.flake8

+[flake8]
+ignore = E203, E266, E501, W503, F403, F401
+max-line-length = 79
+select = B,C,E,F,W,T4,B9
+exclude =
+    # No need to traverse our git directory
+    .git,
+    # There's no value in checking cache directories
+    __pycache__,
+    # Ignore virtual environment contents
+    .venv
+    # The conf file is mostly autogenerated, ignore it
+    docs/source/conf.py,
+    # The old directory contains Flake8 2.0
+    old,
+    # This contains our built documentation
+    build,
+    # This contains builds of flake8 that we don't want to check
+    dist,
+    # Any data produced inside the folder during development
+    data/,
+    # Temporarily ignore tests
+    tests/
+max-complexity = 18

.gitignore

@@ -110,7 +110,6 @@ venv.bak/
 omero_py/omeroweb/
 omero_py/pipeline/
 **.ipynb
-data/
 notebooks/
 *.pdf
 *.h5

.gitlab-ci.yml

-image: python:3.7
+image: python:3.8
 
 cache:
     key: "project-${CI_JOB_NAME}"
@@ -12,9 +12,9 @@ variables:
   TRIGGER_PYPI_NAME: ""
 
 stages:
-  - test
-  - check
-  - release
+  - tests
+  - checks
+  # - release
 
 before_script:
   - test -e $HOME/.poetry/bin/ || curl -sSL https://install.python-poetry.org | python3 -
@@ -22,48 +22,68 @@ before_script:
   - poetry --version
   - poetry config virtualenvs.in-project true
   - pip install --upgrade pip
-  - git remote rm origin && git remote add origin https://${ACCESS_TOKEN_NAME}:${ACCESS_TOKEN}@${CI_SERVER_HOST}/${CI_PROJECT_PATH}.git
-  - git config pull.rebase false
-  - git pull origin HEAD:master
-  - rm -rf ~/.cache/pypoetry
-  - if [ ${var+TRIGGER_PYPI_NAME} ]; then echo "Pipeline triggered by ${TRIGGER_PYPI_NAME}"; poetry add ${TRIGGER_PYPI_NAME}@latest; fi
-  - poetry install -vv
+  # - git remote rm origin && git remote add origin https://${ACCESS_TOKEN_NAME}:${ACCESS_TOKEN}@${CI_SERVER_HOST}/${CI_PROJECT_PATH}.git
+  # - git config pull.rebase false
+  # - git pull origin HEAD:master
+  # - rm -rf ~/.cache/pypoetry
+  # - if [ ${var+TRIGGER_PYPI_NAME} ]; then echo "Pipeline triggered by ${TRIGGER_PYPI_NAME}"; poetry add ${TRIGGER_PYPI_NAME}@latest; fi
+  # - export WITHOUT="docs,network";
+  - export ARGS="--with test,dev";
+  - if [[ "$CI_STAGE_NAME" == "tests" ]]; then echo "Installing system dependencies for ${CI_STAGE_NAME}"; apt update && apt install -y ffmpeg libsm6 libxext6; fi
+  - if [[ "$CI_JOB_NAME" == "Static Type" ]]; then echo "Activating development group"; export ARGS="${ARGS},dev"; fi
+  - if [[ "$CI_JOB_NAME" == "Network Tools Tests" ]]; then echo "Setting flag to compile zeroc-ice"; export ARGS="${ARGS} --all-extras"; fi
+  - poetry install -vv $ARGS
 
-Unit test:
-  stage: test
+Local Tests:
+  stage: tests
   script:
-    - apt update && apt install ffmpeg libsm6 libxext6  -y
-    - poetry run pytest ./tests/
+    # - poetry install -vv
+    - poetry run coverage run -m --branch pytest ./tests --ignore ./tests/aliby/network --ignore ./tests/aliby/pipeline
+    - poetry run coverage report -m
+    - poetry run coverage xml
+  coverage: '/(?i)total.*? (100(?:\.0+)?\%|[1-9]?\d(?:\.\d+)?\%)$/'
+  artifacts:
+    reports:
+      coverage_report:
+        coverage_format: cobertura
+        path: coverage.xml
 
-Python Code Lint:
-  stage: check
+Network Tools Tests:
+  stage: tests
   script:
-    - poetry run black .
+    - poetry run pytest ./tests/aliby/network
+    - DIRNAME="test_datasets"
+    - curl https://zenodo.org/record/7513194/files/test_datasets.tar.gz\?download\=1 -o "test_datasets.tar.gz"
+    - mkdir -p $DIRNAME
+    - tar xvf test_datasets.tar.gz -C $DIRNAME
+    - poetry run pytest -s tests/aliby/pipeline --file $DIRNAME/560_2022_11_30_pypipeline_unit_test_reconstituted_00
 
 Static Type:
-  stage: check
+  stage: checks
   allow_failure: true
   script:
+    - poetry run black .
+    - poetry run isort .
     - poetry run mypy . --exclude 'setup\.py$'
     # We can remove the flag once this is resolved https://github.com/pypa/setuptools/issues/2345
 
-Bump_release:
-  stage: release
-  script:
-    - git config --global user.email ${GITLAB_USER_EMAIL}
-    - git config --global user.name ${GITLAB_USER_NAME}
-    - git pull origin HEAD:MASTER && poetry version ${BUMP_RULE} && git add poetry.lock add pyproject.toml poetry.lock && git commit -m "Bump version" && git push -o ci.skip origin HEAD:master && poetry publish --build --username ${PYPI_USER} --password ${PYPI_PASSWORD}
-
-    - echo "TRIGGER_PYPI_NAME=$(cat pyproject.toml | grep '^name =' | head -n 1 | cut -f3 -d' ' | tr -d \")" >> build.env
-    - echo "Exporting TRIGGER_PYPI_NAME as ${TRIGGER_PYPI_NAME}"
-  only:
-    - master
-  except:
-    changes:
-      - tests/
-      - .*
+# TODO add more tests before activating auto-release
+# Bump_release:
+#   stage: release
+#   script:
+#     - git config --global user.email ${GITLAB_USER_EMAIL}
+#     - git config --global user.name ${GITLAB_USER_NAME}
+#     # - git pull origin HEAD:MASTER && poetry version ${BUMP_RULE} && git add poetry.lock add pyproject.toml poetry.lock && git commit -m "Bump version" && git push -o ci.skip origin HEAD:master && poetry publish --build --username ${PYPI_USER} --password ${PYPI_PASSWORD}
+#     - echo "TRIGGER_PYPI_NAME=$(cat pyproject.toml | grep '^name =' | head -n 1 | cut -f3 -d' ' | tr -d \")" >> build.env
+#     - echo "Exporting TRIGGER_PYPI_NAME as ${TRIGGER_PYPI_NAME}"
+#   only:
+#     - master
+#   except:
+#     changes:
+#       - tests/
+#       - .*
 
-  needs:
-    job: Unit test
+#   needs:
+#     job: Unit test
 
 ## Custom stages ##

.gitlab/issue_templates/bug.md

 ## Summary
 
-(Summarize the bug encountered concisely)
+{Summarize the bug encountered concisely}
+
+I confirm that I have (if relevant):
+- [ ] Read the troubleshooting guide: https://gitlab.com/aliby/aliby/-/wikis/Troubleshooting-(basic)
+- [ ] Updated aliby and aliby-baby.
+- [ ] Tried the unit test.
+- [ ] Tried a scaled-down version of my experiment (distributed=0, filter=0, tps=10)
+- [ ] Tried re-postprocessing.
 
 ## Steps to reproduce
 
-(How one can reproduce the issue - this is very important)
+{How one can reproduce the issue - this is very important}
+
+- aliby version: 0.1.{...}, or if development/unreleased version, commit SHA: {...}
+- platform(s):
+    - [ ] Jura
+    - [ ] Other Linux, please specify distribution and version: {...}
+    - [ ] MacOS, please specify version: {...}
+    - [ ] Windows, please specify version: {...}
+- experiment ID: {...}
+   - Any special things you need to know about this experiment: {...}
 
 ## What is the current bug behavior?
 
@@ -19,7 +35,12 @@
 (Paste any relevant logs - please use code blocks (```) to format console output, logs, and code, as
 it's very hard to read otherwise.)
 
+```
+{PASTE YOUR ERROR MESSAGE HERE!!}
+
+
+```
+
 ## Possible fixes
 
 (If you can, link to the line of code that might be responsible for the problem)
-

.pre-commit-config.yaml

+exclude: '^examples/'
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      # - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+        args: [--markdown-linebreak-ext=md]
+      - id: check-added-large-files
+      - id: check-docstring-first
+      - id: name-tests-test
+        args: [--pytest-test-first]
+  - repo: https://github.com/psf/black
+    rev: 22.6.0
+    hooks:
+      - id: black
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.10.1
+    hooks:
+      - id: isort
+  - repo: https://github.com/PyCQA/flake8
+    rev: 4.0.1
+    hooks:
+      - id: flake8
+        exclude: ^tests/ # Temporarily exclude tests

.readthedocs.yaml

+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-20.04
+  tools:
+    python: "3.8"
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+   configuration: docs/source/conf.py
+
+# If using Sphinx, optionally build your docs in additional formats such as PDF
+# formats:
+#    - pdf
+
+# Optionally declare the Python requirements required to build your docs
+python:
+   install:
+   - requirements: docs/requirements.txt

CONTRIBUTING.md

+# Contributing
+
+We focus our work on python 3.8 due to the current neural network being developed on tensorflow 1. In the near future we will migrate the network to pytorch to support more recent versions of all packages.
+
+## Issues
+All issues are managed within the gitlab [ repository ](https://gitlab.com/aliby/aliby/-/issues), if you don't have an account on the University of Edinburgh's gitlab instance and would like to submit issues please get in touch with [Prof. Peter Swain](mailto:peter.swain@ed.ac.uk ).
+
+## Data aggregation
+
+ALIBY has been tested by a few research groups, but we welcome new data sources for the models and pipeline to be as general as possible. Please get in touch with [ us ](mailto:peter.swain@ed.ac.uk ) if you are interested in testing it on your data.

INSTALL.md

-# Installation 
-
-Tested on: Mac OSX Mojave
-
-## Requirements
-We strongly recommend installing within a python environment as there are many dependencies that you may not want polluting your regular python environment. 
-Make sure you are using python 3.
-
-An environment can be created with using the conda package manager:
-
-    $ conda create --name <env>
-    $ conda activate <env>
-
-Which you can deactivate with: 
-
-    $ conda deactivate
-
-Or using virtualenv: 
-
-    $ python -m virtualenv /path/to/venv/
-    $ source /path/to/venv/bin/activate
-    
-This will download all of your packages under `/path/to/venv` and then activate it. 
-Deactivate using 
-
-    $ deactivate
-
-You will also need to make sure you have a recent version of pip.
-In your local environment, run: 
-
-    $ pip install --upgrade pip
-
-## Pipeline installation
-
-Once you have created your local environment, run:
-
-    $ cd pipeline-core
-    $ pip install -e ./
-
-You will be asked to put in your GitLab credentials for a couple of the packages installed as dependencies.
-The `-e` option will install in 'editable' mode: all of the changes that are made to the code in the repository will immediately be reflected in the installation. 
-This is very useful to keep up with any changes and branching that we make. 
-That way, if you want to keep up with the most recent updates, just run: 
-
-    $ git pull
-
-If you would rather be more in charge of which updates you install and which you don't, remove `-e` from your installation command. 
-In this case (or if you run into a dependency error) in order to update your installed version you will have to run: 
-
-    $ cd pipeline-core
-    $ git pull
-    $ pip install ./
-

LICENSE

+                    GNU AFFERO GENERAL PUBLIC LICENSE
+                       Version 3, 19 November 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU Affero General Public License is a free, copyleft license for
+software and other kinds of works, specifically designed to ensure
+cooperation with the community in the case of network server software.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+our General Public Licenses are intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  Developers that use our General Public Licenses protect your rights
+with two steps: (1) assert copyright on the software, and (2) offer
+you this License which gives you legal permission to copy, distribute
+and/or modify the software.
+
+  A secondary benefit of defending all users' freedom is that
+improvements made in alternate versions of the program, if they
+receive widespread use, become available for other developers to
+incorporate.  Many developers of free software are heartened and
+encouraged by the resulting cooperation.  However, in the case of
+software used on network servers, this result may fail to come about.
+The GNU General Public License permits making a modified version and
+letting the public access it on a server without ever releasing its
+source code to the public.
+
+  The GNU Affero General Public License is designed specifically to
+ensure that, in such cases, the modified source code becomes available
+to the community.  It requires the operator of a network server to
+provide the source code of the modified version running there to the
+users of that server.  Therefore, public use of a modified version, on
+a publicly accessible server, gives the public access to the source
+code of the modified version.
+
+  An older license, called the Affero General Public License and
+published by Affero, was designed to accomplish similar goals.  This is
+a different license, not a version of the Affero GPL, but Affero has
+released a new version of the Affero GPL which permits relicensing under
+this license.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU Affero General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Remote Network Interaction; Use with the GNU General Public License.
+
+  Notwithstanding any other provision of this License, if you modify the
+Program, your modified version must prominently offer all users
+interacting with it remotely through a computer network (if your version
+supports such interaction) an opportunity to receive the Corresponding
+Source of your version by providing access to the Corresponding Source
+from a network server at no charge, through some standard or customary
+means of facilitating copying of software.  This Corresponding Source
+shall include the Corresponding Source for any work covered by version 3
+of the GNU General Public License that is incorporated pursuant to the
+following paragraph.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the work with which it is combined will remain governed by version
+3 of the GNU General Public License.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU Affero General Public License from time to time.  Such new versions
+will be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU Affero General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU Affero General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU Affero General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If your software can interact with users remotely through a computer
+network, you should also make sure that it provides a way for users to
+get its source.  For example, if your program is a web application, its
+interface could display a "Source" link that leads users to an archive
+of the code.  There are many ways you could offer source, and different
+solutions will be better for different programs; see section 13 for the
+specific requirements.
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU AGPL, see
+<http://www.gnu.org/licenses/>.

README.md

-# Pipeline core
+# ALIBY (Analyser of Live-cell Imaging for Budding Yeast)
 
-The core classes and methods for the python microfluidics, microscopy, and 
-analysis pipeline.
-
-### Installation
-See [INSTALL.md](./INSTALL.md) for installation instructions.
+[![docs](https://readthedocs.org/projects/aliby/badge/?version=master)](https://aliby.readthedocs.io/en/latest)
+[![PyPI version](https://badge.fury.io/py/aliby.svg)](https://badge.fury.io/py/aliby)
+[![pipeline](https://gitlab.com/aliby/aliby/badges/master/pipeline.svg?key_text=master)](https://gitlab.com/aliby/aliby/-/pipelines)
+[![dev pipeline](https://gitlab.com/aliby/aliby/badges/dev/pipeline.svg?key_text=dev)](https://gitlab.com/aliby/aliby/-/commits/dev)
+[![coverage](https://gitlab.com/aliby/aliby/badges/dev/coverage.svg)](https://gitlab.com/aliby/aliby/-/commits/dev)
 
+End-to-end processing of cell microscopy time-lapses. ALIBY automates segmentation, tracking, lineage predictions, post-processing and report production. It leverages the existing Python ecosystem and open-source scientific software available to produce seamless and standardised pipelines.
 
 ## Quickstart Documentation
-### Setting up a server
-For testing and development, the easiest way to set up an OMERO server is by
-using Docker images. 
-[The software carpentry](https://software-carpentry.org/) and the [Open
- Microscopy Environment](https://www.openmicroscopy.org), have provided
-[instructions](https://ome.github.io/training-docker/) to do this.
-
-The `docker-compose.yml` file can be used to create an OMERO server with an
-accompanying PostgreSQL database, and an OMERO web server.
-It is described in detail 
-[here](https://ome.github.io/training-docker/12-dockercompose/).
-
-Our version of the `docker-compose.yml` has been adapted from the above to
-use version 5.6 of OMERO.
-
-To start these containers (in background):
-```shell script
-cd pipeline-core
-docker-compose up -d
-```
-Omit the `-d` to run in foreground.
+Installation of [VS Studio](https://visualstudio.microsoft.com/downloads/#microsoft-visual-c-redistributable-for-visual-studio-2022) Native MacOS support for is under work, but you can use containers (e.g., Docker, Podman) in the meantime.
 
-To stop them, in the same directory, run:
-```shell script
-docker-compose stop
-```
+To analyse local data
+ ```bash
+pip install aliby 
+ ```
+ Add any of the optional flags `omero` and `utils` (e.g., `pip install aliby[omero, utils]`). `omero` provides tools to connect with an OMERO server and `utils` provides visualisation, user interface and additional deep learning tools.
+  
+See our [installation instructions]( https://aliby.readthedocs.io/en/latest/INSTALL.html ) for more details.
+
+### CLI
+
+If installed via poetry, you have access to a Command Line Interface (CLI)
+
+ ```bash
+aliby-run --expt_id EXPT_PATH --distributed 4 --tps None
+ ```
+
+And to run Omero servers, the basic arguments are shown:
+ ```bash
+ aliby-run --expt_id XXX --host SERVER.ADDRESS --user USER --password PASSWORD 
+ ```
+
+The output is a folder with the original logfiles and a set of hdf5 files, one with the results of each multidimensional inside.
+
+For more information, including available options, see the page on [running the analysis pipeline](https://aliby.readthedocs.io/en/latest/PIPELINE.html)
 
-### Raw data access
+## Using specific components
 
+### Access raw data
+
+ALIBY's tooling can also be used as an interface to OMERO servers, for example, to fetch a brightfield channel.
  ```python
 from aliby.io.omero import Dataset, Image
 
@@ -56,129 +60,53 @@ with Image(list(image_ids.values())[0], **server_info) as image:
     imgs = dimg[tps, image.metadata["channels"].index("Brightfield"), 2, ...].compute()
     # tps timepoints, Brightfield channel, z=2, all x,y
 ```
- 
+
 ### Tiling the raw data
 
-A `Tiler` object performs trap registration. It is built in different ways, the easiest one is using an image and a the default parameters set.
+A `Tiler` object performs trap registration. It may be built in different ways but the simplest one is using an image and a the default parameters set.
 
 ```python
 from aliby.tile.tiler import Tiler, TilerParameters
 with Image(list(image_ids.values())[0], **server_info) as image:
     tiler = Tiler.from_image(image, TilerParameters.default())
+    tiler.run_tp(0)
 ```
 
 The initialisation should take a few seconds, as it needs to align the images
-in time. 
+in time.
 
 It fetches the metadata from the Image object, and uses the TilerParameters values (all Processes in aliby depend on an associated Parameters class, which is in essence a dictionary turned into a class.)
 
-#### Get a timelapse for a given trap
-TODO: Update this
+#### Get a timelapse for a given tile (remote connection)
 ```python
-channels = [0] #Get only the first channel, this is also the default
-z = [0, 1, 2, 3, 4] #Get all z-positions
-trap_id = 0
-tile_size = 117
-
-# Get a timelapse of the trap
-# The default trap size is 96 by 96
-# The trap is in the center of the image, except for edge cases
-# The output has shape (C, T, X, Y, Z), so in this example: (1, T, 96, 96, 5)
-timelapse = seg_expt.get_trap_timelapse(trap_id, tile_size=tile_size, 
-                                        channels=channels, z=z)
-```
+fpath = "h5/location"
 
-This can take several seconds at the moment.
-For a speed-up: take fewer z-positions if you can.
+tile_id = 9
+trange = range(0, 10)
+ncols = 8
 
-If you're not sure what indices to use:
-```python
-seg_expt.channels # Get a list of channels
-channel = 'Brightfield'
-ch_id = seg_expt.get_channel_index(channel)
+riv = remoteImageViewer(fpath)
+trap_tps = [riv.tiler.get_tiles_timepoint(tile_id, t) for t in trange] 
 
-n_traps = seg_expt.n_traps # Get the number of traps 
-```
-
-#### Get the traps for a given time point
-Alternatively, if you want to get all the traps at a given timepoint:
+# You can also access labelled traps
+m_ts = riv.get_labelled_trap(tile_id=0, tps=[0])
 
-```python
-timepoint = 0
-seg_expt.get_traps_timepoints(timepoint, tile_size=96, channels=None, 
-                                z=[0,1,2,3,4])
-```
-
-## Reading MATLAB files
-*Disclaimer: this is very much still in development so it may not always
- work for you case. If you run into any problems please let me know, or even
- better start an Issue on the project describing your problem.*
-
-At the moment the best/only way to read matlab files is through a `matObject`:
-
-```python
-from aliby.io.matlab import matObject
-cTimelapse = matObject('/path/to/cTimelapse.mat')
-```
-
-You can see an overview of what's in the object:
-```python
-cTimelapse.describe()
+# And plot them directly
+riv.plot_labelled_trap(trap_id=0, channels=[0, 1, 2, 3], trange=range(10))
 ```
 
-The `matObject` has some dictionary-like features although it is *not* a
-dictionary (yet). You can access different parts of the object using keys
-, though, and can use the `keys()` function to do so. This will usually
-work at the first few levels, but if it doesn't you may have run into an
-object that's actually a list or a numpy array.
-
-```python
-cTimelapse.keys()
-```
+Depending on the network speed can take several seconds at the moment.
+For a speed-up: take fewer z-positions if you can.
 
-This should return an iterable of the upper level keys. For example, a
-timelapse object will usually have a `timelapseTrapsOmero` key which you
-can look deeper into in the same manner. Once you've found what you want
-you can usually access it as you would a nested dictionary, for instance:  
+#### Get the tiles for a given time point
+Alternatively, if you want to get all the traps at a given timepoint:
 
 ```python
-cTimelapse['timelapseTrapsOmero']['cTimepoint']['trapLocations']
-```
-
-For more information about using MATLAB files in python objects, please see
- [this page](docs/matlab.md).
-
-## Development guidelines
-In order to separate the python2, python3, and "currently working" versions 
-(\#socialdistancing) of the pipeline, please use the branches:
-* python2.7: for any development on the 2 version
-* python3.6-dev: for any added features for the python3 version
-* master: very sparingly and only for changes that need to be made in both
- versions as I will be merging changes from master into the development
- branches frequently
-    * Ideally for adding features into any branch, espeically master, create
-     a new branch first, then create a pull request (from within Gitlab) before 
-     merging it back so we can check each others' code. This is just to make
-     sure that we can always use the code that is in the master branch without
-     any issues.
- 
-Branching cheat-sheet:
-```git
-git branch my_branch # Create a new branch called branch_name from master
-git branch my_branch another_branch #Branch from another_branch, not master
-git checkout -b my_branch # Create my_branch and switch to it
-
-# Merge changes from master into your branch
-git pull #get any remote changes in master
-git checkout my_branch
-git merge master
-
-# Merge changes from your branch into another branch
-git checkout another_branch
-git merge my_branch #check the doc for --no-ff option, you might want to use it
+timepoint = (4,6)
+tiler.get_tiles_timepoint(timepoint, channels=None,
+                                z=[0,1,2,3,4])
 ```
 
-## TODO
-### Tests
-* test full pipeline with OMERO experiment (no download.)
 
+### Contributing
+See [CONTRIBUTING](https://aliby.readthedocs.io/en/latest/INSTALL.html) on how to help out or get involved.

aliby/experiment.py

-"""Core classes for the pipeline"""
-import atexit
-import itertools
-import os
-import abc
-import glob
-import json
-import warnings
-from getpass import getpass
-from pathlib import Path
-import re
-import logging
-from typing import Union
-
-import h5py
-from tqdm import tqdm
-import pandas as pd
-
-import omero
-from omero.gateway import BlitzGateway
-from logfile_parser import Parser
-
-from agora.io.utils import accumulate
-from aliby.timelapse import TimelapseOMERO, TimelapseLocal
-
-from agora.io.metadata_parser import parse_logfiles
-from agora.io.writer import Writer
-
-logger = logging.getLogger(__name__)
-
-########################### Dask objects ###################################
-##################### ENVIRONMENT INITIALISATION ################
-import omero
-from omero.gateway import BlitzGateway, PixelsWrapper
-from omero.model import enums as omero_enums
-import numpy as np
-
-# Set up the pixels so that we can reuse them across sessions (?)
-PIXEL_TYPES = {
-    omero_enums.PixelsTypeint8: np.int8,
-    omero_enums.PixelsTypeuint8: np.uint8,
-    omero_enums.PixelsTypeint16: np.int16,
-    omero_enums.PixelsTypeuint16: np.uint16,
-    omero_enums.PixelsTypeint32: np.int32,
-    omero_enums.PixelsTypeuint32: np.uint32,
-    omero_enums.PixelsTypefloat: np.float32,
-    omero_enums.PixelsTypedouble: np.float64,
-}
-
-
-class NonCachedPixelsWrapper(PixelsWrapper):
-    """Extend gateway.PixelWrapper to override _prepareRawPixelsStore."""
-
-    def _prepareRawPixelsStore(self):
-        """
-        Creates RawPixelsStore and sets the id etc
-        This overrides the superclass behaviour to make sure that
-        we don't re-use RawPixelStore in multiple processes since
-        the Store may be closed in 1 process while still needed elsewhere.
-        This is needed when napari requests may planes simultaneously,
-        e.g. when switching to 3D view.
-        """
-        ps = self._conn.c.sf.createRawPixelsStore()
-        ps.setPixelsId(self._obj.id.val, True, self._conn.SERVICE_OPTS)
-        return ps
-
-
-omero.gateway.PixelsWrapper = NonCachedPixelsWrapper
-# Update the BlitzGateway to use our NonCachedPixelsWrapper
-omero.gateway.refreshWrappers()
-
-
-######################  DATA ACCESS ###################
-import dask.array as da
-from dask import delayed
-
-
-def get_data_lazy(image) -> da.Array:
-    """Get 5D dask array, with delayed reading from OMERO image."""
-    nt, nc, nz, ny, nx = [getattr(image, f"getSize{x}")() for x in "TCZYX"]
-    pixels = image.getPrimaryPixels()
-    dtype = PIXEL_TYPES.get(pixels.getPixelsType().value, None)
-    get_plane = delayed(lambda idx: pixels.getPlane(*idx))
-
-    def get_lazy_plane(zct):
-        return da.from_delayed(get_plane(zct), shape=(ny, nx), dtype=dtype)
-
-    # 5D stack: TCZXY
-    t_stacks = []
-    for t in range(nt):
-        c_stacks = []
-        for c in range(nc):
-            z_stack = []
-            for z in range(nz):
-                z_stack.append(get_lazy_plane((z, c, t)))
-            c_stacks.append(da.stack(z_stack))
-        t_stacks.append(da.stack(c_stacks))
-    return da.stack(t_stacks)
-
-
-class MetaData:
-    """Small metadata Process that loads log."""
-
-    def __init__(self, log_dir, store):
-        self.log_dir = log_dir
-        self.store = store
-        self.metadata_writer = Writer(self.store)
-
-    def load_logs(self):
-        parsed_flattened = parse_logfiles(self.log_dir)
-        return parsed_flattened
-
-    def run(self):
-        metadata_dict = self.load_logs()
-        self.metadata_writer.write(path="/", meta=metadata_dict, overwrite=False)
-
-    def add_field(self, field_name, field_value):
-        self.metadata_writer.write(
-            path="/", meta={field_name: field_value}, overwrite=False
-        )
-
-    def add_fields(self, fields_values: dict):
-        for field, value in fields_values.items():
-            self.add_field(field, value)
-
-
-########################### Old Objects ####################################
-
-
-class Experiment(abc.ABC):
-    """
-    Abstract base class for experiments.
-    Gives all the functions that need to be implemented in both the local
-    version and the Omero version of the Experiment class.
-
-    As this is an abstract class, experiments can not be directly instantiated
-    through the usual `__init__` function, but must be instantiated from a
-    source.
-    >>> expt = Experiment.from_source(root_directory)
-    Data from the current timelapse can be obtained from the experiment using
-    colon and comma separated slicing.
-    The order of data is C, T, X, Y, Z
-    C, T and Z can have any slice
-    X and Y will only consider the beginning and end as we want the images
-    to be continuous
-    >>> bf_1 = expt[0, 0, :, :, :] # First channel, first timepoint, all x,y,z
-    """
-
-    __metaclass__ = abc.ABCMeta
-
-    # metadata_parser = AcqMetadataParser()
-
-    def __init__(self):
-        self.exptID = ""
-        self._current_position = None
-        self.position_to_process = 0
-
-    def __getitem__(self, item):
-        return self.current_position[item]
-
-    @property
-    def shape(self):
-        return self.current_position.shape
-
-    @staticmethod
-    def from_source(*args, **kwargs):
-        """
-        Factory method to construct an instance of an Experiment subclass (
-        either ExperimentOMERO or ExperimentLocal).
-
-        :param source: Where the data is stored (OMERO server or directory
-        name)
-        :param kwargs: If OMERO server, `user` and `password` keyword
-        arguments are required. If the data is stored locally keyword
-        arguments are ignored.
-        """
-        if len(args) > 1:
-            logger.debug("ExperimentOMERO: {}".format(args, kwargs))
-            return ExperimentOMERO(*args, **kwargs)
-        else:
-            logger.debug("ExperimentLocal: {}".format(args, kwargs))
-            return ExperimentLocal(*args, **kwargs)
-
-    @property
-    @abc.abstractmethod
-    def positions(self):
-        """Returns list of available position names"""
-        return
-
-    @abc.abstractmethod
-    def get_position(self, position):
-        return
-
-    @property
-    def current_position(self):
-        return self._current_position
-
-    @property
-    def channels(self):
-        return self._current_position.channels
-
-    @current_position.setter
-    def current_position(self, position):
-        self._current_position = self.get_position(position)
-
-    def get_hypercube(self, x, y, z_positions, channels, timepoints):
-        return self.current_position.get_hypercube(
-            x, y, z_positions, channels, timepoints
-        )
-
-
-# Todo: cache images like in ExperimentLocal
-class ExperimentOMERO(Experiment):
-    """
-    Experiment class to organise different timelapses.
-    Connected to a Dataset object which handles database I/O.
-    """
-
-    def __init__(self, omero_id, host, port=4064, **kwargs):
-        super(ExperimentOMERO, self).__init__()
-        self.exptID = omero_id
-        # Get annotations
-        self.use_annotations = kwargs.get("use_annotations", True)
-        self._files = None
-        self._tags = None
-
-        # Create a connection
-        self.connection = BlitzGateway(
-            kwargs.get("username") or input("Username: "),
-            kwargs.get("password") or getpass("Password: "),
-            host=host,
-            port=port,
-        )
-        connected = self.connection.connect()
-        try:
-            assert connected is True, "Could not connect to server."
-        except AssertionError as e:
-            self.connection.close()
-            raise (e)
-        try:  # Run everything that could cause the initialisation to fail
-            self.dataset = self.connection.getObject("Dataset", self.exptID)
-            self.name = self.dataset.getName()
-            # Create positions objects
-            self._positions = {
-                img.getName(): img.getId()
-                for img in sorted(
-                    self.dataset.listChildren(), key=lambda x: x.getName()
-                )
-            }
-            # Set up local cache
-            self.root_dir = Path(kwargs.get("save_dir", "./")) / self.name
-            if not self.root_dir.exists():
-                self.root_dir.mkdir(parents=True)
-            self.compression = kwargs.get("compression", None)
-            self.image_cache = h5py.File(self.root_dir / "images.h5", "a")
-
-            # Set up the current position as the first in the list
-            self._current_position = self.get_position(self.positions[0])
-            self.running_tp = 0
-        except Exception as e:
-            # Close the connection!
-            print("Error in initialisation, closing connection.")
-            self.connection.close()
-            print(self.connection.isConnected())
-            raise e
-        atexit.register(self.close)  # Close everything if program ends
-
-    def close(self):
-        print("Clean-up on exit.")
-        self.image_cache.close()
-        self.connection.close()
-
-    @property
-    def files(self):
-        if self._files is None:
-            self._files = {
-                x.getFileName(): x
-                for x in self.dataset.listAnnotations()
-                if isinstance(x, omero.gateway.FileAnnotationWrapper)
-            }
-        return self._files
-
-    @property
-    def tags(self):
-        if self._tags is None:
-            self._tags = {
-                x.getName(): x
-                for x in self.dataset.listAnnotations()
-                if isinstance(x, omero.gateway.TagAnnotationWrapper)
-            }
-        return self._tags
-
-    @property
-    def positions(self):
-        return list(self._positions.keys())
-
-    def _get_position_annotation(self, position):
-        # Get file annotations filtered by position name and ordered by
-        # creation date
-        r = re.compile(position)
-        wrappers = sorted(
-            [self.files[key] for key in filter(r.match, self.files)],
-            key=lambda x: x.creationEventDate(),
-            reverse=True,
-        )
-        # Choose newest file
-        if len(wrappers) < 1:
-            return None
-        else:
-            # Choose the newest annotation and cache it
-            annotation = wrappers[0]
-            filepath = self.root_dir / annotation.getFileName().replace("/", "_")
-            if not filepath.exists():
-                with open(str(filepath), "wb") as fd:
-                    for chunk in annotation.getFileInChunks():
-                        fd.write(chunk)
-            return filepath
-
-    def get_position(self, position):
-        """Get a Timelapse object for a given position by name"""
-        # assert position in self.positions, "Position not available."
-        img = self.connection.getObject("Image", self._positions[position])
-        if self.use_annotations:
-            annotation = self._get_position_annotation(position)
-        else:
-            annotation = None
-        return TimelapseOMERO(img, annotation, self.image_cache)
-
-    def cache_locally(
-        self,
-        root_dir="./",
-        positions=None,
-        channels=None,
-        timepoints=None,
-        z_positions=None,
-    ):
-        """
-        Save the experiment locally.
-
-        :param root_dir: The directory in which the experiment will be
-        saved. The experiment will be a subdirectory of "root_directory"
-        and will be named by its id.
-        """
-        logger.warning("Saving experiment {}; may take some time.".format(self.name))
-
-        if positions is None:
-            positions = self.positions
-        if channels is None:
-            channels = self.current_position.channels
-        if timepoints is None:
-            timepoints = range(self.current_position.size_t)
-        if z_positions is None:
-            z_positions = range(self.current_position.size_z)
-
-        save_dir = Path(root_dir) / self.name
-        if not save_dir.exists():
-            save_dir.mkdir()
-        # Save the images
-        for pos_name in tqdm(positions):
-            pos = self.get_position(pos_name)
-            pos_dir = save_dir / pos_name
-            if not pos_dir.exists():
-                pos_dir.mkdir()
-            self.cache_set(pos, range(pos.size_t))
-
-        self.cache_logs(save_dir)
-        # Save the file annotations
-        cache_config = dict(
-            positions=positions,
-            channels=channels,
-            timepoints=timepoints,
-            z_positions=z_positions,
-        )
-        with open(str(save_dir / "cache.config"), "w") as fd:
-            json.dump(cache_config, fd)
-        logger.info("Downloaded experiment {}".format(self.exptID))
-
-    def cache_logs(self, **kwargs):
-        # Save the file annotations
-        tags = dict()  # and the tag annotations
-        for annotation in self.dataset.listAnnotations():
-            if isinstance(annotation, omero.gateway.FileAnnotationWrapper):
-                filepath = self.root_dir / annotation.getFileName().replace("/", "_")
-                if str(filepath).endswith("txt") and not filepath.exists():
-                    # Save only the text files
-                    with open(str(filepath), "wb") as fd:
-                        for chunk in annotation.getFileInChunks():
-                            fd.write(chunk)
-            if isinstance(annotation, omero.gateway.TagAnnotationWrapper):
-                key = annotation.getDescription()
-                if key == "":
-                    key = "misc. tags"
-                if key in tags:
-                    if not isinstance(tags[key], list):
-                        tags[key] = [tags[key]]
-                    tags[key].append(annotation.getValue())
-                else:
-                    tags[key] = annotation.getValue()
-        with open(str(self.root_dir / "omero_tags.json"), "w") as fd:
-            json.dump(tags, fd)
-        return
-
-    def run(self, keys: Union[list, int], store, **kwargs):
-        if self.running_tp == 0:
-            self.cache_logs(**kwargs)
-            self.running_tp = 1  # Todo rename based on annotations
-        run_tps = dict()
-        for pos, tps in accumulate(keys):
-            position = self.get_position(pos)
-            run_tps[pos] = position.run(tps, store, save_dir=self.root_dir)
-        # Update the keys to match what was actually run
-        keys = [(pos, tp) for pos in run_tps for tp in run_tps[pos]]
-        return keys
-
-
-class ExperimentLocal(Experiment):
-    def __init__(self, root_dir, finished=True):
-        super(ExperimentLocal, self).__init__()
-        self.root_dir = Path(root_dir)
-        self.exptID = self.root_dir.name
-        self._pos_mapper = dict()
-        # Fixme: Made the assumption that the Acq file gets saved before the
-        #  experiment is run and that the information in that file is
-        #  trustworthy.
-        acq_file = self._find_acq_file()
-        acq_parser = Parser("multiDGUI_acq_format")
-        with open(acq_file, "r") as fd:
-            metadata = acq_parser.parse(fd)
-        self.metadata = metadata
-        self.metadata["finished"] = finished
-        self.files = [f for f in self.root_dir.iterdir() if f.is_file()]
-        self.image_cache = h5py.File(self.root_dir / "images.h5", "a")
-        if self.finished:
-            cache = self._find_cache()
-            # log = self._find_log() # Todo: add log metadata
-            if cache is not None:
-                with open(cache, "r") as fd:
-                    cache_config = json.load(fd)
-                self.metadata.update(**cache_config)
-        self._current_position = self.get_position(self.positions[0])
-
-    def _find_file(self, regex):
-        file = glob.glob(os.path.join(str(self.root_dir), regex))
-        if len(file) != 1:
-            return None
-        else:
-            return file[0]
-
-    def _find_acq_file(self):
-        file = self._find_file("*[Aa]cq.txt")
-        if file is None:
-            raise ValueError(
-                "Cannot load this experiment. There are either "
-                "too many or too few acq files."
-            )
-        return file
-
-    def _find_cache(self):
-        return self._find_file("cache.config")
-
-    @property
-    def finished(self):
-        return self.metadata["finished"]
-
-    @property
-    def running(self):
-        return not self.metadata["finished"]
-
-    @property
-    def positions(self):
-        return self.metadata["positions"]["posname"]
-
-    def _get_position_annotation(self, position):
-        r = re.compile(position)
-        files = list(filter(lambda x: r.match(x.stem), self.files))
-        if len(files) == 0:
-            return None
-        files = sorted(files, key=lambda x: x.lstat().st_ctime, reverse=True)
-        # Get the newest and return as string
-        return files[0]
-
-    def get_position(self, position):
-        if position not in self._pos_mapper:
-            annotation = self._get_position_annotation(position)
-            self._pos_mapper[position] = TimelapseLocal(
-                position,
-                self.root_dir,
-                finished=self.finished,
-                annotation=annotation,
-                cache=self.image_cache,
-            )
-        return self._pos_mapper[position]
-
-    def run(self, keys, store, **kwargs):
-        """
-
-        :param keys: List of (position, time point) tuples to process.
-        :return:
-        """
-        run_tps = dict()
-        for pos, tps in accumulate(keys):
-            run_tps[pos] = self.get_position(pos).run(tps, store)
-        # Update the keys to match what was actually run
-        keys = [(pos, tp) for pos in run_tps for tp in run_tps[pos]]
-        return keys

aliby/extract.py

-"""
-A module to extract data from a processed experiment.
-"""
-import h5py
-import numpy as np
-from tqdm import tqdm
-
-from core.io.matlab import matObject
-from growth_rate.estimate_gr import estimate_gr
-
-
-class Extracted:
-    # TODO write the filtering functions.
-    def __init__(self):
-        self.volume = None
-        self._keep = None
-
-    def filter(self, filename=None, **kwargs):
-        """
-        1. Filter out small non-growing tracks. This means:
-            a. the cell size never reaches beyond a certain size-threshold
-            volume_thresh or
-            b. the cell's volume doesn't increase by at least a minimum
-            amount over its lifetime
-        2. Join daughter tracks that are contiguous and within a volume
-           threshold of each other
-        3. Discard tracks that are shorter than a threshold number of
-           timepoints
-
-        This function is used to fix tracking/bud errors in post-processing.
-        The parameters define the thresholds used to determine which cells are
-        discarded.
-        FIXME Ideally we get to a point where this is no longer needed.
-        :return:
-        """
-        #self.join_tracks()
-        filter_out = self.filter_size(**kwargs)
-        filter_out += self.filter_lifespan(**kwargs)
-        # TODO save data or just filtering parameters?
-        #self.to_hdf(filename)
-        self.keep = ~filter_out
-
-    def filter_size(self, volume_thresh=7, growth_thresh=10, **kwargs):
-        """Filter out small and non-growing cells.
-        :param volume_thresh: Size threshold for small cells
-        :param growth_thresh: Size difference threshold for non-growing cells
-        """
-        filter_out = np.where(np.max(self.volume, axis=1) < volume_thresh,
-                              True, False)
-        growth = [v[v > 0] for v in self.volume]
-        growth = np.array([v[-1] - v[0] if len(v) > 0 else 0 for v in growth])
-        filter_out += np.where(growth < growth_thresh, True, False)
-        return filter_out
-
-    def filter_lifespan(self, min_time=5, **kwargs):
-        """Remove daughter cells that have a small life span.
-
-        :param min_time: The minimum life span, under which cells are removed.
-        """
-        # TODO What if there are nan values?
-        filter_out = np.where(np.count_nonzero(self.volume, axis=1) <
-                              min_time, True, False)
-        return filter_out
-
-    def join_tracks(self, threshold=7):
-        """ Join contiguous tracks that are within a certain volume
-        threshold of each other.
-
-        :param threshold: Maximum volume difference to join contiguous tracks.
-        :return:
-        """
-        # For all pairs of cells
-        #
-        pass
-
-
-class ExtractedHDF(Extracted):
-    # TODO pull all the data out of the HFile and filter!
-    def __init__(self, file):
-        # We consider the data to be read-only
-        self.hfile = h5py.File(file, 'r')
-
-
-class ExtractedMat(Extracted):
-    """ Pulls the extracted data out of the MATLAB cTimelapse file.
-
-    This is mostly a convenience function in order to run the
-    gaussian-processes growth-rate estimation
-    """
-    def __init__(self, file, debug=False):
-        ct = matObject(file)
-        self.debug = debug
-        # Pre-computed data
-        # TODO what if there is no timelapseTrapsOmero?
-        self.metadata = ct['timelapseTrapsOmero']['metadata']
-        self.extracted_data = ct['timelapseTrapsOmero']['extractedData']
-        self.channels = ct['timelapseTrapsOmero']['extractionParameters'][
-            'functionParameters']['channels'].tolist()
-        self.time_settings = ct['timelapseTrapsOmero']['metadata']['acq'][
-            'times']
-        # Get filtering information
-        n_cells = self.extracted_data['cellNum'][0].shape
-        self.keep = np.full(n_cells, True)
-        # Not yet computed data
-        self._growth_rate = None
-        self._daughter_index = None
-
-
-    def get_channel_index(self, channel):
-        """Get index of channel based on name. This only considers
-        fluorescence channels."""
-        return self.channels.index(channel)
-
-    @property
-    def trap_num(self):
-        return self.extracted_data['trapNum'][0][self.keep]
-
-    @property
-    def cell_num(self):
-        return self.extracted_data['cellNum'][0][self.keep]
-
-    def identity(self, cell_idx):
-        """Get the (position), trap, and cell label given a cell's global
-        index."""
-        # Todo include position when using full strain
-        trap = self.trap_num[cell_idx]
-        cell = self.cell_num[cell_idx]
-        return trap, cell
-
-    def global_index(self, trap_id, cell_label):
-        """Get the global index of a cell given it's trap/cellNum
-        combination."""
-        candidates = np.where(np.logical_and(
-                            (self.trap_num == trap_id), # +1?
-                            (self.cell_num == cell_label)
-                        ))[0]
-        # TODO raise error if number of candidates != 1
-        if len(candidates) == 1:
-            return candidates[0]
-        elif len(candidates) == 0:
-            return -1
-        else:
-            raise(IndexError("No such cell/trap combination"))
-
-    @property
-    def daughter_label(self):
-        """Returns the cell label of the daughters of each cell over the
-        timelapse.
-
-        0 corresponds to no daughter. This *not* the index of the daughter
-        cell within the data. To get this, use daughter_index.
-        """
-        return self.extracted_data['daughterLabel'][0][self.keep]
-
-    def _single_daughter_idx(self, mother_idx, daughter_labels):
-        trap_id, _ = self.identity(mother_idx)
-        daughter_index = [self.global_index(trap_id, cell_label) for
-                          cell_label
-                          in daughter_labels]
-        return daughter_index
-
-    @property
-    def daughter_index(self):
-        """Returns the global index of the daughters of each cell.
-
-        This is different from the daughter label because it corresponds to
-        the index of the daughter when counting all of the cells. This can
-        be used to index within the data arrays.
-        """
-        if self._daughter_index is None:
-            daughter_index = [self._single_daughter_idx(i, daughter_labels)
-                          for i, daughter_labels in enumerate(
-                                  self.daughter_label)]
-            self._daughter_index = np.array(daughter_index)
-        return self._daughter_index
-
-    @property
-    def births(self):
-        return np.array(self.extracted_data['births'][0].todense())[self.keep]
-
-    @property
-    def volume(self):
-        """Get the volume of all of the cells"""
-        return np.array(self.extracted_data['volume'][0].todense())[self.keep]
-
-    def _gr_estimation(self):
-        dt = self.time_settings['interval'] / 360  # s to h conversion
-        results = []
-        for v in tqdm(self.volume):
-            results.append(estimate_gr(v, dt))
-        merged = {k: np.stack([x[k] for x in results]) for k in results[0]}
-        self._gr_results = merged
-        return
-
-    @property
-    def growth_rate(self):
-        """Get the growth rate for all cells.
-
-        Note that this uses the gaussian processes method of estimating
-        growth rate by default. If there is no growth rate in the given file
-        (usually the case for MATLAB), it needs to run estimation first.
-        This can take a while.
-        """
-        # TODO cache the results of growth rate estimation.
-        if self._gr_results is None:
-            dt = self.time_settings['interval'] / 360  # s to h conversion
-            self._growth_rate = [estimate_gr(v, dt) for v in self.volume]
-        return self._gr_results['growth_rate']
-
-    def _fluo_attribute(self, channel, attribute):
-        channel_id = self.get_channel_index(channel)
-        res = np.array(self.extracted_data[attribute][channel_id].todense())
-        return res[self.keep]
-
-    def protein_localisation(self, channel, method='nucEstConv'):
-        """Returns protein localisation data for a given channel.
-
-        Uses the 'nucEstConv' by default. Alternatives are 'smallPeakConv',
-        'max5px', 'max2p5pc'
-        """
-        return self._fluo_attribute(channel, method)
-
-    def background_fluo(self, channel):
-        return self._fluo_attribute(channel, 'imBackground')
-
-    def mean(self, channel):
-        return self._fluo_attribute(channel, 'mean')
-
-    def median(self, channel):
-        return self._fluo_attribute(channel, 'median')
-
-    def filter(self, filename=None):
-        """Filters and saves results to and HDF5 file.
-
-        This is necessary because we cannot write to the MATLAB file,
-        so the results of the filter cannot be saved in the object.
-        """
-        super().filter(filename=filename)
-        self._growth_rate = None  # reset growth rate so it is recomputed
-
-    def to_hdf(self, filename):
-        """Store the current results, including any filtering done, to a file.
-
-        TODO Should we save filtered results or just re-do?
-        :param filename:
-        :return:
-        """
-        store = h5py.File(filename, 'w')
-        try:
-            # Store (some of the) metadata
-            for meta in ['experiment', 'username', 'microscope',
-                              'comments', 'project', 'date', 'posname',
-                              'exptid']:
-                store.attrs[meta] = self.metadata[meta]
-            # TODO store timing information?
-            store.attrs['time_interval'] = self.time_settings['interval']
-            store.attrs['timepoints'] = self.time_settings['ntimepoints']
-            store.attrs['total_duration'] = self.time_settings['totalduration']
-            # Store volume, births, daughterLabel, trapNum, cellNum
-            for key in ['volume', 'births', 'daughter_label', 'trap_num',
-                        'cell_num']:
-                store[key] = getattr(self, key)
-            # Store growth rate results
-            if self._gr_results:
-                grp = store.create_group('gaussian_process')
-                for key, val in self._gr_results.items():
-                    grp[key] = val
-            for channel in self.channels:
-                # Create a group for each channel
-                grp = store.create_group(channel)
-                # Store protein_localisation, background fluorescence, mean, median
-                # for each channel
-                grp['protein_localisation'] = self.protein_localisation(channel)
-                grp['background_fluo'] = self.background_fluo(channel)
-                grp['mean'] = self.mean(channel)
-                grp['median'] = self.median(channel)
-        finally:
-            store.close()
-

aliby/io/matlab.py

-"""Read and convert MATLAB files from Swain Lab platform.
-
-TODO: Information that I need from lab members esp J and A
-    * Lots of examples to try
-    * Any ideas on what these Map objects are?
-
-TODO: Update Swain Lab wiki
-
-All credit to Matt Bauman for
-the reverse engineering at https://nbviewer.jupyter.org/gist/mbauman/9121961
-"""
-
-import re
-import struct
-import sys
-from collections import Iterable
-from io import BytesIO
-
-import h5py
-import numpy as np
-import pandas as pd
-import scipy
-from numpy.compat import asstr
-
-# TODO only use this if scipy>=1.6 or so
-from scipy.io import matlab
-from scipy.io.matlab.mio5 import MatFile5Reader
-from scipy.io.matlab.mio5_params import mat_struct
-
-from aliby.io.utils import read_int, read_string, read_delim
-
-
-def read_minimat_vars(rdr):
-    rdr.initialize_read()
-    mdict = {"__globals__": []}
-    i = 0
-    while not rdr.end_of_stream():
-        hdr, next_position = rdr.read_var_header()
-        name = asstr(hdr.name)
-        if name == "":
-            name = "var_%d" % i
-            i += 1
-        res = rdr.read_var_array(hdr, process=False)
-        rdr.mat_stream.seek(next_position)
-        mdict[name] = res
-        if hdr.is_global:
-            mdict["__globals__"].append(name)
-    return mdict
-
-
-def read_workspace_vars(fname):
-    fp = open(fname, "rb")
-    rdr = MatFile5Reader(fp, struct_as_record=True, squeeze_me=True)
-    vars = rdr.get_variables()
-    fws = vars["__function_workspace__"]
-    ws_bs = BytesIO(fws.tostring())
-    ws_bs.seek(2)
-    rdr.mat_stream = ws_bs
-    # Guess byte order.
-    mi = rdr.mat_stream.read(2)
-    rdr.byte_order = mi == b"IM" and "<" or ">"
-    rdr.mat_stream.read(4)  # presumably byte padding
-    mdict = read_minimat_vars(rdr)
-    fp.close()
-    return mdict
-
-
-class matObject:
-    """A python read-out of MATLAB objects
-    The objects pulled out of the
-    """
-
-    def __init__(self, filepath):
-        self.filepath = filepath  # For record
-        self.classname = None
-        self.object_name = None
-        self.buffer = None
-        self.version = None
-        self.names = None
-        self.segments = None
-        self.heap = None
-        self.attrs = dict()
-        self._init_buffer()
-        self._init_heap()
-        self._read_header()
-        self.parse_file()
-
-    def __getitem__(self, item):
-        return self.attrs[item]
-
-    def keys(self):
-        """Returns the names of the available properties"""
-        return self.attrs.keys()
-
-    def get(self, item, default=None):
-        return self.attrs.get(item, default)
-
-    def _init_buffer(self):
-        fp = open(self.filepath, "rb")
-        rdr = MatFile5Reader(fp, struct_as_record=True, squeeze_me=True)
-        vars = rdr.get_variables()
-        self.classname = vars["None"]["s2"][0].decode("utf-8")
-        self.object_name = vars["None"]["s0"][0].decode("utf-8")
-        fws = vars["__function_workspace__"]
-        self.buffer = BytesIO(fws.tostring())
-        fp.close()
-
-    def _init_heap(self):
-        super_data = read_workspace_vars(self.filepath)
-        elem = super_data["var_0"][0, 0]
-        if isinstance(elem, mat_struct):
-            self.heap = elem.MCOS[0]["arr"]
-        else:
-            self.heap = elem["MCOS"][0]["arr"]
-
-    def _read_header(self):
-        self.buffer.seek(248)  # the start of the header
-        version = read_int(self.buffer)
-        n_str = read_int(self.buffer)
-
-        offsets = read_int(self.buffer, n=6)
-
-        # check that the next two are zeros
-        reserved = read_int(self.buffer, n=2)
-        assert all(
-            [x == 0 for x in reserved]
-        ), "Non-zero reserved header fields: {}".format(reserved)
-        # check that we are at the right place
-        assert self.buffer.tell() == 288, "String elemnts begin at 288"
-        hdrs = []
-        for i in range(n_str):
-            hdrs.append(read_string(self.buffer))
-        self.names = hdrs
-        self.version = version
-        # The offsets are actually STARTING FROM 248 as well
-        self.segments = [x + 248 for x in offsets]  # list(offsets)
-        return
-
-    def parse_file(self):
-        # Get class attributes from segment 1
-        self.buffer.seek(self.segments[0])
-        classes = self._parse_class_attributes(self.segments[1])
-        # Get first set of properties from segment 2
-        self.buffer.seek(self.segments[1])
-        props1 = self._parse_properties(self.segments[2])
-        # Get the property description from segment 3
-        self.buffer.seek(self.segments[2])
-        object_info = self._parse_prop_description(classes, self.segments[3])
-        # Get more properties from segment 4
-        self.buffer.seek(self.segments[3])
-        props2 = self._parse_properties(self.segments[4])
-        # Check that the last segment is empty
-        self.buffer.seek(self.segments[4])
-        seg5_length = (self.segments[5] - self.segments[4]) // 8
-        read_delim(self.buffer, seg5_length)
-        props = (props1, props2)
-        self._to_attrs(object_info, props)
-
-    def _to_attrs(self, object_info, props):
-        """Re-organise the various classes and subclasses into a nested
-        dictionary.
-        :return:
-        """
-        for pkg_clss, indices, idx in object_info:
-            pkg, clss = pkg_clss
-            idx = max(indices)
-            which = indices.index(idx)
-            obj = flatten_obj(props[which][idx])
-            subdict = self.attrs
-            if pkg != "":
-                subdict = self.attrs.setdefault(pkg, {})
-            if clss in subdict:
-                if isinstance(subdict[clss], list):
-                    subdict[clss].append(obj)
-                else:
-                    subdict[clss] = [subdict[clss]]
-                    subdict[clss].append(obj)
-            else:
-                subdict[clss] = obj
-
-    def describe(self):
-        describe(self.attrs)
-
-    def _parse_class_attributes(self, section_end):
-        """Read the Class attributes = the first segment"""
-        read_delim(self.buffer, 4)
-        classes = []
-        while self.buffer.tell() < section_end:
-            package_index = read_int(self.buffer) - 1
-            package = self.names[package_index] if package_index > 0 else ""
-            name_idx = read_int(self.buffer) - 1
-            name = self.names[name_idx] if name_idx > 0 else ""
-            classes.append((package, name))
-            read_delim(self.buffer, 2)
-        return classes
-
-    def _parse_prop_description(self, classes, section_end):
-        """Parse the description of each property = the third segment"""
-        read_delim(self.buffer, 6)
-        object_info = []
-        while self.buffer.tell() < section_end:
-            class_idx = read_int(self.buffer) - 1
-            class_type = classes[class_idx]
-            read_delim(self.buffer, 2)
-            indices = [x - 1 for x in read_int(self.buffer, 2)]
-            obj_id = read_int(self.buffer)
-            object_info.append((class_type, indices, obj_id))
-        return object_info
-
-    def _parse_properties(self, section_end):
-        """
-        Parse the actual values of the attributes == segments 2 and 4
-        """
-        read_delim(self.buffer, 2)
-        props = []
-        while self.buffer.tell() < section_end:
-            n_props = read_int(self.buffer)
-            d = parse_prop(n_props, self.buffer, self.names, self.heap)
-            if not d:  # Empty dictionary
-                break
-            props.append(d)
-            # Move to next 8-byte aligned offset
-            self.buffer.seek(self.buffer.tell() + self.buffer.tell() % 8)
-        return props
-
-    def to_hdf(self, filename):
-        f = h5py.File(filename, mode="w")
-        save_to_hdf(f, "/", self.attrs)
-
-
-def describe(d, indent=0, width=4, out=None):
-    for key, value in d.items():
-        print(f'{"": <{width * indent}}' + str(key), file=out)
-        if isinstance(value, dict):
-            describe(value, indent + 1, out=out)
-        elif isinstance(value, np.ndarray):
-            print(
-                f'{"": <{width * (indent + 1)}} {value.shape} array '
-                f"of type {value.dtype}",
-                file=out,
-            )
-        elif isinstance(value, scipy.sparse.csc.csc_matrix):
-            print(
-                f'{"": <{width * (indent + 1)}} {value.shape} '
-                f"sparse matrix of type {value.dtype}",
-                file=out,
-            )
-        elif isinstance(value, Iterable) and not isinstance(value, str):
-            print(
-                f'{"": <{width * (indent + 1)}} {type(value)} of len ' f"{len(value)}",
-                file=out,
-            )
-        else:
-            print(f'{"": <{width * (indent + 1)}} {value}', file=out)
-
-
-def parse_prop(n_props, buff, names, heap):
-    d = dict()
-    for i in range(n_props):
-        name_idx, flag, heap_idx = read_int(buff, 3)
-        if flag not in [0, 1, 2] and name_idx == 0:
-            n_props = flag
-            buff.seek(buff.tell() - 1)  # go back on one byte
-            d = parse_prop(n_props, buff, names, heap)
-        else:
-            item_name = names[name_idx - 1]
-            if flag == 0:
-                d[item_name] = names[heap_idx]
-            elif flag == 1:
-                d[item_name] = heap[heap_idx + 2]  # Todo: what is the heap?
-            elif flag == 2:
-                assert 0 <= heap_idx <= 1, (
-                    "Boolean flag has a value other " "than 0 or 1 "
-                )
-                d[item_name] = bool(heap_idx)
-            else:
-                raise ValueError(
-                    "unknown flag {} for property {} with heap "
-                    "index {}".format(flag, item_name, heap_idx)
-                )
-    return d
-
-
-def is_object(x):
-    """Checking object dtype for structured numpy arrays"""
-    if x.dtype.names is not None and len(x.dtype.names) > 1:  # Complex obj
-        return all(x.dtype[ix] == np.object for ix in range(len(x.dtype)))
-    else:  # simple object
-        return x.dtype == np.object
-
-
-def flatten_obj(arr):
-    # TODO turn structured arrays into nested dicts of lists rather that
-    #  lists of dicts
-    if isinstance(arr, np.ndarray):
-        if arr.dtype.names:
-            arrdict = dict()
-            for fieldname in arr.dtype.names:
-                arrdict[fieldname] = flatten_obj(arr[fieldname])
-            arr = arrdict
-        elif arr.dtype == np.object and arr.ndim == 0:
-            arr = flatten_obj(arr[()])
-        elif arr.dtype == np.object and arr.ndim > 0:
-            try:
-                arr = np.stack(arr)
-                if arr.dtype.names:
-                    d = {k: flatten_obj(arr[k]) for k in arr.dtype.names}
-                    arr = d
-            except:
-                arr = [flatten_obj(x) for x in arr.tolist()]
-    elif isinstance(arr, dict):
-        arr = {k: flatten_obj(v) for k, v in arr.items()}
-    elif isinstance(arr, list):
-        try:
-            arr = flatten_obj(np.stack(arr))
-        except:
-            arr = [flatten_obj(x) for x in arr]
-    return arr
-
-
-def save_to_hdf(h5file, path, dic):
-    """
-    Saving a MATLAB object to HDF5
-    """
-    if isinstance(dic, list):
-        dic = {str(i): v for i, v in enumerate(dic)}
-    for key, item in dic.items():
-        if isinstance(item, (int, float, str)):
-            h5file[path].attrs.create(key, item)
-        elif isinstance(item, list):
-            if len(item) == 0 and path + key not in h5file:  # empty list empty group
-                h5file.create_group(path + key)
-            if all(isinstance(x, (int, float, str)) for x in item):
-                if path not in h5file:
-                    h5file.create_group(path)
-                h5file[path].attrs.create(key, item)
-            else:
-                if path + key not in h5file:
-                    h5file.create_group(path + key)
-                save_to_hdf(
-                    h5file, path + key + "/", {str(i): x for i, x in enumerate(item)}
-                )
-        elif isinstance(item, scipy.sparse.csc.csc_matrix):
-            try:
-                h5file.create_dataset(
-                    path + key, data=item.todense(), compression="gzip"
-                )
-            except Exception as e:
-                print(path + key)
-                raise e
-        elif isinstance(item, (np.ndarray, np.int64, np.float64)):
-            if item.dtype == np.dtype("<U1"):  # Strings to 'S' type for HDF5
-                item = item.astype("S")
-            try:
-                h5file.create_dataset(path + key, data=item, compression="gzip")
-            except Exception as e:
-                print(path + key)
-                raise e
-        elif isinstance(item, dict):
-            if path + key not in h5file:
-                h5file.create_group(path + key)
-            save_to_hdf(h5file, path + key + "/", item)
-        elif item is None:
-            continue
-        else:
-            raise ValueError(f"Cannot save {type(item)} type at key {path + key}")
-
-
-## NOT YET FULLY IMPLEMENTED!
-
-
-class _Info:
-    def __init__(self, info):
-        self.info = info
-        self._identity = None
-
-    def __getitem__(self, item):
-        val = self.info[item]
-        if val.shape[0] == 1:
-            val = val[0]
-        if 0 in val[1].shape:
-            val = val[0]
-        if isinstance(val, scipy.sparse.csc.csc_matrix):
-            return np.asarray(val.todense())
-        if val.dtype == np.dtype("O"):
-            # 3d "sparse matrix"
-            if all(isinstance(x, scipy.sparse.csc.csc_matrix) for x in val):
-                val = np.array([x.todense() for x in val])
-            # TODO: The actual object data
-        equality = val[0] == val[1]
-        if isinstance(equality, scipy.sparse.csc.csc_matrix):
-            equality = equality.todense()
-        if equality.all():
-            val = val[0]
-        return np.squeeze(val)
-
-    @property
-    def categories(self):
-        return self.info.dtype.names
-
-
-class TrapInfo(_Info):
-    def __init__(self, info):
-        """
-        The information on all of the traps in a given position.
-
-        :param info: The TrapInfo structure, can be found in the heap of
-        the CTimelapse at index 7
-        """
-        super().__init__(info)
-
-
-class CellInfo(_Info):
-    def __init__(self, info):
-        """
-        The extracted information of all cells in a given position.
-        :param info: The CellInfo structure, can be found in the heap
-        of the CTimelapse at index 15.
-        """
-        super().__init__(info)
-
-    @property
-    def identity(self):
-        if self._identity is None:
-            self._identity = pd.DataFrame(
-                zip(self["trapNum"], self["cellNum"]), columns=["trapNum", "cellNum"]
-            )
-        return self._identity
-
-    def index(self, trapNum, cellNum):
-        query = "trapNum=={} and cellNum=={}".format(trapNum, cellNum)
-        try:
-            result = self.identity.query(query).index[0]
-        except Exception as e:
-            print(query)
-            raise e
-        return result
-
-    @property
-    def nucEstConv1(self):
-        return np.asarray(self.info["nuc_est_conv"][0][0].todense())
-
-    @property
-    def nucEstConv2(self):
-        return np.asarray(self.info["nuc_est_conv"][0][1].todense())
-
-    @property
-    def mothers(self):
-        return np.where((self["births"] != 0).any(axis=1))[0]
-
-    def daughters(self, mother_index):
-        """
-        Get daughters of cell with index `mother_index`.
-
-        :param mother_index: the index of the mother within the data. This is
-        different from the mother's cell/trap identity.
-        """
-        daughter_ids = np.unique(self["daughterLabel"][mother_index]).tolist()
-        daughter_ids.remove(0)
-        mother_trap = self.identity["trapNum"].loc[mother_index]
-        daughters = [self.index(mother_trap, cellNum) for cellNum in daughter_ids]
-        return daughters
-
-
-def _todict(matobj):
-    """
-    A recursive function which constructs from matobjects nested dictionaries
-    """
-    if not hasattr(matobj, "_fieldnames"):
-        return matobj
-    d = {}
-    for strg in matobj._fieldnames:
-        elem = matobj.__dict__[strg]
-        if isinstance(elem, matlab.mio5_params.mat_struct):
-            d[strg] = _todict(elem)
-        elif isinstance(elem, np.ndarray):
-            d[strg] = _toarray(elem)
-        else:
-            d[strg] = elem
-    return d
-
-
-def _toarray(ndarray):
-    """
-    A recursive function which constructs ndarray from cellarrays
-    (which are loaded as numpy ndarrays), recursing into the elements
-    if they contain matobjects.
-    """
-    if ndarray.dtype != "float64":
-        elem_list = []
-        for sub_elem in ndarray:
-            if isinstance(sub_elem, matlab.mio5_params.mat_struct):
-                elem_list.append(_todict(sub_elem))
-            elif isinstance(sub_elem, np.ndarray):
-                elem_list.append(_toarray(sub_elem))
-            else:
-                elem_list.append(sub_elem)
-        return np.array(elem_list)
-    else:
-        return ndarray
-
-
-from pathlib import Path
-
-
-class Strain:
-    """The cell info for all the positions of a strain."""
-
-    def __init__(self, origin, strain):
-        self.origin = Path(origin)
-        self.files = [x for x in origin.iterdir() if strain in str(x)]
-        self.cts = [matObject(x) for x in self.files]
-        self.cinfos = [CellInfo(x.heap[15]) for x in self.cts]
-        self._identity = None
-
-    def __getitem__(self, item):
-        try:
-            return np.concatenate([c[item] for c in self.cinfos])
-        except ValueError:  # If first axis is the channel
-            return np.concatenate([c[item] for c in self.cinfos], axis=1)
-
-    @property
-    def categories(self):
-        return set.union(*[set(c.categories) for c in self.cinfos])
-
-    @property
-    def identity(self):
-        if self._identity is None:
-            identities = []
-            for pos_id, cinfo in enumerate(self.cinfos):
-                identity = cinfo.identity
-                identity["position"] = pos_id
-                identities.append(identity)
-            self._identity = pd.concat(identities, ignore_index=True)
-        return self._identity
-
-    def index(self, posNum, trapNum, cellNum):
-        query = "position=={} and trapNum=={} and cellNum=={}".format(
-            posNum, trapNum, cellNum
-        )
-        try:
-            result = self.identity.query(query).index[0]
-        except Exception as e:
-            raise e
-        return result
-
-    @property
-    def mothers(self):
-        # At least two births are needed to be considered a mother cell
-        return np.where(np.count_nonzero(self["births"], axis=1) > 3)[0]
-
-    def daughters(self, mother_index):
-        """
-        Get daughters of cell with index `mother_index`.
-
-        :param mother_index: the index of the mother within the data. This is
-        different from the mother's pos/trap/cell identity.
-        """
-        daughter_ids = np.unique(self["daughterLabel"][mother_index]).tolist()
-        if 0 in daughter_ids:
-            daughter_ids.remove(0)
-        mother_pos_trap = self.identity[["position", "trapNum"]].loc[mother_index]
-        daughters = []
-        for cellNum in daughter_ids:
-            try:
-                daughters.append(self.index(*mother_pos_trap, cellNum))
-            except IndexError:
-                continue
-        return daughters

aliby/io/omero.py

-import h5py
-import omero
-from omero.gateway import BlitzGateway
-from aliby.experiment import get_data_lazy
-from agora.io.cells import CellsHDF
-
-
-class Argo:
-    # TODO use the one in extraction?
-    def __init__(
-        self, host="islay.bio.ed.ac.uk", username="upload", password="***REMOVED***"
-    ):
-        self.conn = None
-        self.host = host
-        self.username = username
-        self.password = password
-
-    def get_meta(self):
-        pass
-
-    def __enter__(self):
-        self.conn = BlitzGateway(
-            host=self.host, username=self.username, passwd=self.password
-        )
-        self.conn.connect()
-        return self
-
-    def __exit__(self, *exc):
-        self.conn.close()
-        return False
-
-
-class Dataset(Argo):
-    def __init__(self, expt_id, **server_info):
-        super().__init__(**server_info)
-        self.expt_id = expt_id
-        self._files = None
-
-    @property
-    def dataset(self):
-        return self.conn.getObject("Dataset", self.expt_id)
-
-    @property
-    def name(self):
-        return self.dataset.getName()
-
-    @property
-    def date(self):
-        return self.dataset.getDate()
-
-    @property
-    def unique_name(self):
-        return "_".join((self.date.strftime("%Y_%m_%d").replace("/", "_"), self.name))
-
-    def get_images(self):
-        return {im.getName(): im.getId() for im in self.dataset.listChildren()}
-
-    @property
-    def files(self):
-        if self._files is None:
-            self._files = {
-                x.getFileName(): x
-                for x in self.dataset.listAnnotations()
-                if isinstance(x, omero.gateway.FileAnnotationWrapper)
-            }
-        if not len(self._files):
-            raise Exception("Exception:Metadata: Experiment has no annotation files.")
-        return self._files
-
-    @property
-    def tags(self):
-        if self._tags is None:
-            self._tags = {
-                x.getName(): x
-                for x in self.dataset.listAnnotations()
-                if isinstance(x, omero.gateway.TagAnnotationWrapper)
-            }
-        return self._tags
-
-    def cache_logs(self, root_dir):
-        for name, annotation in self.files.items():
-            filepath = root_dir / annotation.getFileName().replace("/", "_")
-            if str(filepath).endswith("txt") and not filepath.exists():
-                # Save only the text files
-                with open(str(filepath), "wb") as fd:
-                    for chunk in annotation.getFileInChunks():
-                        fd.write(chunk)
-        return True
-
-
-class Image(Argo):
-    def __init__(self, image_id, **server_info):
-        super().__init__(**server_info)
-        self.image_id = image_id
-        self._image_wrap = None
-
-    @property
-    def image_wrap(self):
-        # TODO check that it is alive/ connected
-        if self._image_wrap is None:
-            self._image_wrap = self.conn.getObject("Image", self.image_id)
-        return self._image_wrap
-
-    @property
-    def name(self):
-        return self.image_wrap.getName()
-
-    @property
-    def data(self):
-        return get_data_lazy(self.image_wrap)
-
-    @property
-    def metadata(self):
-        meta = dict()
-        meta["size_x"] = self.image_wrap.getSizeX()
-        meta["size_y"] = self.image_wrap.getSizeY()
-        meta["size_z"] = self.image_wrap.getSizeZ()
-        meta["size_c"] = self.image_wrap.getSizeC()
-        meta["size_t"] = self.image_wrap.getSizeT()
-        meta["channels"] = self.image_wrap.getChannelLabels()
-        meta["name"] = self.image_wrap.getName()
-        return meta
-
-
-class Cells(CellsHDF):
-    def __init__(self, filename):
-        file = h5py.File(filename, "r")
-        super().__init__(file)
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, *exc):
-        self.close
-        return False

aliby/io/utils.py

-import re
-import struct
-
-
-def clean_ascii(text):
-    return re.sub(r'[^\x20-\x7F]', '.', text)
-
-
-def xxd(x, start=0, stop=None):
-    if stop is None:
-        stop = len(x)
-    for i in range(start, stop, 8):
-        # Row number
-        print("%04d" % i, end="   ")
-        # Hexadecimal bytes
-        for r in range(i, i + 8):
-            print("%02x" % x[r], end="")
-            if (r + 1) % 4 == 0:
-                print("  ", end="")
-        # ASCII
-        print("   ", clean_ascii(x[i:i + 8].decode('utf-8', errors='ignore')),
-              "   ", end="")
-        # Int32
-        print('{:>10} {:>10}'.format(*struct.unpack('II', x[i: i + 8])),
-              end="   ")
-        print("")  # Newline
-    return
-
-
-# Buffer reading functions
-def read_int(buffer, n=1):
-    res = struct.unpack('I' * n, buffer.read(4 * n))
-    if n == 1:
-        res = res[0]
-    return res
-
-
-def read_string(buffer):
-    return ''.join([x.decode() for x in iter(lambda: buffer.read(1), b'\x00')])
-
-
-def read_delim(buffer, n):
-    delim = read_int(buffer, n)
-    assert all([x == 0 for x in delim]), "Unknown nonzero value in delimiter"

aliby/multiexperiment.py

-from pathos.multiprocessing import Pool
-
-from aliby.pipeline import PipelineParameters, Pipeline
-
-
-class MultiExp:
-    """
-    Manages cases when you need to segment several different experiments with a single
-    position (e.g. pH calibration).
-    """
-
-    def __init__(self, expt_ids, npools=8, *args, **kwargs):
-
-        self.expt_ids = expt_ids
-
-    def run(self):
-        run_expt = lambda expt: Pipeline(
-            PipelineParameters.default(general={"expt_id": expt, "distributed": 0})
-        ).run()
-        with Pool(npools) as p:
-            results = p.map(lambda x: self.create_pipeline(x), self.exp_ids)
-
-    @classmethod
-    def default(self):
-        return cls(expt_ids=list(range(20448, 20467 + 1)))

aliby/pipeline.py

-"""
-Pipeline and chaining elements.
-"""
-import logging
-import os
-from abc import ABC, abstractmethod
-from typing import List
-from pathlib import Path
-import traceback
-
-from itertools import groupby
-import re
-import h5py
-import yaml
-from tqdm import tqdm
-from time import perf_counter
-from pathos.multiprocessing import Pool
-
-import numpy as np
-import pandas as pd
-from scipy import ndimage
-
-from aliby.experiment import MetaData
-from aliby.haystack import initialise_tf
-from aliby.baby_client import BabyRunner, BabyParameters
-from aliby.tile.tiler import Tiler, TilerParameters
-from aliby.io.omero import Dataset, Image
-from agora.abc import ParametersABC, ProcessABC
-from agora.io.writer import TilerWriter, BabyWriter, StateWriter
-from agora.io.reader import StateReader
-from agora.io.signal import Signal
-from extraction.core.extractor import Extractor, ExtractorParameters
-from extraction.core.functions.defaults import exparams_from_meta
-from postprocessor.core.processor import PostProcessor, PostProcessorParameters
-from postprocessor.compiler import ExperimentCompiler, PageOrganiser
-
-logging.basicConfig(
-    filename="aliby.log",
-    filemode="w",
-    format="%(name)s - %(levelname)s - %(message)s",
-    level=logging.DEBUG,
-)
-
-
-class PipelineParameters(ParametersABC):
-    def __init__(
-        self, general, tiler, baby, extraction, postprocessing, reporting=None
-    ):
-        self.general = general
-        self.tiler = tiler
-        self.baby = baby
-        self.extraction = extraction
-        self.postprocessing = postprocessing
-        self.reporting = reporting
-
-    @classmethod
-    def default(
-        cls,
-        general={},
-        tiler={},
-        baby={},
-        extraction={},
-        postprocessing={},
-        reporting={},
-    ):
-        """
-        Load unit test experiment
-        :expt_id: Experiment id
-        :directory: Output directory
-
-        Provides default parameters for the entire pipeline. This downloads the logfiles and sets the default
-        timepoints and extraction parameters from there.
-        """
-        expt_id = general.get("expt_id", 19993)
-        directory = Path(general.get("directory", "../data"))
-        with Dataset(int(expt_id), **general.get("server_info")) as conn:
-            directory = directory / conn.unique_name
-            if not directory.exists():
-                directory.mkdir(parents=True)
-                # Download logs to use for metadata
-            conn.cache_logs(directory)
-        meta = MetaData(directory, None).load_logs()
-        tps = meta["time_settings/ntimepoints"][0]
-        defaults = {
-            "general": dict(
-                id=expt_id,
-                distributed=0,
-                tps=tps,
-                directory=str(directory),
-                filter="",
-                earlystop=dict(
-                    min_tp=100,
-                    thresh_pos_clogged=0.3,
-                    thresh_trap_clogged=7,
-                    ntps_to_eval=5,
-                ),
-            )
-        }
-        defaults["tiler"] = TilerParameters.default().to_dict()
-        defaults["baby"] = BabyParameters.default().to_dict()
-        defaults["extraction"] = exparams_from_meta(meta)
-        defaults["postprocessing"] = PostProcessorParameters.default().to_dict()
-        for k in defaults.keys():
-            exec("defaults[k].update(" + k + ")")
-        return cls(**{k: v for k, v in defaults.items()})
-
-    def load_logs(self):
-        parsed_flattened = parse_logfiles(self.log_dir)
-        return parsed_flattened
-
-
-class Pipeline(ProcessABC):
-    """
-    A chained set of Pipeline elements connected through pipes.
-    Tiling, Segmentation,Extraction and Postprocessing should use their own default parameters.
-    These can be overriden passing the key:value of parameters to override to a PipelineParameters class
-
-    """
-
-    def __init__(self, parameters: PipelineParameters, store=None):
-        super().__init__(parameters)
-
-        if store is None:
-            store = self.parameters.general["directory"]
-        self.store = store
-
-    @classmethod
-    def from_yaml(cls, fpath):
-        # This is just a convenience function, think before implementing
-        # for other processes
-        return cls(parameters=PipelineParameters.from_yaml(fpath))
-
-    @classmethod
-    def from_existing_h5(cls, fpath):
-        with h5py.File(fpath, "r") as f:
-            pipeline_parameters = PipelineParameters.from_yaml(f.attrs["parameters"])
-
-        return cls(pipeline_parameters)
-
-    def run(self):
-        # Config holds the general information, use in main
-        # Steps holds the description of tasks with their parameters
-        # Steps: all holds general tasks
-        # steps: strain_name holds task for a given strain
-        config = self.parameters.to_dict()
-        expt_id = config["general"]["id"]
-        distributed = config["general"]["distributed"]
-        pos_filter = config["general"]["filter"]
-        root_dir = config["general"]["directory"]
-        root_dir = Path(root_dir)
-
-        print("Searching OMERO")
-        # Do all initialis
-        with Dataset(int(expt_id), **self.general["server_info"]) as conn:
-            image_ids = conn.get_images()
-            directory = root_dir / conn.unique_name
-            if not directory.exists():
-                directory.mkdir(parents=True)
-                # Download logs to use for metadata
-            conn.cache_logs(directory)
-
-        # Modify to the configuration
-        self.parameters.general["directory"] = directory
-        config["general"]["directory"] = directory
-
-        # Filter TODO integrate filter onto class and add regex
-        filt_int = lambda d, filt: {
-            k: v for i, (k, v) in enumerate(d.items()) if i == filt
-        }
-
-        filt_str = lambda d, filt: {
-            k: v for k, v in image_ids.items() if re.search(filt, k)
-        }
-
-        def pick_filter(image_ids, filt):
-            if isinstance(filt, str):
-                image_ids = filt_str(image_ids, filt)
-            elif isinstance(filt, int):
-                image_ids = filt_int(image_ids, filt)
-            return image_ids
-
-        if isinstance(pos_filter, list):
-            image_ids = {
-                k: v
-                for filt in pos_filter
-                for k, v in pick_filter(image_ids, filt).items()
-            }
-        else:
-            image_ids = pick_filter(image_ids, pos_filter)
-
-        assert len(image_ids), "No images to segment"
-
-        if distributed != 0:  # Gives the number of simultaneous processes
-            with Pool(distributed) as p:
-                results = p.map(lambda x: self.create_pipeline(x), image_ids.items())
-            return results
-        else:  # Sequential
-            results = []
-            for k, v in image_ids.items():
-                r = self.create_pipeline((k, v))
-                results.append(r)
-
-    def create_pipeline(self, image_id):
-        config = self.parameters.to_dict()
-        name, image_id = image_id
-        general_config = config["general"]
-        session = None
-        earlystop = general_config["earlystop"]
-        try:
-            directory = general_config["directory"]
-
-            with Image(image_id, **self.general["server_info"]) as image:
-                filename = f"{directory}/{image.name}.h5"
-                meta = MetaData(directory, filename)
-                from_start = True
-                trackers_state = None
-                if (
-                    not general_config.get("overwrite", False)
-                    and Path(filename).exists()
-                ):
-                    try:
-                        print(f"Existing file {filename} will be used.")
-                        with h5py.File(filename, "r") as f:
-                            tiler = Tiler.from_hdf5(image, filename)
-                            s = Signal(filename)
-                            process_from = (
-                                f.attrs["last_processed"]
-                                or s.get_raw("/general/None/extraction/volume").columns[
-                                    -1
-                                ]
-                                or 0
-                            )
-                            # get state array
-                            trackers_state = StateReader(
-                                filename
-                            ).get_formatted_states()
-                            tiler.n_processed = process_from
-                            process_from += 1
-                        from_start = False
-                    except:
-                        pass
-
-                if from_start:  # New experiment or overwriting
-                    try:
-                        os.remove(filename)
-                    except:
-                        pass
-
-                    process_from = 0
-                    meta.run()
-                    meta.add_fields(
-                        {"omero_id,": config["general"]["id"], "image_id": image_id}
-                    )
-                    try:
-                        tiler = Tiler.from_image(
-                            image, TilerParameters.from_dict(config["tiler"])
-                        )
-                    except:
-                        # Remove and try to run again?
-                        meta.add_fields({"end_status": "Untiled"})
-
-                writer = TilerWriter(filename)
-                session = initialise_tf(2)
-                runner = BabyRunner.from_tiler(
-                    BabyParameters.from_dict(config["baby"]), tiler
-                )
-                if trackers_state:
-                    runner.crawler.trackers_state = trackers_state
-
-                bwriter = BabyWriter(filename)
-                swriter = StateWriter(filename)
-
-                # Limit extraction parameters during run using the available channels in tiler
-                av_channels = set((*tiler.channels, "general"))
-                config["extraction"]["tree"] = {
-                    k: v
-                    for k, v in config["extraction"]["tree"].items()
-                    if k in av_channels
-                }
-                config["extraction"]["sub_bg"] = av_channels.intersection(
-                    config["extraction"]["sub_bg"]
-                )
-
-                av_channels_wsub = av_channels.union(
-                    [c + "_bgsub" for c in config["extraction"]["sub_bg"]]
-                )
-                for op in config["extraction"]["multichannel_ops"]:
-                    config["extraction"]["multichannel_ops"][op] = [
-                        x
-                        for x in config["extraction"]["multichannel_ops"]
-                        if len(x[0]) == len(av_channels_wsub.intersection(x[0]))
-                    ]
-                config["extraction"]["multichannel_ops"] = {
-                    k: v
-                    for k, v in config["extraction"]["multichannel_ops"].items()
-                    if len(v)
-                }
-
-                exparams = ExtractorParameters.from_dict(config["extraction"])
-                ext = Extractor.from_tiler(exparams, store=filename, tiler=tiler)
-
-                # RUN
-                # Adjust tps based on how many tps are available on the server
-                tps = min(general_config["tps"], image.data.shape[0])
-                frac_clogged_traps = 0
-                for i in tqdm(
-                    range(process_from, tps), desc=image.name, initial=process_from
-                ):
-                    if (
-                        frac_clogged_traps < earlystop["thresh_pos_clogged"]
-                        or i < earlystop["min_tp"]
-                    ):
-                        t = perf_counter()
-                        trap_info = tiler.run_tp(i)
-                        logging.debug(f"Timing:Trap:{perf_counter() - t}s")
-                        t = perf_counter()
-                        writer.write(trap_info, overwrite=[], tp=i)
-                        logging.debug(f"Timing:Writing-trap:{perf_counter() - t}s")
-                        t = perf_counter()
-                        seg = runner.run_tp(i)
-                        logging.debug(f"Timing:Segmentation:{perf_counter() - t}s")
-                        # logging.debug(
-                        #     f"Segmentation failed:Segmentation:{perf_counter() - t}s"
-                        # )
-                        t = perf_counter()
-                        bwriter.write(seg, overwrite=["mother_assign"], tp=i)
-                        logging.debug(f"Timing:Writing-baby:{perf_counter() - t}s")
-
-                        # TODO add time-skipping for cases when the
-                        # an interruption happens after writing segmentation but before extraction
-                        t = perf_counter()
-                        labels, masks = groupby_traps(
-                            seg["trap"],
-                            seg["cell_label"],
-                            seg["edgemasks"],
-                            tiler.n_traps,
-                        )
-                        tmp = ext.run(tps=[i], masks=masks, labels=labels)
-                        logging.debug(f"Timing:Extraction:{perf_counter() - t}s")
-                    else:  # Stop if more than X% traps are clogged
-                        logging.debug(
-                            f"EarlyStop:{earlystop['thresh_pos_clogged']*100}% traps clogged at time point {i}"
-                        )
-                        print(
-                            f"Stopping analysis at time {i} with {frac_clogged_traps} clogged traps"
-                        )
-                        meta.add_fields({"end_status": "Clogged"})
-                        break
-
-                    if (
-                        i > earlystop["min_tp"]
-                    ):  # Calculate the fraction of clogged traps
-                        frac_clogged_traps = self.check_earlystop(filename, earlystop)
-                        logging.debug(f"Quality:Clogged_traps:{frac_clogged_traps}")
-                        print("Frac clogged traps: ", frac_clogged_traps)
-
-                    # State Writer to recover interrupted experiments
-                    swriter.write(
-                        data=runner.crawler.tracker_states,
-                        overwrite=swriter.datatypes.keys(),
-                    )
-                    meta.add_fields({"last_processed": i})
-
-                    import pickle as pkl
-
-                    with open(
-                        Path(bwriter.file).parent / f"{i}_live_state.pkl", "wb"
-                    ) as f:
-                        pkl.dump(runner.crawler.tracker_states, f)
-                    with open(
-                        Path(bwriter.file).parent / f"{i}_read_state.pkl", "wb"
-                    ) as f:
-                        pkl.dump(StateReader(bwriter.file).get_formatted_states(), f)
-                # Run post processing
-
-                meta.add_fields({"end_status": "Success"})
-                post_proc_params = PostProcessorParameters.from_dict(
-                    self.parameters.postprocessing
-                ).to_dict()
-                PostProcessor(filename, post_proc_params).run()
-
-                return 1
-
-        except Exception as e:  # bug in the trap getting
-            logging.exception(
-                f"Caught exception in worker thread (x = {name}):", exc_info=True
-            )
-            print(f"Caught exception in worker thread (x = {name}):")
-            # This prints the type, value, and stack trace of the
-            # current exception being handled.
-            traceback.print_exc()
-            print()
-            raise e
-        finally:
-            if session:
-                session.close()
-
-        try:
-            compiler = ExperimentCompiler(None, filepath)
-            tmp = compiler.run()
-            po = PageOrganiser(tmp, grid_spec=(3, 2))
-            po.plot()
-            po.save(fullpath / f"{directory}report.pdf")
-        except Exception as e:
-            print(e)
-
-    def check_earlystop(self, filename, es_parameters):
-        s = Signal(filename)
-        df = s["/extraction/general/None/area"]
-        frac_clogged_traps = (
-            df[df.columns[-1 - es_parameters["ntps_to_eval"] : -1]]
-            .dropna(how="all")
-            .notna()
-            .groupby("trap")
-            .apply(sum)
-            .apply(np.mean, axis=1)
-            > es_parameters["thresh_trap_clogged"]
-        ).mean()
-        return frac_clogged_traps
-
-
-def groupby_traps(traps, labels, edgemasks, ntraps):
-    # Group data by traps to pass onto extractor without re-reading hdf5
-    iterators = [
-        groupby(zip(traps, dset), lambda x: x[0]) for dset in (labels, edgemasks)
-    ]
-    label_d = {key: [x[1] for x in group] for key, group in iterators[0]}
-    mask_d = {
-        key: np.dstack([ndimage.morphology.binary_fill_holes(x[1]) for x in group])
-        for key, group in iterators[1]
-    }
-    labels = {i: label_d.get(i, []) for i in range(ntraps)}
-    masks = {i: mask_d.get(i, []) for i in range(ntraps)}
-
-    return labels, masks

aliby/post_processing.py

-"""
-Post-processing utilities
-
-Notes: I don't have statistics on ranges of radii for each of the knots in
-the radial spline representation, but we regularly extract the average of
-these radii for each cell. So, depending on camera/lens, we get:
-    * 60x evolve: mean radii of 2-14 pixels (and measured areas of 30-750
-    pixels^2)
-    * 60x prime95b: mean radii of 3-24 pixels (and measured areas of 60-2000
-	pixels^2)
-
-And I presume that for a 100x lens we would get an ~5/3 increase over those
-values.
-
-In terms of the current volume estimation method, it's currently only
-implemented in the AnalysisToolbox repository, but it's super simple:
-
-mVol = 4/3*pi*sqrt(mArea/pi).^3
-
-where mArea is simply the sum of pixels for that cell.
-"""
-import matplotlib.pyplot as plt
-import numpy as np
-from mpl_toolkits.mplot3d.art3d import Poly3DCollection
-from scipy import ndimage
-from skimage.morphology import erosion, ball
-from skimage import measure, draw
-
-
-def my_ball(radius):
-    """Generates a ball-shaped structuring element.
-
-    This is the 3D equivalent of a disk.
-    A pixel is within the neighborhood if the Euclidean distance between
-    it and the origin is no greater than radius.
-
-    Parameters
-    ----------
-    radius : int
-        The radius of the ball-shaped structuring element.
-
-    Other Parameters
-    ----------------
-    dtype : data-type
-        The data type of the structuring element.
-
-    Returns
-    -------
-    selem : ndarray
-        The structuring element where elements of the neighborhood
-        are 1 and 0 otherwise.
-    """
-    n = 2 * radius + 1
-    Z, Y, X = np.mgrid[-radius:radius:n * 1j,
-              -radius:radius:n * 1j,
-              -radius:radius:n * 1j]
-    X **= 2
-    Y **= 2
-    Z **= 2
-    X += Y
-    X += Z
-    # s = X ** 2 + Y ** 2 + Z ** 2
-    return X <= radius * radius
-
-def circle_outline(r):
-    return ellipse_perimeter(r, r)
-
-def ellipse_perimeter(x, y):
-    im_shape = int(2*max(x, y) + 1)
-    img = np.zeros((im_shape, im_shape), dtype=np.uint8)
-    rr, cc = draw.ellipse_perimeter(int(im_shape//2), int(im_shape//2),
-                                    int(x), int(y))
-    img[rr, cc] = 1
-    return np.pad(img, 1)
-
-def capped_cylinder(x, y):
-    max_size = (y + 2*x + 2)
-    pixels = np.zeros((max_size, max_size))
-
-    rect_start = ((max_size-x)//2, x + 1)
-    rr, cc = draw.rectangle_perimeter(rect_start, extent=(x, y),
-                                     shape=(max_size, max_size))
-    pixels[rr, cc] = 1
-    circle_centres = [(max_size//2 - 1, x),
-                      (max_size//2 - 1, max_size - x - 1 )]
-    for r, c in circle_centres:
-        rr, cc = draw.circle_perimeter(r, c, (x + 1)//2,
-                                       shape=(max_size, max_size))
-        pixels[rr, cc] = 1
-    pixels = ndimage.morphology.binary_fill_holes(pixels)
-    pixels ^= erosion(pixels)
-    return pixels
-
-def volume_of_sphere(radius):
-    return 4 / 3 * np.pi * radius**3
-
-def plot_voxels(voxels):
-    verts, faces, normals, values = measure.marching_cubes_lewiner(
-        voxels, 0)
-    fig = plt.figure(figsize=(10, 10))
-    ax = fig.add_subplot(111, projection='3d')
-    mesh = Poly3DCollection(verts[faces])
-    mesh.set_edgecolor('k')
-    ax.add_collection3d(mesh)
-    ax.set_xlim(0, voxels.shape[0])
-    ax.set_ylim(0, voxels.shape[1])
-    ax.set_zlim(0, voxels.shape[2])
-    plt.tight_layout()
-    plt.show()
-
-# Volume estimation
-def union_of_spheres(outline, shape='my_ball', debug=False):
-    filled = ndimage.binary_fill_holes(outline)
-    nearest_neighbor = ndimage.morphology.distance_transform_edt(
-        outline == 0) * filled
-    voxels = np.zeros((filled.shape[0], filled.shape[1], max(filled.shape)))
-    c_z = voxels.shape[2] // 2
-    for x,y in zip(*np.where(filled)):
-        radius = nearest_neighbor[(x,y)]
-        if radius > 0:
-            if shape == 'ball':
-                b = ball(radius)
-            elif shape == 'my_ball':
-                b = my_ball(radius)
-            else:
-                raise ValueError(f"{shape} is not an accepted value for "
-                                 f"shape.")
-            centre_b = ndimage.measurements.center_of_mass(b)
-
-            I,J,K = np.ogrid[:b.shape[0], :b.shape[1], :b.shape[2]]
-            voxels[I + int(x - centre_b[0]), J + int(y - centre_b[1]),
-                   K + int(c_z - centre_b[2])] += b
-    if debug:
-        plot_voxels(voxels)
-    return voxels.astype(bool).sum()
-
-def improved_uos(outline, shape='my_ball', debug=False):
-    filled = ndimage.binary_fill_holes(outline)
-    nearest_neighbor = ndimage.morphology.distance_transform_edt(
-        outline == 0) * filled
-    voxels = np.zeros((filled.shape[0], filled.shape[1], max(filled.shape)))
-    c_z = voxels.shape[2] // 2
-
-    while np.any(nearest_neighbor != 0):
-        radius = np.max(nearest_neighbor)
-        x, y = np.argwhere(nearest_neighbor == radius)[0]
-        if shape == 'ball':
-            b = ball(np.ceil(radius))
-        elif shape == 'my_ball':
-            b = my_ball(np.ceil(radius))
-        else:
-            raise ValueError(f"{shape} is not an accepted value for shape")
-        centre_b = ndimage.measurements.center_of_mass(b)
-
-        I, J, K = np.ogrid[:b.shape[0], :b.shape[1], :b.shape[2]]
-        voxels[I + int(x - centre_b[0]), J + int(y - centre_b[1]),
-               K + int(c_z - centre_b[2])] += b
-
-        # Use the central disk of the ball from voxels to get the circle
-        # = 0 if nn[x,y] < r else nn[x,y]
-        rr, cc = draw.circle(x, y, np.ceil(radius), nearest_neighbor.shape)
-        nearest_neighbor[rr, cc] = 0
-    if debug:
-        plot_voxels(voxels)
-    return voxels.astype(bool).sum()
-
-def conical(outline, debug=False):
-    nearest_neighbor = ndimage.morphology.distance_transform_edt(
-        outline == 0) * ndimage.binary_fill_holes(outline)
-    if debug:
-        hf = plt.figure()
-        ha = hf.add_subplot(111, projection='3d')
-
-        X, Y = np.meshgrid(np.arange(nearest_neighbor.shape[0]),
-                           np.arange(nearest_neighbor.shape[1]))
-        ha.plot_surface(X, Y, nearest_neighbor)
-        plt.show()
-    return 4 * nearest_neighbor.sum()
-
-def volume(outline, method='spheres'):
-    if method=='conical':
-        return conical(outline)
-    elif method=='spheres':
-        return union_of_spheres(outline)
-    else:
-        raise ValueError(f"Method {method} not implemented.")
-
-def circularity(outline):
-    pass
\ No newline at end of file

aliby/results.py

-"""Pipeline results classes and utilities"""
-
-
-class SegmentationResults:
-    """
-    Object storing the data from the Segmentation pipeline.
-    Everything is stored as an `AttributeDict`, which is a `defaultdict` where
-    you can get elements as attributes.
-
-    In addition, it implements:
-     - IO functionality (read from file, write to file)
-    """
-    def __init__(self, raw_expt):
-        pass
-
-
-
-
-class CellResults:
-    """
-    Results on a set of cells TODO: what set of cells, how?
-
-    Contains:
-    * cellInf describing which cells are taken into account
-    * annotations on the cell
-    * segmentation maps of the cell TODO: how to define and save this?
-    * trapLocations TODO: why is this not part of cellInf?
-    """
-
-    def __init__(self, cellInf=None, annotations=None, segmentation=None,
-                 trapLocations=None):
-        self._cellInf = cellInf
-        self._annotations = annotations
-        self._segmentation = segmentation
-        self._trapLocations = trapLocations

aliby/tile/tiler.py

-"""Segment/segmented pipelines.
-Includes splitting the image into traps/parts,
-cell segmentation, nucleus segmentation."""
-import warnings
-from functools import lru_cache
-
-import h5py
-import numpy as np
-
-from pathlib import Path, PosixPath
-
-from skimage.registration import phase_cross_correlation
-
-from agora.abc import ParametersABC, ProcessABC
-from aliby.tile.traps import segment_traps
-
-from agora.io.writer import load_attributes
-
-trap_template_directory = Path(__file__).parent / "trap_templates"
-# TODO do we need multiple templates, one for each setup?
-trap_template = np.array([])  # np.load(trap_template_directory / "trap_prime.npy")
-
-
-def get_tile_shapes(x, tile_size, max_shape):
-    half_size = tile_size // 2
-    xmin = int(x[0] - half_size)
-    ymin = max(0, int(x[1] - half_size))
-    if xmin + tile_size > max_shape[0]:
-        xmin = max_shape[0] - tile_size
-    if ymin + tile_size > max_shape[1]:
-        ymin = max_shape[1] - tile_size
-    return xmin, xmin + tile_size, ymin, ymin + tile_size
-
-
-###################### Dask versions ########################
-class Trap:
-    def __init__(self, centre, parent, size, max_size):
-        self.centre = centre
-        self.parent = parent  # Used to access drifts
-        self.size = size
-        self.half_size = size // 2
-        self.max_size = max_size
-
-    def padding_required(self, tp):
-        """Check if we need to pad the trap image for this time point."""
-        try:
-            assert all(self.at_time(tp) - self.half_size >= 0)
-            assert all(self.at_time(tp) + self.half_size <= self.max_size)
-        except AssertionError:
-            return True
-        return False
-
-    def at_time(self, tp):
-        """Return trap centre at time tp"""
-        drifts = self.parent.drifts
-        return self.centre - np.sum(drifts[: tp + 1], axis=0)
-
-    def as_tile(self, tp):
-        """Return trap in the OMERO tile format of x, y, w, h
-
-        Also returns the padding necessary for this tile.
-        """
-        x, y = self.at_time(tp)
-        # tile bottom corner
-        x = int(x - self.half_size)
-        y = int(y - self.half_size)
-        return x, y, self.size, self.size
-
-    def as_range(self, tp):
-        """Return trap in a range format, two slice objects that can be used in Arrays"""
-        x, y, w, h = self.as_tile(tp)
-        return slice(x, x + w), slice(y, y + h)
-
-
-class TrapLocations:
-    def __init__(self, initial_location, tile_size, max_size=1200, drifts=[]):
-        self.tile_size = tile_size
-        self.max_size = max_size
-        self.initial_location = initial_location
-        self.traps = [
-            Trap(centre, self, tile_size, max_size) for centre in initial_location
-        ]
-        self.drifts = drifts
-
-        # @classmethod
-        # def from_source(cls, fpath: str):
-        #     with h5py.File(fpath, "r") as f:
-        #         # TODO read tile size from file metadata
-        #         drifts = f["trap_info/drifts"][()].tolist()
-        #         tlocs = cls(f["trap_info/trap_locations"][()], tile_size=96, drifts=drifts)
-
-        # return tlocs
-
-    @property
-    def shape(self):
-        return len(self.traps), len(self.drifts)
-
-    def __len__(self):
-        return len(self.traps)
-
-    def __iter__(self):
-        yield from self.traps
-
-    def padding_required(self, tp):
-        return any([trap.padding_required(tp) for trap in self.traps])
-
-    def to_dict(self, tp):
-        res = dict()
-        if tp == 0:
-            res["trap_locations"] = self.initial_location
-            res["attrs/tile_size"] = self.tile_size
-            res["attrs/max_size"] = self.max_size
-        res["drifts"] = np.expand_dims(self.drifts[tp], axis=0)
-        # res["processed_timepoints"] = tp
-        return res
-
-    @classmethod
-    def read_hdf5(cls, file):
-        with h5py.File(file, "r") as hfile:
-            trap_info = hfile["trap_info"]
-            initial_locations = trap_info["trap_locations"][()]
-            drifts = trap_info["drifts"][()].tolist()
-            max_size = trap_info.attrs["max_size"]
-            tile_size = trap_info.attrs["tile_size"]
-        trap_locs = cls(initial_locations, tile_size, max_size=max_size)
-        trap_locs.drifts = drifts
-        return trap_locs
-
-
-class TilerParameters(ParametersABC):
-    def __init__(
-        self, tile_size: int, ref_channel: str, ref_z: int, template_name: str = None
-    ):
-        self.tile_size = tile_size
-        self.ref_channel = ref_channel
-        self.ref_z = ref_z
-        self.template_name = template_name
-
-    @classmethod
-    def from_template(cls, template_name: str, ref_channel: str, ref_z: int):
-        return cls(template.shape[0], ref_channel, ref_z, template_path=template_name)
-
-    @classmethod
-    def default(cls):
-        return cls(117, "Brightfield", 0)
-
-
-class Tiler(ProcessABC):
-    """A dummy TimelapseTiler object fora Dask Demo.
-
-    Does trap finding and image registration."""
-
-    def __init__(
-        self,
-        image,
-        metadata,
-        parameters: TilerParameters,
-        trap_locs=None,
-    ):
-        super().__init__(parameters)
-        self.image = image
-        self.channels = metadata["channels"]
-        self.ref_channel = self.get_channel_index(parameters.ref_channel)
-        self.trap_locs = trap_locs
-
-    @classmethod
-    def from_image(cls, image, parameters: TilerParameters):
-        return cls(image.data, image.metadata, parameters)
-
-    @classmethod
-    def from_hdf5(cls, image, filepath):
-        trap_locs = TrapLocations.read_hdf5(filepath)
-        metadata = load_attributes(filepath)
-        metadata["channels"] = metadata["channels/channel"].tolist()
-        return cls(
-            image.data,
-            metadata,
-            TilerParameters.default(),
-            trap_locs=trap_locs,
-        )
-
-    @lru_cache(maxsize=2)
-    def get_tc(self, t, c):
-        # Get image
-        full = self.image[t, c].compute()  # FORCE THE CACHE
-        return full
-
-    @property
-    def shape(self):
-        c, t, z, y, x = self.image.shape
-        return (c, t, x, y, z)
-
-    @property
-    def n_processed(self):
-        if not hasattr(self, "_n_processed"):
-            self._n_processed = 0
-        return self._n_processed
-
-    @n_processed.setter
-    def n_processed(self, value):
-        self._n_processed = value
-
-    @property
-    def n_traps(self):
-        return len(self.trap_locs)
-
-    @property
-    def finished(self):
-        return self.n_processed == self.image.shape[0]
-
-    def _initialise_traps(self, tile_size):
-        """Find initial trap positions.
-
-        Removes all those that are too close to the edge so no padding is necessary.
-        """
-        half_tile = tile_size // 2
-        max_size = min(self.image.shape[-2:])
-        initial_image = self.image[
-            0, self.ref_channel, self.ref_z
-        ]  # First time point, first channel, first z-position
-        trap_locs = segment_traps(initial_image, tile_size)
-        trap_locs = [
-            [x, y]
-            for x, y in trap_locs
-            if half_tile < x < max_size - half_tile
-            and half_tile < y < max_size - half_tile
-        ]
-        self.trap_locs = TrapLocations(trap_locs, tile_size)
-
-    def find_drift(self, tp):
-        # TODO check that the drift doesn't move any tiles out of the image, remove them from list if so
-        prev_tp = max(0, tp - 1)
-        drift, error, _ = phase_cross_correlation(
-            self.image[prev_tp, self.ref_channel, self.ref_z],
-            self.image[tp, self.ref_channel, self.ref_z],
-        )
-        if 0 < tp < len(self.trap_locs.drifts):
-            self.trap_locs.drifts[tp] = drift.tolist()
-        else:
-            self.trap_locs.drifts.append(drift.tolist())
-
-    def get_tp_data(self, tp, c):
-        traps = []
-        full = self.get_tc(tp, c)
-        # if self.trap_locs.padding_required(tp):
-        for trap in self.trap_locs:
-            ndtrap = self.ifoob_pad(full, trap.as_range(tp))
-
-            traps.append(ndtrap)
-        return np.stack(traps)
-
-    def get_trap_data(self, trap_id, tp, c):
-        full = self.get_tc(tp, c)
-        trap = self.trap_locs.traps[trap_id]
-        ndtrap = self.ifoob_pad(full, trap.as_range(tp))
-
-        return ndtrap
-
-    @staticmethod
-    def ifoob_pad(full, slices):
-        """
-        Returns the slices padded if it is out of bounds
-
-        Parameters:
-        ----------
-        full: (zstacks, max_size, max_size) ndarray
-        Entire position with zstacks as first axis
-        slices: tuple of two slices
-        Each slice indicates an axis to index
-
-
-        Returns
-        Trap for given slices, padded with median if needed, or np.nan if the padding is too much
-        """
-        max_size = full.shape[-1]
-
-        y, x = [slice(max(0, s.start), min(max_size, s.stop)) for s in slices]
-        trap = full[:, y, x]
-
-        padding = np.array(
-            [(-min(0, s.start), -min(0, max_size - s.stop)) for s in slices]
-        )
-        if padding.any():
-            tile_size = slices[0].stop - slices[0].start
-            if (padding > tile_size / 4).any():
-                trap = np.full((full.shape[0], tile_size, tile_size), np.nan)
-            else:
-
-                trap = np.pad(trap, [[0, 0]] + padding.tolist(), "median")
-
-        return trap
-
-    def run_tp(self, tp):
-        # assert tp >= self.n_processed, "Time point already processed"
-        # TODO check contiguity?
-        if self.n_processed == 0:
-            self._initialise_traps(self.tile_size)
-        self.find_drift(tp)  # Get drift
-        # update n_processed
-        self.n_processed = tp + 1
-        # Return result for writer
-        return self.trap_locs.to_dict(tp)
-
-    def run(self, tp):
-        if self.n_processed == 0:
-            self._initialise_traps(self.tile_size)
-        self.find_drift(tp)  # Get drift
-        # update n_processed
-        self.n_processed += 1
-        # Return result for writer
-        return self.trap_locs.to_dict(tp)
-
-    # The next set of functions are necessary for the extraction object
-    def get_traps_timepoint(self, tp, tile_size=None, channels=None, z=None):
-        # FIXME we currently ignore the tile size
-        # FIXME can we ignore z(always  give)
-        res = []
-        for c in channels:
-            val = self.get_tp_data(tp, c)[:, z]  # Only return requested z
-            # positions
-            # Starts at traps, z, y, x
-            # Turn to Trap, C, T, X, Y, Z order
-            val = val.swapaxes(1, 3).swapaxes(1, 2)
-            val = np.expand_dims(val, axis=1)
-            res.append(val)
-        return np.stack(res, axis=1)
-
-    def get_channel_index(self, item):
-        for i, ch in enumerate(self.channels):
-            if item in ch:
-                return i
-
-    def get_position_annotation(self):
-        # TODO required for matlab support
-        return None