1
0
mirror of https://github.com/gsi-upm/senpy synced 2024-11-24 09:02:28 +00:00

Add 'community-plugins/' from commit '4c73797246c6aff8d055abfef73d3f0d34b933a8'

git-subtree-dir: community-plugins
git-subtree-mainline: 7f712952be
git-subtree-split: 4c73797246
This commit is contained in:
J. Fernando Sánchez 2023-09-20 13:32:30 +02:00
commit e1d888ebd6
77 changed files with 11412 additions and 0 deletions

View File

@ -0,0 +1,2 @@
.*
data

65
community-plugins/.gitignore vendored Normal file
View File

@ -0,0 +1,65 @@
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
# C extensions
*.so
# Distribution / packaging
.Python
env/
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
*.egg-info/
.installed.cfg
*.egg
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*,cover
# Translations
*.mo
*.pot
# Django stuff:
*.log
# Sphinx documentation
docs/_build/
# PyBuilder
target/
.*
*.pyc
**/__pycache__
*/wordnet1.6
*/Corpus
*/a-hierarchy.xml
*/a-synsets.xml
*/wn16.txt

View File

@ -0,0 +1,51 @@
# Uncomment if you want to use docker-in-docker
# image: gsiupm/dockermake:latest
# services:
# - docker:dind
# When using dind, it's wise to use the overlayfs driver for
# improved performance.
variables:
GIT_SUBMODULE_STRATEGY: recursive
stages:
- build
- test
- push
- deploy
- clean
before_script:
- make -e login
build:
stage: build
script:
- make -e docker-build
only:
- master
- fix-makefiles
test:
stage: test
script:
- make -e test
push:
stage: push
script:
- make -e docker-push
deploy:
stage: deploy
script:
- make -e deploy
only:
- master
- fix-makefiles
clean :
stage: clean
script:
- make -e clean
when: manual

3
community-plugins/.gitmodules vendored Normal file
View File

@ -0,0 +1,3 @@
[submodule "data"]
path = data
url = ../data

View File

@ -0,0 +1,27 @@
These makefiles are recipes for several common tasks in different types of projects.
To add them to your project, simply do:
```
git remote add makefiles ssh://git@lab.cluster.gsi.dit.upm.es:2200/docs/templates/makefiles.git
git subtree add --prefix=.makefiles/ makefiles master
touch Makefile
echo "include .makefiles/base.mk" >> Makefile
```
Now you can take advantage of the recipes.
For instance, to add useful targets for a python project, just add this to your Makefile:
```
include .makefiles/python.mk
```
You may need to set special variables like the name of your project or the python versions you're targetting.
Take a look at each specific `.mk` file for more information, and the `Makefile` in the [senpy](https://lab.cluster.gsi.dit.upm.es/senpy/senpy) project for a real use case.
If you update the makefiles from your repository, make sure to push the changes for review in upstream (this repository):
```
make makefiles-push
```
It will automatically commit all unstaged changes in the .makefiles folder.

View File

@ -0,0 +1,36 @@
export
NAME ?= $(shell basename $(CURDIR))
VERSION ?= $(shell git describe --tags --dirty 2>/dev/null)
ifeq ($(VERSION),)
VERSION:=unknown
endif
# Get the location of this makefile.
MK_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
-include .env
-include ../.env
help: ## Show this help.
@fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/\(.*:\)[^#]*##\s*\(.*\)/\1\t\2/' | column -t -s " "
config: ## Load config from the environment. You should run it once in every session before other tasks. Run: eval $(make config)
@awk '{ print "export " $$0}' ../.env
@awk '{ print "export " $$0}' .env
@echo "# Please, run: "
@echo "# eval \$$(make config)"
# If you need to run a command on the key/value pairs, use this:
# @awk '{ split($$0, a, "="); "echo " a[2] " | base64 -w 0" |& getline b64; print "export " a[1] "=" a[2]; print "export " a[1] "_BASE64=" b64}' .env
ci: ## Run a task using gitlab-runner. Only use to debug problems in the CI pipeline
gitlab-runner exec shell --builds-dir '.builds' --env CI_PROJECT_NAME=$(NAME) ${action}
include $(MK_DIR)/makefiles.mk
include $(MK_DIR)/docker.mk
include $(MK_DIR)/git.mk
info:: ## List all variables
env
.PHONY:: config help ci

View File

@ -0,0 +1,51 @@
ifndef IMAGENAME
ifdef CI_REGISTRY_IMAGE
IMAGENAME=$(CI_REGISTRY_IMAGE)
else
IMAGENAME=$(NAME)
endif
endif
IMAGEWTAG?=$(IMAGENAME):$(VERSION)
DOCKER_FLAGS?=$(-ti)
DOCKER_CMD?=
docker-login: ## Log in to the registry. It will only be used in the server, or when running a CI task locally (if CI_BUILD_TOKEN is set).
ifeq ($(CI_BUILD_TOKEN),)
@echo "Not logging in to the docker registry" "$(CI_REGISTRY)"
else
@docker login -u gitlab-ci-token -p $(CI_BUILD_TOKEN) $(CI_REGISTRY)
endif
ifeq ($(HUB_USER),)
@echo "Not logging in to global the docker registry"
else
@docker login -u $(HUB_USER) -p $(HUB_PASSWORD)
endif
docker-clean: ## Remove docker credentials
ifeq ($(HUB_USER),)
else
@docker logout
endif
docker-run: ## Build a generic docker image
docker run $(DOCKER_FLAGS) $(IMAGEWTAG) $(DOCKER_CMD)
docker-build: ## Build a generic docker image
docker build . -t $(IMAGEWTAG)
docker-push: docker-build docker-login ## Push a generic docker image
docker push $(IMAGEWTAG)
docker-latest-push: docker-build ## Push the latest image
docker tag $(IMAGEWTAG) $(IMAGENAME)
docker push $(IMAGENAME)
login:: docker-login
clean:: docker-clean
docker-info:
@echo IMAGEWTAG=${IMAGEWTAG}
.PHONY:: docker-login docker-clean login clean

View File

@ -0,0 +1,28 @@
commit:
git commit -a
tag:
git tag ${VERSION}
git-push::
git push --tags -u origin HEAD
git-pull:
git pull --all
push-github: ## Push the code to github. You need to set up GITHUB_DEPLOY_KEY
ifeq ($(GITHUB_DEPLOY_KEY),)
else
$(eval KEY_FILE := "$(shell mktemp)")
@printf '%b' '$(GITHUB_DEPLOY_KEY)' > $(KEY_FILE)
@git remote rm github-deploy || true
git remote add github-deploy $(GITHUB_REPO)
-@GIT_SSH_COMMAND="ssh -i $(KEY_FILE)" git fetch github-deploy $(CI_COMMIT_REF_NAME)
@GIT_SSH_COMMAND="ssh -i $(KEY_FILE)" git push github-deploy HEAD:$(CI_COMMIT_REF_NAME)
rm $(KEY_FILE)
endif
push:: git-push
pull:: git-pull
.PHONY:: commit tag push git-push git-pull push-github

View File

@ -0,0 +1,51 @@
# Deployment with Kubernetes
# KUBE_CA_PEM_FILE is the path of a certificate file. It automatically set by GitLab
# if you enable Kubernetes integration in a project.
#
# As of this writing, Kubernetes integration can not be set on a group level, so it has to
# be manually set in every project.
# Alternatively, we use a custom KUBE_CA_BUNDLE environment variable, which can be set at
# the group level. In this case, the variable contains the whole content of the certificate,
# which we dump to a temporary file
#
# Check if the KUBE_CA_PEM_FILE exists. Otherwise, create it from KUBE_CA_BUNDLE
KUBE_CA_TEMP=false
ifndef KUBE_CA_PEM_FILE
KUBE_CA_PEM_FILE:=$$PWD/.ca.crt
CREATED:=$(shell printf '%b\n' '$(KUBE_CA_BUNDLE)' > $(KUBE_CA_PEM_FILE))
endif
KUBE_TOKEN?=""
KUBE_NAMESPACE?=$(NAME)
KUBECTL=docker run --rm -v $(KUBE_CA_PEM_FILE):/tmp/ca.pem -i lachlanevenson/k8s-kubectl --server="$(KUBE_URL)" --token="$(KUBE_TOKEN)" --certificate-authority="/tmp/ca.pem" -n $(KUBE_NAMESPACE)
CI_COMMIT_REF_NAME?=master
info:: ## Print variables. Useful for debugging.
@echo "#KUBERNETES"
@echo KUBE_URL=$(KUBE_URL)
@echo KUBE_CA_PEM_FILE=$(KUBE_CA_PEM_FILE)
@echo KUBE_CA_BUNDLE=$$KUBE_CA_BUNDLE
@echo KUBE_TOKEN=$(KUBE_TOKEN)
@echo KUBE_NAMESPACE=$(KUBE_NAMESPACE)
@echo KUBECTL=$(KUBECTL)
@echo "#CI"
@echo CI_PROJECT_NAME=$(CI_PROJECT_NAME)
@echo CI_REGISTRY=$(CI_REGISTRY)
@echo CI_REGISTRY_USER=$(CI_REGISTRY_USER)
@echo CI_COMMIT_REF_NAME=$(CI_COMMIT_REF_NAME)
@echo "CREATED=$(CREATED)"
#
# Deployment and advanced features
#
deploy: ## Deploy to kubernetes using the credentials in KUBE_CA_PEM_FILE (or KUBE_CA_BUNDLE ) and TOKEN
@ls k8s/*.yaml k8s/*.yml k8s/*.tmpl 2>/dev/null || true
@cat k8s/*.yaml k8s/*.yml k8s/*.tmpl 2>/dev/null | envsubst | $(KUBECTL) apply -f -
deploy-check: ## Get the deployed configuration.
@$(KUBECTL) get deploy,pods,svc,ingress
.PHONY:: info deploy deploy-check

View File

@ -0,0 +1,17 @@
makefiles-remote:
@git remote add makefiles ssh://git@lab.cluster.gsi.dit.upm.es:2200/docs/templates/makefiles.git 2>/dev/null || true
makefiles-commit: makefiles-remote
git add -f .makefiles
git commit -em "Updated makefiles from ${NAME}"
makefiles-push:
git subtree push --prefix=.makefiles/ makefiles $(NAME)
makefiles-pull: makefiles-remote
git subtree pull --prefix=.makefiles/ makefiles master --squash
pull:: makefiles-pull
push:: makefiles-push
.PHONY:: makefiles-remote makefiles-commit makefiles-push makefiles-pull pull push

View File

@ -0,0 +1,5 @@
init: ## Init pre-commit hooks (i.e. enforcing format checking before allowing a commit)
pip install --user pre-commit
pre-commit install
.PHONY:: init

View File

@ -0,0 +1,100 @@
PYVERSIONS ?= 3.5
PYMAIN ?= $(firstword $(PYVERSIONS))
TARNAME ?= $(NAME)-$(VERSION).tar.gz
VERSIONFILE ?= $(NAME)/VERSION
DEVPORT ?= 6000
.FORCE:
version: .FORCE
@echo $(VERSION) > $(VERSIONFILE)
@echo $(VERSION)
yapf: ## Format python code
yapf -i -r $(NAME)
yapf -i -r tests
dockerfiles: $(addprefix Dockerfile-,$(PYVERSIONS)) ## Generate dockerfiles for each python version
@unlink Dockerfile >/dev/null
ln -s Dockerfile-$(PYMAIN) Dockerfile
Dockerfile-%: Dockerfile.template ## Generate a specific dockerfile (e.g. Dockerfile-2.7)
sed "s/{{PYVERSION}}/$*/" Dockerfile.template > Dockerfile-$*
quick_build: $(addprefix build-, $(PYMAIN))
build: $(addprefix build-, $(PYVERSIONS)) ## Build all images / python versions
build-%: version Dockerfile-% ## Build a specific version (e.g. build-2.7)
docker build -t '$(IMAGEWTAG)-python$*' --cache-from $(IMAGENAME):python$* -f Dockerfile-$* .;
dev-%: ## Launch a specific development environment using docker (e.g. dev-2.7)
@docker start $(NAME)-dev$* || (\
$(MAKE) build-$*; \
docker run -d -w /usr/src/app/ -p $(DEVPORT):5000 -v $$PWD:/usr/src/app --entrypoint=/bin/bash -ti --name $(NAME)-dev$* '$(IMAGEWTAG)-python$*'; \
)\
docker exec -ti $(NAME)-dev$* bash
dev: dev-$(PYMAIN) ## Launch a development environment using docker, using the default python version
quick_test: test-$(PYMAIN)
test-%: ## Run setup.py from in an isolated container, built from the base image. (e.g. test-2.7)
# This speeds tests up because the image has most (if not all) of the dependencies already.
docker rm $(NAME)-test-$* || true
docker create -ti --name $(NAME)-test-$* --entrypoint="" -w /usr/src/app/ $(IMAGENAME):python$* python setup.py test
docker cp . $(NAME)-test-$*:/usr/src/app
docker start -a $(NAME)-test-$*
test: $(addprefix test-,$(PYVERSIONS)) ## Run the tests with the main python version
run-%: build-%
docker run --rm -p $(DEVPORT):5000 -ti '$(IMAGEWTAG)-python$(PYMAIN)' --default-plugins
run: run-$(PYMAIN)
# Pypy - Upload a package
dist/$(TARNAME): version
python setup.py sdist;
sdist: dist/$(TARNAME) ## Generate the distribution file (wheel)
pip_test-%: sdist ## Test the distribution file using pip install and a specific python version (e.g. pip_test-2.7)
docker run --rm -v $$PWD/dist:/dist/ python:$* pip install /dist/$(TARNAME);
pip_test: $(addprefix pip_test-,$(PYVERSIONS)) ## Test pip installation with the main python version
pip_upload: pip_test ## Upload package to pip
python setup.py sdist upload ;
# Pushing to docker
push-latest: $(addprefix push-latest-,$(PYVERSIONS)) ## Push the "latest" tag to dockerhub
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGENAME)'
docker push '$(IMAGENAME):latest'
docker push '$(IMAGEWTAG)'
push-latest-%: build-% ## Push the latest image for a specific python version
docker tag $(IMAGENAME):$(VERSION)-python$* $(IMAGENAME):python$*
docker push $(IMAGENAME):$(VERSION)-python$*
docker push $(IMAGENAME):python$*
push-%: build-% ## Push the image of the current version (tagged). e.g. push-2.7
docker push $(IMAGENAME):$(VERSION)-python$*
push:: $(addprefix push-,$(PYVERSIONS)) ## Push an image with the current version for every python version
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker push $(IMAGENAME):$(VERSION)
clean:: ## Clean older docker images and containers related to this project and dev environments
@docker stop $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
@docker rm $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
@docker ps -a | grep $(IMAGENAME) | awk '{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1;}}' | xargs docker rm -v 2>/dev/null|| true
@docker images | grep $(IMAGENAME) | awk '{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1":"$$2;}}' | xargs docker rmi 2>/dev/null|| true
.PHONY:: yapf dockerfiles Dockerfile-% quick_build build build-% dev-% quick-dev test quick_test push-latest push-latest-% push-% push version .FORCE

View File

@ -0,0 +1,12 @@
language: python
python:
- "2.7"
- "3.4"
env:
- PLUGIN=example-plugin
- PLUGIN=sentiText
install:
- "pip install senpy pytest"
- "python -m senpy --only-install -f $PLUGIN"
script:
- "py.test $PLUGIN"

View File

@ -0,0 +1 @@
from gsiupm/senpy:1.0.1-python3.6

202
community-plugins/LICENSE Normal file
View File

@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "{}"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright {yyyy} {name of copyright owner}
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

View File

@ -0,0 +1,30 @@
PYVERSION=3.7
NAME=senpycommunity
REPO=gsiupm
PLUGINS= $(filter %/, $(wildcard */))
IMAGENAME=gsiupm/senpy-plugins-community
DOCKER_FLAGS=-e MOCK_REQUESTS=$(MOCK_REQUESTS)
DEV_PORT?=5000
ifdef SENPY_FOLDER
DOCKER_FLAGS+= -v $(realpath $(SENPY_FOLDER)):/usr/src/app/
endif
all: build run
test-fast-%: docker-build
docker run $(DOCKER_FLAGS) -v $$PWD/$*:/senpy-plugins/ -v $$PWD/data:/data/ --rm $(IMAGEWTAG) --only-test $(TEST_FLAGS)
test-fast: test-fast-/
test: docker-build
docker run $(DOCKER_FLAGS) -v $$PWD/data:/data/ --rm $(IMAGEWTAG) --only-test $(TEST_FLAGS)
dev: docker-build
docker run -p $(DEV_PORT):5000 $(DOCKER_FLAGS) -ti $(DOCKER_FLAGS) -v $$PWD/$*:/senpy-plugins/ --entrypoint /bin/bash -v $$PWD/data:/data/ --rm $(IMAGEWTAG)
.PHONY:: test test-fast dev
include .makefiles/base.mk
include .makefiles/k8s.mk

View File

@ -0,0 +1,76 @@
# Senpy Plugins
# Requirements
Some of these plugins require licensed files to run, such as lexicons or corpora.
You can **manually download these resources and add them to the `data` folder**.
Most plugins will look for these resources on activation.
By default, we set the flag `--allow-fail` in senpy, so if a plugin fails to activate, the server will still run with the remaining plugins.
# Running
## Using docker
To deploy all the plugins in this repository, run:
```
docker-compose up
```
A server should now be available at `http://localhost:5000`.
Alternatively, you can use docker manually with the version of senpy you wish:
```
docker run --rm -ti -p 5000:5000 -v $PWD:/senpy-plugins gsiupm/senpy:0.10.8-python2.7
```
Note that some versions are untested.
## Manually
First, install senpy from source or through pip:
```
pip install senpy
```
Now, you can try to run your plugins:
```
senpy -f .
```
Each plugin has different requirements.
Senpy will try its best to automatically install requirements (python libraries and NLTK resources) for each plugin.
Some cases may require manual installation of dependencies, or external packages.
# For developers / Contributors
## Licensed data
In our deployments, we keep all licensed data in a private submodule.
You will likely need to initialize this submodule if you're a contributor:
```
git submodule update --init --recursive
```
## Adding a plugin from a separate repository
To add a plugin that has been developed in its own repository, you can use git-subtree as so:
```
$mname=<your plugin name>
$murl=<URL to your repository>
git remote add $mname $murl
git subtree add --prefix=$mname $mname master
```
Make sure to also add
# LICENSE
This compilation of plugins for Senpy use Apache 2.0 License. Some of the resources used for train these plugins can not be distributed, specifically, resources for the plugins `emotion-anew` and `emotion-wnaffect`. For more information visit [Senpy documentation](senpy.readthedocs.io)

@ -0,0 +1 @@
Subproject commit f34155c3891b8919a1d73bae410cb5113f1bf959

View File

@ -0,0 +1,12 @@
version: '3'
services:
community:
build: .
image: "${IMAGEWTAG:-gsi-upm/senpy-community:dev}"
volumes:
- ".:/senpy-plugins/"
# - "./data:/data"
ports:
- '5000:5000'
command:
- "--allow-fail"

View File

@ -0,0 +1,60 @@
# Plugin emotion-anew
This plugin consists on an **emotion classifier** that detects six possible emotions:
- Anger : general-dislike.
- Fear : negative-fear.
- Disgust : shame.
- Joy : gratitude, affective, enthusiasm, love, joy, liking.
- Sadness : ingrattitude, daze, humlity, compassion, despair, anxiety, sadness.
- Neutral: not detected a particulary emotion.
The plugin uses **ANEW lexicon** dictionary to calculate VAD (valence-arousal-dominance) of the sentence and determinate which emotion is closer to this value. To do this comparision, it is defined that each emotion has a centroid, calculated according to this article: http://www.aclweb.org/anthology/W10-0208.
The plugin is going to look for the words in the sentence that appear in the ANEW dictionary and calculate the average VAD score for the sentence. Once this score is calculated, it is going to seek the emotion that is closest to this value.
The response of this plugin uses [Onyx ontology](https://www.gsi.dit.upm.es/ontologies/onyx/) developed at GSI UPM, to express the information.
## Installation
* Download
```
git clone https://lab.cluster.gsi.dit.upm.es/senpy/emotion-anew.git
```
* Get data
```
cd emotion-anew
git submodule update --init --recursive
```
* Run
```
docker run -p 5000:5000 -v $PWD:/plugins gsiupm/senpy:python2.7 -f /plugins
```
## Data format
`data/Corpus/affective-isear.tsv` contains data from ISEAR Databank: http://emotion-research.net/toolbox/toolboxdatabase.2006-10-13.2581092615
##Usage
Params accepted:
- Language: English (en) and Spanish (es).
- Input: input text to analyse.
Example request:
```
http://senpy.cluster.gsi.dit.upm.es/api/?algo=emotion-anew&language=en&input=I%20love%20Madrid
```
Example respond: This plugin follows the standard for the senpy plugin response. For more information, please visit [senpy documentation](http://senpy.readthedocs.io). Specifically, NIF API section.
# Known issues
- To obtain Anew dictionary you can download from here: <https://github.com/hcorona/SMC2015/blob/master/resources/ANEW2010All.txt>
- This plugin only supports **Python2**
![alt GSI Logo][logoGSI]
[logoES]: https://www.gsi.dit.upm.es/ontologies/onyx/img/eurosentiment_logo.png "EuroSentiment logo"
[logoGSI]: http://www.gsi.dit.upm.es/images/stories/logos/gsi.png "GSI Logo"

View File

@ -0,0 +1,227 @@
# -*- coding: utf-8 -*-
import re
import nltk
import csv
import sys
import os
import unicodedata
import string
import xml.etree.ElementTree as ET
import math
from sklearn.svm import LinearSVC
from sklearn.feature_extraction import DictVectorizer
from nltk import bigrams
from nltk import trigrams
from nltk.corpus import stopwords
from pattern.en import parse as parse_en
from pattern.es import parse as parse_es
from senpy.plugins import EmotionPlugin, SenpyPlugin
from senpy.models import Results, EmotionSet, Entry, Emotion
class ANEW(EmotionPlugin):
description = "This plugin consists on an emotion classifier using ANEW lexicon dictionary. It averages the VAD (valence-arousal-dominance) value of each word in the text that is also in the ANEW dictionary. To obtain a categorical value (e.g., happy) use the emotion conversion API (e.g., `emotion-model=emoml:big6`)."
author = "@icorcuera"
version = "0.5.2"
name = "emotion-anew"
extra_params = {
"language": {
"description": "language of the input",
"aliases": ["language", "l"],
"required": True,
"options": ["es","en"],
"default": "en"
}
}
anew_path_es = "Dictionary/Redondo(2007).csv"
anew_path_en = "Dictionary/ANEW2010All.txt"
onyx__usesEmotionModel = "emoml:pad-dimensions"
nltk_resources = ['stopwords']
def activate(self, *args, **kwargs):
self._stopwords = stopwords.words('english')
dictionary={}
dictionary['es'] = {}
with self.open(self.anew_path_es,'r') as tabfile:
reader = csv.reader(tabfile, delimiter='\t')
for row in reader:
dictionary['es'][row[2]]={}
dictionary['es'][row[2]]['V']=row[3]
dictionary['es'][row[2]]['A']=row[5]
dictionary['es'][row[2]]['D']=row[7]
dictionary['en'] = {}
with self.open(self.anew_path_en,'r') as tabfile:
reader = csv.reader(tabfile, delimiter='\t')
for row in reader:
dictionary['en'][row[0]]={}
dictionary['en'][row[0]]['V']=row[2]
dictionary['en'][row[0]]['A']=row[4]
dictionary['en'][row[0]]['D']=row[6]
self._dictionary = dictionary
def _my_preprocessor(self, text):
regHttp = re.compile('(http://)[a-zA-Z0-9]*.[a-zA-Z0-9/]*(.[a-zA-Z0-9]*)?')
regHttps = re.compile('(https://)[a-zA-Z0-9]*.[a-zA-Z0-9/]*(.[a-zA-Z0-9]*)?')
regAt = re.compile('@([a-zA-Z0-9]*[*_/&%#@$]*)*[a-zA-Z0-9]*')
text = re.sub(regHttp, '', text)
text = re.sub(regAt, '', text)
text = re.sub('RT : ', '', text)
text = re.sub(regHttps, '', text)
text = re.sub('[0-9]', '', text)
text = self._delete_punctuation(text)
return text
def _delete_punctuation(self, text):
exclude = set(string.punctuation)
s = ''.join(ch for ch in text if ch not in exclude)
return s
def _extract_ngrams(self, text, lang):
unigrams_lemmas = []
unigrams_words = []
pos_tagged = []
if lang == 'es':
sentences = list(parse_es(text, lemmata=True).split())
else:
sentences = list(parse_en(text, lemmata=True).split())
for sentence in sentences:
for token in sentence:
if token[0].lower() not in self._stopwords:
unigrams_words.append(token[0].lower())
unigrams_lemmas.append(token[4])
pos_tagged.append(token[1])
return unigrams_lemmas,unigrams_words,pos_tagged
def _find_ngrams(self, input_list, n):
return zip(*[input_list[i:] for i in range(n)])
def _extract_features(self, tweet,dictionary,lang):
feature_set={}
ngrams_lemmas,ngrams_words,pos_tagged = self._extract_ngrams(tweet,lang)
pos_tags={'NN':'NN', 'NNS':'NN', 'JJ':'JJ', 'JJR':'JJ', 'JJS':'JJ', 'RB':'RB', 'RBR':'RB',
'RBS':'RB', 'VB':'VB', 'VBD':'VB', 'VGB':'VB', 'VBN':'VB', 'VBP':'VB', 'VBZ':'VB'}
totalVAD=[0,0,0]
matches=0
for word in range(len(ngrams_lemmas)):
VAD=[]
if ngrams_lemmas[word] in dictionary:
matches+=1
totalVAD = [totalVAD[0]+float(dictionary[ngrams_lemmas[word]]['V']),
totalVAD[1]+float(dictionary[ngrams_lemmas[word]]['A']),
totalVAD[2]+float(dictionary[ngrams_lemmas[word]]['D'])]
elif ngrams_words[word] in dictionary:
matches+=1
totalVAD = [totalVAD[0]+float(dictionary[ngrams_words[word]]['V']),
totalVAD[1]+float(dictionary[ngrams_words[word]]['A']),
totalVAD[2]+float(dictionary[ngrams_words[word]]['D'])]
if matches==0:
emotion='neutral'
else:
totalVAD=[totalVAD[0]/matches,totalVAD[1]/matches,totalVAD[2]/matches]
feature_set['V'] = totalVAD[0]
feature_set['A'] = totalVAD[1]
feature_set['D'] = totalVAD[2]
return feature_set
def analyse_entry(self, entry, activity):
params = activity.params
text_input = entry.text
text = self._my_preprocessor(text_input)
dictionary = self._dictionary[params['language']]
feature_set=self._extract_features(text, dictionary, params['language'])
emotions = EmotionSet()
emotions.id = "Emotions0"
emotion1 = Emotion(id="Emotion0")
emotion1["emoml:pad-dimensions_pleasure"] = feature_set['V']
emotion1["emoml:pad-dimensions_arousal"] = feature_set['A']
emotion1["emoml:pad-dimensions_dominance"] = feature_set['D']
emotion1.prov(activity)
emotions.prov(activity)
emotions.onyx__hasEmotion.append(emotion1)
entry.emotions = [emotions, ]
yield entry
ontology = "http://gsi.dit.upm.es/ontologies/wnaffect/ns#"
test_cases = [
{
'name': 'anger with VAD=(2.12, 6.95, 5.05)',
'input': 'I hate you',
'expected': {
'onyx:hasEmotionSet': [{
'onyx:hasEmotion': [{
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 6.95,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 5.05,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 2.12,
}]
}]
}
}, {
'input': 'i am sad',
'expected': {
'onyx:hasEmotionSet': [{
'onyx:hasEmotion': [{
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 4.13,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 3.45,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 1.61,
}]
}]
}
}, {
'name': 'joy',
'input': 'i am happy with my marks',
'expected': {
'onyx:hasEmotionSet': [{
'onyx:hasEmotion': [{
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 6.49,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 6.63,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 8.21,
}]
}]
}
}, {
'name': 'negative-feat',
'input': 'This movie is scary',
'expected': {
'onyx:hasEmotionSet': [{
'onyx:hasEmotion': [{
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 5.8100000000000005,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 4.33,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 5.050000000000001,
}]
}]
}
}, {
'name': 'negative-fear',
'input': 'this cake is disgusting' ,
'expected': {
'onyx:hasEmotionSet': [{
'onyx:hasEmotion': [{
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#arousal": 5.09,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#dominance": 4.4,
"http://www.gsi.dit.upm.es/ontologies/onyx/vocabularies/anew/ns#valence": 5.109999999999999,
}]
}]
}
}
]

View File

@ -0,0 +1,11 @@
---
module: emotion-anew
requirements:
- numpy
- pandas
- nltk
- scipy
- scikit-learn
- textblob
- pattern
- lxml

View File

@ -0,0 +1,181 @@
#!/usr/local/bin/python
# coding: utf-8
from future import standard_library
standard_library.install_aliases()
import os
import re
import sys
import string
import numpy as np
from six.moves import urllib
from nltk.corpus import stopwords
from senpy import EmotionBox, models
def ignore(dchars):
deletechars = "".join(dchars)
tbl = str.maketrans("", "", deletechars)
ignore = lambda s: s.translate(tbl)
return ignore
class DepecheMood(EmotionBox):
'''
Plugin that uses the DepecheMood emotion lexicon.
DepecheMood is an emotion lexicon automatically generated from news articles where users expressed their associated emotions. It contains two languages (English and Italian), as well as three types of word representations (token, lemma and lemma#PoS). For English, the lexicon contains 165k tokens, while the Italian version contains 116k. Unsupervised techniques can be applied to generate simple but effective baselines. To learn more, please visit https://github.com/marcoguerini/DepecheMood and http://www.depechemood.eu/
'''
author = 'Oscar Araque'
name = 'emotion-depechemood'
version = '0.1'
requirements = ['pandas']
nltk_resources = ["stopwords"]
onyx__usesEmotionModel = 'wna:WNAModel'
EMOTIONS = ['wna:negative-fear',
'wna:amusement',
'wna:anger',
'wna:annoyance',
'wna:indifference',
'wna:joy',
'wna:awe',
'wna:sadness']
DM_EMOTIONS = ['AFRAID', 'AMUSED', 'ANGRY', 'ANNOYED', 'DONT_CARE', 'HAPPY', 'INSPIRED', 'SAD',]
def __init__(self, *args, **kwargs):
super(DepecheMood, self).__init__(*args, **kwargs)
self.LEXICON_URL = "https://github.com/marcoguerini/DepecheMood/raw/master/DepecheMood%2B%2B/DepecheMood_english_token_full.tsv"
self._denoise = ignore(set(string.punctuation)|set('«»'))
self._stop_words = []
self._lex_vocab = None
self._lex = None
def activate(self):
self._lex = self.download_lex()
self._lex_vocab = set(list(self._lex.keys()))
self._stop_words = stopwords.words('english') + ['']
def clean_str(self, string):
string = re.sub(r"[^A-Za-z0-9().,!?\'\`]", " ", string)
string = re.sub(r"[0-9]+", " num ", string)
string = re.sub(r"\'s", " \'s", string)
string = re.sub(r"\'ve", " \'ve", string)
string = re.sub(r"n\'t", " n\'t", string)
string = re.sub(r"\'re", " \'re", string)
string = re.sub(r"\'d", " \'d", string)
string = re.sub(r"\'ll", " \'ll", string)
string = re.sub(r"\.", " . ", string)
string = re.sub(r",", " , ", string)
string = re.sub(r"!", " ! ", string)
string = re.sub(r"\(", " ( ", string)
string = re.sub(r"\)", " ) ", string)
string = re.sub(r"\?", " ? ", string)
string = re.sub(r"\s{2,}", " ", string)
return string.strip().lower()
def preprocess(self, text):
if text is None:
return None
tokens = self._denoise(self.clean_str(text)).split(' ')
tokens = [tok for tok in tokens if tok not in self._stop_words]
return tokens
def estimate_emotion(self, tokens, emotion):
s = []
for tok in tokens:
s.append(self._lex[tok][emotion])
dividend = np.sum(s) if np.sum(s) > 0 else 0
divisor = len(s) if len(s) > 0 else 1
S = np.sum(s) / divisor
return S
def estimate_all_emotions(self, tokens):
S = []
intersection = set(tokens) & self._lex_vocab
for emotion in self.DM_EMOTIONS:
s = self.estimate_emotion(intersection, emotion)
S.append(s)
return S
def download_lex(self, file_path='DepecheMood_english_token_full.tsv', freq_threshold=10):
import pandas as pd
try:
file_path = self.find_file(file_path)
except IOError:
file_path = self.path(file_path)
filename, _ = urllib.request.urlretrieve(self.LEXICON_URL, file_path)
lexicon = pd.read_csv(file_path, sep='\t', index_col=0)
lexicon = lexicon[lexicon['freq'] >= freq_threshold]
lexicon.drop('freq', axis=1, inplace=True)
lexicon = lexicon.T.to_dict()
return lexicon
def predict_one(self, features, **kwargs):
tokens = self.preprocess(features[0])
estimation = self.estimate_all_emotions(tokens)
return estimation
test_cases = [
{
'entry': {
'nif:isString': 'My cat is very happy',
},
'expected': {
'onyx:hasEmotionSet': [
{
'onyx:hasEmotion': [
{
'onyx:hasEmotionCategory': 'wna:negative-fear',
'onyx:hasEmotionIntensity': 0.05278117640010922
},
{
'onyx:hasEmotionCategory': 'wna:amusement',
'onyx:hasEmotionIntensity': 0.2114806151413433,
},
{
'onyx:hasEmotionCategory': 'wna:anger',
'onyx:hasEmotionIntensity': 0.05726119426520887
},
{
'onyx:hasEmotionCategory': 'wna:annoyance',
'onyx:hasEmotionIntensity': 0.12295990731053638,
},
{
'onyx:hasEmotionCategory': 'wna:indifference',
'onyx:hasEmotionIntensity': 0.1860159893608025,
},
{
'onyx:hasEmotionCategory': 'wna:joy',
'onyx:hasEmotionIntensity': 0.12904050973724163,
},
{
'onyx:hasEmotionCategory': 'wna:awe',
'onyx:hasEmotionIntensity': 0.17973650399862967,
},
{
'onyx:hasEmotionCategory': 'wna:sadness',
'onyx:hasEmotionIntensity': 0.060724103786128455,
},
]
}
]
}
}
]
if __name__ == '__main__':
from senpy.utils import easy, easy_load, easy_test
# sp, app = easy_load()
# for plug in sp.analysis_plugins:
# plug.test()
easy_test(debug=False)

View File

@ -0,0 +1,2 @@
__pycache__
*.pyc

View File

@ -0,0 +1,67 @@
# Uncomment if you want to use docker-in-docker
# image: gsiupm/dockermake:latest
# services:
# - docker:dind
# When using dind, it's wise to use the overlayfs driver for
# improved performance.
stages:
- test
- push
- deploy
- clean
before_script:
- make -e login
.test: &test_definition
stage: test
script:
- make -e test-$PYTHON_VERSION
test-3.5:
<<: *test_definition
variables:
PYTHON_VERSION: "3.5"
.image: &image_definition
stage: push
script:
- make -e push-$PYTHON_VERSION
only:
- tags
- triggers
push-3.5:
<<: *image_definition
variables:
PYTHON_VERSION: "3.5"
push-latest:
<<: *image_definition
variables:
PYTHON_VERSION: latest
only:
- tags
- triggers
deploy:
stage: deploy
environment: production
script:
- make -e deploy
only:
- tags
- triggers
clean :
stage: clean
script:
- make -e clean
when: manual
cleanup_py:
stage: clean
when: always # this is important; run even if preceding stages failed.
script:
- docker logout

View File

@ -0,0 +1,27 @@
These makefiles are recipes for several common tasks in different types of projects.
To add them to your project, simply do:
```
git remote add makefiles ssh://git@lab.cluster.gsi.dit.upm.es:2200/docs/templates/makefiles.git
git subtree add --prefix=.makefiles/ makefiles master
touch Makefile
echo "include .makefiles/base.mk" >> Makefile
```
Now you can take advantage of the recipes.
For instance, to add useful targets for a python project, just add this to your Makefile:
```
include .makefiles/python.mk
```
You may need to set special variables like the name of your project or the python versions you're targetting.
Take a look at each specific `.mk` file for more information, and the `Makefile` in the [senpy](https://lab.cluster.gsi.dit.upm.es/senpy/senpy) project for a real use case.
If you update the makefiles from your repository, make sure to push the changes for review in upstream (this repository):
```
make makefiles-push
```
It will automatically commit all unstaged changes in the .makefiles folder.

View File

@ -0,0 +1,36 @@
export
NAME ?= $(shell basename $(CURDIR))
VERSION ?= $(shell git describe --tags --dirty 2>/dev/null)
ifeq ($(VERSION),)
VERSION:=unknown
endif
# Get the location of this makefile.
MK_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
-include .env
-include ../.env
help: ## Show this help.
@fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/\(.*:\)[^#]*##\s*\(.*\)/\1\t\2/' | column -t -s " "
config: ## Load config from the environment. You should run it once in every session before other tasks. Run: eval $(make config)
@awk '{ print "export " $$0}' ../.env
@awk '{ print "export " $$0}' .env
@echo "# Please, run: "
@echo "# eval \$$(make config)"
# If you need to run a command on the key/value pairs, use this:
# @awk '{ split($$0, a, "="); "echo " a[2] " | base64 -w 0" |& getline b64; print "export " a[1] "=" a[2]; print "export " a[1] "_BASE64=" b64}' .env
ci: ## Run a task using gitlab-runner. Only use to debug problems in the CI pipeline
gitlab-runner exec shell --builds-dir '.builds' --env CI_PROJECT_NAME=$(NAME) ${action}
include $(MK_DIR)/makefiles.mk
include $(MK_DIR)/docker.mk
include $(MK_DIR)/git.mk
info:: ## List all variables
env
.PHONY:: config help ci

View File

@ -0,0 +1,29 @@
IMAGENAME?=$(NAME)
IMAGEWTAG?=$(IMAGENAME):$(VERSION)
docker-login: ## Log in to the registry. It will only be used in the server, or when running a CI task locally (if CI_BUILD_TOKEN is set).
ifeq ($(CI_BUILD_TOKEN),)
@echo "Not logging in to the docker registry" "$(CI_REGISTRY)"
else
@docker login -u gitlab-ci-token -p $(CI_BUILD_TOKEN) $(CI_REGISTRY)
endif
ifeq ($(HUB_USER),)
@echo "Not logging in to global the docker registry"
else
@docker login -u $(HUB_USER) -p $(HUB_PASSWORD)
endif
docker-clean: ## Remove docker credentials
ifeq ($(HUB_USER),)
else
@docker logout
endif
login:: docker-login
clean:: docker-clean
docker-info:
@echo IMAGEWTAG=${IMAGEWTAG}
.PHONY:: docker-login docker-clean login clean

View File

@ -0,0 +1,28 @@
commit:
git commit -a
tag:
git tag ${VERSION}
git-push::
git push --tags -u origin HEAD
git-pull:
git pull --all
push-github: ## Push the code to github. You need to set up GITHUB_DEPLOY_KEY
ifeq ($(GITHUB_DEPLOY_KEY),)
else
$(eval KEY_FILE := "$(shell mktemp)")
@echo "$(GITHUB_DEPLOY_KEY)" > $(KEY_FILE)
@git remote rm github-deploy || true
git remote add github-deploy $(GITHUB_REPO)
-@GIT_SSH_COMMAND="ssh -i $(KEY_FILE)" git fetch github-deploy $(CI_COMMIT_REF_NAME)
@GIT_SSH_COMMAND="ssh -i $(KEY_FILE)" git push github-deploy HEAD:$(CI_COMMIT_REF_NAME)
rm $(KEY_FILE)
endif
push:: git-push
pull:: git-pull
.PHONY:: commit tag push git-push git-pull push-github

View File

@ -0,0 +1,51 @@
# Deployment with Kubernetes
# KUBE_CA_PEM_FILE is the path of a certificate file. It automatically set by GitLab
# if you enable Kubernetes integration in a project.
#
# As of this writing, Kubernetes integration can not be set on a group level, so it has to
# be manually set in every project.
# Alternatively, we use a custom KUBE_CA_BUNDLE environment variable, which can be set at
# the group level. In this case, the variable contains the whole content of the certificate,
# which we dump to a temporary file
#
# Check if the KUBE_CA_PEM_FILE exists. Otherwise, create it from KUBE_CA_BUNDLE
KUBE_CA_TEMP=false
ifndef KUBE_CA_PEM_FILE
KUBE_CA_PEM_FILE:=$$PWD/.ca.crt
CREATED:=$(shell echo -e "$(KUBE_CA_BUNDLE)" > $(KUBE_CA_PEM_FILE))
endif
KUBE_TOKEN?=""
KUBE_NAMESPACE?=$(NAME)
KUBECTL=docker run --rm -v $(KUBE_CA_PEM_FILE):/tmp/ca.pem -i lachlanevenson/k8s-kubectl --server="$(KUBE_URL)" --token="$(KUBE_TOKEN)" --certificate-authority="/tmp/ca.pem" -n $(KUBE_NAMESPACE)
CI_COMMIT_REF_NAME?=master
info:: ## Print variables. Useful for debugging.
@echo "#KUBERNETES"
@echo KUBE_URL=$(KUBE_URL)
@echo KUBE_CA_PEM_FILE=$(KUBE_CA_PEM_FILE)
@echo KUBE_CA_BUNDLE=$$KUBE_CA_BUNDLE
@echo KUBE_TOKEN=$(KUBE_TOKEN)
@echo KUBE_NAMESPACE=$(KUBE_NAMESPACE)
@echo KUBECTL=$(KUBECTL)
@echo "#CI"
@echo CI_PROJECT_NAME=$(CI_PROJECT_NAME)
@echo CI_REGISTRY=$(CI_REGISTRY)
@echo CI_REGISTRY_USER=$(CI_REGISTRY_USER)
@echo CI_COMMIT_REF_NAME=$(CI_COMMIT_REF_NAME)
@echo "CREATED=$(CREATED)"
#
# Deployment and advanced features
#
deploy: ## Deploy to kubernetes using the credentials in KUBE_CA_PEM_FILE (or KUBE_CA_BUNDLE ) and TOKEN
@ls k8s/*.yaml k8s/*.yml k8s/*.tmpl 2>/dev/null || true
@cat k8s/*.yaml k8s/*.yml k8s/*.tmpl 2>/dev/null | envsubst | $(KUBECTL) apply -f -
deploy-check: ## Get the deployed configuration.
@$(KUBECTL) get deploy,pods,svc,ingress
.PHONY:: info deploy deploy-check

View File

@ -0,0 +1,17 @@
makefiles-remote:
@git remote add makefiles ssh://git@lab.cluster.gsi.dit.upm.es:2200/docs/templates/makefiles.git 2>/dev/null || true
makefiles-commit: makefiles-remote
git add -f .makefiles
git commit -em "Updated makefiles from ${NAME}"
makefiles-push:
git subtree push --prefix=.makefiles/ makefiles $(NAME)
makefiles-pull: makefiles-remote
git subtree pull --prefix=.makefiles/ makefiles master --squash
pull:: makefiles-pull
push:: makefiles-push
.PHONY:: makefiles-remote makefiles-commit makefiles-push makefiles-pull pull push

View File

@ -0,0 +1,5 @@
init: ## Init pre-commit hooks (i.e. enforcing format checking before allowing a commit)
pip install --user pre-commit
pre-commit install
.PHONY:: init

View File

@ -0,0 +1,100 @@
PYVERSIONS ?= 3.5
PYMAIN ?= $(firstword $(PYVERSIONS))
TARNAME ?= $(NAME)-$(VERSION).tar.gz
VERSIONFILE ?= $(NAME)/VERSION
DEVPORT ?= 6000
.FORCE:
version: .FORCE
@echo $(VERSION) > $(VERSIONFILE)
@echo $(VERSION)
yapf: ## Format python code
yapf -i -r $(NAME)
yapf -i -r tests
dockerfiles: $(addprefix Dockerfile-,$(PYVERSIONS)) ## Generate dockerfiles for each python version
@unlink Dockerfile >/dev/null
ln -s Dockerfile-$(PYMAIN) Dockerfile
Dockerfile-%: Dockerfile.template ## Generate a specific dockerfile (e.g. Dockerfile-2.7)
sed "s/{{PYVERSION}}/$*/" Dockerfile.template > Dockerfile-$*
quick_build: $(addprefix build-, $(PYMAIN))
build: $(addprefix build-, $(PYVERSIONS)) ## Build all images / python versions
build-%: version Dockerfile-% ## Build a specific version (e.g. build-2.7)
docker build -t '$(IMAGEWTAG)-python$*' --cache-from $(IMAGENAME):python$* -f Dockerfile-$* .;
dev-%: ## Launch a specific development environment using docker (e.g. dev-2.7)
@docker start $(NAME)-dev$* || (\
$(MAKE) build-$*; \
docker run -d -w /usr/src/app/ -p $(DEVPORT):5000 -v $$PWD:/usr/src/app --entrypoint=/bin/bash -ti --name $(NAME)-dev$* '$(IMAGEWTAG)-python$*'; \
)\
docker exec -ti $(NAME)-dev$* bash
dev: dev-$(PYMAIN) ## Launch a development environment using docker, using the default python version
quick_test: test-$(PYMAIN)
test-%: ## Run setup.py from in an isolated container, built from the base image. (e.g. test-2.7)
# This speeds tests up because the image has most (if not all) of the dependencies already.
docker rm $(NAME)-test-$* || true
docker create -ti --name $(NAME)-test-$* --entrypoint="" -w /usr/src/app/ $(IMAGENAME):python$* python setup.py test
docker cp . $(NAME)-test-$*:/usr/src/app
docker start -a $(NAME)-test-$*
test: $(addprefix test-,$(PYVERSIONS)) ## Run the tests with the main python version
run-%: build-%
docker run --rm -p $(DEVPORT):5000 -ti '$(IMAGEWTAG)-python$(PYMAIN)' --default-plugins
run: run-$(PYMAIN)
# Pypy - Upload a package
dist/$(TARNAME): version
python setup.py sdist;
sdist: dist/$(TARNAME) ## Generate the distribution file (wheel)
pip_test-%: sdist ## Test the distribution file using pip install and a specific python version (e.g. pip_test-2.7)
docker run --rm -v $$PWD/dist:/dist/ python:$* pip install /dist/$(TARNAME);
pip_test: $(addprefix pip_test-,$(PYVERSIONS)) ## Test pip installation with the main python version
pip_upload: pip_test ## Upload package to pip
python setup.py sdist upload ;
# Pushing to docker
push-latest: $(addprefix push-latest-,$(PYVERSIONS)) ## Push the "latest" tag to dockerhub
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGENAME)'
docker push '$(IMAGENAME):latest'
docker push '$(IMAGEWTAG)'
push-latest-%: build-% ## Push the latest image for a specific python version
docker tag $(IMAGENAME):$(VERSION)-python$* $(IMAGENAME):python$*
docker push $(IMAGENAME):$(VERSION)-python$*
docker push $(IMAGENAME):python$*
push-%: build-% ## Push the image of the current version (tagged). e.g. push-2.7
docker push $(IMAGENAME):$(VERSION)-python$*
push:: $(addprefix push-,$(PYVERSIONS)) ## Push an image with the current version for every python version
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker push $(IMAGENAME):$(VERSION)
clean:: ## Clean older docker images and containers related to this project and dev environments
@docker stop $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
@docker rm $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
@docker ps -a | grep $(IMAGENAME) | awk '{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1;}}' | xargs docker rm -v 2>/dev/null|| true
@docker images | grep $(IMAGENAME) | awk '{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1":"$$2;}}' | xargs docker rmi 2>/dev/null|| true
.PHONY:: yapf dockerfiles Dockerfile-% quick_build build build-% dev-% quick-dev test quick_test push-latest push-latest-% push-% push version .FORCE

View File

@ -0,0 +1,5 @@
FROM gsiupm/senpy:python2.7
MAINTAINER manuel.garcia-amado.sancho@alumnos.upm.es
COPY data /data

View File

@ -0,0 +1,4 @@
FROM gsiupm/senpy:python3.5
MAINTAINER manuel.garcia-amado.sancho@alumnos.upm.es
COPY data /data

View File

@ -0,0 +1,3 @@
FROM gsiupm/senpy:python{{PYVERSION}}
MAINTAINER manuel.garcia-amado.sancho@alumnos.upm.es

View File

@ -0,0 +1,9 @@
NAME:=wnaffect
VERSIONFILE:=VERSION
IMAGENAME:=registry.cluster.gsi.dit.upm.es/senpy/emotion-wnaffect
PYVERSIONS:=2.7 3.5
DEVPORT:=5000
include .makefiles/base.mk
include .makefiles/k8s.mk
include .makefiles/python.mk

View File

@ -0,0 +1,62 @@
# WordNet-Affect plugin
This plugin uses WordNet-Affect (http://wndomains.fbk.eu/wnaffect.html) to calculate the percentage of each emotion. The plugin classifies among five diferent emotions: anger, fear, disgust, joy and sadness. It is has been used a emotion mapping enlarge the emotions:
- anger : general-dislike
- fear : negative-fear
- disgust : shame
- joy : gratitude, affective, enthusiasm, love, joy, liking
- sadness : ingrattitude, daze, humlity, compassion, despair, anxiety, sadness
## Installation
* Download
```
git clone https://lab.cluster.gsi.dit.upm.es/senpy/emotion-wnaffect.git
```
* Get data
```
cd emotion-wnaffect
git submodule update --init --recursive
```
* Run
```
docker run -p 5000:5000 -v $PWD:/plugins gsiupm/senpy -f /plugins
```
## Data format
`data/a-hierarchy.xml` is a xml file
`data/a-synsets.xml` is a xml file
## Usage
The parameters accepted are:
- Language: English (en).
- Input: Text to analyse.
Example request:
```
http://senpy.cluster.gsi.dit.upm.es/api/?algo=emotion-wnaffect&language=en&input=I%20love%20Madrid
```
Example respond: This plugin follows the standard for the senpy plugin response. For more information, please visit [senpy documentation](http://senpy.readthedocs.io). Specifically, NIF API section.
The response of this plugin uses [Onyx ontology](https://www.gsi.dit.upm.es/ontologies/onyx/) developed at GSI UPM for semantic web.
This plugin uses WNAffect labels for emotion analysis.
The emotion-wnaffect.senpy file can be copied and modified to use different versions of wnaffect with the same python code.
## Known issues
- This plugin run on **Python2.7** and **Python3.5**
- Wnaffect and corpora files are not included in the repository, but can be easily added either to the docker image (using a volume) or in a new docker image.
- You can download Wordnet 1.6 here: <http://wordnetcode.princeton.edu/1.6/wn16.unix.tar.gz> and extract the dict folder.
- The hierarchy and synsets files can be found here: <https://github.com/larsmans/wordnet-domains-sentiwords/tree/master/wn-domains/wn-affect-1.1>
![alt GSI Logo][logoGSI]
[logoGSI]: http://www.gsi.dit.upm.es/images/stories/logos/gsi.png "GSI Logo"

View File

@ -0,0 +1,278 @@
# -*- coding: utf-8 -*-
from __future__ import division
import re
import nltk
import os
import string
import xml.etree.ElementTree as ET
from nltk.corpus import stopwords
from nltk.corpus import WordNetCorpusReader
from nltk.stem import wordnet
from emotion import Emotion as Emo
from senpy.plugins import EmotionPlugin, AnalysisPlugin, ShelfMixin
from senpy.models import Results, EmotionSet, Entry, Emotion
class WNAffect(EmotionPlugin, ShelfMixin):
'''
Emotion classifier using WordNet-Affect to calculate the percentage
of each emotion. This plugin classifies among 6 emotions: anger,fear,disgust,joy,sadness
or neutral. The only available language is English (en)
'''
name = 'emotion-wnaffect'
author = ["@icorcuera", "@balkian"]
version = '0.2'
extra_params = {
'language': {
"@id": 'lang_wnaffect',
'description': 'language of the input',
'aliases': ['language', 'l'],
'required': True,
'options': ['en',]
}
}
synsets_path = "a-synsets.xml"
hierarchy_path = "a-hierarchy.xml"
wn16_path = "wordnet1.6/dict"
onyx__usesEmotionModel = "emoml:big6"
nltk_resources = ['stopwords', 'averaged_perceptron_tagger', 'wordnet']
def _load_synsets(self, synsets_path):
"""Returns a dictionary POS tag -> synset offset -> emotion (str -> int -> str)."""
tree = ET.parse(synsets_path)
root = tree.getroot()
pos_map = {"noun": "NN", "adj": "JJ", "verb": "VB", "adv": "RB"}
synsets = {}
for pos in ["noun", "adj", "verb", "adv"]:
tag = pos_map[pos]
synsets[tag] = {}
for elem in root.findall(
".//{0}-syn-list//{0}-syn".format(pos, pos)):
offset = int(elem.get("id")[2:])
if not offset: continue
if elem.get("categ"):
synsets[tag][offset] = Emo.emotions[elem.get(
"categ")] if elem.get(
"categ") in Emo.emotions else None
elif elem.get("noun-id"):
synsets[tag][offset] = synsets[pos_map["noun"]][int(
elem.get("noun-id")[2:])]
return synsets
def _load_emotions(self, hierarchy_path):
"""Loads the hierarchy of emotions from the WordNet-Affect xml."""
tree = ET.parse(hierarchy_path)
root = tree.getroot()
for elem in root.findall("categ"):
name = elem.get("name")
if name == "root":
Emo.emotions["root"] = Emo("root")
else:
Emo.emotions[name] = Emo(name, elem.get("isa"))
def activate(self, *args, **kwargs):
self._stopwords = stopwords.words('english')
self._wnlemma = wordnet.WordNetLemmatizer()
self._syntactics = {'N': 'n', 'V': 'v', 'J': 'a', 'S': 's', 'R': 'r'}
local_path = os.environ.get("SENPY_DATA")
self._categories = {
'anger': [
'general-dislike',
],
'fear': [
'negative-fear',
],
'disgust': [
'shame',
],
'joy':
['gratitude', 'affective', 'enthusiasm', 'love', 'joy', 'liking'],
'sadness': [
'ingrattitude', 'daze', 'humility', 'compassion', 'despair',
'anxiety', 'sadness'
]
}
self._wnaffect_mappings = {
'anger': 'anger',
'fear': 'negative-fear',
'disgust': 'disgust',
'joy': 'joy',
'sadness': 'sadness'
}
self._load_emotions(self.find_file(self.hierarchy_path))
if 'total_synsets' not in self.sh:
total_synsets = self._load_synsets(self.find_file(self.synsets_path))
self.sh['total_synsets'] = total_synsets
self._total_synsets = self.sh['total_synsets']
self._wn16_path = self.wn16_path
self._wn16 = WordNetCorpusReader(self.find_file(self._wn16_path), nltk.data.find(self.find_file(self._wn16_path)))
def deactivate(self, *args, **kwargs):
self.save()
def _my_preprocessor(self, text):
regHttp = re.compile(
'(http://)[a-zA-Z0-9]*.[a-zA-Z0-9/]*(.[a-zA-Z0-9]*)?')
regHttps = re.compile(
'(https://)[a-zA-Z0-9]*.[a-zA-Z0-9/]*(.[a-zA-Z0-9]*)?')
regAt = re.compile('@([a-zA-Z0-9]*[*_/&%#@$]*)*[a-zA-Z0-9]*')
text = re.sub(regHttp, '', text)
text = re.sub(regAt, '', text)
text = re.sub('RT : ', '', text)
text = re.sub(regHttps, '', text)
text = re.sub('[0-9]', '', text)
text = self._delete_punctuation(text)
return text
def _delete_punctuation(self, text):
exclude = set(string.punctuation)
s = ''.join(ch for ch in text if ch not in exclude)
return s
def _extract_ngrams(self, text):
unigrams_lemmas = []
pos_tagged = []
unigrams_words = []
tokens = text.split()
for token in nltk.pos_tag(tokens):
unigrams_words.append(token[0])
pos_tagged.append(token[1])
if token[1][0] in self._syntactics.keys():
unigrams_lemmas.append(
self._wnlemma.lemmatize(token[0], self._syntactics[token[1]
[0]]))
else:
unigrams_lemmas.append(token[0])
return unigrams_words, unigrams_lemmas, pos_tagged
def _find_ngrams(self, input_list, n):
return zip(*[input_list[i:] for i in range(n)])
def _clean_pos(self, pos_tagged):
pos_tags = {
'NN': 'NN',
'NNP': 'NN',
'NNP-LOC': 'NN',
'NNS': 'NN',
'JJ': 'JJ',
'JJR': 'JJ',
'JJS': 'JJ',
'RB': 'RB',
'RBR': 'RB',
'RBS': 'RB',
'VB': 'VB',
'VBD': 'VB',
'VGB': 'VB',
'VBN': 'VB',
'VBP': 'VB',
'VBZ': 'VB'
}
for i in range(len(pos_tagged)):
if pos_tagged[i] in pos_tags:
pos_tagged[i] = pos_tags[pos_tagged[i]]
return pos_tagged
def _extract_features(self, text):
feature_set = {k: 0 for k in self._categories}
ngrams_words, ngrams_lemmas, pos_tagged = self._extract_ngrams(text)
matches = 0
pos_tagged = self._clean_pos(pos_tagged)
tag_wn = {
'NN': self._wn16.NOUN,
'JJ': self._wn16.ADJ,
'VB': self._wn16.VERB,
'RB': self._wn16.ADV
}
for i in range(len(pos_tagged)):
if pos_tagged[i] in tag_wn:
synsets = self._wn16.synsets(ngrams_words[i],
tag_wn[pos_tagged[i]])
if synsets:
offset = synsets[0].offset()
if offset in self._total_synsets[pos_tagged[i]]:
if self._total_synsets[pos_tagged[i]][offset] is None:
continue
else:
emotion = self._total_synsets[pos_tagged[i]][
offset].get_level(5).name
matches += 1
for i in self._categories:
if emotion in self._categories[i]:
feature_set[i] += 1
if matches == 0:
matches = 1
for i in feature_set:
feature_set[i] = (feature_set[i] / matches)
return feature_set
def analyse_entry(self, entry, activity):
params = activity.params
text_input = entry['nif:isString']
text = self._my_preprocessor(text_input)
feature_text = self._extract_features(text)
emotionSet = EmotionSet(id="Emotions0")
emotions = emotionSet.onyx__hasEmotion
for i in feature_text:
emotions.append(
Emotion(
onyx__hasEmotionCategory=self._wnaffect_mappings[i],
onyx__hasEmotionIntensity=feature_text[i]))
entry.emotions = [emotionSet]
yield entry
def test(self, *args, **kwargs):
results = list()
params = {'algo': 'emotion-wnaffect',
'intype': 'direct',
'expanded-jsonld': 0,
'informat': 'text',
'prefix': '',
'plugin_type': 'analysisPlugin',
'urischeme': 'RFC5147String',
'outformat': 'json-ld',
'i': 'Hello World',
'input': 'Hello World',
'conversion': 'full',
'language': 'en',
'algorithm': 'emotion-wnaffect'}
self.activate()
texts = {'I hate you': 'anger',
'i am sad': 'sadness',
'i am happy with my marks': 'joy',
'This movie is scary': 'negative-fear'}
for text in texts:
response = next(self.analyse_entry(Entry(nif__isString=text),
self.activity(params)))
expected = texts[text]
emotionSet = response.emotions[0]
max_emotion = max(emotionSet['onyx:hasEmotion'], key=lambda x: x['onyx:hasEmotionIntensity'])
assert max_emotion['onyx:hasEmotionCategory'] == expected

View File

@ -0,0 +1,6 @@
---
module: emotion-wnaffect
requirements:
- nltk>=3.0.5
- lxml>=3.4.2
async: false

View File

@ -0,0 +1,95 @@
# -*- coding: utf-8 -*-
"""
Clement Michard (c) 2015
"""
class Emotion:
"""Defines an emotion."""
emotions = {} # name to emotion (str -> Emotion)
def __init__(self, name, parent_name=None):
"""Initializes an Emotion object.
name -- name of the emotion (str)
parent_name -- name of the parent emotion (str)
"""
self.name = name
self.parent = None
self.level = 0
self.children = []
if parent_name:
self.parent = Emotion.emotions[parent_name] if parent_name else None
self.parent.children.append(self)
self.level = self.parent.level + 1
def get_level(self, level):
"""Returns the parent of self at the given level.
level -- level in the hierarchy (int)
"""
em = self
while em.level > level and em.level >= 0:
em = em.parent
return em
def __str__(self):
"""Returns the emotion string formatted."""
return self.name
def nb_children(self):
"""Returns the number of children of the emotion."""
return sum(child.nb_children() for child in self.children) + 1
@staticmethod
def printTree(emotion=None, indent="", last='updown'):
"""Prints the hierarchy of emotions.
emotion -- root emotion (Emotion)
"""
if not emotion:
emotion = Emotion.emotions["root"]
size_branch = {child: child.nb_children() for child in emotion.children}
leaves = sorted(emotion.children, key=lambda emotion: emotion.nb_children())
up, down = [], []
if leaves:
while sum(size_branch[e] for e in down) < sum(size_branch[e] for e in leaves):
down.append(leaves.pop())
up = leaves
for leaf in up:
next_last = 'up' if up.index(leaf) is 0 else ''
next_indent = '{0}{1}{2}'.format(indent, ' ' if 'up' in last else '', " " * len(emotion.name))
Emotion.printTree(leaf, indent=next_indent, last=next_last)
if last == 'up':
start_shape = ''
elif last == 'down':
start_shape = ''
elif last == 'updown':
start_shape = ' '
else:
start_shape = ''
if up:
end_shape = ''
elif down:
end_shape = ''
else:
end_shape = ''
print ('{0}{1}{2}{3}'.format(indent, start_shape, emotion.name, end_shape))
for leaf in down:
next_last = 'down' if down.index(leaf) is len(down) - 1 else ''
next_indent = '{0}{1}{2}'.format(indent, ' ' if 'down' in last else '', " " * len(emotion.name))
Emotion.printTree(leaf, indent=next_indent, last=next_last)

View File

@ -0,0 +1,94 @@
# coding: utf-8
# In[1]:
# -*- coding: utf-8 -*-
"""
Clement Michard (c) 2015
"""
import os
import sys
import nltk
from emotion import Emotion
from nltk.corpus import WordNetCorpusReader
import xml.etree.ElementTree as ET
class WNAffect:
"""WordNet-Affect resource."""
nltk_resources = ['averaged_perceptron_tagger']
def __init__(self, wordnet16_dir, wn_domains_dir):
"""Initializes the WordNet-Affect object."""
cwd = os.getcwd()
nltk.data.path.append(cwd)
wn16_path = "{0}/dict".format(wordnet16_dir)
self.wn16 = WordNetCorpusReader(os.path.abspath("{0}/{1}".format(cwd, wn16_path)), nltk.data.find(wn16_path))
self.flat_pos = {'NN':'NN', 'NNS':'NN', 'JJ':'JJ', 'JJR':'JJ', 'JJS':'JJ', 'RB':'RB', 'RBR':'RB', 'RBS':'RB', 'VB':'VB', 'VBD':'VB', 'VGB':'VB', 'VBN':'VB', 'VBP':'VB', 'VBZ':'VB'}
self.wn_pos = {'NN':self.wn16.NOUN, 'JJ':self.wn16.ADJ, 'VB':self.wn16.VERB, 'RB':self.wn16.ADV}
self._load_emotions(wn_domains_dir)
self.synsets = self._load_synsets(wn_domains_dir)
def _load_synsets(self, wn_domains_dir):
"""Returns a dictionary POS tag -> synset offset -> emotion (str -> int -> str)."""
tree = ET.parse("{0}/a-synsets.xml".format(wn_domains_dir))
root = tree.getroot()
pos_map = { "noun": "NN", "adj": "JJ", "verb": "VB", "adv": "RB" }
synsets = {}
for pos in ["noun", "adj", "verb", "adv"]:
tag = pos_map[pos]
synsets[tag] = {}
for elem in root.findall(".//{0}-syn-list//{0}-syn".format(pos, pos)):
offset = int(elem.get("id")[2:])
if not offset: continue
if elem.get("categ"):
synsets[tag][offset] = Emotion.emotions[elem.get("categ")] if elem.get("categ") in Emotion.emotions else None
elif elem.get("noun-id"):
synsets[tag][offset] = synsets[pos_map["noun"]][int(elem.get("noun-id")[2:])]
return synsets
def _load_emotions(self, wn_domains_dir):
"""Loads the hierarchy of emotions from the WordNet-Affect xml."""
tree = ET.parse("{0}/a-hierarchy.xml".format(wn_domains_dir))
root = tree.getroot()
for elem in root.findall("categ"):
name = elem.get("name")
if name == "root":
Emotion.emotions["root"] = Emotion("root")
else:
Emotion.emotions[name] = Emotion(name, elem.get("isa"))
def get_emotion(self, word, pos):
"""Returns the emotion of the word.
word -- the word (str)
pos -- part-of-speech (str)
"""
if pos in self.flat_pos:
pos = self.flat_pos[pos]
synsets = self.wn16.synsets(word, self.wn_pos[pos])
if synsets:
offset = synsets[0].offset()
if offset in self.synsets[pos]:
return self.synsets[pos][offset]
return None
if __name__ == "__main__":
wordnet16, wndomains32, word, pos = sys.argv[1:5]
wna = WNAffect(wordnet16, wndomains32)
print wna.get_emotion(word, pos)

View File

@ -0,0 +1,36 @@
from senpy.plugins import AnalysisPlugin
from senpy.models import Response, Entry
class ExamplePlugin(AnalysisPlugin):
'''A *VERY* simple plugin that exemplifies the development of Senpy Plugins'''
name = "example-plugin"
author = "@balkian"
version = "0.1"
extra_params = {
"parameter": {
"@id": "parameter",
"description": "this parameter does nothing, it is only an example",
"aliases": ["parameter", "param"],
"required": True,
"default": 42
}
}
custom_attribute = "42"
def analyse_entry(self, entry, activity):
params = activity.params
self.log.debug('Analysing with the example.')
self.log.debug('The answer to this response is: %s.' % params['parameter'])
resp = Response()
entry['example:reversed'] = entry.text[::-1]
entry['example:the_answer'] = params['parameter']
yield entry
test_cases = [{
'input': 'hello',
'expected': {
'example:reversed': 'olleh'
}
}]

View File

@ -0,0 +1,8 @@
Deploy senpy to a kubernetes cluster.
The files are templates, which need to be expanded with something like envsubst.
Example usage:
```
cat k8s/*.ya*ml | envsubst | kubectl apply -n senpy -f -
```

View File

@ -0,0 +1,36 @@
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: senpy-$NAME-latest
spec:
replicas: 1
template:
metadata:
labels:
role: $NAME-latest
app: test
spec:
containers:
- name: senpy-latest
image: $IMAGEWTAG
imagePullPolicy: Always
resources:
limits:
memory: "2048Mi"
cpu: "1000m"
ports:
- name: web
containerPort: 5000
volumeMounts:
# name must match the volume name below
- name: senpy-data
mountPath: "/data"
subPath: data
env:
- name: SENPY_DATA
value: '/data'
volumes:
- name: senpy-data
persistentVolumeClaim:
claimName: senpy-pvc

View File

@ -0,0 +1,24 @@
---
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
name: senpy-$NAME-ingress
annotations:
ingress.kubernetes.io/proxy-body-size: 0m
ingress.kubernetes.io/proxy-buffer-size: "256k"
spec:
rules:
- host: senpy.cluster.gsi.dit.upm.es
http:
paths:
- path: /
backend:
serviceName: senpy-$NAME-latest
servicePort: 5000
- host: senpy.gsi.upm.es
http:
paths:
- path: /
backend:
serviceName: senpy-$NAME-latest
servicePort: 5000

View File

@ -0,0 +1,12 @@
---
apiVersion: v1
kind: Service
metadata:
name: senpy-$NAME-latest
spec:
type: ClusterIP
ports:
- port: 5000
protocol: TCP
selector:
role: $NAME-latest

View File

@ -0,0 +1,28 @@
# Sentiment basic plugin
This plugin is based on the classifier developed for the TASS 2015 competition. It has been developed for Spanish and English. This is a demo plugin that uses only some features from the TASS 2015 classifier. To use the entirely functional classifier you can use the service in: http://senpy.cluster.gsi.dit.upm.es
There is more information avaliable in:
- Aspect based Sentiment Analysis of Spanish Tweets, Oscar Araque and Ignacio Corcuera-Platas and Constantino Román-Gómez and Carlos A. Iglesias and J. Fernando Sánchez-Rada. http://gsi.dit.upm.es/es/investigacion/publicaciones?view=publication&task=show&id=376
## Usage
Params accepted:
- Language: Spanish (es).
- Input: text to analyse.
Example request:
```
http://senpy.cluster.gsi.dit.upm.es/api/?algo=sentiment-basic&language=es&input=I%20love%20Madrid
```
Example respond: This plugin follows the standard for the senpy plugin response. For more information, please visit [senpy documentation](http://senpy.readthedocs.io). Specifically, NIF API section.
This plugin only supports **python2**
![alt GSI Logo][logoGSI]
[logoGSI]: http://www.gsi.dit.upm.es/images/stories/logos/gsi.png "GSI Logo"

View File

@ -0,0 +1,177 @@
#!/usr/bin/python
# -*- coding: utf-8 -*-
import os
import sys
import string
import nltk
import pickle
from sentiwn import SentiWordNet
from nltk.corpus import wordnet as wn
from textblob import TextBlob
from scipy.interpolate import interp1d
from os import path
from senpy.plugins import SentimentBox, SenpyPlugin
from senpy.models import Results, Entry, Sentiment, Error
if sys.version_info[0] >= 3:
unicode = str
class SentimentBasic(SentimentBox):
'''
Sentiment classifier using rule-based classification for Spanish. Based on english to spanish translation and SentiWordNet sentiment knowledge. This is a demo plugin that uses only some features from the TASS 2015 classifier. To use the entirely functional classifier you can use the service in: http://senpy.cluster.gsi.dit.upm.es.
'''
name = "sentiment-basic"
author = "github.com/nachtkatze"
version = "0.1.1"
extra_params = {
"language": {
"description": "language of the text",
"aliases": ["language", "l"],
"required": True,
"options": ["en","es", "it", "fr"],
"default": "en"
}
}
sentiword_path = "SentiWordNet_3.0.txt"
pos_path = "unigram_spanish.pickle"
maxPolarityValue = 1
minPolarityValue = -1
nltk_resources = ['punkt','wordnet', 'omw']
with_polarity = False
def _load_swn(self):
self.swn_path = self.find_file(self.sentiword_path)
swn = SentiWordNet(self.swn_path)
return swn
def _load_pos_tagger(self):
self.pos_path = self.find_file(self.pos_path)
with open(self.pos_path, 'rb') as f:
tagger = pickle.load(f)
return tagger
def activate(self, *args, **kwargs):
self._swn = self._load_swn()
self._pos_tagger = self._load_pos_tagger()
def _remove_punctuation(self, tokens):
return [t for t in tokens if t not in string.punctuation]
def _tokenize(self, text):
sentence_ = {}
words = nltk.word_tokenize(text)
sentence_['sentence'] = text
tokens_ = [w.lower() for w in words]
sentence_['tokens'] = self._remove_punctuation(tokens_)
return sentence_
def _pos(self, tokens):
tokens['tokens'] = self._pos_tagger.tag(tokens['tokens'])
return tokens
def _compare_synsets(self, synsets, tokens):
for synset in synsets:
for word, lemmas in tokens['lemmas'].items():
for lemma in lemmas:
synset_ = lemma.synset()
if synset == synset_:
return synset
return None
def predict_one(self, features, activity):
language = activity.param("language")
text = features[0]
tokens = self._tokenize(text)
tokens = self._pos(tokens)
sufixes = {'es':'spa','en':'eng','it':'ita','fr':'fra'}
tokens['lemmas'] = {}
for w in tokens['tokens']:
lemmas = wn.lemmas(w[0], lang=sufixes[language])
if len(lemmas) == 0:
continue
tokens['lemmas'][w[0]] = lemmas
if language == "en":
trans = TextBlob(unicode(text))
else:
try:
trans = TextBlob(unicode(text)).translate(from_lang=language,to='en')
except Exception as ex:
raise Error('Could not translate the text from "{}" to "{}": {}'.format(language,
'en',
str(ex)))
useful_synsets = {}
for w_i, t_w in enumerate(trans.sentences[0].words):
synsets = wn.synsets(trans.sentences[0].words[w_i])
if len(synsets) == 0:
continue
eq_synset = self._compare_synsets(synsets, tokens)
useful_synsets[t_w] = eq_synset
scores = {}
scores = {}
if useful_synsets != None:
for word in useful_synsets:
if useful_synsets[word] is None:
continue
temp_scores = self._swn.get_score(useful_synsets[word].name().split('.')[0].replace(' ',' '))
for score in temp_scores:
if score['synset'] == useful_synsets[word]:
t_score = score['pos'] - score['neg']
f_score = 'neu'
if t_score > 0:
f_score = 'pos'
elif t_score < 0:
f_score = 'neg'
score['score'] = f_score
scores[word] = score
break
g_score = 0.5
for i in scores:
n_pos = 0.0
n_neg = 0.0
for w in scores:
if scores[w]['score'] == 'pos':
n_pos += 1.0
elif scores[w]['score'] == 'neg':
n_neg += 1.0
inter = interp1d([-1.0, 1.0], [0.0, 1.0])
try:
g_score = (n_pos - n_neg) / (n_pos + n_neg)
g_score = float(inter(g_score))
except:
if n_pos == 0 and n_neg == 0:
g_score = 0.5
if g_score > 0.5: # Positive
return [1, 0, 0]
elif g_score < 0.5: # Negative
return [0, 0, 1]
else:
return [0, 1, 0]
test_cases = [
{
'input': 'Odio ir al cine',
'params': {'language': 'es'},
'polarity': 'marl:Negative'
},
{
'input': 'El cielo está nublado',
'params': {'language': 'es'},
'polarity': 'marl:Neutral'
},
{
'input': 'Esta tarta está muy buena',
'params': {'language': 'es'},
'polarity': 'marl:Negative' # SURPRISINGLY!
}
]

View File

@ -0,0 +1,7 @@
---
module: sentiment-basic
requirements:
- nltk>=3.0.5
- scipy>=0.14.0
- textblob

View File

@ -0,0 +1,70 @@
#!/usr/bin/env python
"""
Author : Jaganadh Gopinadhan <jaganadhg@gmail.com>
Copywright (C) : Jaganadh Gopinadhan
Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
"""
import sys,os
import re
from nltk.corpus import wordnet
class SentiWordNet(object):
"""
Interface to SentiWordNet
"""
def __init__(self,swn_file):
"""
"""
self.swn_file = swn_file
self.pos_synset = self.__parse_swn_file()
def __parse_swn_file(self):
"""
Parse the SentiWordNet file and populate the POS and SynsetID hash
"""
pos_synset_hash = {}
swn_data = open(self.swn_file,'r').readlines()
head_less_swn_data = filter((lambda line: not re.search(r"^\s*#",\
line)), swn_data)
for data in head_less_swn_data:
fields = data.strip().split("\t")
try:
pos,syn_set_id,pos_score,neg_score,syn_set_score,\
gloss = fields
except:
print("Found data without all details")
pass
if pos and syn_set_score:
pos_synset_hash[(pos,int(syn_set_id))] = (float(pos_score),\
float(neg_score))
return pos_synset_hash
def get_score(self,word,pos=None):
"""
Get score for a given word/word pos combination
"""
senti_scores = []
synsets = wordnet.synsets(word,pos)
for synset in synsets:
if (synset.pos(), synset.offset()) in self.pos_synset:
pos_val, neg_val = self.pos_synset[(synset.pos(), synset.offset())]
senti_scores.append({"pos":pos_val,"neg":neg_val,\
"obj": 1.0 - (pos_val - neg_val),'synset':synset})
return senti_scores

View File

@ -0,0 +1,5 @@
.*
.env
__pycache__
.pyc
VERSION

View File

@ -0,0 +1,67 @@
# Uncomment if you want to use docker-in-docker
# image: gsiupm/dockermake:latest
# services:
# - docker:dind
# When using dind, it's wise to use the overlayfs driver for
# improved performance.
stages:
- test
- push
- deploy
- clean
before_script:
- make -e login
.test: &test_definition
stage: test
script:
- make -e test-$PYTHON_VERSION
test-3.5:
<<: *test_definition
variables:
PYTHON_VERSION: "3.5"
.image: &image_definition
stage: push
script:
- make -e push-$PYTHON_VERSION
only:
- tags
- triggers
push-3.5:
<<: *image_definition
variables:
PYTHON_VERSION: "3.5"
push-latest:
<<: *image_definition
variables:
PYTHON_VERSION: latest
only:
- tags
- triggers
deploy:
stage: deploy
environment: production
script:
- make -e deploy
only:
- tags
- triggers
clean :
stage: clean
script:
- make -e clean
when: manual
cleanup_py:
stage: clean
when: always # this is important; run even if preceding stages failed.
script:
- docker logout

View File

@ -0,0 +1,27 @@
These makefiles are recipes for several common tasks in different types of projects.
To add them to your project, simply do:
```
git remote add makefiles ssh://git@lab.cluster.gsi.dit.upm.es:2200/docs/templates/makefiles.git
git subtree add --prefix=.makefiles/ makefiles master
touch Makefile
echo "include .makefiles/base.mk" >> Makefile
```
Now you can take advantage of the recipes.
For instance, to add useful targets for a python project, just add this to your Makefile:
```
include .makefiles/python.mk
```
You may need to set special variables like the name of your project or the python versions you're targetting.
Take a look at each specific `.mk` file for more information, and the `Makefile` in the [senpy](https://lab.cluster.gsi.dit.upm.es/senpy/senpy) project for a real use case.
If you update the makefiles from your repository, make sure to push the changes for review in upstream (this repository):
```
make makefiles-push
```
It will automatically commit all unstaged changes in the .makefiles folder.

View File

@ -0,0 +1,36 @@
export
NAME ?= $(shell basename $(CURDIR))
VERSION ?= $(shell git describe --tags --dirty 2>/dev/null)
ifeq ($(VERSION),)
VERSION:="unknown"
endif
# Get the location of this makefile.
MK_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
-include .env
-include ../.env
help: ## Show this help.
@fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/\(.*:\)[^#]*##\s*\(.*\)/\1\t\2/' | column -t -s " "
config: ## Load config from the environment. You should run it once in every session before other tasks. Run: eval $(make config)
@awk '{ print "export " $$0}' ../.env
@awk '{ print "export " $$0}' .env
@echo "# Please, run: "
@echo "# eval \$$(make config)"
# If you need to run a command on the key/value pairs, use this:
# @awk '{ split($$0, a, "="); "echo " a[2] " | base64 -w 0" |& getline b64; print "export " a[1] "=" a[2]; print "export " a[1] "_BASE64=" b64}' .env
ci: ## Run a task using gitlab-runner. Only use to debug problems in the CI pipeline
gitlab-runner exec shell --builds-dir '.builds' --env CI_PROJECT_NAME=$(NAME) ${action}
include $(MK_DIR)/makefiles.mk
include $(MK_DIR)/docker.mk
include $(MK_DIR)/git.mk
info:: ## List all variables
env
.PHONY:: config help ci

View File

@ -0,0 +1,29 @@
IMAGENAME?=$(NAME)
IMAGEWTAG?=$(IMAGENAME):$(VERSION)
docker-login: ## Log in to the registry. It will only be used in the server, or when running a CI task locally (if CI_BUILD_TOKEN is set).
ifeq ($(CI_BUILD_TOKEN),)
@echo "Not logging in to the docker registry" "$(CI_REGISTRY)"
else
@docker login -u gitlab-ci-token -p $(CI_BUILD_TOKEN) $(CI_REGISTRY)
endif
ifeq ($(HUB_USER),)
@echo "Not logging in to global the docker registry"
else
@docker login -u $(HUB_USER) -p $(HUB_PASSWORD)
endif
docker-clean: ## Remove docker credentials
ifeq ($(HUB_USER),)
else
@docker logout
endif
login:: docker-login
clean:: docker-clean
docker-info:
@echo IMAGEWTAG=${IMAGEWTAG}
.PHONY:: docker-login docker-clean login clean

View File

@ -0,0 +1,28 @@
commit:
git commit -a
tag:
git tag ${VERSION}
git-push::
git push --tags -u origin HEAD
git-pull:
git pull --all
push-github: ## Push the code to github. You need to set up GITHUB_DEPLOY_KEY
ifeq ($(GITHUB_DEPLOY_KEY),)
else
$(eval KEY_FILE := "$(shell mktemp)")
@echo "$(GITHUB_DEPLOY_KEY)" > $(KEY_FILE)
@git remote rm github-deploy || true
git remote add github-deploy $(GITHUB_REPO)
-@GIT_SSH_COMMAND="ssh -i $(KEY_FILE)" git fetch github-deploy $(CI_COMMIT_REF_NAME)
@GIT_SSH_COMMAND="ssh -i $(KEY_FILE)" git push github-deploy HEAD:$(CI_COMMIT_REF_NAME)
rm $(KEY_FILE)
endif
push:: git-push
pull:: git-pull
.PHONY:: commit tag push git-push git-pull push-github

View File

@ -0,0 +1,51 @@
# Deployment with Kubernetes
# KUBE_CA_PEM_FILE is the path of a certificate file. It automatically set by GitLab
# if you enable Kubernetes integration in a project.
#
# As of this writing, Kubernetes integration can not be set on a group level, so it has to
# be manually set in every project.
# Alternatively, we use a custom KUBE_CA_BUNDLE environment variable, which can be set at
# the group level. In this case, the variable contains the whole content of the certificate,
# which we dump to a temporary file
#
# Check if the KUBE_CA_PEM_FILE exists. Otherwise, create it from KUBE_CA_BUNDLE
KUBE_CA_TEMP=false
ifndef KUBE_CA_PEM_FILE
KUBE_CA_PEM_FILE:=$$PWD/.ca.crt
CREATED:=$(shell echo -e "$(KUBE_CA_BUNDLE)" > $(KUBE_CA_PEM_FILE))
endif
KUBE_TOKEN?=""
KUBE_NAMESPACE?=$(NAME)
KUBECTL=docker run --rm -v $(KUBE_CA_PEM_FILE):/tmp/ca.pem -i lachlanevenson/k8s-kubectl --server="$(KUBE_URL)" --token="$(KUBE_TOKEN)" --certificate-authority="/tmp/ca.pem" -n $(KUBE_NAMESPACE)
CI_COMMIT_REF_NAME?=master
info:: ## Print variables. Useful for debugging.
@echo "#KUBERNETES"
@echo KUBE_URL=$(KUBE_URL)
@echo KUBE_CA_PEM_FILE=$(KUBE_CA_PEM_FILE)
@echo KUBE_CA_BUNDLE=$$KUBE_CA_BUNDLE
@echo KUBE_TOKEN=$(KUBE_TOKEN)
@echo KUBE_NAMESPACE=$(KUBE_NAMESPACE)
@echo KUBECTL=$(KUBECTL)
@echo "#CI"
@echo CI_PROJECT_NAME=$(CI_PROJECT_NAME)
@echo CI_REGISTRY=$(CI_REGISTRY)
@echo CI_REGISTRY_USER=$(CI_REGISTRY_USER)
@echo CI_COMMIT_REF_NAME=$(CI_COMMIT_REF_NAME)
@echo "CREATED=$(CREATED)"
#
# Deployment and advanced features
#
deploy: ## Deploy to kubernetes using the credentials in KUBE_CA_PEM_FILE (or KUBE_CA_BUNDLE ) and TOKEN
@ls k8s/*.yaml k8s/*.yml k8s/*.tmpl 2>/dev/null || true
@cat k8s/*.yaml k8s/*.yml k8s/*.tmpl 2>/dev/null | envsubst | $(KUBECTL) apply -f -
deploy-check: ## Get the deployed configuration.
@$(KUBECTL) get deploy,pods,svc,ingress
.PHONY:: info deploy deploy-check

View File

@ -0,0 +1,17 @@
makefiles-remote:
@git remote add makefiles ssh://git@lab.cluster.gsi.dit.upm.es:2200/docs/templates/makefiles.git 2>/dev/null || true
makefiles-commit: makefiles-remote
git add -f .makefiles
git commit -em "Updated makefiles from ${NAME}"
makefiles-push:
git subtree push --prefix=.makefiles/ makefiles $(NAME)
makefiles-pull: makefiles-remote
git subtree pull --prefix=.makefiles/ makefiles master --squash
pull:: makefiles-pull
push:: makefiles-push
.PHONY:: makefiles-remote makefiles-commit makefiles-push makefiles-pull pull push

View File

@ -0,0 +1,5 @@
init: ## Init pre-commit hooks (i.e. enforcing format checking before allowing a commit)
pip install --user pre-commit
pre-commit install
.PHONY:: init

View File

@ -0,0 +1,100 @@
PYVERSIONS ?= 3.5
PYMAIN ?= $(firstword $(PYVERSIONS))
TARNAME ?= $(NAME)-$(VERSION).tar.gz
VERSIONFILE ?= $(NAME)/VERSION
DEVPORT ?= 6000
.FORCE:
version: .FORCE
@echo $(VERSION) > $(VERSIONFILE)
@echo $(VERSION)
yapf: ## Format python code
yapf -i -r $(NAME)
yapf -i -r tests
dockerfiles: $(addprefix Dockerfile-,$(PYVERSIONS)) ## Generate dockerfiles for each python version
@unlink Dockerfile >/dev/null
ln -s Dockerfile-$(PYMAIN) Dockerfile
Dockerfile-%: Dockerfile.template ## Generate a specific dockerfile (e.g. Dockerfile-2.7)
sed "s/{{PYVERSION}}/$*/" Dockerfile.template > Dockerfile-$*
quick_build: $(addprefix build-, $(PYMAIN))
build: $(addprefix build-, $(PYVERSIONS)) ## Build all images / python versions
build-%: version Dockerfile-% ## Build a specific version (e.g. build-2.7)
docker build -t '$(IMAGEWTAG)-python$*' --cache-from $(IMAGENAME):python$* -f Dockerfile-$* .;
dev-%: ## Launch a specific development environment using docker (e.g. dev-2.7)
@docker start $(NAME)-dev$* || (\
$(MAKE) build-$*; \
docker run -d -w /usr/src/app/ -p $(DEVPORT):5000 -v $$PWD:/usr/src/app --entrypoint=/bin/bash -ti --name $(NAME)-dev$* '$(IMAGEWTAG)-python$*'; \
)\
docker exec -ti $(NAME)-dev$* bash
dev: dev-$(PYMAIN) ## Launch a development environment using docker, using the default python version
quick_test: test-$(PYMAIN)
test-%: ## Run setup.py from in an isolated container, built from the base image. (e.g. test-2.7)
# This speeds tests up because the image has most (if not all) of the dependencies already.
docker rm $(NAME)-test-$* || true
docker create -ti --name $(NAME)-test-$* --entrypoint="" -w /usr/src/app/ $(IMAGENAME):python$* python setup.py test
docker cp . $(NAME)-test-$*:/usr/src/app
docker start -a $(NAME)-test-$*
test: $(addprefix test-,$(PYVERSIONS)) ## Run the tests with the main python version
run-%: build-%
docker run --rm -p $(DEVPORT):5000 -ti '$(IMAGEWTAG)-python$(PYMAIN)' --default-plugins
run: run-$(PYMAIN)
# Pypy - Upload a package
dist/$(TARNAME): version
python setup.py sdist;
sdist: dist/$(TARNAME) ## Generate the distribution file (wheel)
pip_test-%: sdist ## Test the distribution file using pip install and a specific python version (e.g. pip_test-2.7)
docker run --rm -v $$PWD/dist:/dist/ python:$* pip install /dist/$(TARNAME);
pip_test: $(addprefix pip_test-,$(PYVERSIONS)) ## Test pip installation with the main python version
pip_upload: pip_test ## Upload package to pip
python setup.py sdist upload ;
# Pushing to docker
push-latest: $(addprefix push-latest-,$(PYVERSIONS)) ## Push the "latest" tag to dockerhub
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGENAME)'
docker push '$(IMAGENAME):latest'
docker push '$(IMAGEWTAG)'
push-latest-%: build-% ## Push the latest image for a specific python version
docker tag $(IMAGENAME):$(VERSION)-python$* $(IMAGENAME):python$*
docker push $(IMAGENAME):$(VERSION)-python$*
docker push $(IMAGENAME):python$*
push-%: build-% ## Push the image of the current version (tagged). e.g. push-2.7
docker push $(IMAGENAME):$(VERSION)-python$*
push:: $(addprefix push-,$(PYVERSIONS)) ## Push an image with the current version for every python version
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker push $(IMAGENAME):$(VERSION)
clean:: ## Clean older docker images and containers related to this project and dev environments
@docker stop $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
@docker rm $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
@docker ps -a | grep $(IMAGENAME) | awk '{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1;}}' | xargs docker rm -v 2>/dev/null|| true
@docker images | grep $(IMAGENAME) | awk '{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1":"$$2;}}' | xargs docker rmi 2>/dev/null|| true
.PHONY:: yapf dockerfiles Dockerfile-% quick_build build build-% dev-% quick-dev test quick_test push-latest push-latest-% push-% push version .FORCE

View File

@ -0,0 +1 @@
Dockerfile-3.5

View File

@ -0,0 +1,4 @@
FROM gsiupm/senpy:0.10.4-python3.5
MAINTAINER manuel.garcia-amado.sancho@alumnos.upm.es

View File

@ -0,0 +1,4 @@
FROM gsiupm/senpy:0.10.4-python{{PYVERSION}}
MAINTAINER manuel.garcia-amado.sancho@alumnos.upm.es

View File

@ -0,0 +1,9 @@
NAME:=meaningcloud
VERSIONFILE:=VERSION
IMAGENAME:=registry.cluster.gsi.dit.upm.es/senpy/sentiment-meaningcloud
PYVERSIONS:= 3.5
DEVPORT:=5000
include .makefiles/base.mk
include .makefiles/k8s.mk
include .makefiles/python.mk

View File

@ -0,0 +1,34 @@
# Senpy Plugin MeaningCloud
MeaningCloud plugin uses API from Meaning Cloud to perform sentiment analysis.
For more information about Meaning Cloud and its services, please visit: https://www.meaningcloud.com/developer/apis
## Usage
To use this plugin, you need to obtain an API key from meaningCloud signing up here: https://www.meaningcloud.com/developer/login
When you had obtained the meaningCloud API Key, you have to provide it to the plugin, using the param **apiKey**.
To use this plugin, you should use a GET Requests with the following possible params:
Params:
- Language: English (en) and Spanish (es). (default: en)
- API Key: the API key from Meaning Cloud. Aliases: ["apiKey","meaningCloud-key"]. (required)
- Input: text to analyse.(required)
- Model: model provided to Meaning Cloud API (for general domain). (default: general)
## Example of Usage
Example request:
```
http://senpy.cluster.gsi.dit.upm.es/api/?algo=meaningCloud&language=en&apiKey=<put here your API key>&input=I%20love%20Madrid
```
Example respond: This plugin follows the standard for the senpy plugin response. For more information, please visit [senpy documentation](http://senpy.readthedocs.io). Specifically, NIF API section.
This plugin supports **python2.7** and **python3**.
![alt GSI Logo][logoGSI]
[logoGSI]: http://www.gsi.dit.upm.es/images/stories/logos/gsi.png "GSI Logo"

View File

@ -0,0 +1,28 @@
version: '3'
services:
dev:
image: gsiupm/senpy:latest
entrypoint: ["/bin/bash"]
working_dir: "/senpy-plugins"
tty: true
ports:
- "127.0.0.1:5005:5000"
volumes:
- ".:/senpy-plugins"
test:
image: gsiupm/senpy:latest
entrypoint: ["py.test"]
working_dir: "/usr/src/app/"
volumes:
- ".:/senpy-plugins/"
command:
[]
meaningcloud:
image: "${IMAGENAME-gsiupm/meaningcloud}:${VERSION-dev}"
build:
context: .
dockerfile: Dockerfile-3.5
ports:
- 5001:5000
volumes:
- "./data:/data"

View File

@ -0,0 +1,7 @@
Deploy senpy to a kubernetes cluster.
Usage:
```
kubectl apply -f . -n senpy
```

View File

@ -0,0 +1,27 @@
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: ${NAME}
spec:
replicas: 1
template:
metadata:
labels:
role: senpy-plugin
app: ${NAME}
spec:
containers:
- name: senpy-latest
image: ${CI_REGISTRY_IMAGE}:${VERSION}
imagePullPolicy: Always
args:
- "-f"
- "/senpy-plugins"
resources:
limits:
memory: "512Mi"
cpu: "1000m"
ports:
- name: web
containerPort: 5000

View File

@ -0,0 +1,14 @@
---
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
name: ${NAME}
spec:
rules:
- host: ${NAME}.senpy.cluster.gsi.dit.upm.es
http:
paths:
- path: /
backend:
serviceName: ${NAME}
servicePort: 5000

View File

@ -0,0 +1,12 @@
---
apiVersion: v1
kind: Service
metadata:
name: ${NAME}
spec:
type: ClusterIP
ports:
- port: 5000
protocol: TCP
selector:
app: ${NAME}

View File

@ -0,0 +1,254 @@
# -*- coding: utf-8 -*-
import time
import requests
import json
import string
import os
from os import path
import time
from senpy.plugins import SentimentPlugin
from senpy.models import Results, Entry, Entity, Topic, Sentiment, Error
from senpy.utils import check_template
class MeaningCloudPlugin(SentimentPlugin):
'''
Sentiment analysis with meaningCloud service.
To use this plugin, you need to obtain an API key from meaningCloud signing up here:
https://www.meaningcloud.com/developer/login
When you had obtained the meaningCloud API Key, you have to provide it to the plugin, using param apiKey.
Example request:
http://senpy.cluster.gsi.dit.upm.es/api/?algo=meaningCloud&language=en&apiKey=YOUR_API_KEY&input=I%20love%20Madrid.
'''
name = 'sentiment-meaningcloud'
author = 'GSI UPM'
version = "1.1"
maxPolarityValue = 1
minPolarityValue = -1
extra_params = {
"language": {
"description": "language of the input",
"aliases": ["language", "l"],
"required": True,
"options": ["en","es","ca","it","pt","fr","auto"],
"default": "auto"
},
"apikey":{
"description": "API key for the meaningcloud service. See https://www.meaningcloud.com/developer/login",
"aliases": ["apiKey", "meaningcloud-key", "meaningcloud-apikey"],
"required": True
}
}
def _polarity(self, value):
if 'NONE' in value:
polarity = 'marl:Neutral'
polarityValue = 0
elif 'N' in value:
polarity = 'marl:Negative'
polarityValue = -1
elif 'P' in value:
polarity = 'marl:Positive'
polarityValue = 1
return polarity, polarityValue
def analyse_entry(self, entry, activity):
params = activity.params
txt = entry['nif:isString']
api = 'http://api.meaningcloud.com/'
lang = params.get("language")
model = "general"
key = params["apikey"]
parameters = {
'key': key,
'model': model,
'lang': lang,
'of': 'json',
'txt': txt,
'tt': 'a'
}
try:
r = requests.post(
api + "sentiment-2.1", params=parameters, timeout=3)
parameters['lang'] = r.json()['model'].split('_')[1]
lang = parameters['lang']
r2 = requests.post(
api + "topics-2.0", params=parameters, timeout=3)
except requests.exceptions.Timeout:
raise Error("Meaning Cloud API does not response")
api_response = r.json()
api_response_topics = r2.json()
if not api_response.get('score_tag'):
raise Error(r.json())
entry['language_detected'] = lang
self.log.debug(api_response)
agg_polarity, agg_polarityValue = self._polarity(
api_response.get('score_tag', None))
agg_opinion = Sentiment(
id="Opinion0",
marl__hasPolarity=agg_polarity,
marl__polarityValue=agg_polarityValue,
marl__opinionCount=len(api_response['sentence_list']))
agg_opinion.prov(self)
entry.sentiments.append(agg_opinion)
self.log.debug(api_response['sentence_list'])
count = 1
for sentence in api_response['sentence_list']:
for nopinion in sentence['segment_list']:
self.log.debug(nopinion)
polarity, polarityValue = self._polarity(
nopinion.get('score_tag', None))
opinion = Sentiment(
id="Opinion{}".format(count),
marl__hasPolarity=polarity,
marl__polarityValue=polarityValue,
marl__aggregatesOpinion=agg_opinion.get('id'),
nif__anchorOf=nopinion.get('text', None),
nif__beginIndex=int(nopinion.get('inip', None)),
nif__endIndex=int(nopinion.get('endp', None)))
count += 1
opinion.prov(self)
entry.sentiments.append(opinion)
mapper = {'es': 'es.', 'en': '', 'ca': 'es.', 'it':'it.', 'fr':'fr.', 'pt':'pt.'}
for sent_entity in api_response_topics['entity_list']:
resource = "_".join(sent_entity.get('form', None).split())
entity = Entity(
id="Entity{}".format(sent_entity.get('id')),
itsrdf__taIdentRef="http://{}dbpedia.org/resource/{}".format(
mapper[lang], resource),
nif__anchorOf=sent_entity.get('form', None),
nif__beginIndex=int(sent_entity['variant_list'][0].get('inip', None)),
nif__endIndex=int(sent_entity['variant_list'][0].get('endp', None)))
sementity = sent_entity['sementity'].get('type', None).split(">")[-1]
entity['@type'] = "ODENTITY_{}".format(sementity)
entity.prov(self)
if 'senpy:hasEntity' not in entry:
entry['senpy:hasEntity'] = []
entry['senpy:hasEntity'].append(entity)
for topic in api_response_topics['concept_list']:
if 'semtheme_list' in topic:
for theme in topic['semtheme_list']:
concept = Topic()
concept.id = "Topic{}".format(topic.get('id'))
concept['@type'] = "ODTHEME_{}".format(theme['type'].split(">")[-1])
concept['fam:topic-reference'] = "http://dbpedia.org/resource/{}".format(theme['type'].split('>')[-1])
entry.prov(self)
if 'senpy:hasTopic' not in entry:
entry['senpy:hasTopic'] = []
entry['senpy:hasTopic'].append(concept)
yield entry
test_cases = [
{
'params': {
'algo': 'sentiment-meaningCloud',
'intype': 'direct',
'expanded-jsonld': 0,
'informat': 'text',
'prefix': '',
'plugin_type': 'analysisPlugin',
'urischeme': 'RFC5147String',
'outformat': 'json-ld',
'conversion': 'full',
'language': 'en',
'apikey': '00000',
'algorithm': 'sentiment-meaningCloud'
},
'input': 'Hello World Obama',
'expected': {
'marl:hasOpinion': [
{'marl:hasPolarity': 'marl:Neutral'}],
'senpy:hasEntity': [
{'itsrdf:taIdentRef': 'http://dbpedia.org/resource/Obama'}],
'senpy:hasTopic': [
{'fam:topic-reference': 'http://dbpedia.org/resource/Astronomy'}]
},
'responses': [
{
'url': 'http://api.meaningcloud.com/sentiment-2.1',
'method': 'POST',
'json': {
'model': 'general_en',
'sentence_list': [{
'text':
'Hello World',
'endp':
'10',
'inip':
'0',
'segment_list': [{
'text':
'Hello World',
'segment_type':
'secondary',
'confidence':
'100',
'inip':
'0',
'agreement':
'AGREEMENT',
'endp':
'10',
'polarity_term_list': [],
'score_tag':
'NONE'
}],
'score_tag':
'NONE',
}],
'score_tag':
'NONE'
}
}, {
'url': 'http://api.meaningcloud.com/topics-2.0',
'method': 'POST',
'json': {
'entity_list': [{
'form':
'Obama',
'id':
'__1265958475430276310',
'variant_list': [{
'endp': '16',
'form': 'Obama',
'inip': '12'
}],
'sementity': {
'fiction': 'nonfiction',
'confidence': 'uncertain',
'class': 'instance',
'type': 'Top>Person'
}
}],
'concept_list': [{
'form':
'world',
'id':
'5c053cd39d',
'relevance':
'100',
'semtheme_list': [{
'id': 'ODTHEME_ASTRONOMY',
'type': 'Top>NaturalSciences>Astronomy'
}]
}],
}
}]
}
]
if __name__ == '__main__':
from senpy import easy_test
easy_test()

View File

@ -0,0 +1,87 @@
#
# Copyright 2014 Grupo de Sistemas Inteligentes (GSI) DIT, UPM
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import requests
import json
from senpy.plugins import SentimentBox
from senpy import easy_test
ENDPOINT = 'http://sentiment.gelbukh.com/sentiment/run.php'
class Senticnet(SentimentBox):
'''Connects to the SenticNet free polarity detection API: http://sentiment.gelbukh.com/sentiment/'''
author = "@balkian"
version = '0.1'
url = "https://github.com/gsi-upm/senpy-plugins-community"
extra_params = {
}
classes = ['marl:Positive', 'marl:Neutral', 'marl:Negative']
binary = True
def predict_one(self, features, activity):
text = ' '.join(features)
res = requests.post(ENDPOINT,
data={'input': text})
if '-' not in res.text:
raise Exception('Invalid response from server: {}'.format(res.text))
label = res.text.split('-')[1].lower()
if 'positive' in label:
return [1, 0, 0]
elif 'negative' in label:
return [0, 0, 1]
return [0, 1, 0]
test_cases = [
{
'entry': {
'nif:isString': 'I love Titanic'
},
'params': {},
'expected': {
"nif:isString": "I love Titanic",
'marl:hasOpinion': [
{
'marl:hasPolarity': 'marl:Positive',
}
]
},
}, {
'entry': {
'nif:isString': 'I hate my life'
},
'params': {},
'expected': {
"nif:isString": "I hate my life",
'marl:hasOpinion': [
{
'marl:hasPolarity': 'marl:Negative',
}
]
},
},
]
if __name__ == '__main__':
easy_test()

View File

@ -0,0 +1,42 @@
# Sentimet-vader plugin
Vader is a plugin developed at GSI UPM for sentiment analysis.
The response of this plugin uses [Marl ontology](https://www.gsi.dit.upm.es/ontologies/marl/) developed at GSI UPM for semantic web.
## Acknowledgements
This plugin uses the vaderSentiment module underneath, which is described in the paper:
VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text
C.J. Hutto and Eric Gilbert
Eighth International Conference on Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014.
If you use this plugin in your research, please cite the above paper.
For more information about the functionality, check the official repository
https://github.com/cjhutto/vaderSentiment
## Usage
Parameters:
- Language: es (Spanish), en(English).
- Input: Text to analyse.
Example request:
```
http://senpy.cluster.gsi.dit.upm.es/api/?algo=sentiment-vader&language=en&input=I%20love%20Madrid
```
Example respond: This plugin follows the standard for the senpy plugin response. For more information, please visit [senpy documentation](http://senpy.readthedocs.io). Specifically, NIF API section.
This plugin supports **python3**
![alt GSI Logo][logoGSI]
[logoGSI]: http://www.gsi.dit.upm.es/images/stories/logos/gsi.png "GSI Logo"
========

View File

@ -0,0 +1,368 @@
#!/usr/bin/python
# coding: utf-8
'''
Created on July 04, 2013
@author: C.J. Hutto
Citation Information
If you use any of the VADER sentiment analysis tools
(VADER sentiment lexicon or Python code for rule-based sentiment
analysis engine) in your work or research, please cite the paper.
For example:
Hutto, C.J. & Gilbert, E.E. (2014). VADER: A Parsimonious Rule-based Model for
Sentiment Analysis of Social Media Text. Eighth International Conference on
Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014.
'''
import os, math, re, sys, fnmatch, string
import codecs
def make_lex_dict(f):
maps = {}
with codecs.open(f, encoding='iso-8859-1') as f:
for wmsr in f:
w, m = wmsr.strip().split('\t')[:2]
maps[w] = m
return maps
f = 'vader_sentiment_lexicon.txt' # empirically derived valence ratings for words, emoticons, slang, swear words, acronyms/initialisms
try:
word_valence_dict = make_lex_dict(f)
except:
f = os.path.join(os.path.dirname(__file__),'vader_sentiment_lexicon.txt')
word_valence_dict = make_lex_dict(f)
# for removing punctuation
regex_remove_punctuation = re.compile('[%s]' % re.escape(string.punctuation))
def sentiment(text):
"""
Returns a float for sentiment strength based on the input text.
Positive values are positive valence, negative value are negative valence.
"""
wordsAndEmoticons = str(text).split() #doesn't separate words from adjacent punctuation (keeps emoticons & contractions)
text_mod = regex_remove_punctuation.sub('', text) # removes punctuation (but loses emoticons & contractions)
wordsOnly = str(text_mod).split()
# get rid of empty items or single letter "words" like 'a' and 'I' from wordsOnly
for word in wordsOnly:
if len(word) <= 1:
wordsOnly.remove(word)
# now remove adjacent & redundant punctuation from [wordsAndEmoticons] while keeping emoticons and contractions
puncList = [".", "!", "?", ",", ";", ":", "-", "'", "\"",
"!!", "!!!", "??", "???", "?!?", "!?!", "?!?!", "!?!?"]
for word in wordsOnly:
for p in puncList:
pword = p + word
x1 = wordsAndEmoticons.count(pword)
while x1 > 0:
i = wordsAndEmoticons.index(pword)
wordsAndEmoticons.remove(pword)
wordsAndEmoticons.insert(i, word)
x1 = wordsAndEmoticons.count(pword)
wordp = word + p
x2 = wordsAndEmoticons.count(wordp)
while x2 > 0:
i = wordsAndEmoticons.index(wordp)
wordsAndEmoticons.remove(wordp)
wordsAndEmoticons.insert(i, word)
x2 = wordsAndEmoticons.count(wordp)
# get rid of residual empty items or single letter "words" like 'a' and 'I' from wordsAndEmoticons
for word in wordsAndEmoticons:
if len(word) <= 1:
wordsAndEmoticons.remove(word)
# remove stopwords from [wordsAndEmoticons]
#stopwords = [str(word).strip() for word in open('stopwords.txt')]
#for word in wordsAndEmoticons:
# if word in stopwords:
# wordsAndEmoticons.remove(word)
# check for negation
negate = ["aint", "arent", "cannot", "cant", "couldnt", "darent", "didnt", "doesnt",
"ain't", "aren't", "can't", "couldn't", "daren't", "didn't", "doesn't",
"dont", "hadnt", "hasnt", "havent", "isnt", "mightnt", "mustnt", "neither",
"don't", "hadn't", "hasn't", "haven't", "isn't", "mightn't", "mustn't",
"neednt", "needn't", "never", "none", "nope", "nor", "not", "nothing", "nowhere",
"oughtnt", "shant", "shouldnt", "uhuh", "wasnt", "werent",
"oughtn't", "shan't", "shouldn't", "uh-uh", "wasn't", "weren't",
"without", "wont", "wouldnt", "won't", "wouldn't", "rarely", "seldom", "despite"]
def negated(list, nWords=[], includeNT=True):
nWords.extend(negate)
for word in nWords:
if word in list:
return True
if includeNT:
for word in list:
if "n't" in word:
return True
if "least" in list:
i = list.index("least")
if i > 0 and list[i-1] != "at":
return True
return False
def normalize(score, alpha=15):
# normalize the score to be between -1 and 1 using an alpha that approximates the max expected value
normScore = score/math.sqrt( ((score*score) + alpha) )
return normScore
def wildCardMatch(patternWithWildcard, listOfStringsToMatchAgainst):
listOfMatches = fnmatch.filter(listOfStringsToMatchAgainst, patternWithWildcard)
return listOfMatches
def isALLCAP_differential(wordList):
countALLCAPS= 0
for w in wordList:
if str(w).isupper():
countALLCAPS += 1
cap_differential = len(wordList) - countALLCAPS
if cap_differential > 0 and cap_differential < len(wordList):
isDiff = True
else: isDiff = False
return isDiff
isCap_diff = isALLCAP_differential(wordsAndEmoticons)
b_incr = 0.293 #(empirically derived mean sentiment intensity rating increase for booster words)
b_decr = -0.293
# booster/dampener 'intensifiers' or 'degree adverbs' http://en.wiktionary.org/wiki/Category:English_degree_adverbs
booster_dict = {"absolutely": b_incr, "amazingly": b_incr, "awfully": b_incr, "completely": b_incr, "considerably": b_incr,
"decidedly": b_incr, "deeply": b_incr, "effing": b_incr, "enormously": b_incr,
"entirely": b_incr, "especially": b_incr, "exceptionally": b_incr, "extremely": b_incr,
"fabulously": b_incr, "flipping": b_incr, "flippin": b_incr,
"fricking": b_incr, "frickin": b_incr, "frigging": b_incr, "friggin": b_incr, "fully": b_incr, "fucking": b_incr,
"greatly": b_incr, "hella": b_incr, "highly": b_incr, "hugely": b_incr, "incredibly": b_incr,
"intensely": b_incr, "majorly": b_incr, "more": b_incr, "most": b_incr, "particularly": b_incr,
"purely": b_incr, "quite": b_incr, "really": b_incr, "remarkably": b_incr,
"so": b_incr, "substantially": b_incr,
"thoroughly": b_incr, "totally": b_incr, "tremendously": b_incr,
"uber": b_incr, "unbelievably": b_incr, "unusually": b_incr, "utterly": b_incr,
"very": b_incr,
"almost": b_decr, "barely": b_decr, "hardly": b_decr, "just enough": b_decr,
"kind of": b_decr, "kinda": b_decr, "kindof": b_decr, "kind-of": b_decr,
"less": b_decr, "little": b_decr, "marginally": b_decr, "occasionally": b_decr, "partly": b_decr,
"scarcely": b_decr, "slightly": b_decr, "somewhat": b_decr,
"sort of": b_decr, "sorta": b_decr, "sortof": b_decr, "sort-of": b_decr}
sentiments = []
for item in wordsAndEmoticons:
v = 0
i = wordsAndEmoticons.index(item)
if (i < len(wordsAndEmoticons)-1 and str(item).lower() == "kind" and \
str(wordsAndEmoticons[i+1]).lower() == "of") or str(item).lower() in booster_dict:
sentiments.append(v)
continue
item_lowercase = str(item).lower()
if item_lowercase in word_valence_dict:
#get the sentiment valence
v = float(word_valence_dict[item_lowercase])
#check if sentiment laden word is in ALLCAPS (while others aren't)
c_incr = 0.733 #(empirically derived mean sentiment intensity rating increase for using ALLCAPs to emphasize a word)
if str(item).isupper() and isCap_diff:
if v > 0: v += c_incr
else: v -= c_incr
#check if the preceding words increase, decrease, or negate/nullify the valence
def scalar_inc_dec(word, valence):
scalar = 0.0
word_lower = str(word).lower()
if word_lower in booster_dict:
scalar = booster_dict[word_lower]
if valence < 0: scalar *= -1
#check if booster/dampener word is in ALLCAPS (while others aren't)
if str(word).isupper() and isCap_diff:
if valence > 0: scalar += c_incr
else: scalar -= c_incr
return scalar
n_scalar = -0.74
if i > 0 and str(wordsAndEmoticons[i-1]).lower() not in word_valence_dict:
s1 = scalar_inc_dec(wordsAndEmoticons[i-1], v)
v = v+s1
if negated([wordsAndEmoticons[i-1]]): v = v*n_scalar
if i > 1 and str(wordsAndEmoticons[i-2]).lower() not in word_valence_dict:
s2 = scalar_inc_dec(wordsAndEmoticons[i-2], v)
if s2 != 0: s2 = s2*0.95
v = v+s2
# check for special use of 'never' as valence modifier instead of negation
if wordsAndEmoticons[i-2] == "never" and (wordsAndEmoticons[i-1] == "so" or wordsAndEmoticons[i-1] == "this"):
v = v*1.5
# otherwise, check for negation/nullification
elif negated([wordsAndEmoticons[i-2]]): v = v*n_scalar
if i > 2 and str(wordsAndEmoticons[i-3]).lower() not in word_valence_dict:
s3 = scalar_inc_dec(wordsAndEmoticons[i-3], v)
if s3 != 0: s3 = s3*0.9
v = v+s3
# check for special use of 'never' as valence modifier instead of negation
if wordsAndEmoticons[i-3] == "never" and \
(wordsAndEmoticons[i-2] == "so" or wordsAndEmoticons[i-2] == "this") or \
(wordsAndEmoticons[i-1] == "so" or wordsAndEmoticons[i-1] == "this"):
v = v*1.25
# otherwise, check for negation/nullification
elif negated([wordsAndEmoticons[i-3]]): v = v*n_scalar
# check for special case idioms using a sentiment-laden keyword known to SAGE
special_case_idioms = {"the shit": 3, "the bomb": 3, "bad ass": 1.5, "yeah right": -2,
"cut the mustard": 2, "kiss of death": -1.5, "hand to mouth": -2}
# future work: consider other sentiment-laden idioms
#other_idioms = {"back handed": -2, "blow smoke": -2, "blowing smoke": -2, "upper hand": 1, "break a leg": 2,
# "cooking with gas": 2, "in the black": 2, "in the red": -2, "on the ball": 2,"under the weather": -2}
onezero = "{} {}".format(str(wordsAndEmoticons[i-1]), str(wordsAndEmoticons[i]))
twoonezero = "{} {} {}".format(str(wordsAndEmoticons[i-2]), str(wordsAndEmoticons[i-1]), str(wordsAndEmoticons[i]))
twoone = "{} {}".format(str(wordsAndEmoticons[i-2]), str(wordsAndEmoticons[i-1]))
threetwoone = "{} {} {}".format(str(wordsAndEmoticons[i-3]), str(wordsAndEmoticons[i-2]), str(wordsAndEmoticons[i-1]))
threetwo = "{} {}".format(str(wordsAndEmoticons[i-3]), str(wordsAndEmoticons[i-2]))
if onezero in special_case_idioms: v = special_case_idioms[onezero]
elif twoonezero in special_case_idioms: v = special_case_idioms[twoonezero]
elif twoone in special_case_idioms: v = special_case_idioms[twoone]
elif threetwoone in special_case_idioms: v = special_case_idioms[threetwoone]
elif threetwo in special_case_idioms: v = special_case_idioms[threetwo]
if len(wordsAndEmoticons)-1 > i:
zeroone = "{} {}".format(str(wordsAndEmoticons[i]), str(wordsAndEmoticons[i+1]))
if zeroone in special_case_idioms: v = special_case_idioms[zeroone]
if len(wordsAndEmoticons)-1 > i+1:
zeroonetwo = "{} {}".format(str(wordsAndEmoticons[i]), str(wordsAndEmoticons[i+1]), str(wordsAndEmoticons[i+2]))
if zeroonetwo in special_case_idioms: v = special_case_idioms[zeroonetwo]
# check for booster/dampener bi-grams such as 'sort of' or 'kind of'
if threetwo in booster_dict or twoone in booster_dict:
v = v+b_decr
# check for negation case using "least"
if i > 1 and str(wordsAndEmoticons[i-1]).lower() not in word_valence_dict \
and str(wordsAndEmoticons[i-1]).lower() == "least":
if (str(wordsAndEmoticons[i-2]).lower() != "at" and str(wordsAndEmoticons[i-2]).lower() != "very"):
v = v*n_scalar
elif i > 0 and str(wordsAndEmoticons[i-1]).lower() not in word_valence_dict \
and str(wordsAndEmoticons[i-1]).lower() == "least":
v = v*n_scalar
sentiments.append(v)
# check for modification in sentiment due to contrastive conjunction 'but'
if 'but' in wordsAndEmoticons or 'BUT' in wordsAndEmoticons:
try: bi = wordsAndEmoticons.index('but')
except: bi = wordsAndEmoticons.index('BUT')
for s in sentiments:
si = sentiments.index(s)
if si < bi:
sentiments.pop(si)
sentiments.insert(si, s*0.5)
elif si > bi:
sentiments.pop(si)
sentiments.insert(si, s*1.5)
if sentiments:
sum_s = float(sum(sentiments))
#print sentiments, sum_s
# check for added emphasis resulting from exclamation points (up to 4 of them)
ep_count = str(text).count("!")
if ep_count > 4: ep_count = 4
ep_amplifier = ep_count*0.292 #(empirically derived mean sentiment intensity rating increase for exclamation points)
if sum_s > 0: sum_s += ep_amplifier
elif sum_s < 0: sum_s -= ep_amplifier
# check for added emphasis resulting from question marks (2 or 3+)
qm_count = str(text).count("?")
qm_amplifier = 0
if qm_count > 1:
if qm_count <= 3: qm_amplifier = qm_count*0.18
else: qm_amplifier = 0.96
if sum_s > 0: sum_s += qm_amplifier
elif sum_s < 0: sum_s -= qm_amplifier
compound = normalize(sum_s)
# want separate positive versus negative sentiment scores
pos_sum = 0.0
neg_sum = 0.0
neu_count = 0
for sentiment_score in sentiments:
if sentiment_score > 0:
pos_sum += (float(sentiment_score) +1) # compensates for neutral words that are counted as 1
if sentiment_score < 0:
neg_sum += (float(sentiment_score) -1) # when used with math.fabs(), compensates for neutrals
if sentiment_score == 0:
neu_count += 1
if pos_sum > math.fabs(neg_sum): pos_sum += (ep_amplifier+qm_amplifier)
elif pos_sum < math.fabs(neg_sum): neg_sum -= (ep_amplifier+qm_amplifier)
total = pos_sum + math.fabs(neg_sum) + neu_count
pos = math.fabs(pos_sum / total)
neg = math.fabs(neg_sum / total)
neu = math.fabs(neu_count / total)
else:
compound = 0.0; pos = 0.0; neg = 0.0; neu = 0.0
s = {"neg" : round(neg, 3),
"neu" : round(neu, 3),
"pos" : round(pos, 3),
"compound" : round(compound, 4)}
return s
if __name__ == '__main__':
# --- examples -------
sentences = [
"VADER is smart, handsome, and funny.", # positive sentence example
"VADER is smart, handsome, and funny!", # punctuation emphasis handled correctly (sentiment intensity adjusted)
"VADER is very smart, handsome, and funny.", # booster words handled correctly (sentiment intensity adjusted)
"VADER is VERY SMART, handsome, and FUNNY.", # emphasis for ALLCAPS handled
"VADER is VERY SMART, handsome, and FUNNY!!!",# combination of signals - VADER appropriately adjusts intensity
"VADER is VERY SMART, really handsome, and INCREDIBLY FUNNY!!!",# booster words & punctuation make this close to ceiling for score
"The book was good.", # positive sentence
"The book was kind of good.", # qualified positive sentence is handled correctly (intensity adjusted)
"The plot was good, but the characters are uncompelling and the dialog is not great.", # mixed negation sentence
"A really bad, horrible book.", # negative sentence with booster words
"At least it isn't a horrible book.", # negated negative sentence with contraction
":) and :D", # emoticons handled
"", # an empty string is correctly handled
"Today sux", # negative slang handled
"Today sux!", # negative slang with punctuation emphasis handled
"Today SUX!", # negative slang with capitalization emphasis
"Today kinda sux! But I'll get by, lol" # mixed sentiment example with slang and constrastive conjunction "but"
]
paragraph = "It was one of the worst movies I've seen, despite good reviews. \
Unbelievably bad acting!! Poor direction. VERY poor production. \
The movie was bad. Very bad movie. VERY bad movie. VERY BAD movie. VERY BAD movie!"
from nltk import tokenize
lines_list = tokenize.sent_tokenize(paragraph)
sentences.extend(lines_list)
tricky_sentences = [
"Most automated sentiment analysis tools are shit.",
"VADER sentiment analysis is the shit.",
"Sentiment analysis has never been good.",
"Sentiment analysis with VADER has never been this good.",
"Warren Beatty has never been so entertaining.",
"I won't say that the movie is astounding and I wouldn't claim that the movie is too banal either.",
"I like to hate Michael Bay films, but I couldn't fault this one",
"It's one thing to watch an Uwe Boll film, but another thing entirely to pay for it",
"The movie was too good",
"This movie was actually neither that funny, nor super witty.",
"This movie doesn't care about cleverness, wit or any other kind of intelligent humor.",
"Those who find ugly meanings in beautiful things are corrupt without being charming.",
"There are slow and repetitive parts, BUT it has just enough spice to keep it interesting.",
"The script is not fantastic, but the acting is decent and the cinematography is EXCELLENT!",
"Roger Dodger is one of the most compelling variations on this theme.",
"Roger Dodger is one of the least compelling variations on this theme.",
"Roger Dodger is at least compelling as a variation on the theme.",
"they fall in love with the product",
"but then it breaks",
"usually around the time the 90 day warranty expires",
"the twin towers collapsed today",
"However, Mr. Carter solemnly argues, his client carried out the kidnapping under orders and in the ''least offensive way possible.''"
]
sentences.extend(tricky_sentences)
for sentence in sentences:
print(sentence)
ss = sentiment(sentence)
print("\t" + str(ss))
print("\n\n Done!")

View File

@ -0,0 +1,74 @@
# -*- coding: utf-8 -*-
from vaderSentiment import sentiment
from senpy.plugins import SentimentBox, SenpyPlugin
from senpy.models import Results, Sentiment, Entry
import logging
class VaderSentimentPlugin(SentimentBox):
'''
Sentiment classifier using vaderSentiment module. Params accepted: Language: {en, es}. The output uses Marl ontology developed at GSI UPM for semantic web.
'''
name = "sentiment-vader"
module = "sentiment-vader"
author = "@icorcuera"
version = "0.1.1"
extra_params = {
"language": {
"description": "language of the input",
"@id": "lang_rand",
"aliases": ["language", "l"],
"default": "auto",
"options": ["es", "en", "auto"]
},
"aggregate": {
"description": "Show only the strongest sentiment (aggregate) or all sentiments",
"aliases": ["aggregate","agg"],
"options": [True, False],
"default": False
}
}
requirements = {}
_VADER_KEYS = ['pos', 'neu', 'neg']
binary = False
def predict_one(self, features, activity):
text_input = ' '.join(features)
scores = sentiment(text_input)
sentiments = []
for k in self._VADER_KEYS:
sentiments.append(scores[k])
if activity.param('aggregate'):
m = max(sentiments)
sentiments = [k if k==m else None for k in sentiments]
return sentiments
test_cases = []
test_cases = [
{
'input': 'I am tired :(',
'polarity': 'marl:Negative'
},
{
'input': 'I love pizza :(',
'polarity': 'marl:Positive'
},
{
'input': 'I enjoy going to the cinema :)',
'polarity': 'marl:Negative'
},
{
'input': 'This cake is disgusting',
'polarity': 'marl:Negative'
},
]

File diff suppressed because it is too large Load Diff