pymrio 0.6.0__py3-none-any.whl

doc/source/conf.py

@@ -0,0 +1,275 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# pymrio documentation build configuration file, created by
+# sphinx-quickstart on Fri May 30 10:59:10 2014.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+import os
+import sys
+
+# add the pymrio path for the autodoc function
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+# Added all these to make readthedocs work
+sys.path.insert(0, os.path.abspath("."))
+sys.path.insert(0, os.path.abspath(".."))
+sys.path.insert(0, os.path.abspath("../.."))
+sys.path.insert(0, os.path.abspath("../../.."))
+
+# -- General configuration ----
+
+
+# If your documentation needs a minimal Sphinx version, state it here.
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
+extensions = [
+    "sphinx.ext.napoleon",
+    "sphinx.ext.autodoc",
+    "nbsphinx",
+    "IPython.sphinxext.ipython_console_highlighting",
+    "sphinx.ext.mathjax",
+    "sphinx.ext.coverage",
+    "sphinx.ext.autosummary",
+]
+
+nbsphinx_execute = "never"
+
+napoleon_numpy_docstring = True
+napoleon_google_docstring = False
+
+napoleon_include_init_with_doc = False
+napoleon_include_private_with_doc = True
+napoleon_use_param = True
+napoleon_use_ivar = True
+
+# automatically generate api references
+autosummary_generate = ["api_references.rst"]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# The suffix of source filenames.
+source_suffix = ".rst"
+
+# The encoding of source files.
+# source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = "index"
+
+# General information about the project.
+project = "pymrio"
+copyright = "2014, Konstantin Stadler"
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+
+import pymrio  # noqa
+
+version = pymrio.__version__
+# The full version, including alpha/beta/rc tags.
+release = pymrio.__version__
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+# language = None
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+# today = ''
+# Else, today_fmt is used as the format for a strftime call.
+# today_fmt = '%B %d, %Y'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = ["_build", "**.ipynb_checkpoints"]
+
+# The reST default role (used for this markup: `text`) to use for all
+# documents.
+# default_role = None
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+# add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+# add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+# show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = "sphinx"
+
+# A list of ignored prefixes for module index sorting.
+# modindex_common_prefix = []
+
+
+# -- Options for HTML output ------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for a
+# list of builtin themes.
+# html_theme = 'pyramid'
+html_theme = "sphinx_rtd_theme"
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+html_theme_options = {}
+
+# Add any paths that contain custom themes here, relative to this directory.
+# html_theme_path = []
+
+# The name for this set of Sphinx documents.  If None, it defaults to
+# "<project> v<release> documentation".
+# html_title = None
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+# html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+# html_logo = None
+
+# The name of an image file (within the static path) to use as favicon of the
+# docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
+# pixels large.
+# html_favicon = None
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+# html_static_path = ["_static"]
+
+# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
+# using the given strftime format.
+# html_last_updated_fmt = '%b %d, %Y'
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+# html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+# html_sidebars = {}
+
+# Additional templates that should be rendered to pages, maps page names to
+# template names.
+# html_additional_pages = {}
+
+# If false, no module index is generated.
+# html_domain_indices = True
+
+# If false, no index is generated.
+# html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+# html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+# html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+# html_show_sphinx = True
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+# html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+# html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+# html_file_suffix = None
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = "pymriodoc"
+
+
+# -- Options for LaTeX output ------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    "papersize": "a4paper",
+    # The font size ('10pt', '11pt' or '12pt').
+    "pointsize": "11pt",
+    # Additional stuff for the LaTeX preamble.
+    # 'preamble': '',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples (source start
+# file, target name, title, author, documentclass [howto/manual]).
+latex_documents = [
+    ("index", "pymrio.tex", "pymrio Documentation", "Konstantin Stadler", "manual"),
+]
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+# latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+# latex_use_parts = False
+
+# If true, show page references after internal links.
+# latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+# latex_show_urls = False
+
+# Documents to append as an appendix to all manuals.
+# latex_appendices = []
+
+# If false, no module index is generated.
+# latex_domain_indices = True
+
+
+# -- Options for manual page output --------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [("index", "pymrio", "pymrio Documentation", ["Konstantin Stadler"], 1)]
+
+# If true, show URL addresses after external links.
+# man_show_urls = False
+
+
+# -- Options for Texinfo output --------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (
+        "index",
+        "pymrio",
+        "pymrio Documentation",
+        "Konstantin Stadler",
+        "pymrio",
+        "One line description of project.",
+        "Miscellaneous",
+    ),
+]
+
+# Documents to append as an appendix to all manuals.
+# texinfo_appendices = []
+
+# If false, no module index is generated.
+# texinfo_domain_indices = True
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+# texinfo_show_urls = 'footnote'

doc/source/notebooks/adjusting.py

@@ -0,0 +1,177 @@
+# ---
+# jupyter:
+#   jupytext:
+#     formats: ipynb,py:light
+#     text_representation:
+#       extension: .py
+#       format_name: light
+#       format_version: '1.5'
+#       jupytext_version: 1.16.4
+#   kernelspec:
+#     display_name: Python 3 (ipykernel)
+#     language: python
+#     name: python3
+# ---
+
+# # Adjusting, Renaming and Restructuring
+
+# In this tutorial we will cover how to modify the structure of an MRIO system.
+# This includes renaming sectors, regions and Y categories,
+# as well as restructuring (extracting and merging) satellite accounts.
+
+
+# We use the small test MRIO system that is included in the pymrio package for all examples.
+# The method work the same for any MRIO system.
+
+import pymrio
+
+mrio = pymrio.load_test()
+
+# We can use several functions to get a quick overview over the MRIO system [(see the Exploring MRIO tutorial for more examples)](explore.ipynb).
+
+mrio.get_sectors()
+
+mrio.get_regions()
+
+mrio.get_Y_categories()
+
+# A list of available satellite accounts can be obtained by
+
+mrio.get_extensions()
+
+# this returns a generator over all extensions, to just get the names which can be used to loop over the extensions. To just get the names:
+
+list(mrio.get_extensions())
+
+# ## Renaming
+
+# ### Manual renaming
+
+# All the names returned are literally just names and can easily be renamed.
+# To rename sectors or regions just pass a dictionary with the new names:
+
+mrio.rename_regions({"reg1": "REGION A", "reg2": "REGION B"})
+
+mrio.get_regions()
+
+# Renaming sectors or Y categories works the same way
+
+mrio.rename_sectors({"mining": "dwarf business"})
+mrio.rename_Y_categories({"Final consumption expenditure by households": "fin_house"})
+
+mrio.get_sectors()
+
+mrio.get_Y_categories()
+
+# ### Renaming based on included classifications synonyms
+
+# Some MRIOs come with a selections of names which can be used for renaming.
+# These can be obtained via 'get_classification', passing the name of the IO (pass None to get a list of available classifications).
+
+mrio_class = pymrio.get_classification(mrio_name="test")
+
+# The classification data contains different names and aggregation levels for the sectors and final demand categories. The easiest way to explore the classification data is by using the autocomplete functionality. Depending on the editor your are using this might work with typing mrio_class.sectors. pressing Tab or Ctrl-Space. The same works for mrio_class.finaldemand.
+
+# Alternatively it is possible to just print the underlying dataframes with (similar for finaldemand)
+
+mrio_class.sectors
+
+# This can be used to generate dictionaries for renaming the sectors of the MRIO, eg with:
+
+conv_dict = mrio_class.get_sector_dict(
+    mrio_class.sectors.TestMrioName, mrio_class.sectors.TestMrioCode
+)
+conv_dict
+
+# This can then be used for renaming the sectors:
+
+mrio = pymrio.load_test()
+
+mrio.rename_sectors(conv_dict)
+mrio.get_sectors()
+
+
+# In the mrio_class.sectors you will also find an entry 'Type' which
+# represents a many to one mapping.
+# This can be used for aggregating the
+# MRIO and is explained [in the aggregation tutorial](aggregation_examples.ipynb#Aggregation-by-renaming).
+
+# # Extracting satellite accounts
+
+# Each extension/satellite account of the MRIO contains a method 'extract'.
+# This takes an index and extracts the corresponding satellite account entries.
+# The index can either be obtained manually, or one can use the contains/match/fullmatch methods of the extension to get the index.
+
+# Below we extract all extensions rows from the emission satallite account which contain the word 'air'.
+
+air_emission_index = mrio.emissions.contains("air")
+air_accounts_dict = mrio.emissions.extract(index=air_emission_index)
+
+# The result is a dictionary with the extracted satellite accounts. The keys are the names of the satellite accounts and the values are the extracted satellite accounts.
+
+air_accounts_dict.keys()
+
+# Alternatively, one can automatically convert the extracted satellite accounts to a new MRIO extension.
+
+air_accounts_extension = mrio.emissions.extract(
+    index=air_emission_index, return_type="extension"
+)
+print(air_accounts_extension)
+
+# The extract method can also be applied over all extensions.
+# This work well in combinaton with the contains/match/fullmatch methods of the extension.
+
+# Satellite accounts can be extracted from the MRIO system
+# by using the extension_extract method.
+# This method takes the name of the satellite account as first argument
+# and a list of regions as second argument.
+# The regions can be given as a list of region names or as a list of region indices.
+# The method returns a new MRIO system with the extracted satellite account.
+
+# In the somehow derived example below we extract entries accross
+# all accounts that contain the word 'Added' or the letter 2.
+
+cross_accounts_index = mrio.extension_contains("Added|2")
+
+# We can also extract all data from the satellite accounts with these indexes.
+
+cross_accounts_dict = mrio.extension_extract(cross_accounts_index)
+
+# This returns a dictionary of dictionaries with the extracted satellite accounts.
+
+cross_accounts_dict.keys()
+
+cross_accounts_dict["Emissions"].keys()
+
+# Again, we can also build a new MRIO extension from the extracted satellite accounts.
+
+# This can be either one per extension (by passing return_type="extension")
+
+cross_accounts_extension = mrio.extension_extract(
+    cross_accounts_index, return_type="extension"
+)
+
+# Or by passing any other string to return_type, which will be used as the new name of the extension.
+
+cross_accounts_all_new = mrio.extension_extract(
+    cross_accounts_index, return_type="new_name"
+)
+
+print(cross_accounts_all_new)
+
+# Index values levels and names of the new extension are based on the combination
+# of the original extensions index levels.
+# These are filled for nan for entries which did not have them before.
+
+cross_accounts_all_new.get_rows()
+
+# Both extract methods, extension_extract and extract, can also be used to extract only
+# a subset of the available dataframe accounts. This can be done by passing a list of
+# dataframe names to the dataframes parameter.
+
+only_fys = mrio.extension_extract(
+    cross_accounts_index, dataframes=["F_Y"], include_empty=True
+)
+
+only_fys.keys()
+only_fys["Emissions"].keys()

doc/source/notebooks/advanced_group_stressors.py

@@ -0,0 +1,139 @@
+# ---
+# jupyter:
+#   jupytext:
+#     text_representation:
+#       extension: .py
+#       format_name: percent
+#       format_version: '1.3'
+#       jupytext_version: 1.16.4
+#   kernelspec:
+#     display_name: Python 3 (ipykernel)
+#     language: python
+#     name: python3
+# ---
+
+# %% [markdown]
+# # Advanced functionality - pandas groupby with pymrio satellite accounts
+
+# %% [markdown]
+# This notebook examplifies how to directly apply [Pandas](https://pandas.pydata.org/) core functions (in this case [groupby and aggregation](https://pandas.pydata.org/pandas-docs/stable/groupby.html)) to the pymrio system.
+
+# %% [markdown]
+# ## WIOD material extension aggregation - stressor w/o compartment info
+
+# %% [markdown]
+# Here we use the WIOD MRIO system (see the notebook ["Automatic downloading of MRIO databases"](autodownload.ipynb#WIOD-download) for how to automatically retrieve this database) and will aggregate the WIOD material stressor for used and unused materials.  We assume, that the WIOD system is available at
+
+# %%
+wiod_folder = "/tmp/mrios/WIOD2013"
+
+# %% [markdown]
+# To get started we import pymrio
+
+# %%
+import pymrio
+
+# %% [markdown]
+# For the example here, we use the data from 2009:
+
+# %%
+wiod09 = pymrio.parse_wiod(path=wiod_folder, year=2009)
+
+# %% [markdown]
+# WIOD includes multiple material accounts, specified for the "Used" and "Unused" category, as well as information on the total. We will use the latter to confirm our calculations:
+
+# %%
+wiod09.mat.F
+
+# %% [markdown]
+# To aggregate these with the Pandas groupby function, we need to specify the groups which should be grouped by Pandas.
+# Pymrio contains a helper function which builds such a matching dictionary.
+# The matching can also include regular expressions to simplify the build:
+
+# %%
+groups = wiod09.mat.get_index(
+    as_dict=True,
+    grouping_pattern={".*_Used": "Material Used", ".*_Unused": "Material Unused"},
+)
+groups
+
+# %% [markdown]
+# Note, that the grouping contains the rows which do not match any of the specified groups.
+# This allows to easily aggregates only parts of a specific stressor set. To actually omit these groups
+# include them in the matching pattern and provide None as value.
+#
+# To have the aggregated data alongside the original data, we first copy the detailed satellite account:
+
+# %%
+wiod09.mat_agg = wiod09.mat.copy(new_name="Aggregated matrial accounts")
+
+# %% [markdown]
+# Then, we use the pymrio get_DataFrame iterator together with the pandas groupby and sum functions to aggregate the stressors.
+# For the dataframe containing the unit information, we pass a custom function which concatenate non-unique unit strings.
+
+# %%
+for df_name, df in zip(
+    wiod09.mat_agg.get_DataFrame(data=False, with_unit=True, with_population=False),
+    wiod09.mat_agg.get_DataFrame(data=True, with_unit=True, with_population=False),
+):
+    if df_name == "unit":
+        wiod09.mat_agg.__dict__[df_name] = df.groupby(groups).apply(
+            lambda x: " & ".join(x.unit.unique())
+        )
+    else:
+        wiod09.mat_agg.__dict__[df_name] = df.groupby(groups).sum()
+
+# %%
+wiod09.mat_agg.F
+
+# %%
+wiod09.mat_agg.unit
+
+# %% [markdown]
+# ## Use with stressors including compartment information:
+
+# %% [markdown]
+# The same regular expression grouping can be used to aggregate stressor data which is given per compartment.
+# To do so, the matching dict needs to consist of tuples corresponding to a valid index value in the DataFrames.
+# Each position in the tuple is interprested as a regular expression.
+# Using the get_index method gives a good indication how a valid grouping dict should look like:
+
+# %%
+tt = pymrio.load_test()
+tt.emissions.get_index(as_dict=True)
+
+# %% [markdown]
+# With that information, we can now build our own grouping dict, e.g.:
+
+# %%
+agg_groups = {("emis.*", ".*"): "all emissions"}
+
+# %%
+group_dict = tt.emissions.get_index(as_dict=True, grouping_pattern=agg_groups)
+group_dict
+
+# %% [markdown]
+# Which can then be used to aggregate the satellite account:
+
+# %%
+for df_name, df in zip(
+    tt.emissions.get_DataFrame(data=False, with_unit=True, with_population=False),
+    tt.emissions.get_DataFrame(data=True, with_unit=True, with_population=False),
+):
+    if df_name == "unit":
+        tt.emissions.__dict__[df_name] = df.groupby(group_dict).apply(
+            lambda x: " & ".join(x.unit.unique())
+        )
+    else:
+        tt.emissions.__dict__[df_name] = df.groupby(group_dict).sum()
+
+# %% [markdown]
+# In this case we loose the information on the compartment. To reset the index do:
+
+# %%
+import pandas as pd
+
+tt.emissions.set_index(pd.Index(tt.emissions.get_index(), name="stressor"))
+
+# %%
+tt.emissions.F