Water meters

.gitattributes

@@ -0,0 +1,6 @@
+# Set the default behavior, in case people don't have core.autocrlf set.
+* text=auto
+
+# Explicitly declare text files you want to always be normalized on checkout.
+*.py text
+*.sh text

.gitignore

@@ -0,0 +1,6 @@
+*.pyc
+.cache/*
+__pycache__
+__pycache__/*
+*/__pycache__/*
+.ipynb_checkpoints

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "meters/dataset"]
+	path = meters/dataset
+	url = https://github.com/analysiscenter/dataset.git

README.md

@@ -1 +1,58 @@
-# meters
+# meters
+
+`Meters` is a framework for building end-to-end machine learning models for recognition of digits on any meters.
+
+Main features:
+
+* convert images to blosc format
+* load images(from blosc) and labels (from csv)
+* separate numbers (and labels respectively) from cropped area with meter's value
+* arrange new custom actions into pipeline
+* easily configure pipeline
+* build, train and test custom models for research.
+
+# About Meters
+
+Meters has two module: [``batch``](https://github.com/analysiscenter/meters/tree/master/meters/batch) and [``pipelines``](https://github.com/analysiscenter/meters/tree/master/meters/pipelines)
+
+``batch`` module contains MeterBatch class which includes actions for preprocessing.
+
+``pipelines`` module contains PipelineFactory class that builds pipelines for:
+
+  * training simple models to classify digits on meters
+  * making predictions by trained model.
+
+# Basic usage
+
+Here is an example of a pipeline that loads blosc images, makes preprocessing and trains a model for 50 epochs:
+```python
+ppl = (
+    dataset.train
+    .load(src=src, fmt='blosc', components='images')
+    .load(src='path/to/data.csv', fmt='csv', components=['coordinates', 'labels'], index_col='file_name')
+    .crop_from_bbox()
+    .split_labels()
+    .split_to_digits()
+    .init_model('dynamic', MeterModel, 'meter_model', config=model_config)
+    .train_model('meter_model', fetches='loss', make_data=concatenate_water, save_to=V('loss'), mode='a')
+    .run(batch_size=25, shuffle=True, drop_last=True, n_epochs=50)
+  )
+```
+
+# Installation
+
+With [git clone](https://git-scm.com/docs/git-clone):
+
+    git clone https://github.com/analysiscenter/meters.git
+
+If your python file is located in another directory, you might need to add a path to `meters` submodule location::
+
+    import sys
+    sys.path.insert(0, '/path/to/meters')
+    import meters
+
+# Citing Meters
+
+Please cite Meters in your publications if it helps your research:
+
+``Khudorozhkov R., Broilovskiy A., Mylzenova D., Ivanov G. Meters library for data science research of meters. 2018.``

docs/.gitignore

@@ -0,0 +1,2 @@
+*/__pycache__/*
+.ipynb_checkpoints

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = python -msphinx
+SPHINXPROJ    = Meters
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+    @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+    @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/api/meters.batch.rst

@@ -0,0 +1,22 @@
+MeterBatch
+==========
+.. autoclass:: meters.batch.MeterBatch
+    :show-inheritance:
+
+Methods
+-------
+Input methods
+^^^^^^^^^^^^^
+    .. automethod:: meters.batch.MeterBatch.load
+
+Hidden methods
+^^^^^^^^^^^^^^
+    .. automethod:: meters.batch.MeterBatch._init_component
+    .. automethod:: meters.batch.MeterBatch._reraise_exceptions
+    .. automethod:: meters.batch.MeterBatch._assemble_load
+
+Batch processing
+^^^^^^^^^^^^^^^^
+    .. automethod:: meters.batch.MeterBatch.split_to_digits
+    .. automethod:: meters.batch.MeterBatch.crop_from_bbox
+    .. automethod:: meters.batch.MeterBatch.split_labels

docs/api/meters.pipelines.rst

@@ -0,0 +1,19 @@
+PipelineFactory
+===============
+.. autoclass:: meters.pipelines.PipelineFactory
+    :show-inheritance:
+
+Methods
+-------
+Methods for creating a pipeline
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+	.. automethod:: meters.pipelines.PipelineFactory.load_all
+	.. automethod:: meters.pipelines.PipelineFactory.make_digits
+	.. automethod:: meters.pipelines.PipelineFactory.simple_train
+	.. automethod:: meters.pipelines.PipelineFactory.simple_predict
+
+Secondary methods
+^^^^^^^^^^^^^^^^^
+
+	.. automethod:: meters.pipelines.PipelineFactory._update_config
+	.. automethod:: meters.pipelines.PipelineFactory.add_lazy_run

docs/api/meters.rst

@@ -0,0 +1,9 @@
+API
+====
+
+.. toctree::
+   :maxdepth: 2
+   :titlesonly:
+
+   meters.batch
+   meters.pipelines

docs/conf.py

@@ -0,0 +1,220 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# meters documentation build configuration file, created by
+# sphinx-quickstart on Wed Jan 10 15:41:41 2018.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# 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.
+
+# 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.
+
+import os
+import sys
+sys.path.insert(0, os.path.join(".."))
+import meters
+
+# -- 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.autodoc',
+    'sphinx.ext.doctest',
+    'sphinx.ext.coverage',
+    'sphinx.ext.mathjax',
+    'sphinx.ext.viewcode',
+    'sphinx.ext.githubpages',
+    'sphinx.ext.intersphinx',
+    'sphinx.ext.napoleon'
+]
+
+napoleon_use_rtype = False
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+source_suffix = ['.rst', '.md']
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 'Meters'
+copyright = '2018, Analysis Center'
+author = 'Analysis Center'
+
+# 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.
+release = meters.__version__
+# The full version, including alpha/beta/rc tags.
+version = '.'.join(release.split('.')[:2])
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = False
+
+
+# -- 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 = 'alabaster'
+html_theme = "classic"
+# html_theme_options = {
+#     "rightsidebar": "true",
+#     "relbarbgcolor": "black"
+# }
+# 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 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']
+
+# Custom sidebar templates, must be a dictionary that maps document names
+# to template names.
+#
+# This is required for the alabaster theme
+# refs: http://alabaster.readthedocs.io/en/latest/installation.html#sidebars
+# html_sidebars = {
+#     '**': [
+#         'relations.html',  # needs 'show_related': True theme option to display
+#         'searchbox.html',
+#     ]
+# }
+
+
+autoclass_content = 'class'
+add_module_names = False
+
+intersphinx_mapping = {
+    'python': ('https://docs.python.org/3', None),
+    'numpy': ('http://docs.scipy.org/doc/numpy/', None),
+    'scipy': ('http://docs.scipy.org/doc/scipy/reference/', None),
+    'pandas': ('http://pandas-docs.github.io/pandas-docs-travis/', None),
+}
+
+viewcode_import = True
+
+# -- Options for HTMLHelp output ------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'Metersdoc'
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'meters.tex', 'meters Documentation',
+     'Analysis Center', 'manual'),
+]
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'meters', 'meters Documentation',
+     [author], 1)
+]
+
+
+# -- 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 = [
+    (master_doc, 'meters', 'meters Documentation',
+     author, 'meters', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+
+# -- Options for Epub output ----------------------------------------------
+
+# # Bibliographic Dublin Core info.
+# epub_title = project
+# epub_author = author
+# epub_publisher = author
+# epub_copyright = copyright
+
+# # The unique identifier of the text. This can be a ISBN number
+# # or the project homepage.
+# #
+# # epub_identifier = ''
+
+# # A unique identification for the text.
+# #
+# # epub_uid = ''
+
+# # A list of files that should not be packed into the epub file.
+# epub_exclude_files = ['search.html']
+
+
+
+# # Example configuration for intersphinx: refer to the Python standard library.
+# intersphinx_mapping = {'https://docs.python.org/': None}