager

[![Newsletter](https://img.shields.io/badge/newsletter-subscribe!-informational.svg?style=flat)](mailto:contact%40openfisca.org?subject=Subscribe%20to%20your%20newsletter%20%7C%20S'inscrire%20%C3%A0%20votre%20newsletter&body=%5BEnglish%20version%20below%5D%0A%0ABonjour%2C%0A%0AVotre%C2%A0pr%C3%A9sence%C2%A0ici%C2%A0nous%C2%A0ravit%C2%A0!%20%F0%9F%98%83%0A%0AEnvoyez-nous%20cet%20email%20pour%20que%20l'on%20puisse%20vous%20inscrire%20%C3%A0%20la%20newsletter.%20%0A%0AAh%C2%A0!%20Et%20si%20vous%20pouviez%20remplir%20ce%20petit%20questionnaire%2C%20%C3%A7a%20serait%20encore%20mieux%C2%A0!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2F45M0VR1TYKD1RGzX2%0A%0AAmiti%C3%A9%2C%0AL%E2%80%99%C3%A9quipe%20OpenFisca%0A%0A%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%20ENGLISH%20VERSION%20%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%0A%0AHi%2C%20%0A%0AWe're%20glad%20to%20see%20you%20here!%20%F0%9F%98%83%0A%0APlease%20send%20us%20this%20email%2C%20so%20we%20can%20subscribe%20you%20to%20the%20newsletter.%0A%0AAlso%2C%20if%20you%20can%20fill%20out%20this%20short%20survey%2C%20even%20better!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2FsOg8K1abhhm441LG2%0A%0ACheers%2C%0AThe%20OpenFisca%20Team)
[![Twitter](https://img.shields.io/badge/twitter-follow%20us!-9cf.svg?style=flat)](https://twitter.com/intent/follow?screen_name=openfisca)
[![Slack](https://img.shields.io/badge/slack-join%20us!-blueviolet.svg?style=flat)](mailto:contact%40openfisca.org?subject=Join%20you%20on%20Slack%20%7C%20Nous%20rejoindre%20sur%20Slack&body=%5BEnglish%20version%20below%5D%0A%0ABonjour%2C%0A%0AVotre%C2%A0pr%C3%A9sence%C2%A0ici%C2%A0nous%C2%A0ravit%C2%A0!%20%F0%9F%98%83%0A%0ARacontez-nous%20un%20peu%20de%20vous%2C%20et%20du%20pourquoi%20de%20votre%20int%C3%A9r%C3%AAt%20de%20rejoindre%20la%20communaut%C3%A9%20OpenFisca%20sur%20Slack.%0A%0AAh%C2%A0!%20Et%20si%20vous%20pouviez%20remplir%20ce%20petit%20questionnaire%2C%20%C3%A7a%20serait%20encore%20mieux%C2%A0!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2F45M0VR1TYKD1RGzX2%0A%0AN%E2%80%99oubliez%20pas%20de%20nous%20envoyer%20cet%20email%C2%A0!%20Sinon%2C%20on%20ne%20pourra%20pas%20vous%20contacter%20ni%20vous%20inviter%20sur%20Slack.%0A%0AAmiti%C3%A9%2C%0AL%E2%80%99%C3%A9quipe%20OpenFisca%0A%0A%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%20ENGLISH%20VERSION%20%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%0A%0AHi%2C%20%0A%0AWe're%20glad%20to%20see%20you%20here!%20%F0%9F%98%83%0A%0APlease%20tell%20us%20a%20bit%20about%20you%20and%20why%20you%20want%20to%20join%20the%20OpenFisca%20community%20on%20Slack.%0A%0AAlso%2C%20if%20you%20can%20fill%20out%20this%20short%20survey%2C%20even%20better!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2FsOg8K1abhhm441LG2.%0A%0ADon't%20forget%20to%20send%20us%20this%20email!%20Otherwise%20we%20won't%20be%20able%20to%20contact%20you%20back%2C%20nor%20invite%20you%20on%20Slack.%0A%0ACheers%2C%0AThe%20OpenFisca%20Team)
[![CircleCI](https://img.shields.io/circleci/project/github/openfisca/openfisca-survey-manager/master.svg?style=flat)](https://circleci.com/gh/openfisca/openfisca-survey-manager)
[![Coveralls](https://img.shields.io/coveralls/github/openfisca/openfisca-survey-manager/master.svg?style=flat)](https://coveralls.io/github/openfisca/openfisca-survey-manager?branch=master)
[![Python](https://img.shields.io/pypi/pyversions/openfisca-survey-manager.svg)](https://pypi.python.org/pypi/openfisca-survey-manager)
[![PyPi](https://img.shields.io/pypi/v/openfisca-survey-manager.svg?style=flat)](https://pypi.python.org/pypi/openfisca-survey-manager)

## [EN] Introduction

[OpenFisca](https://openfisca.org) is a versatile microsimulation free software. You can check the [online documentation](https://openfisca.org/doc/) for more details.

This repository contains the Survey-Manager module, to work with OpenFisca and survey data.

It provides two main features:
* A Python API to access data in [Hierarchical Data Format](https://en.wikipedia.org/wiki/Hierarchical_Data_Format) (HDF).
* A script that transforms SAS, Stata, SPSS, and CSV data files to HDF data files, along with some metadata so they can be used by the Python API.

> For France survey data, you might find useful information on the next steps in [openfisca-france-data](https://github.com/openfisca/openfisca-france-data) repository.

## [FR] Introduction

[OpenFisca](https://openfisca.org) est un logiciel libre de micro-simulation. Pour plus d'information, vous pouvez consulter la [documentation officielle](https://openfisca.org/doc/).

Ce dépôt contient le module Survey-Manager. Il facilite l'usage d'OpenFisca avec des données d'enquête.

Il fournit deux fonctionnalités principales:
* Une API Python permettant l'accès à des données au format [Hierarchical Data Format](https://fr.wikipedia.org/wiki/Hierarchical_Data_Format) (HDF).
* Un script qui tranforme les fichiers de données aux formats SAS, Stata, SPSS, and CSV data files en fichiers de données au format HDF, avec quelques metadonnées leur permettant d'être utilisés par l'API Python.

> Si vous disposez de données d'enquête sur la France, le dépôt [openfisca-france-data](https://github.com/openfisca/openfisca-france-data) pourrait être utile à vos prochaines étapes de traitement.

## Environment

OpenFisca-Survey-Manager runs on Python 3.7. More recent versions should work, but are not tested.

> Backward compatibility with Python 2.7 has been dropped since January 1st, 2019.

## Usage

### Installation

#### Install with PIP

If you're developing your own script or looking to run `OpenFisca-Survey-Manager` without editing it, you don't need to get its source code. It just needs to be known by your environment.
To do so, first, install the package with `pip`:

```shell
pip install --upgrade pip
pip install openfisca-survey-manager
```

This should not display any error and end with:

`Successfully installed [... openfisca-survey-manager-xx.xx.xx ...]`

It comes with `build-collection` command that we will use in the next steps.

> If you want to improve this module, please see the `Development` section below.

#### Install with Conda

Create an anvironment and install openfisca-survey-manager
```
conda create -n survey python=3.8
conda activate survey
conda install -c conda-forge -c openfisca openfisca-survey-manager
```

You are ready to go !

To exit your environment:
```
conda deactivate
```

### Getting the configuration directory path

To be able to use OpenFisca-Survey-Manager, you have to create two configuration files:
* `raw_data.ini`,
* and `config.ini`.

To know where to copy them to, use the following command:

```shell
build-collection --help
```

You should get the following result.

```shell
usage: build-collection [-h] -c COLLECTION [-d] [-m] [-p PATH] [-s SURVEY]
                        [-v]

optional arguments:
  -h, --help            show this help message and exit
  -c COLLECTION, --collection COLLECTION
                        name of collection to build or update
  -d, --replace-data    erase existing survey data HDF5 file (instead of
                        failing when HDF5 file already exists)
  -m, --replace-metadata
                        erase existing collection metadata JSON file (instead
                        of just adding new surveys)
  -p PATH, --path PATH  path to the config files directory (default =
                        /your/path/.config/openfisca-survey-manager)
  -s SURVEY, --survey SURVEY
                        name of survey to build or update (default = all)
  -v, --verbose         increase output verbosity
```

Take note of the default configuration directory path in `-p PATH, --path PATH` option's description. This is the directory where you will set your `raw_data.ini` and `config.ini` files. In this example, it is `/Users/you/.config/openfisca-survey-manager`.

> If you want to use a different path, you can pass the `--path /another/path` option to `build-collection`. This feature is still experimental though.

### Editing the config files

Configuration files are INI files (text files).

The `raw_data.ini` lists your input surveys while `config.ini` specifies the paths to SurveyManager outputs.

> `raw_data.ini` and `config.ini` must not be committed (they are already ignored by [`.gitignore`](.gitignore)).

#### raw_data.ini, for inputs configuration

To initialise your `raw_data.ini` file, you can follow these steps:

  1. Copy the template file [raw_data_template.ini](openfisca_survey_manager/config_files_templates/raw_data_template.ini) to the configuration directory path you identified in the previous step and rename it to `raw_data.ini`.
  Ex: `/your/path/.config/openfisca-survey-manager/raw_data.ini`

  2. Edit the latter by adding a section title for your survey.
  For example, if you name your survey `housing_survey`, you should get a line with:
  ```ini
  [housing_survey]
  ```

  3. Add a reference to the location of your raw data **directory** (SAS, stata DTA files, SPSS, CSV files).
  For paths in Windows, use `/` instead of `\` to separate folders.
  You do not need to put quotes, even when the path name contains spaces.

  Your file should look like this:

  ```ini
  [housing_survey]

  2014 = /path/to/your/raw/data/HOUSING_2014
  ```

You can also set multiple surveys as follows:

```ini
[revenue_survey]

2014 = /path/to/your/raw/data/REVENUE_2014
2015 = /path/to/your/raw/data/REVENUE_2015
2016 = /path/to/your/raw/data/REVENUE_2016

[housing_survey]

2014 = /path/to/your/raw/data/HOUSING_2014
```

#### config.ini, for outputs configuration

To initilalise your `config.ini` file:

  1. Copy its template file [config_template.ini](openfisca_survey_manager/config_files_templates/config_template.ini) to your configuration directory and rename it to `config.ini`.
  Ex: `/your/path/.config/openfisca-survey-manager/config.ini`.

  2. Define a `collections_directory` path where the SurveyManager will generate your survey inputs and outputs JSON description.
  Ex: `/.../openfisca-survey-manager/transformed_housing_survey`
  For a `housing_survey`, you will get a `/.../openfisca-survey-manager/transformed_housing_survey/housing_survey.json` file.

  3. Define an `output_directory` where the generated HDF file will be registered.
    This directory could be a sub-directory of your `collections_directory`.

  4. Define a `tmp_directory` that will store temporay calculation results. Its content will be deleted at the end of the calculation.
    This directory could be a sub-directory of your `collections_directory`.

Your `config.ini` file should look similar to this:

  ```ini
  [collections]

  collections_directory = /path/to/your/collections/directory

  [data]

  output_directory = /path/to/your/data/output/directory
  tmp_directory = /path/to/your/data/tmp/directory
  ```

> Make sure those directories exist, otherwise the script will fail.

### Building the HDF5 files

This step will read your configuration files and you survey data and generate a HDF5 file (`.h5`) for your survey.
To build the HDF5 files, we'll use the [`build-collection`](openfisca_survey_manager/scripts/build_collection.py) script.

Here is an example for one survey with one serie: our `housing_survey` that knows only 2014 serie. We call our survey as a collection (with `-c` option) and build the HDF5 file with this command:

```shell
build-collection -c housing_survey -d -m -v
```

`-d -m` options put you on the safe side as they remove previous outputs if they exist.

It will generate:
* A `housing_survey.json` listing a `housing_survey_2014` survey with both:
  * your input `tables` and your input file paths in an `informations` key,
  * the transformed survey path in a `hdf5_file_path` key.
* Your transformed survey in a `housing_survey_2014.h5` file.

#### build-collection, what else?

As `build-collection --help` shows, other options exist. Here are other usage examples.

If you have multiple series of one survey like the `revenue_survey`, you can run the specific `2015` serie with:

```shell
build-collection -c revenue_survey -s 2015 -d -m -v
```

Or if you want to specify a different configuration directory path:

```shell
build-collection -p /another/path -c housing_survey -s 2014 -d -m -v
```

> The `--path /another/path` option is still experimental though.

It should work. If it doesn't, please do not hesitate to [open an issue](https://github.com/openfisca/openfisca-survey-manager/issues/new).


## Development

If you want to contribute to OpenFisca-Survey-Manager, please be welcomed! To install it locally in development mode:

```shell
git clone https://github.com/openfisca/openfisca-survey-manager.git
cd openfisca-survey-manager
make install
```

## Testing

To run the entire test suite:

```sh
make test
```

To run the entire test suite with the same config as in CI:

```sh
CI=True make test
```

## Style

This repository adheres to a certain coding style, and we invite you to follow it for your contributions to be integrated promptly.

To run the style checker:

```sh
make check-style
```

To automatically style-format your code changes:

```sh
make format-style
```

To automatically style-format your code changes each time you commit:

```sh
touch .git/hooks/pre-commit
chmod +x .git/hooks/pre-commit

tee -a .git/hooks/pre-commit << END
#!/bin/sh
#
# Automatically format your code before committing.
exec make format-style
END
```


%package help
Summary:	Development documents and examples for OpenFisca-Survey-Manager
Provides:	python3-OpenFisca-Survey-Manager-doc
%description help
# OpenFisca Survey Manager

[![Newsletter](https://img.shields.io/badge/newsletter-subscribe!-informational.svg?style=flat)](mailto:contact%40openfisca.org?subject=Subscribe%20to%20your%20newsletter%20%7C%20S'inscrire%20%C3%A0%20votre%20newsletter&body=%5BEnglish%20version%20below%5D%0A%0ABonjour%2C%0A%0AVotre%C2%A0pr%C3%A9sence%C2%A0ici%C2%A0nous%C2%A0ravit%C2%A0!%20%F0%9F%98%83%0A%0AEnvoyez-nous%20cet%20email%20pour%20que%20l'on%20puisse%20vous%20inscrire%20%C3%A0%20la%20newsletter.%20%0A%0AAh%C2%A0!%20Et%20si%20vous%20pouviez%20remplir%20ce%20petit%20questionnaire%2C%20%C3%A7a%20serait%20encore%20mieux%C2%A0!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2F45M0VR1TYKD1RGzX2%0A%0AAmiti%C3%A9%2C%0AL%E2%80%99%C3%A9quipe%20OpenFisca%0A%0A%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%20ENGLISH%20VERSION%20%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%0A%0AHi%2C%20%0A%0AWe're%20glad%20to%20see%20you%20here!%20%F0%9F%98%83%0A%0APlease%20send%20us%20this%20email%2C%20so%20we%20can%20subscribe%20you%20to%20the%20newsletter.%0A%0AAlso%2C%20if%20you%20can%20fill%20out%20this%20short%20survey%2C%20even%20better!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2FsOg8K1abhhm441LG2%0A%0ACheers%2C%0AThe%20OpenFisca%20Team)
[![Twitter](https://img.shields.io/badge/twitter-follow%20us!-9cf.svg?style=flat)](https://twitter.com/intent/follow?screen_name=openfisca)
[![Slack](https://img.shields.io/badge/slack-join%20us!-blueviolet.svg?style=flat)](mailto:contact%40openfisca.org?subject=Join%20you%20on%20Slack%20%7C%20Nous%20rejoindre%20sur%20Slack&body=%5BEnglish%20version%20below%5D%0A%0ABonjour%2C%0A%0AVotre%C2%A0pr%C3%A9sence%C2%A0ici%C2%A0nous%C2%A0ravit%C2%A0!%20%F0%9F%98%83%0A%0ARacontez-nous%20un%20peu%20de%20vous%2C%20et%20du%20pourquoi%20de%20votre%20int%C3%A9r%C3%AAt%20de%20rejoindre%20la%20communaut%C3%A9%20OpenFisca%20sur%20Slack.%0A%0AAh%C2%A0!%20Et%20si%20vous%20pouviez%20remplir%20ce%20petit%20questionnaire%2C%20%C3%A7a%20serait%20encore%20mieux%C2%A0!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2F45M0VR1TYKD1RGzX2%0A%0AN%E2%80%99oubliez%20pas%20de%20nous%20envoyer%20cet%20email%C2%A0!%20Sinon%2C%20on%20ne%20pourra%20pas%20vous%20contacter%20ni%20vous%20inviter%20sur%20Slack.%0A%0AAmiti%C3%A9%2C%0AL%E2%80%99%C3%A9quipe%20OpenFisca%0A%0A%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%20ENGLISH%20VERSION%20%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%3D%0A%0AHi%2C%20%0A%0AWe're%20glad%20to%20see%20you%20here!%20%F0%9F%98%83%0A%0APlease%20tell%20us%20a%20bit%20about%20you%20and%20why%20you%20want%20to%20join%20the%20OpenFisca%20community%20on%20Slack.%0A%0AAlso%2C%20if%20you%20can%20fill%20out%20this%20short%20survey%2C%20even%20better!%0Ahttps%3A%2F%2Fgoo.gl%2Fforms%2FsOg8K1abhhm441LG2.%0A%0ADon't%20forget%20to%20send%20us%20this%20email!%20Otherwise%20we%20won't%20be%20able%20to%20contact%20you%20back%2C%20nor%20invite%20you%20on%20Slack.%0A%0ACheers%2C%0AThe%20OpenFisca%20Team)
[![CircleCI](https://img.shields.io/circleci/project/github/openfisca/openfisca-survey-manager/master.svg?style=flat)](https://circleci.com/gh/openfisca/openfisca-survey-manager)
[![Coveralls](https://img.shields.io/coveralls/github/openfisca/openfisca-survey-manager/master.svg?style=flat)](https://coveralls.io/github/openfisca/openfisca-survey-manager?branch=master)
[![Python](https://img.shields.io/pypi/pyversions/openfisca-survey-manager.svg)](https://pypi.python.org/pypi/openfisca-survey-manager)
[![PyPi](https://img.shields.io/pypi/v/openfisca-survey-manager.svg?style=flat)](https://pypi.python.org/pypi/openfisca-survey-manager)

## [EN] Introduction

[OpenFisca](https://openfisca.org) is a versatile microsimulation free software. You can check the [online documentation](https://openfisca.org/doc/) for more details.

This repository contains the Survey-Manager module, to work with OpenFisca and survey data.

It provides two main features:
* A Python API to access data in [Hierarchical Data Format](https://en.wikipedia.org/wiki/Hierarchical_Data_Format) (HDF).
* A script that transforms SAS, Stata, SPSS, and CSV data files to HDF data files, along with some metadata so they can be used by the Python API.

> For France survey data, you might find useful information on the next steps in [openfisca-france-data](https://github.com/openfisca/openfisca-france-data) repository.

## [FR] Introduction

[OpenFisca](https://openfisca.org) est un logiciel libre de micro-simulation. Pour plus d'information, vous pouvez consulter la [documentation officielle](https://openfisca.org/doc/).

Ce dépôt contient le module Survey-Manager. Il facilite l'usage d'OpenFisca avec des données d'enquête.

Il fournit deux fonctionnalités principales:
* Une API Python permettant l'accès à des données au format [Hierarchical Data Format](https://fr.wikipedia.org/wiki/Hierarchical_Data_Format) (HDF).
* Un script qui tranforme les fichiers de données aux formats SAS, Stata, SPSS, and CSV data files en fichiers de données au format HDF, avec quelques metadonnées leur permettant d'être utilisés par l'API Python.

> Si vous disposez de données d'enquête sur la France, le dépôt [openfisca-france-data](https://github.com/openfisca/openfisca-france-data) pourrait être utile à vos prochaines étapes de traitement.

## Environment

OpenFisca-Survey-Manager runs on Python 3.7. More recent versions should work, but are not tested.

> Backward compatibility with Python 2.7 has been dropped since January 1st, 2019.

## Usage

### Installation

#### Install with PIP

If you're developing your own script or looking to run `OpenFisca-Survey-Manager` without editing it, you don't need to get its source code. It just needs to be known by your environment.
To do so, first, install the package with `pip`:

```shell
pip install --upgrade pip
pip install openfisca-survey-manager
```

This should not display any error and end with:

`Successfully installed [... openfisca-survey-manager-xx.xx.xx ...]`

It comes with `build-collection` command that we will use in the next steps.

> If you want to improve this module, please see the `Development` section below.

#### Install with Conda

Create an anvironment and install openfisca-survey-manager
```
conda create -n survey python=3.8
conda activate survey
conda install -c conda-forge -c openfisca openfisca-survey-manager
```

You are ready to go !

To exit your environment:
```
conda deactivate
```

### Getting the configuration directory path

To be able to use OpenFisca-Survey-Manager, you have to create two configuration files:
* `raw_data.ini`,
* and `config.ini`.

To know where to copy them to, use the following command:

```shell
build-collection --help
```

You should get the following result.

```shell
usage: build-collection [-h] -c COLLECTION [-d] [-m] [-p PATH] [-s SURVEY]
                        [-v]

optional arguments:
  -h, --help            show this help message and exit
  -c COLLECTION, --collection COLLECTION
                        name of collection to build or update
  -d, --replace-data    erase existing survey data HDF5 file (instead of
                        failing when HDF5 file already exists)
  -m, --replace-metadata
                        erase existing collection metadata JSON file (instead
                        of just adding new surveys)
  -p PATH, --path PATH  path to the config files directory (default =
                        /your/path/.config/openfisca-survey-manager)
  -s SURVEY, --survey SURVEY
                        name of survey to build or update (default = all)
  -v, --verbose         increase output verbosity
```

Take note of the default configuration directory path in `-p PATH, --path PATH` option's description. This is the directory where you will set your `raw_data.ini` and `config.ini` files. In this example, it is `/Users/you/.config/openfisca-survey-manager`.

> If you want to use a different path, you can pass the `--path /another/path` option to `build-collection`. This feature is still experimental though.

### Editing the config files

Configuration files are INI files (text files).

The `raw_data.ini` lists your input surveys while `config.ini` specifies the paths to SurveyManager outputs.

> `raw_data.ini` and `config.ini` must not be committed (they are already ignored by [`.gitignore`](.gitignore)).

#### raw_data.ini, for inputs configuration

To initialise your `raw_data.ini` file, you can follow these steps:

  1. Copy the template file [raw_data_template.ini](openfisca_survey_manager/config_files_templates/raw_data_template.ini) to the configuration directory path you identified in the previous step and rename it to `raw_data.ini`.
  Ex: `/your/path/.config/openfisca-survey-manager/raw_data.ini`

  2. Edit the latter by adding a section title for your survey.
  For example, if you name your survey `housing_survey`, you should get a line with:
  ```ini
  [housing_survey]
  ```

  3. Add a reference to the location of your raw data **directory** (SAS, stata DTA files, SPSS, CSV files).
  For paths in Windows, use `/` instead of `\` to separate folders.
  You do not need to put quotes, even when the path name contains spaces.

  Your file should look like this:

  ```ini
  [housing_survey]

  2014 = /path/to/your/raw/data/HOUSING_2014
  ```

You can also set multiple surveys as follows:

```ini
[revenue_survey]

2014 = /path/to/your/raw/data/REVENUE_2014
2015 = /path/to/your/raw/data/REVENUE_2015
2016 = /path/to/your/raw/data/REVENUE_2016

[housing_survey]

2014 = /path/to/your/raw/data/HOUSING_2014
```

#### config.ini, for outputs configuration

To initilalise your `config.ini` file:

  1. Copy its template file [config_template.ini](openfisca_survey_manager/config_files_templates/config_template.ini) to your configuration directory and rename it to `config.ini`.
  Ex: `/your/path/.config/openfisca-survey-manager/config.ini`.

  2. Define a `collections_directory` path where the SurveyManager will generate your survey inputs and outputs JSON description.
  Ex: `/.../openfisca-survey-manager/transformed_housing_survey`
  For a `housing_survey`, you will get a `/.../openfisca-survey-manager/transformed_housing_survey/housing_survey.json` file.

  3. Define an `output_directory` where the generated HDF file will be registered.
    This directory could be a sub-directory of your `collections_directory`.

  4. Define a `tmp_directory` that will store temporay calculation results. Its content will be deleted at the end of the calculation.
    This directory could be a sub-directory of your `collections_directory`.

Your `config.ini` file should look similar to this:

  ```ini
  [collections]

  collections_directory = /path/to/your/collections/directory

  [data]

  output_directory = /path/to/your/data/output/directory
  tmp_directory = /path/to/your/data/tmp/directory
  ```

> Make sure those directories exist, otherwise the script will fail.

### Building the HDF5 files

This step will read your configuration files and you survey data and generate a HDF5 file (`.h5`) for your survey.
To build the HDF5 files, we'll use the [`build-collection`](openfisca_survey_manager/scripts/build_collection.py) script.

Here is an example for one survey with one serie: our `housing_survey` that knows only 2014 serie. We call our survey as a collection (with `-c` option) and build the HDF5 file with this command:

```shell
build-collection -c housing_survey -d -m -v
```

`-d -m` options put you on the safe side as they remove previous outputs if they exist.

It will generate:
* A `housing_survey.json` listing a `housing_survey_2014` survey with both:
  * your input `tables` and your input file paths in an `informations` key,
  * the transformed survey path in a `hdf5_file_path` key.
* Your transformed survey in a `housing_survey_2014.h5` file.

#### build-collection, what else?

As `build-collection --help` shows, other options exist. Here are other usage examples.

If you have multiple series of one survey like the `revenue_survey`, you can run the specific `2015` serie with:

```shell
build-collection -c revenue_survey -s 2015 -d -m -v
```

Or if you want to specify a different configuration directory path:

```shell
build-collection -p /another/path -c housing_survey -s 2014 -d -m -v
```

> The `--path /another/path` option is still experimental though.

It should work. If it doesn't, please do not hesitate to [open an issue](https://github.com/openfisca/openfisca-survey-manager/issues/new).


## Development

If you want to contribute to OpenFisca-Survey-Manager, please be welcomed! To install it locally in development mode:

```shell
git clone https://github.com/openfisca/openfisca-survey-manager.git
cd openfisca-survey-manager
make install
```

## Testing

To run the entire test suite:

```sh
make test
```

To run the entire test suite with the same config as in CI:

```sh
CI=True make test
```

## Style

This repository adheres to a certain coding style, and we invite you to follow it for your contributions to be integrated promptly.

To run the style checker:

```sh
make check-style
```

To automatically style-format your code changes:

```sh
make format-style
```

To automatically style-format your code changes each time you commit:

```sh
touch .git/hooks/pre-commit
chmod +x .git/hooks/pre-commit

tee -a .git/hooks/pre-commit << END
#!/bin/sh
#
# Automatically format your code before committing.
exec make format-style
END
```


%prep
%autosetup -n OpenFisca-Survey-Manager-0.47.2

%build
%py3_build

%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
	find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
	find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
	find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
	find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
	find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .

%files -n python3-OpenFisca-Survey-Manager -f filelist.lst
%dir %{python3_sitelib}/*

%files help -f doclist.lst
%{_docdir}/*

%changelog
* Fri May 05 2023 Python_Bot <Python_Bot@openeuler.org> - 0.47.2-1
- Package Spec generated