1
0
mirror of https://github.com/gsi-upm/senpy synced 2025-10-19 17:58:28 +00:00

Compare commits

..

1 Commits

Author SHA1 Message Date
J. Fernando Sánchez
87589e994a Fixed version.sh 2017-02-27 12:32:34 +01:00
65 changed files with 776 additions and 1737 deletions

2
.gitignore vendored
View File

@@ -6,5 +6,3 @@ build
README.html README.html
__pycache__ __pycache__
VERSION VERSION
Dockerfile-*
Dockerfile

View File

@@ -1,98 +1,80 @@
# Uncomment if you want to use docker-in-docker image: docker:latest
# image: gsiupm/dockermake:latest
# services:
# - docker:dind
# When using dind, it's wise to use the overlayfs driver for # When using dind, it's wise to use the overlayfs driver for
# improved performance. # improved performance.
variables:
DOCKER_DRIVER: overlay
DOCKERFILE: Dockerfile
before_script:
- sh version.sh > senpy/VERSION
stages: stages:
- test - test
- push - images
- deploy - release
- clean
before_script:
- docker login -u $HUB_USER -p $HUB_PASSWORD
.test: &test_definition .test: &test_definition
variables:
PIP_CACHE_DIR: "$CI_PROJECT_DIR/pip-cache"
cache:
paths:
- .eggs/
- "$CI_PROJECT_DIR/pip-cache"
- .venv
key: "$CI_PROJECT_NAME"
stage: test stage: test
script: script:
- make -e test-$PYTHON_VERSION - pip install --use-wheel -U pip setuptools virtualenv
- virtualenv .venv/$PYTHON_VERSION
- source .venv/$PYTHON_VERSION/bin/activate
- pip install --use-wheel -r requirements.txt
- pip install --use-wheel -r test-requirements.txt
- py.test --cov=senpy --cov-report term-missing
- python
test-3.5: test-3.5:
<<: *test_definition <<: *test_definition
variables: image: "python:3.5"
PYTHON_VERSION: "3.5"
test-2.7: test-2.7:
<<: *test_definition <<: *test_definition
variables: image: "python:2.7"
PYTHON_VERSION: "2.7"
.image: &image_definition .image: &image_definition
stage: push variables:
PYTHON_VERSION: "3.5"
before_script:
- docker login -u gitlab-ci-token -p $CI_BUILD_TOKEN $CI_REGISTRY
script: script:
- make -e push-$PYTHON_VERSION - docker build -f Dockerfile-3.5 . -t $CI_REGISTRY_IMAGE:$CI_BUILD_REF_SLUG-$PYTHON_VERSION
- docker push $CI_REGISTRY_IMAGE:$CI_BUILD_REF_SLUG-$PYTHON_VERSION
stage: images
only: only:
- tags - tags
- triggers - triggers
push-3.5: image-3.5:
<<: *image_definition <<: *image_definition
variables: variables:
PYTHON_VERSION: "3.5" PYTHON_VERSION: "3.5"
push-2.7: image-2.7:
<<: *image_definition <<: *image_definition
variables: variables:
PYTHON_VERSION: "2.7" PYTHON_VERSION: "2.7"
push-latest: image-latest:
<<: *image_definition stage: release
variables: before_script:
PYTHON_VERSION: latest - docker login -u gitlab-ci-token -p $CI_BUILD_TOKEN $CI_REGISTRY
script:
- docker build -f Dockerfile . -t $CI_REGISTRY_IMAGE
- docker tag $CI_REGISTRY_IMAGE $CI_REGISTRY_IMAGE:$CI_BUILD_REF_SLUG
- docker push $CI_REGISTRY_IMAGE
- docker push $CI_REGISTRY_IMAGE:$CI_BUILD_REF_SLUG
only: only:
- master - master
- triggers - triggers
push-github:
stage: deploy
script:
- make -e push-github
only:
- master
- triggers
deploy_pypi:
stage: deploy
script: # Configure the PyPI credentials, then push the package, and cleanup the creds.
- echo "[server-login]" >> ~/.pypirc
- echo "username=" ${PYPI_USER} >> ~/.pypirc
- echo "password=" ${PYPI_PASSWORD} >> ~/.pypirc
- make pip_upload
- echo "" > ~/.pypirc && rm ~/.pypirc # If the above fails, this won't run.
only:
- /^v\d+\.\d+\.\d+([abc]\d*)?$/ # PEP-440 compliant version (tags)
except:
- branches
deploy:
stage: deploy
environment: test
script:
- make -e deploy
only:
- master
clean_docker :
stage: clean
script:
- make -e clean
when: manual
cleanup_pypirc:
stage: clean
when: always # this is important; run even if preceding stages failed.
script:
- rm -vf ~/.pypirc # we don't want to leave these around, but GitLab may clean up anyway.
- docker logout

View File

@@ -1,5 +0,0 @@
- repo: git://github.com/pre-commit/pre-commit-hooks
sha: e626cd57090d8df0be21e4df0f4e55cc3511d6ab
hooks:
- id: flake8
- id: check-json

View File

@@ -1,13 +1,8 @@
sudo: required
services:
- docker
language: python language: python
python:
env: - "2.7"
- PYV=2.7 - "3.4"
- PYV=3.4 - "3.5"
- PYV=3.5 install: "pip install -r requirements.txt"
# run nosetests - Tests # run nosetests - Tests
script: make test-$PYV script: nosetests

1
Dockerfile Symbolic link
View File

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

21
Dockerfile-2.7 Normal file
View File

@@ -0,0 +1,21 @@
from python:2.7
RUN mkdir /cache/
ENV PIP_CACHE_DIR=/cache/
WORKDIR /usr/src/app
ADD requirements.txt /usr/src/app/
RUN pip install --use-wheel -r requirements.txt
ADD . /usr/src/app/
RUN pip install .
VOLUME /data/
RUN mkdir /senpy-plugins/
WORKDIR /senpy-plugins/
ONBUILD ADD . /senpy-plugins/
ONBUILD RUN python -m senpy --only-install -f /senpy-plugins
ENTRYPOINT ["python", "-m", "senpy", "-f", "/senpy-plugins/", "--host", "0.0.0.0"]

21
Dockerfile-3.4 Normal file
View File

@@ -0,0 +1,21 @@
from python:3.4
RUN mkdir /cache/
ENV PIP_CACHE_DIR=/cache/
WORKDIR /usr/src/app
ADD requirements.txt /usr/src/app/
RUN pip install --use-wheel -r requirements.txt
ADD . /usr/src/app/
RUN pip install .
VOLUME /data/
RUN mkdir /senpy-plugins/
WORKDIR /senpy-plugins/
ONBUILD ADD . /senpy-plugins/
ONBUILD RUN python -m senpy --only-install -f /senpy-plugins
ENTRYPOINT ["python", "-m", "senpy", "-f", "/senpy-plugins/", "--host", "0.0.0.0"]

21
Dockerfile-3.5 Normal file
View File

@@ -0,0 +1,21 @@
FROM python:3.5
RUN mkdir /cache/
ENV PIP_CACHE_DIR=/cache/
WORKDIR /usr/src/app
ADD requirements.txt /usr/src/app/
RUN pip install --use-wheel -r requirements.txt
ADD . /usr/src/app/
RUN pip install .
VOLUME /data/
RUN mkdir /senpy-plugins/
WORKDIR /senpy-plugins/
ONBUILD ADD . /senpy-plugins/
ONBUILD RUN python -m senpy --only-install -f /senpy-plugins
ENTRYPOINT ["python", "-m", "senpy", "-f", "/senpy-plugins/", "--host", "0.0.0.0"]

33
Dockerfile.deps Normal file
View File

@@ -0,0 +1,33 @@
from python:2.7
RUN apt-get update
RUN apt-get -y install git
RUN mkdir -p /senpy-plugins
RUN apt-get -y install python-numpy
RUN apt-get -y install python-scipy
RUN apt-get -y install python-sklearn
RUN apt-get -y install python-gevent
RUN apt-get -y install libopenblas-dev
RUN apt-get -y install gfortran
RUN apt-get -y install libxml2-dev libxslt1-dev python-dev
#RUN pip install --upgrade pip
ADD id_rsa /root/.ssh/id_rsa
RUN chmod 700 /root/.ssh/id_rsa
RUN echo "Host github.com\n\tStrictHostKeyChecking no\n" >> /root/.ssh/config
RUN git clone https://github.com/gsi-upm/senpy /usr/src/app/
RUN git clone git@github.com:gsi-upm/senpy-plugins-enterprise /senpy-plugins/enterprise
RUN git clone https://github.com/gsi-upm/senpy-plugins-community /senpy-plugins/community
RUN pip install /usr/src/app
RUN pip install --no-use-wheel -r /senpy-plugins/enterprise/requirements.txt
RUN python -m nltk.downloader stopwords
RUN python -m nltk.downloader punkt
RUN python -m nltk.downloader maxent_treebank_pos_tagger
RUN python -m nltk.downloader wordnet
WORKDIR /senpy-plugins
ENTRYPOINT ["python", "-m", "senpy", "-f", ".", "--host", "0.0.0.0"]

View File

@@ -1,22 +1,21 @@
from python:{{PYVERSION}} from python:{{PYVERSION}}
MAINTAINER J. Fernando Sánchez <jf.sanchez@upm.es> RUN mkdir /cache/
ENV PIP_CACHE_DIR=/cache/
WORKDIR /usr/src/app
ADD requirements.txt /usr/src/app/
RUN pip install --use-wheel -r requirements.txt
ADD . /usr/src/app/
RUN pip install .
RUN mkdir /cache/ /senpy-plugins /data/
VOLUME /data/ VOLUME /data/
ENV PIP_CACHE_DIR=/cache/ SENPY_DATA=/data RUN mkdir /senpy-plugins/
ONBUILD COPY . /senpy-plugins/ WORKDIR /senpy-plugins/
ONBUILD ADD . /senpy-plugins/
ONBUILD RUN python -m senpy --only-install -f /senpy-plugins ONBUILD RUN python -m senpy --only-install -f /senpy-plugins
ONBUILD WORKDIR /senpy-plugins/
ENTRYPOINT ["python", "-m", "senpy", "-f", "/senpy-plugins/", "--host", "0.0.0.0"]
WORKDIR /usr/src/app
COPY test-requirements.txt requirements.txt /usr/src/app/
RUN pip install --use-wheel -r test-requirements.txt -r requirements.txt
COPY . /usr/src/app/
RUN pip install --no-index --no-deps --editable .
ENTRYPOINT ["python", "-m", "senpy", "-f", "/senpy-plugins/", "--host", "0.0.0.0"]

129
Makefile
View File

@@ -1,43 +1,25 @@
NAME=senpy PYVERSIONS=3.5 3.4 2.7
VERSION=$(shell git describe --tags --dirty 2>/dev/null)
GITHUB_REPO=git@github.com:gsi-upm/senpy.git
IMAGENAME=gsiupm/senpy
IMAGEWTAG=$(IMAGENAME):$(VERSION)
PYVERSIONS=3.5 2.7
PYMAIN=$(firstword $(PYVERSIONS)) PYMAIN=$(firstword $(PYVERSIONS))
NAME=senpy
DEVPORT=5000 REPO=gsiupm
VERSION=$(shell ./version.sh)
TARNAME=$(NAME)-$(VERSION).tar.gz TARNAME=$(NAME)-$(VERSION).tar.gz
action="test-${PYMAIN}" IMAGENAME=$(REPO)/$(NAME):$(VERSION)
TEST_COMMAND=gitlab-runner exec docker --cache-dir=/tmp/gitlabrunner --docker-volumes /tmp/gitlabrunner:/tmp/gitlabrunner --env CI_PROJECT_NAME=$(NAME)
KUBE_CA_PEM_FILE=""
KUBE_URL=""
KUBE_TOKEN=""
KUBE_NAMESPACE=$(NAME)
KUBECTL=docker run --rm -v $(KUBE_CA_PEM_FILE):/tmp/ca.pem -v $$PWD:/tmp/cwd/ -i lachlanevenson/k8s-kubectl --server="$(KUBE_URL)" --token="$(KUBE_TOKEN)" --certificate-authority="/tmp/ca.pem" -n $(KUBE_NAMESPACE)
CI_REGISTRY=docker.io
CI_REGISTRY_USER=gitlab
CI_BUILD_TOKEN=""
CI_COMMIT_REF_NAME=master
all: build run all: build run
.FORCE: FORCE:
version: .FORCE version: FORCE
@echo $(VERSION) > $(NAME)/VERSION @echo $(VERSION) > $(NAME)/VERSION
@echo $(VERSION) @echo $(VERSION)
yapf: yapf:
yapf -i -r $(NAME) yapf -i -r senpy
yapf -i -r tests yapf -i -r tests
init: dev:
pip install --user pre-commit pip install --user pre-commit
pre-commit install pre-commit install
@@ -52,32 +34,29 @@ quick_build: $(addprefix build-, $(PYMAIN))
build: $(addprefix build-, $(PYVERSIONS)) build: $(addprefix build-, $(PYVERSIONS))
build-%: version Dockerfile-% build-%: Dockerfile-%
docker build -t '$(IMAGEWTAG)-python$*' --cache-from $(IMAGENAME):python$* -f Dockerfile-$* .; docker build -t '$(IMAGENAME)-python$*' -f Dockerfile-$* .;
quick_test: $(addprefix test-,$(PYMAIN)) quick_test: $(addprefix test-,$(PYMAIN))
dev-%: test: $(addprefix test-,$(PYVERSIONS))
@docker start $(NAME)-dev$* || (\
debug-%:
@docker start $(NAME)-debug || (\
$(MAKE) build-$*; \ $(MAKE) build-$*; \
docker run -d -w /usr/src/app/ -p $(DEVPORT):5000 -v $$PWD:/usr/src/app --entrypoint=/bin/bash -ti --name $(NAME)-dev$* '$(IMAGEWTAG)-python$*'; \ docker run -d -w /usr/src/app/ -v $$PWD:/usr/src/app --entrypoint=/bin/bash -p 5000:5000 -ti --name $(NAME)-debug '$(IMAGENAME)-python$*'; \
docker exec -ti $(NAME)-debug pip install -r test-requirements.txt; \
)\ )\
docker exec -ti $(NAME)-dev$* bash docker attach $(NAME)-debug
dev: dev-$(PYMAIN) debug: debug-$(PYMAIN)
test-all: $(addprefix test-,$(PYVERSIONS))
test-%: test-%:
docker run --rm --entrypoint /usr/local/bin/python -w /usr/src/app $(IMAGENAME):python$* setup.py test $(TEST_COMMAND) test-$*
test: test-$(PYMAIN) dist/$(TARNAME):
dist/$(TARNAME): version
docker run --rm -ti -v $$PWD:/usr/src/app/ -w /usr/src/app/ python:$(PYMAIN) python setup.py sdist; docker run --rm -ti -v $$PWD:/usr/src/app/ -w /usr/src/app/ python:$(PYMAIN) python setup.py sdist;
docker run --rm -ti -v $$PWD:/usr/src/app/ -w /usr/src/app/ python:$(PYMAIN) chmod -R a+rwx dist;
sdist: dist/$(TARNAME) sdist: dist/$(TARNAME)
@@ -86,14 +65,20 @@ pip_test-%: sdist
pip_test: $(addprefix pip_test-,$(PYVERSIONS)) pip_test: $(addprefix pip_test-,$(PYVERSIONS))
pip_upload: pip_test upload-%: test-%
python setup.py sdist upload ; docker push '$(IMAGENAME)-python$*'
upload: test $(addprefix upload-,$(PYVERSIONS))
docker tag '$(IMAGENAME)-python$(PYMAIN)' '$(IMAGENAME)'
docker tag '$(IMAGENAME)-python$(PYMAIN)' '$(REPO)/$(NAME)'
docker push '$(IMAGENAME)'
docker push '$(REPO)/$(NAME)'
clean: clean:
@docker ps -a | grep $(IMAGENAME) | awk '{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1;}}' | xargs docker rm -v 2>/dev/null|| true @docker ps -a | awk '/$(REPO)\/$(NAME)/{ 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":"$$2;}}' | xargs docker rmi 2>/dev/null|| true @docker images | awk '/$(REPO)\/$(NAME)/{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1":"$$2;}}' | xargs docker rmi 2>/dev/null|| true
@docker stop $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true @docker rmi $(NAME)-debug 2>/dev/null || true
@docker rm $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
git_commit: git_commit:
git commit -a git commit -a
@@ -101,47 +86,17 @@ git_commit:
git_tag: git_tag:
git tag ${VERSION} git tag ${VERSION}
git_push: upload_git:
git push --tags origin master git push --tags origin master
pip_upload:
python setup.py sdist upload ;
pip_test: $(addprefix pip_test-,$(PYVERSIONS))
run-%: build-% run-%: build-%
docker run --rm -p $(DEVPORT):5000 -ti '$(IMAGEWTAG)-python$(PYMAIN)' --default-plugins docker run --rm -p 5000:5000 -ti '$(IMAGENAME)-python$(PYMAIN)' --default-plugins
run: run-$(PYMAIN) run: run-$(PYMAIN)
push-latest: $(addprefix push-latest-,$(PYVERSIONS)) .PHONY: test test-% build-% build test pip_test run yapf dev
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGENAME)'
docker push '$(IMAGENAME):latest'
docker push '$(IMAGEWTAG)'
push-latest-%: build-%
docker tag $(IMAGENAME):$(VERSION)-python$* $(IMAGENAME):python$*
docker push $(IMAGENAME):$(VERSION)-python$*
docker push $(IMAGENAME):python$*
push-%: build-%
docker push $(IMAGENAME):$(VERSION)-python$*
push: $(addprefix push-,$(PYVERSIONS))
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker push $(IMAGENAME):$(VERSION)
push-github:
$(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 push github-deploy $(CI_COMMIT_REF_NAME)
rm $(KEY_FILE)
ci:
gitlab-runner exec docker --docker-volumes /var/run/docker.sock:/var/run/docker.sock --env CI_PROJECT_NAME=$(NAME) ${action}
deploy:
@$(KUBECTL) delete secret $(CI_REGISTRY) || true
@$(KUBECTL) create secret docker-registry $(CI_REGISTRY) --docker-server=$(CI_REGISTRY) --docker-username=$(CI_REGISTRY_USER) --docker-email=$(CI_REGISTRY_USER) --docker-password=$(CI_BUILD_TOKEN)
@$(KUBECTL) apply -f /tmp/cwd/k8s/
.PHONY: test test-% test-all build-% build test pip_test run yapf push-main push-% dev ci version .FORCE deploy

View File

@@ -23,7 +23,7 @@ Through PIP
.. code:: bash .. code:: bash
pip install -U --user senpy pip install --user senpy
Alternatively, you can use the development version: Alternatively, you can use the development version:
@@ -38,56 +38,9 @@ If you want to install senpy globally, use sudo instead of the ``--user`` flag.
Docker Image Docker Image
************ ************
Build the image or use the pre-built one: ``docker run -ti -p 5000:5000 gsiupm/senpy --default-plugins``. Build the image or use the pre-built one: ``docker run -ti -p 5000:5000 gsiupm/senpy --host 0.0.0.0 --default-plugins``.
To add custom plugins, add a volume and tell senpy where to find the plugins: ``docker run -ti -p 5000:5000 -v <PATH OF PLUGINS>:/plugins gsiupm/senpy --default-plugins -f /plugins`` To add custom plugins, add a volume and tell senpy where to find the plugins: ``docker run -ti -p 5000:5000 -v <PATH OF PLUGINS>:/plugins gsiupm/senpy --host 0.0.0.0 --default-plugins -f /plugins``
Developing
----------
Developing/debugging
********************
This command will run the senpy container using the latest image available, mounting your current folder so you get your latest code:
.. code:: bash
# Python 3.5
make dev
# Python 2.7
make dev-2.7
Building a docker image
***********************
.. code:: bash
# Python 3.5
make build-3.5
# Python 2.7
make build-2.7
Testing
*******
.. code:: bash
make test
Running
*******
This command will run the senpy server listening on localhost:5000
.. code:: bash
# Python 3.5
make run-3.5
# Python 2.7
make run-2.7
Usage Usage
----- -----
@@ -96,14 +49,12 @@ However, the easiest and recommended way is to just use the command-line tool to
.. code:: bash .. code:: bash
senpy senpy
or, alternatively: or, alternatively:
.. code:: bash .. code:: bash
python -m senpy python -m senpy

Binary file not shown.

Before

Width:  |  Height:  |  Size: 208 KiB

View File

@@ -1,5 +1,5 @@
NIF API NIF API
------- =======
.. http:get:: /api .. http:get:: /api
Basic endpoint for sentiment/emotion analysis. Basic endpoint for sentiment/emotion analysis.
@@ -22,32 +22,38 @@ NIF API
Content-Type: text/javascript Content-Type: text/javascript
{ {
"@context":"http://127.0.0.1/api/contexts/Results.jsonld", "@context": [
"@id":"_:Results_11241245.22", "http://127.0.0.1/static/context.jsonld",
"@type":"results" ],
"analysis": [ "analysis": [
"plugins/sentiment-140_0.1" {
], "@id": "SentimentAnalysisExample",
"entries": [ "@type": "marl:SentimentAnalysis",
{ "dc:language": "en",
"@id": "_:Entry_11241245.22" "marl:maxPolarityValue": 10.0,
"@type":"entry", "marl:minPolarityValue": 0.0
"emotions": [], }
"entities": [], ],
"sentiments": [ "domain": "wndomains:electronics",
{ "entries": [
"@id": "Sentiment0", {
"@type": "sentiment", "opinions": [
"marl:hasPolarity": "marl:Negative", {
"marl:polarityValue": 0, "prov:generatedBy": "SentimentAnalysisExample",
"prefix": "" "marl:polarityValue": 7.8,
} "marl:hasPolarity": "marl:Positive",
], "marl:describesObject": "http://www.gsi.dit.upm.es",
"suggestions": [], }
"text": "This text makes me sad.\nwhilst this text makes me happy and surprised at the same time.\nI cannot believe it!", ],
"topics": [] "nif:isString": "I love GSI",
} "strings": [
] {
"nif:anchorOf": "GSI",
"nif:taIdentRef": "http://www.gsi.dit.upm.es"
}
]
}
]
} }
:query i input: No default. Depends on informat and intype :query i input: No default. Depends on informat and intype
@@ -56,7 +62,6 @@ NIF API
:query o outformat: one of `turtle` (default), `text`, `json-ld` :query o outformat: one of `turtle` (default), `text`, `json-ld`
:query p prefix: prefix for the URIs :query p prefix: prefix for the URIs
:query algo algorithm: algorithm/plugin to use for the analysis. For a list of options, see :http:get:`/api/plugins`. If not provided, the default plugin will be used (:http:get:`/api/plugins/default`). :query algo algorithm: algorithm/plugin to use for the analysis. For a list of options, see :http:get:`/api/plugins`. If not provided, the default plugin will be used (:http:get:`/api/plugins/default`).
:query algo emotionModel: desired emotion model in the results. If the requested algorithm does not use that emotion model, there are conversion plugins specifically for this. If none of the plugins match, an error will be returned, which includes the results *as is*.
:reqheader Accept: the response content type depends on :reqheader Accept: the response content type depends on
:mailheader:`Accept` header :mailheader:`Accept` header
@@ -64,7 +69,6 @@ NIF API
header of request header of request
:statuscode 200: no error :statuscode 200: no error
:statuscode 404: service not found :statuscode 404: service not found
:statuscode 400: error while processing the request
.. http:post:: /api .. http:post:: /api
@@ -86,59 +90,56 @@ NIF API
.. sourcecode:: http .. sourcecode:: http
{ {
"@id": "plugins/sentiment-140_0.1", "@context": {
"@type": "sentimentPlugin", ...
"author": "@balkian", },
"description": "Sentiment classifier using rule-based classification for English and Spanish. This plugin uses sentiment140 data to perform classification. For more information: http://help.sentiment140.com/for-students/", "sentiment140": {
"extra_params": { "name": "sentiment140",
"language": { "is_activated": true,
"@id": "lang_sentiment140", "version": "0.1",
"aliases": [ "extra_params": {
"language", "@id": "extra_params_sentiment140_0.1",
"l" "language": {
], "required": false,
"options": [ "@id": "lang_sentiment140",
"es", "options": [
"en", "es",
"auto" "en",
], "auto"
"required": false ],
} "aliases": [
}, "language",
"is_activated": true, "l"
"maxPolarityValue": 1.0, ]
"minPolarityValue": 0.0, }
"module": "sentiment-140", },
"name": "sentiment-140", "@id": "sentiment140_0.1"
"requirements": {}, },
"version": "0.1" "rand": {
}, "name": "rand",
{ "is_activated": true,
"@id": "plugins/ExamplePlugin_0.1", "version": "0.1",
"@type": "sentimentPlugin", "extra_params": {
"author": "@balkian", "@id": "extra_params_rand_0.1",
"custom_attribute": "42", "language": {
"description": "I am just an example", "required": false,
"extra_params": { "@id": "lang_rand",
"parameter": { "options": [
"@id": "parameter", "es",
"aliases": [ "en",
"parameter", "auto"
"param" ],
], "aliases": [
"default": 42, "language",
"required": true "l"
} ]
}, }
"is_activated": true, },
"maxPolarityValue": 1.0, "@id": "rand_0.1"
"minPolarityValue": 0.0, }
"module": "example", }
"name": "ExamplePlugin",
"requirements": "noop",
"version": "0.1"
}
.. http:get:: /api/plugins/<pluginname> .. http:get:: /api/plugins/<pluginname>
@@ -147,7 +148,7 @@ NIF API
.. sourcecode:: http .. sourcecode:: http
GET /api/plugins/rand/ HTTP/1.1 GET /api/plugins/rand HTTP/1.1
Host: localhost Host: localhost
Accept: application/json, text/javascript Accept: application/json, text/javascript
@@ -157,61 +158,51 @@ NIF API
.. sourcecode:: http .. sourcecode:: http
{ {
"@context": "http://127.0.0.1/api/contexts/ExamplePlugin.jsonld", "@id": "rand_0.1",
"@id": "plugins/ExamplePlugin_0.1", "extra_params": {
"@type": "sentimentPlugin", "@id": "extra_params_rand_0.1",
"author": "@balkian", "language": {
"custom_attribute": "42", "@id": "lang_rand",
"description": "I am just an example", "aliases": [
"extra_params": { "language",
"parameter": { "l"
"@id": "parameter", ],
"aliases": [ "options": [
"parameter", "es",
"param" "en",
], "auto"
"default": 42, ],
"required": true "required": false
} }
}, },
"is_activated": true, "is_activated": true,
"maxPolarityValue": 1.0, "name": "rand",
"minPolarityValue": 0.0, "version": "0.1"
"module": "example",
"name": "ExamplePlugin",
"requirements": "noop",
"version": "0.1"
} }
.. http:get:: /api/plugins/default .. http:get:: /api/plugins/default
Return the information about the default plugin. Return the information about the default plugin.
.. http:get:: /api/plugins/<pluginname>/{de}activate
{De}activate a plugin.
**Example request**:
.. sourcecode:: http
GET /api/plugins/rand/deactivate HTTP/1.1
Host: localhost
Accept: application/json, text/javascript
**Example response**:
.. sourcecode:: http
{
"@context": {},
"message": "Ok"
}

View File

@@ -1,7 +0,0 @@
API and Schema
##############
.. toctree::
vocabularies.rst
api.rst
schema.rst

View File

@@ -1,15 +0,0 @@
Architecture
============
The main component of a sentiment analysis service is the algorithm itself. However, for the algorithm to work, it needs to get the appropriate parameters from the user, format the results according to the defined API, interact with the user whn errors occur or more information is needed, etc.
Senpy proposes a modular and dynamic architecture that allows:
* Implementing different algorithms in a extensible way, yet offering a common interface.
* Offering common services that facilitate development, so developers can focus on implementing new and better algorithms.
The framework consists of two main modules: Senpy core, which is the building block of the service, and Senpy plugins, which consist of the analysis algorithm. The next figure depicts a simplified version of the processes involved in an analysis with the Senpy framework.
.. image:: senpy-architecture.png
:width: 100%
:align: center

View File

@@ -1,78 +0,0 @@
{
"@context": "http://mixedemotions-project.eu/ns/context.jsonld",
"@id": "me:Result1",
"@type": "results",
"analysis": [
"me:SAnalysis1",
"me:SgAnalysis1",
"me:EmotionAnalysis1",
"me:NER1",
{
"@type": "analysis",
"@id": "wrong"
}
],
"entries": [
{
"@id": "http://micro.blog/status1",
"@type": [
"nif:RFC5147String",
"nif:Context"
],
"nif:isString": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"entities": [
{
"@id": "http://micro.blog/status1#char=5,13",
"nif:beginIndex": 5,
"nif:endIndex": 13,
"nif:anchorOf": "Microsoft",
"me:references": "http://dbpedia.org/page/Microsoft",
"prov:wasGeneratedBy": "me:NER1"
},
{
"@id": "http://micro.blog/status1#char=25,37",
"nif:beginIndex": 25,
"nif:endIndex": 37,
"nif:anchorOf": "Windows Phone",
"me:references": "http://dbpedia.org/page/Windows_Phone",
"prov:wasGeneratedBy": "me:NER1"
}
],
"suggestions": [
{
"@id": "http://micro.blog/status1#char=16,77",
"nif:beginIndex": 16,
"nif:endIndex": 77,
"nif:anchorOf": "put your Windows Phone on your newest #open technology program",
"prov:wasGeneratedBy": "me:SgAnalysis1"
}
],
"sentiments": [
{
"@id": "http://micro.blog/status1#char=80,97",
"nif:beginIndex": 80,
"nif:endIndex": 97,
"nif:anchorOf": "You'll be awesome.",
"marl:hasPolarity": "marl:Positive",
"marl:polarityValue": 0.9,
"prov:wasGeneratedBy": "me:SAnalysis1"
}
],
"emotions": [
{
"@id": "http://micro.blog/status1#char=0,109",
"nif:anchorOf": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"prov:wasGeneratedBy": "me:EAnalysis1",
"onyx:hasEmotion": [
{
"onyx:hasEmotionCategory": "wna:liking"
},
{
"onyx:hasEmotionCategory": "wna:excitement"
}
]
}
]
}
]
}

View File

@@ -37,7 +37,6 @@ extensions = [
'sphinx.ext.todo', 'sphinx.ext.todo',
'sphinxcontrib.httpdomain', 'sphinxcontrib.httpdomain',
'sphinx.ext.coverage', 'sphinx.ext.coverage',
'sphinx.ext.autosectionlabel'
] ]
# Add any paths that contain templates here, relative to this directory. # Add any paths that contain templates here, relative to this directory.
@@ -55,21 +54,20 @@ master_doc = 'index'
# General information about the project. # General information about the project.
project = u'Senpy' project = u'Senpy'
copyright = u'2016, J. Fernando Sánchez' copyright = u'2016, J. Fernando Sánchez'
description = u'A framework for sentiment and emotion analysis services'
# The version info for the project you're documenting, acts as replacement for # The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the # |version| and |release|, also used in various other places throughout the
# built documents. # built documents.
# #
# The short X.Y version. # The short X.Y version.
# with open('../senpy/VERSION') as f: with open('../senpy/VERSION') as f:
# version = f.read().strip() version = f.read().strip()
# The full version, including alpha/beta/rc tags. # The full version, including alpha/beta/rc tags.
# release = version release = version
# The language for content autogenerated by Sphinx. Refer to documentation # The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages. # for a list of supported languages.
language = None #language = None
# There are two options for replacing |today|: either, you set today to some # There are two options for replacing |today|: either, you set today to some
# non-false value, then it is used: # non-false value, then it is used:
@@ -106,14 +104,14 @@ pygments_style = 'sphinx'
#keep_warnings = False #keep_warnings = False
html_theme = 'alabaster'
# -- Options for HTML output ---------------------------------------------- # -- Options for HTML output ----------------------------------------------
# if not on_rtd: # only import and set the theme if we're building docs locally if not on_rtd: # only import and set the theme if we're building docs locally
# import sphinx_rtd_theme import sphinx_rtd_theme
# html_theme_path = [sphinx_rtd_theme.get_html_theme_path()] html_theme = 'sphinx_rtd_theme'
html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
# else: else:
# html_theme = 'default' html_theme = 'default'
# The theme to use for HTML and HTML Help pages. See the documentation for # The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes. # a list of builtin themes.
@@ -121,13 +119,7 @@ html_theme = 'alabaster'
# Theme options are theme-specific and customize the look and feel of a theme # Theme options are theme-specific and customize the look and feel of a theme
# further. For a list of options available for each theme, see the # further. For a list of options available for each theme, see the
# documentation. # documentation.
html_theme_options = { #html_theme_options = {}
'logo': 'header.png',
'github_user': 'gsi-upm',
'github_repo': 'senpy',
'github_banner': True,
}
# Add any paths that contain custom themes here, relative to this directory. # Add any paths that contain custom themes here, relative to this directory.
#html_theme_path = [] #html_theme_path = []
@@ -167,13 +159,7 @@ html_static_path = ['_static']
#html_use_smartypants = True #html_use_smartypants = True
# Custom sidebar templates, maps document names to template names. # Custom sidebar templates, maps document names to template names.
html_sidebars = { #html_sidebars = {}
'**': [
'about.html',
'navigation.html',
'searchbox.html',
]
}
# Additional templates that should be rendered to pages, maps page names to # Additional templates that should be rendered to pages, maps page names to
# template names. # template names.

View File

@@ -1,116 +0,0 @@
Conversion
----------
Senpy includes experimental support for emotion/sentiment conversion plugins.
Use
===
Consider the original query: http://127.0.0.1:5000/api/?i=hello&algo=emoRand
The requested plugin (emoRand) returns emotions using Ekman's model (or big6 in EmotionML):
.. code:: json
... rest of the document ...
{
"@type": "emotionSet",
"onyx:hasEmotion": {
"@type": "emotion",
"onyx:hasEmotionCategory": "emoml:big6anger"
},
"prov:wasGeneratedBy": "plugins/emoRand_0.1"
}
To get these emotions in VAD space (FSRE dimensions in EmotionML), we'd do this:
http://127.0.0.1:5000/api/?i=hello&algo=emoRand&emotionModel=emoml:fsre-dimensions
This call, provided there is a valid conversion plugin from Ekman's to VAD, would return something like this:
.. code:: json
... rest of the document ...
{
"@type": "emotionSet",
"onyx:hasEmotion": {
"@type": "emotion",
"onyx:hasEmotionCategory": "emoml:big6anger"
},
"prov:wasGeneratedBy": "plugins/emoRand_0.1"
}, {
"@type": "emotionSet",
"onyx:hasEmotion": {
"@type": "emotion",
"A": 7.22,
"D": 6.28,
"V": 8.6
},
"prov:wasGeneratedBy": "plugins/Ekman2VAD_0.1"
}
That is called a *full* response, as it simply adds the converted emotion alongside.
It is also possible to get the original emotion nested within the new converted emotion, using the `conversion=nested` parameter:
.. code:: json
... rest of the document ...
{
"@type": "emotionSet",
"onyx:hasEmotion": {
"@type": "emotion",
"onyx:hasEmotionCategory": "emoml:big6anger"
},
"prov:wasGeneratedBy": "plugins/emoRand_0.1"
"onyx:wasDerivedFrom": {
"@type": "emotionSet",
"onyx:hasEmotion": {
"@type": "emotion",
"A": 7.22,
"D": 6.28,
"V": 8.6
},
"prov:wasGeneratedBy": "plugins/Ekman2VAD_0.1"
}
}
Lastly, `conversion=filtered` would only return the converted emotions.
Developing a conversion plugin
================================
Conversion plugins are discovered by the server just like any other plugin.
The difference is the slightly different API, and the need to specify the `source` and `target` of the conversion.
For instance, an emotion conversion plugin needs the following:
.. code:: yaml
---
onyx:doesConversion:
- onyx:conversionFrom: emoml:big6
onyx:conversionTo: emoml:fsre-dimensions
- onyx:conversionFrom: emoml:fsre-dimensions
onyx:conversionTo: emoml:big6
.. code:: python
class MyConversion(EmotionConversionPlugin):
def convert(self, emotionSet, fromModel, toModel, params):
pass

View File

@@ -1,8 +1,7 @@
Demo Demo
---- ----
There is a demo available on http://senpy.cluster.gsi.dit.upm.es/, where you can test a serie of different plugins. There is a demo available on http://senpy.demos.gsi.dit.upm.es/, where you can a serie of different plugins. You can use them in the playground or make a directly requests to the service.
You can use the playground (a web interface) or make HTTP requests to the service API.
.. image:: senpy-playground.png .. image:: senpy-playground.png
:height: 400px :height: 400px
@@ -13,4 +12,64 @@ You can use the playground (a web interface) or make HTTP requests to the servic
Plugins Demo Plugins Demo
============ ============
The source code and description of the plugins used in the demo is available here: https://lab.cluster.gsi.dit.upm.es/senpy/senpy-plugins-community/. The next plugins are available at the demo:
* emoTextAnew extracts the VAD (valence-arousal-dominance) of a sentence by matching words from the ANEW dictionary.
* emoTextWordnetAffect based on the hierarchy of WordnetAffect to calculate the emotion of the sentence.
* vaderSentiment utilizes the software from vaderSentiment to calculate the sentiment of a sentence.
* sentiText is a software developed during the TASS 2015 competition, it has been adapted for English and Spanish.
emoTextANEW plugin
******************
This plugin is going to used the ANEW lexicon dictionary to calculate de VAD (valence-arousal-dominance) of the sentence and the determinate which emotion is closer to this value.
Each emotion has a centroid, which it has been approximated using the formula described in 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.
emoTextWAF plugin
*****************
This plugin uses WordNet-Affect (http://wndomains.fbk.eu/wnaffect.html) to calculate the percentage of each emotion. The emotions that are going to be used are: 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
sentiText plugin
****************
This plugin is based in the classifier developed for the TASS 2015 competition. It has been developed for Spanish and English. The different phases that has this plugin when it is activated:
* Train both classifiers (English and Spanish).
* Initialize resources (dictionaries,stopwords,etc.).
* Extract bag of words,lemmas and chars.
Once the plugin is activated, the features that are going to be extracted for the classifiers are:
* Matches with the bag of words extracted from the train corpus.
* Sentiment score of the sentences extracted from the dictionaries (lexicons and emoticons).
* Identify negations and intensifiers in the sentences.
* Complementary features such as exclamation and interrogation marks, eloganted and caps words, hashtags, etc.
The plugin has a preprocessor, which is focues on Twitter corpora, that is going to be used for cleaning the text to simplify the feature extraction.
There is more information avaliable in the next article.
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=37
vaderSentiment plugin
*********************
For developing this plugin, it has been used the module vaderSentiment, 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

View File

@@ -1,74 +0,0 @@
{
"@context": "http://mixedemotions-project.eu/ns/context.jsonld",
"@id": "me:Result1",
"@type": "results",
"analysis": [
"me:SAnalysis1",
"me:SgAnalysis1",
"me:EmotionAnalysis1",
"me:NER1"
],
"entries": [
{
"@id": "http://micro.blog/status1",
"@type": [
"nif:RFC5147String",
"nif:Context"
],
"nif:isString": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"entities": [
{
"@id": "http://micro.blog/status1#char=5,13",
"nif:beginIndex": 5,
"nif:endIndex": 13,
"nif:anchorOf": "Microsoft",
"me:references": "http://dbpedia.org/page/Microsoft",
"prov:wasGeneratedBy": "me:NER1"
},
{
"@id": "http://micro.blog/status1#char=25,37",
"nif:beginIndex": 25,
"nif:endIndex": 37,
"nif:anchorOf": "Windows Phone",
"me:references": "http://dbpedia.org/page/Windows_Phone",
"prov:wasGeneratedBy": "me:NER1"
}
],
"suggestions": [
{
"@id": "http://micro.blog/status1#char=16,77",
"nif:beginIndex": 16,
"nif:endIndex": 77,
"nif:anchorOf": "put your Windows Phone on your newest #open technology program",
"prov:wasGeneratedBy": "me:SgAnalysis1"
}
],
"sentiments": [
{
"@id": "http://micro.blog/status1#char=80,97",
"nif:beginIndex": 80,
"nif:endIndex": 97,
"nif:anchorOf": "You'll be awesome.",
"marl:hasPolarity": "marl:Positive",
"marl:polarityValue": 0.9,
"prov:wasGeneratedBy": "me:SAnalysis1"
}
],
"emotions": [
{
"@id": "http://micro.blog/status1#char=0,109",
"nif:anchorOf": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"prov:wasGeneratedBy": "me:EAnalysis1",
"onyx:hasEmotion": [
{
"onyx:hasEmotionCategory": "wna:liking"
},
{
"onyx:hasEmotionCategory": "wna:excitement"
}
]
}
]
}
]
}

View File

@@ -1,28 +1,19 @@
.. Senpy documentation master file, created by
sphinx-quickstart on Tue Feb 24 08:57:32 2015.
You can adapt this file completely to your liking, but it should at least
contain the root `toctree` directive.
Welcome to Senpy's documentation! Welcome to Senpy's documentation!
================================= =================================
With Senpy, you can easily turn your sentiment or emotion analysis algorithm into a full blown semantic service. Contents:
Sharing your sentiment analysis with the world has never been easier.
Senpy provides:
* Parameter validation, error handling
* Formatting: JSON-LD, Turtle/n-triples input and output, or simple text input
* Linked Data. Results are semantically annotated, using a series of well established vocabularies, and sane default URIs.
* A web UI where users can explore your service and test different settings
* A client to interact with any senpy service
* A command line tool
.. toctree:: .. toctree::
:caption: Learn more about senpy
:maxdepth: 2
senpy senpy
installation installation
usage usage
apischema api
schema
plugins plugins
conversion
demo demo
research.rst :maxdepth: 2

View File

@@ -22,35 +22,6 @@ If you want to install senpy globally, use sudo instead of the ``--user`` flag.
Docker Image Docker Image
************ ************
Build the image or use the pre-built one: Build the image or use the pre-built one: ``docker run -ti -p 5000:5000 gsiupm/senpy --host 0.0.0.0 --default-plugins``.
.. code:: bash
docker run -ti -p 5000:5000 gsiupm/senpy --host 0.0.0.0 --default-plugins
To add custom plugins, use a docker volume:
.. code:: bash
docker run -ti -p 5000:5000 -v <PATH OF PLUGINS>:/plugins gsiupm/senpy --host 0.0.0.0 --default-plugins -f /plugins
Alias
.....
If you are using the docker approach regularly, it is advisable to use a script or an alias to simplify your executions:
.. code:: bash
alias senpy='docker run --rm -ti -p 5000:5000 -v $PWD:/senpy-plugins gsiupm/senpy --default-plugins'
Python 2
........
There is a Senpy version for python2 too:
.. code:: bash
docker run -ti -p 5000:5000 gsiupm/senpy:python2.7 --host 0.0.0.0 --default-plugins
To add custom plugins, add a volume and tell senpy where to find the plugins: ``docker run -ti -p 5000:5000 -v <PATH OF PLUGINS>:/plugins gsiupm/senpy --host 0.0.0.0 --default-plugins -f /plugins``

View File

@@ -1,35 +1,26 @@
Developing new plugins Developing new plugins
---------------------- ----------------------
This document describes how to develop a new analysis plugin. For an example of conversion plugins, see :doc:`conversion`. Each plugin represents a different analysis process.There are two types of files that are needed by senpy for loading a plugin:
A more step-by-step tutorial with slides is available `here <https://lab.cluster.gsi.dit.upm.es/senpy/senpy-tutorial>`__ - Definition file, has the ".senpy" extension.
- Code file, is a python file.
What is a plugin? This separation will allow us to deploy plugins that use the same code but employ different parameters.
=================
A plugin is a program that, given a text, will add annotations to it.
In practice, a plugin consists of at least two files:
- Definition file: a `.senpy` file that describes the plugin (e.g. what input parameters it accepts, what emotion model it uses).
- Python module: the actual code that will add annotations to each input.
This separation allows us to deploy plugins that use the same code but employ different parameters.
For instance, one could use the same classifier and processing in several plugins, but train with different datasets. For instance, one could use the same classifier and processing in several plugins, but train with different datasets.
This scenario is particularly useful for evaluation purposes. This scenario is particularly useful for evaluation purposes.
The only limitation is that the name of each plugin needs to be unique. The only limitation is that the name of each plugin needs to be unique.
Plugin Definition files Plugins Definitions
======================= ===================
The definition file contains all the attributes of the plugin, and can be written in YAML or JSON. The definition file contains all the attributes of the plugin, and can be written in YAML or JSON.
When the server is launched, it will recursively search for definition files in the plugin folder (the current folder, by default).
The most important attributes are: The most important attributes are:
* **name**: unique name that senpy will use internally to identify the plugin. * **name**: unique name that senpy will use internally to identify the plugin.
* **module**: indicates the module that contains the plugin code, which will be automatically loaded by senpy. * **module**: indicates the module that contains the plugin code, which will be automatically loaded by senpy.
* **version** * **version**
* extra_params: to add parameters to the senpy API when this plugin is requested. Those parameters may be required, and have aliased names. For instance: * extra_params: used to specify parameters that the plugin accepts that are not already part of the senpy API. Those parameters may be required, and have aliased names. For instance:
.. code:: yaml .. code:: yaml
@@ -75,28 +66,10 @@ The basic methods in a plugin are:
* __init__ * __init__
* activate: used to load memory-hungry resources * activate: used to load memory-hungry resources
* deactivate: used to free up resources * deactivate: used to free up resources
* analyse_entry: called in every user requests. It takes two parameters: ``Entry``, the entry object, and ``params``, the parameters supplied by the user. It should yield one or more ``Entry`` objects. * analyse_entry: called in every user requests. It takes in the parameters supplied by a user and should yield one or more ``Entry`` objects.
Plugins are loaded asynchronously, so don't worry if the activate method takes too long. The plugin will be marked as activated once it is finished executing the method. Plugins are loaded asynchronously, so don't worry if the activate method takes too long. The plugin will be marked as activated once it is finished executing the method.
Entries
=======
Entries are objects that can be annotated.
By default, entries are `NIF contexts <http://persistence.uni-leipzig.org/nlp2rdf/ontologies/nif-core/nif-core.html>`_ represented in JSON-LD format.
Annotations are added to the object like this:
.. code:: python
entry = Entry()
entry.vocabulary__annotationName = 'myvalue'
entry['vocabulary:annotationName'] = 'myvalue'
entry['annotationNameURI'] = 'myvalue'
Where vocabulary is one of the prefixes defined in the default senpy context, and annotationURI is a full URI.
The value may be any valid JSON-LD dictionary.
For simplicity, senpy includes a series of models by default in the ``senpy.models`` module.
Example plugin Example plugin
============== ==============
@@ -142,13 +115,6 @@ Now, in a file named ``helloworld.py``:
F.A.Q. F.A.Q.
====== ======
What annotations can I use?
???????????????????????????
You can add almost any annotation to an entry.
The most common use cases are covered in the :doc:`schema`.
Why does the analyse function yield instead of return? Why does the analyse function yield instead of return?
?????????????????????????????????????????????????????? ??????????????????????????????????????????????????????
@@ -183,11 +149,7 @@ Training a classifier can be time time consuming. To avoid running the training
def deactivate(self): def deactivate(self):
self.close() self.close()
You can specify a 'shelf_file' in your .senpy file. By default the ShelfMixin creates a file based on the plugin name and stores it in that plugin's folder. You can speficy a 'shelf_file' in your .senpy file. By default the ShelfMixin creates a file based on the plugin name and stores it in that plugin's folder.
Shelves may get corrupted if the plugin exists unexpectedly.
A corrupt shelf prevents the plugin from loading.
If you do not care about the pickle, you can force your plugin to remove the corrupted file and load anyway, set the 'force_shelf' to True in your .senpy file.
I want to implement my service as a plugin, How i can do it? I want to implement my service as a plugin, How i can do it?
???????????????????????????????????????????????????????????? ????????????????????????????????????????????????????????????

View File

@@ -1,11 +0,0 @@
Research
--------
If you use Senpy in your research, please cite `Senpy: A Pragmatic Linked Sentiment Analysis Framework <http://gsi.dit.upm.es/index.php/es/investigacion/publicaciones?view=publication&task=show&id=417>`__ (`BibTex <http://gsi.dit.upm.es/index.php/es/investigacion/publicaciones?controller=publications&task=export&format=bibtex&id=417>`__):
.. code-block:: text
Sánchez-Rada, J. F., Iglesias, C. A., Corcuera, I., & Araque, Ó. (2016, October).
Senpy: A Pragmatic Linked Sentiment Analysis Framework.
In Data Science and Advanced Analytics (DSAA),
2016 IEEE International Conference on (pp. 735-742). IEEE.

View File

@@ -1,74 +1,74 @@
Schema Schema Examples
------ ===============
All the examples in this page use the :download:`the main schema <_static/schemas/definitions.json>`. All the examples in this page use the :download:`the main schema <_static/schemas/definitions.json>`.
Simple NIF annotation Simple NIF annotation
..................... ---------------------
Description Description
,,,,,,,,,,, ...........
This example covers the basic example in the NIF documentation: `<http://persistence.uni-leipzig.org/nlp2rdf/ontologies/nif-core/nif-core.html>`_. This example covers the basic example in the NIF documentation: `<http://persistence.uni-leipzig.org/nlp2rdf/ontologies/nif-core/nif-core.html>`_.
Representation Representation
,,,,,,,,,,,,,, ..............
.. literalinclude:: examples/results/example-basic.json .. literalinclude:: examples/example-basic.json
:language: json-ld :language: json-ld
Sentiment Analysis Sentiment Analysis
..................... ---------------------
Description Description
,,,,,,,,,,, ...........
Representation Representation
,,,,,,,,,,,,,, ..............
.. literalinclude:: examples/results/example-sentiment.json .. literalinclude:: examples/example-sentiment.json
:emphasize-lines: 5-10,25-33 :emphasize-lines: 5-10,25-33
:language: json-ld :language: json-ld
Suggestion Mining Suggestion Mining
................. -----------------
Description Description
,,,,,,,,,,, ...........
Representation Representation
,,,,,,,,,,,,,, ..............
.. literalinclude:: examples/results/example-suggestion.json .. literalinclude:: examples/example-suggestion.json
:emphasize-lines: 5-8,22-27 :emphasize-lines: 5-8,22-27
:language: json-ld :language: json-ld
Emotion Analysis Emotion Analysis
................ ----------------
Description Description
,,,,,,,,,,, ...........
Representation Representation
,,,,,,,,,,,,,, ..............
.. literalinclude:: examples/results/example-emotion.json .. literalinclude:: examples/example-emotion.json
:language: json-ld :language: json-ld
:emphasize-lines: 5-8,25-37 :emphasize-lines: 5-8,25-37
Named Entity Recognition Named Entity Recognition
........................ ------------------------
Description Description
,,,,,,,,,,, ...........
Representation Representation
,,,,,,,,,,,,,, ..............
.. literalinclude:: examples/results/example-ner.json .. literalinclude:: examples/example-ner.json
:emphasize-lines: 5-8,19-34 :emphasize-lines: 5-8,19-34
:language: json-ld :language: json-ld
Complete example Complete example
................ ----------------
Description Description
,,,,,,,,,,, ...........
This example covers all of the above cases, integrating all the annotations in the same document. This example covers all of the above cases, integrating all the annotations in the same document.
Representation Representation
,,,,,,,,,,,,,, ..............
.. literalinclude:: examples/results/example-complete.json .. literalinclude:: examples/example-complete.json
:language: json-ld :language: json-ld

View File

@@ -1,32 +1,35 @@
What is Senpy? What is Senpy?
-------------- --------------
Senpy is a framework that turns your sentiment or emotion analysis algorithm into a full blown semantic service. Senpy is an open source reference implementation of a linked data model for sentiment and emotion analysis services based on the vocabularies NIF, Marl and Onyx.
Senpy takes care of:
* Interfacing with the user: parameter validation, error handling. The overall goal of the reference implementation Senpy is easing the adoption of the proposed linked data model for sentiment and emotion analysis services, so that services from different providers become interoperable. With this aim, the design of the reference implementation has focused on its extensibility and reusability.
* Formatting: JSON-LD, Turtle/n-triples input and output, or simple text input
* Linked Data: senpy results are semantically annotated, using a series of well established vocabularies, and sane default URIs.
* User interface: a web UI where users can explore your service and test different settings
* A client to interact with the service. Currently only available in Python.
Sharing your sentiment analysis with the world has never been easier! A modular approach allows organizations to replace individual components with custom ones developed in-house. Furthermore, organizations can benefit from reusing prepackages modules that provide advanced functionalities, such as algorithms for sentiment and emotion analysis, linked data publication or emotion and sentiment mapping between different providers.
Senpy for service developers Specifications
============================ ==============
Check out the :doc:`plugins` if you have developed an analysis algorithm (e.g. sentiment analysis) and you want to publish it as a service. The model used in Senpy is based on the following specifications:
Senpy for end users * Marl, a vocabulary designed to annotate and describe subjetive opinions expressed on the web or in information systems.
=================== * Onyx, which is built one the same principles as Marl to annotate and describe emotions, and provides interoperability with Emotion Markup Language.
* NIF 2.0, which defines a semantic format and APO for improving interoperability among natural language processing services
All services built using senpy share a common interface. Architecture
This allows users to use them (almost) interchangeably. ============
Senpy comes with a :ref:`built-in client`.
The main component of a sentiment analysis service is the algorithm itself. However, for the algorithm to work, it needs to get the appropriate parameters from the user, format the results according to the defined API, interact with the user whn errors occur or more information is needed, etc.
.. toctree:: Senpy proposes a modular and dynamic architecture that allows:
:caption: Interested? Check out senpy's:
architecture
* Implementing different algorithms in a extensible way, yet offering a common interface.
* Offering common services that facilitate development, so developers can focus on implementing new and better algorithms.
The framework consists of two main modules: Senpy core, which is the building block of the service, and Senpy plugins, which consist of the analysis algorithm. The next figure depicts a simplified version of the processes involved in an analysis with the Senpy framework.
.. image:: senpy-architecture.png
:height: 400px
:width: 800px
:scale: 100 %
:align: center

View File

@@ -1,9 +1,20 @@
Usage Usage
----- -----
First of all, you need to install the package. The easiest and recommended way is to just use the command-line tool to load your plugins and launch the server.
See :doc:`installation` for installation instructions.
Once installed, the `senpy` command should be available. .. code:: bash
senpy
Or, alternatively:
.. code:: bash
python -m senpy
This will create a server with any modules found in the current path.
Useful command-line options Useful command-line options
=========================== ===========================
@@ -12,19 +23,19 @@ In case you want to load modules, which are located in different folders under t
.. code:: bash .. code:: bash
senpy -f . python -m senpy -f .
The default port used by senpy is 5000, but you can change it using the `--port` flag. The default port used by senpy is 5000, but you can change it using the option `--port`.
.. code:: bash .. code:: bash
senpy --port 8080 python -m senpy --port 8080
Also, the host can be changed where senpy is deployed. The default value is `127.0.0.1`. Also, the host can be changed where senpy is deployed. The default value is `127.0.0.1`.
.. code:: bash .. code:: bash
senpy --host 0.0.0.0 python -m senpy --host 0.0.0.0
For more options, see the `--help` page. For more options, see the `--help` page.
@@ -37,37 +48,28 @@ Once the server is launched, there is a basic endpoint in the server, which prov
In case you want to know the different endpoints of the server, there is more information available in the NIF API section_. In case you want to know the different endpoints of the server, there is more information available in the NIF API section_.
CLI demo Video example
======== =============
This video shows how to use senpy through command-line tool. This video shows how to use senpy through command-line tool.
.. image:: https://asciinema.org/a/9uwef1ghkjk062cw2t4mhzpyk.png https://asciinema.org/a/9uwef1ghkjk062cw2t4mhzpyk
:width: 100%
:target: https://asciinema.org/a/9uwef1ghkjk062cw2t4mhzpyk
:alt: CLI demo
Request example in python
=========================
Built-in client This example shows how to make a request to a plugin.
===============
This example shows how to make a request to the default plugin:
.. code:: python .. code:: python
from senpy.client import Client import requests
import json
c = Client('http://127.0.0.1:5000/api/') r = requests.get('http://127.0.0.1:5000/api/?algo=rand&i=Testing')
r = c.analyse('hello world') response = r.content.decode('utf-8')
response_json = json.loads(response)
for entry in r.entries:
print('{} -> {}'.format(entry.text, entry.emotions))
.. _section: http://senpy.readthedocs.org/en/latest/api.html .. _section: http://senpy.readthedocs.org/en/latest/api.html
Conversion
==========
See :doc:`conversion`

View File

@@ -1,8 +0,0 @@
Vocabularies and model
======================
The model used in Senpy is based on the following vocabularies:
* Marl, a vocabulary designed to annotate and describe subjetive opinions expressed on the web or in information systems.
* Onyx, which is built one the same principles as Marl to annotate and describe emotions, and provides interoperability with Emotion Markup Language.
* NIF 2.0, which defines a semantic format and APO for improving interoperability among natural language processing services

View File

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

View File

@@ -1,25 +0,0 @@
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: senpy-latest
spec:
replicas: 1
template:
metadata:
labels:
role: senpy-latest
app: test
spec:
containers:
- name: senpy-latest
image: gsiupm/senpy:latest
args:
- "--default-plugins"
resources:
limits:
memory: "512Mi"
cpu: "1000m"
ports:
- name: web
containerPort: 5000

View File

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

View File

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

View File

@@ -1,6 +1,6 @@
Flask>=0.10.1 Flask>=0.10.1
requests>=2.4.1 requests>=2.4.1
tornado>=4.4.3 gevent>=1.1rc4
PyLD>=0.6.5 PyLD>=0.6.5
six six
future future

View File

@@ -17,6 +17,7 @@
""" """
Sentiment analysis server in Python Sentiment analysis server in Python
""" """
from __future__ import print_function
from .version import __version__ from .version import __version__
import logging import logging

View File

@@ -22,19 +22,35 @@ the server.
from flask import Flask from flask import Flask
from senpy.extensions import Senpy from senpy.extensions import Senpy
from tornado.wsgi import WSGIContainer from gevent.wsgi import WSGIServer
from tornado.httpserver import HTTPServer from gevent.monkey import patch_all
from tornado.ioloop import IOLoop
import logging import logging
import os import os
import sys
import argparse import argparse
import senpy import senpy
patch_all(thread=False)
SERVER_PORT = os.environ.get("PORT", 5000) SERVER_PORT = os.environ.get("PORT", 5000)
def info(type, value, tb):
if hasattr(sys, 'ps1') or not sys.stderr.isatty():
# we are in interactive mode or we don't have a tty-like
# device, so we call the default hook
sys.__excepthook__(type, value, tb)
else:
import traceback
import pdb
# we are NOT in interactive mode, print the exception...
traceback.print_exception(type, value, tb)
print
# ...then start the debugger in post-mortem mode.
# pdb.pm() # deprecated
pdb.post_mortem(tb) # more "modern"
def main(): def main():
parser = argparse.ArgumentParser(description='Run a Senpy server') parser = argparse.ArgumentParser(description='Run a Senpy server')
parser.add_argument( parser.add_argument(
@@ -78,41 +94,28 @@ def main():
action='store_true', action='store_true',
default=False, default=False,
help='Do not run a server, only install plugin dependencies') help='Do not run a server, only install plugin dependencies')
parser.add_argument(
'--version',
'-v',
action='store_true',
default=False,
help='Output the senpy version and exit')
args = parser.parse_args() args = parser.parse_args()
if args.version:
print('Senpy version {}'.format(senpy.__version__))
exit(1)
logging.basicConfig() logging.basicConfig()
rl = logging.getLogger() rl = logging.getLogger()
rl.setLevel(getattr(logging, args.level)) rl.setLevel(getattr(logging, args.level))
app = Flask(__name__) app = Flask(__name__)
app.debug = args.debug app.debug = args.debug
if args.debug:
sys.excepthook = info
sp = Senpy(app, args.plugins_folder, default_plugins=args.default_plugins) sp = Senpy(app, args.plugins_folder, default_plugins=args.default_plugins)
if args.only_install: if args.only_install:
sp.install_deps() sp.install_deps()
return return
sp.activate_all() sp.activate_all()
print('Senpy version {}'.format(senpy.__version__)) http_server = WSGIServer((args.host, args.port), app)
print('Server running on port %s:%d. Ctrl+C to quit' % (args.host, try:
args.port)) print('Senpy version {}'.format(senpy.__version__))
if not app.debug: print('Server running on port %s:%d. Ctrl+C to quit' % (args.host,
http_server = HTTPServer(WSGIContainer(app)) args.port))
http_server.listen(args.port, address=args.host) http_server.serve_forever()
try: except KeyboardInterrupt:
IOLoop.instance().start() print('Bye!')
except KeyboardInterrupt: http_server.stop()
print('Bye!')
http_server.stop()
else:
app.run(args.host,
args.port,
debug=True)
sp.deactivate_all() sp.deactivate_all()

View File

@@ -26,13 +26,6 @@ API_PARAMS = {
"aliases": ["emotionModel", "emoModel"], "aliases": ["emotionModel", "emoModel"],
"required": False "required": False
}, },
"plugin_type": {
"@id": "pluginType",
"description": 'What kind of plugins to list',
"aliases": ["pluginType", "plugin_type"],
"required": True,
"default": "analysisPlugin"
},
"conversion": { "conversion": {
"@id": "conversion", "@id": "conversion",
"description": "How to show the elements that have (not) been converted", "description": "How to show the elements that have (not) been converted",
@@ -70,7 +63,7 @@ NIF_PARAMS = {
"aliases": ["f", "informat"], "aliases": ["f", "informat"],
"required": False, "required": False,
"default": "text", "default": "text",
"options": ["turtle", "text", "json-ld"], "options": ["turtle", "text"],
}, },
"intype": { "intype": {
"@id": "intype", "@id": "intype",

View File

@@ -25,7 +25,6 @@ from .version import __version__
from functools import wraps from functools import wraps
import logging import logging
import json
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
@@ -75,7 +74,7 @@ def basic_api(f):
@wraps(f) @wraps(f)
def decorated_function(*args, **kwargs): def decorated_function(*args, **kwargs):
raw_params = get_params(request) raw_params = get_params(request)
headers = {'X-ORIGINAL-PARAMS': json.dumps(raw_params)} headers = {'X-ORIGINAL-PARAMS': raw_params}
# Get defaults # Get defaults
web_params = parse_params({}, spec=WEB_PARAMS) web_params = parse_params({}, spec=WEB_PARAMS)
api_params = parse_params({}, spec=API_PARAMS) api_params = parse_params({}, spec=API_PARAMS)
@@ -93,9 +92,6 @@ def basic_api(f):
response = f(*args, **kwargs) response = f(*args, **kwargs)
except Error as ex: except Error as ex:
response = ex response = ex
logger.error(ex)
if current_app.debug:
raise
in_headers = web_params['inHeaders'] != "0" in_headers = web_params['inHeaders'] != "0"
expanded = api_params['expanded-jsonld'] expanded = api_params['expanded-jsonld']
@@ -125,9 +121,7 @@ def api():
@basic_api @basic_api
def plugins(): def plugins():
sp = current_app.senpy sp = current_app.senpy
ptype = request.params.get('plugin_type') dic = Plugins(plugins=list(sp.plugins.values()))
plugins = sp.filter_plugins(plugin_type=ptype)
dic = Plugins(plugins=list(plugins.values()))
return dic return dic

View File

@@ -1,7 +1,6 @@
import requests import requests
import logging import logging
from . import models from . import models
from .plugins import default_plugin_type
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
@@ -13,16 +12,13 @@ class Client(object):
def analyse(self, input, method='GET', **kwargs): def analyse(self, input, method='GET', **kwargs):
return self.request('/', method=method, input=input, **kwargs) return self.request('/', method=method, input=input, **kwargs)
def plugins(self, ptype=default_plugin_type):
resp = self.request(path='/plugins', plugin_type=ptype).plugins
return {p.name: p for p in resp}
def request(self, path=None, method='GET', **params): def request(self, path=None, method='GET', **params):
url = '{}{}'.format(self.endpoint, path) url = '{}{}'.format(self.endpoint, path)
response = requests.request(method=method, url=url, params=params) response = requests.request(method=method, url=url, params=params)
try: try:
resp = models.from_dict(response.json()) resp = models.from_dict(response.json())
resp.validate(resp) resp.validate(resp)
return resp
except Exception as ex: except Exception as ex:
logger.error(('There seems to be a problem with the response:\n' logger.error(('There seems to be a problem with the response:\n'
'\tURL: {url}\n' '\tURL: {url}\n'
@@ -37,6 +33,3 @@ class Client(object):
code=response.status_code, code=response.status_code,
content=response.content)) content=response.content))
raise ex raise ex
if isinstance(resp, models.Error):
raise resp
return resp

View File

@@ -5,35 +5,26 @@ It orchestrates plugin (de)activation and analysis.
from future import standard_library from future import standard_library
standard_library.install_aliases() standard_library.install_aliases()
from . import plugins from .plugins import SentimentPlugin, SenpyPlugin
from .plugins import SenpyPlugin from .models import Error, Entry, Results
from .models import Error, Entry, Results, from_string
from .blueprints import api_blueprint, demo_blueprint, ns_blueprint from .blueprints import api_blueprint, demo_blueprint, ns_blueprint
from .api import API_PARAMS, NIF_PARAMS, parse_params from .api import API_PARAMS, NIF_PARAMS, parse_params
from threading import Thread from threading import Thread
import os import os
import copy
import fnmatch import fnmatch
import inspect import inspect
import sys import sys
import importlib import imp
import logging import logging
import traceback import traceback
import yaml import yaml
import subprocess import pip
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
def log_subprocess_output(process):
for line in iter(process.stdout.readline, b''):
logger.info('%r', line)
for line in iter(process.stderr.readline, b''):
logger.error('%r', line)
class Senpy(object): class Senpy(object):
""" Default Senpy extension for Flask """ """ Default Senpy extension for Flask """
@@ -85,105 +76,74 @@ class Senpy(object):
else: else:
logger.debug("Not a folder: %s", folder) logger.debug("Not a folder: %s", folder)
def _find_plugins(self, params): def _find_plugin(self, params):
if not self.analysis_plugins: api_params = parse_params(params, spec=API_PARAMS)
algo = None
if "algorithm" in api_params and api_params["algorithm"]:
algo = api_params["algorithm"]
elif self.plugins:
algo = self.default_plugin and self.default_plugin.name
if not algo:
raise Error( raise Error(
status=404, status=404,
message=("No plugins found." message=("No plugins found."
" Please install one.")) " Please install one.").format(algo))
api_params = parse_params(params, spec=API_PARAMS) if algo not in self.plugins:
algos = None logger.debug(("The algorithm '{}' is not valid\n"
if "algorithm" in api_params and api_params["algorithm"]: "Valid algorithms: {}").format(algo,
algos = api_params["algorithm"].split(',') self.plugins.keys()))
elif self.default_plugin:
algos = [self.default_plugin.name, ]
else:
raise Error( raise Error(
status=404, status=404,
message="No default plugin found, and None provided") message="The algorithm '{}' is not valid".format(algo))
plugins = list() if not self.plugins[algo].is_activated:
for algo in algos: logger.debug("Plugin not activated: {}".format(algo))
if algo not in self.plugins: raise Error(
logger.debug(("The algorithm '{}' is not valid\n" status=400,
"Valid algorithms: {}").format(algo, message=("The algorithm '{}'"
self.plugins.keys())) " is not activated yet").format(algo))
raise Error( return self.plugins[algo]
status=404,
message="The algorithm '{}' is not valid".format(algo))
if not self.plugins[algo].is_activated: def _get_params(self, params, plugin):
logger.debug("Plugin not activated: {}".format(algo))
raise Error(
status=400,
message=("The algorithm '{}'"
" is not activated yet").format(algo))
plugins.append(self.plugins[algo])
return plugins
def _get_params(self, params, plugin=None):
nif_params = parse_params(params, spec=NIF_PARAMS) nif_params = parse_params(params, spec=NIF_PARAMS)
if plugin: extra_params = plugin.get('extra_params', {})
extra_params = plugin.get('extra_params', {}) specific_params = parse_params(params, spec=extra_params)
specific_params = parse_params(params, spec=extra_params) nif_params.update(specific_params)
nif_params.update(specific_params)
return nif_params return nif_params
def _get_entries(self, params): def _get_entries(self, params):
entry = None
if params['informat'] == 'text': if params['informat'] == 'text':
results = Results()
entry = Entry(text=params['input']) entry = Entry(text=params['input'])
results.entries.append(entry)
elif params['informat'] == 'json-ld':
results = from_string(params['input'], cls=Results)
else: else:
raise NotImplemented('Informat {} is not implemented'.format(params['informat'])) raise NotImplemented('Only text input format implemented')
return results yield entry
def _process_entries(self, entries, plugins, nif_params):
if not plugins:
for i in entries:
yield i
return
plugin = plugins[0]
specific_params = self._get_params(nif_params, plugin)
results = plugin.analyse_entries(entries, specific_params)
for i in self._process_entries(results, plugins[1:], nif_params):
yield i
def _process_response(self, resp, plugins, nif_params):
entries = resp.entries
resp.entries = []
for plug in plugins:
resp.analysis.append(plug.id)
for i in self._process_entries(entries, plugins, nif_params):
resp.entries.append(i)
return resp
def analyse(self, **api_params): def analyse(self, **api_params):
"""
Main method that analyses a request, either from CLI or HTTP.
It uses a dictionary of parameters, provided by the user.
"""
logger.debug("analysing with params: {}".format(api_params)) logger.debug("analysing with params: {}".format(api_params))
plugins = self._find_plugins(api_params) plugin = self._find_plugin(api_params)
nif_params = self._get_params(api_params) nif_params = self._get_params(api_params, plugin)
resp = self._get_entries(nif_params) resp = Results()
if 'with_parameters' in api_params: if 'with_parameters' in api_params:
resp.parameters = nif_params resp.parameters = nif_params
try: try:
resp = self._process_response(resp, plugins, nif_params) entries = []
self.convert_emotions(resp, plugins, nif_params) for i in self._get_entries(nif_params):
entries += list(plugin.analyse_entry(i, nif_params))
resp.entries = entries
self.convert_emotions(resp, plugin, nif_params)
resp.analysis.append(plugin.id)
logger.debug("Returning analysis result: {}".format(resp)) logger.debug("Returning analysis result: {}".format(resp))
except (Error, Exception) as ex: except Error as ex:
if not isinstance(ex, Error):
ex = Error(message=str(ex), status=500)
logger.exception('Error returning analysis result') logger.exception('Error returning analysis result')
raise ex resp = ex
except Exception as ex:
logger.exception('Error returning analysis result')
resp = Error(message=str(ex), status=500)
return resp return resp
def _conversion_candidates(self, fromModel, toModel): def _conversion_candidates(self, fromModel, toModel):
candidates = self.filter_plugins(plugin_type='emotionConversionPlugin') candidates = self.filter_plugins(**{'@type': 'emotionConversionPlugin'})
for name, candidate in candidates.items(): for name, candidate in candidates.items():
for pair in candidate.onyx__doesConversion: for pair in candidate.onyx__doesConversion:
logging.debug(pair) logging.debug(pair)
@@ -193,42 +153,37 @@ class Senpy(object):
# logging.debug('Found candidate: {}'.format(candidate)) # logging.debug('Found candidate: {}'.format(candidate))
yield candidate yield candidate
def convert_emotions(self, resp, plugins, params): def convert_emotions(self, resp, plugin, params):
""" """
Conversion of all emotions in a response **in place**. Conversion of all emotions in a response.
In addition to converting from one model to another, it has In addition to converting from one model to another, it has
to include the conversion plugin to the analysis list. to include the conversion plugin to the analysis list.
Needless to say, this is far from an elegant solution, but it works. Needless to say, this is far from an elegant solution, but it works.
@todo refactor and clean up @todo refactor and clean up
""" """
fromModel = plugin.get('onyx:usesEmotionModel', None)
toModel = params.get('emotionModel', None) toModel = params.get('emotionModel', None)
output = params.get('conversion', None)
logger.debug('Asked for model: {}'.format(toModel))
logger.debug('Analysis plugin uses model: {}'.format(fromModel))
if not toModel: if not toModel:
return return
try:
logger.debug('Asked for model: {}'.format(toModel)) candidate = next(self._conversion_candidates(fromModel, toModel))
output = params.get('conversion', None) except StopIteration:
candidates = {} e = Error(('No conversion plugin found for: '
for plugin in plugins: '{} -> {}'.format(fromModel, toModel)))
try: e.original_response = resp
fromModel = plugin.get('onyx:usesEmotionModel', None) e.parameters = params
candidates[plugin.id] = next(self._conversion_candidates(fromModel, toModel)) raise e
logger.debug('Analysis plugin {} uses model: {}'.format(plugin.id, fromModel))
except StopIteration:
e = Error(('No conversion plugin found for: '
'{} -> {}'.format(fromModel, toModel)))
e.original_response = resp
e.parameters = params
raise e
newentries = [] newentries = []
for i in resp.entries: for i in resp.entries:
if output == "full": if output == "full":
newemotions = copy.deepcopy(i.emotions) newemotions = i.emotions.copy()
else: else:
newemotions = [] newemotions = []
for j in i.emotions: for j in i.emotions:
plugname = j['prov:wasGeneratedBy']
candidate = candidates[plugname]
resp.analysis.append(candidate.id)
for k in candidate.convert(j, fromModel, toModel, params): for k in candidate.convert(j, fromModel, toModel, params):
k.prov__wasGeneratedBy = candidate.id k.prov__wasGeneratedBy = candidate.id
if output == 'nested': if output == 'nested':
@@ -237,14 +192,13 @@ class Senpy(object):
i.emotions = newemotions i.emotions = newemotions
newentries.append(i) newentries.append(i)
resp.entries = newentries resp.entries = newentries
resp.analysis = list(set(resp.analysis)) resp.analysis.append(candidate.id)
@property @property
def default_plugin(self): def default_plugin(self):
candidate = self._default candidate = self._default
if not candidate: if not candidate:
candidates = self.filter_plugins(plugin_type='analysisPlugin', candidates = self.filter_plugins(is_activated=True)
is_activated=True)
if len(candidates) > 0: if len(candidates) > 0:
candidate = list(candidates.values())[0] candidate = list(candidates.values())[0]
logger.debug("Default: {}".format(candidate)) logger.debug("Default: {}".format(candidate))
@@ -298,12 +252,11 @@ class Senpy(object):
logger.error(msg) logger.error(msg)
raise Error(msg) raise Error(msg)
if sync or 'async' in plugin and not plugin.async: if sync:
act() act()
else: else:
th = Thread(target=act) th = Thread(target=act)
th.start() th.start()
return th
def deactivate_plugin(self, plugin_name, sync=False): def deactivate_plugin(self, plugin_name, sync=False):
try: try:
@@ -323,45 +276,31 @@ class Senpy(object):
"Error deactivating plugin {}: {}".format(plugin.name, ex)) "Error deactivating plugin {}: {}".format(plugin.name, ex))
logger.error("Trace: {}".format(traceback.format_exc())) logger.error("Trace: {}".format(traceback.format_exc()))
if sync or 'async' in plugin and not plugin.async: if sync:
deact() deact()
else: else:
th = Thread(target=deact) th = Thread(target=deact)
th.start() th.start()
return th
@classmethod @classmethod
def validate_info(cls, info): def validate_info(cls, info):
return all(x in info for x in ('name', 'module', 'description', 'version')) return all(x in info for x in ('name', 'module', 'version'))
def install_deps(self): def install_deps(self):
for i in self.plugins.values(): for i in self.plugins.values():
self._install_deps(i) self._install_deps(i._info)
@classmethod @classmethod
def _install_deps(cls, info=None): def _install_deps(cls, info=None):
requirements = info.get('requirements', []) requirements = info.get('requirements', [])
if requirements: if requirements:
pip_args = ['pip'] pip_args = []
pip_args.append('install') pip_args.append('install')
pip_args.append('--use-wheel') pip_args.append('--use-wheel')
for req in requirements: for req in requirements:
pip_args.append(req) pip_args.append(req)
logger.info('Installing requirements: ' + str(requirements)) logger.info('Installing requirements: ' + str(requirements))
process = subprocess.Popen(pip_args, pip.main(pip_args)
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
log_subprocess_output(process)
exitcode = process.wait()
if exitcode != 0:
raise Error("Dependencies not properly installed")
@classmethod
def _load_module(cls, name, root):
sys.path.append(root)
tmp = importlib.import_module(name)
sys.path.remove(root)
return tmp
@classmethod @classmethod
def _load_plugin_from_info(cls, info, root): def _load_plugin_from_info(cls, info, root):
@@ -370,10 +309,11 @@ class Senpy(object):
return None, None return None, None
module = info["module"] module = info["module"]
name = info["name"] name = info["name"]
sys.path.append(root)
(fp, pathname, desc) = imp.find_module(module, [root, ])
cls._install_deps(info) cls._install_deps(info)
tmp = cls._load_module(module, root) tmp = imp.load_module(module, fp, pathname, desc)
sys.path.remove(root)
candidate = None candidate = None
for _, obj in inspect.getmembers(tmp): for _, obj in inspect.getmembers(tmp):
if inspect.isclass(obj) and inspect.getmodule(obj) == tmp: if inspect.isclass(obj) and inspect.getmodule(obj) == tmp:
@@ -419,9 +359,23 @@ class Senpy(object):
return self._plugin_list return self._plugin_list
def filter_plugins(self, **kwargs): def filter_plugins(self, **kwargs):
return plugins.pfilter(self.plugins, **kwargs) """ Filter plugins by different criteria """
@property def matches(plug):
def analysis_plugins(self): res = all(getattr(plug, k, None) == v for (k, v) in kwargs.items())
""" Return only the analysis plugins """ logger.debug(
return self.filter_plugins(plugin_type='analysisPlugin') "matching {} with {}: {}".format(plug.name, kwargs, res))
return res
if not kwargs:
return self.plugins
else:
return {n: p for n, p in self.plugins.items() if matches(p)}
def sentiment_plugins(self):
""" Return only the sentiment plugins """
return {
p: plugin
for p, plugin in self.plugins.items()
if isinstance(plugin, SentimentPlugin)
}

View File

@@ -214,7 +214,6 @@ class BaseModel(SenpyMixin, dict):
temp['@type'] = getattr(self, '@type') temp['@type'] = getattr(self, '@type')
except AttributeError: except AttributeError:
logger.warn('Creating an instance of an unknown model') logger.warn('Creating an instance of an unknown model')
super(BaseModel, self).__init__(temp) super(BaseModel, self).__init__(temp)
def _get_key(self, key): def _get_key(self, key):
@@ -237,10 +236,7 @@ class BaseModel(SenpyMixin, dict):
self.__setitem__(self._get_key(key), value) self.__setitem__(self._get_key(key), value)
def __delattr__(self, key): def __delattr__(self, key):
try: self.__delitem__(self._get_key(key))
object.__delattr__(self, key)
except AttributeError:
self.__delitem__(self._get_key(key))
def _plain_dict(self): def _plain_dict(self):
d = {k: v for (k, v) in self.items() if k[0] != "_"} d = {k: v for (k, v) in self.items() if k[0] != "_"}
@@ -256,32 +252,13 @@ def register(rsubclass, rtype=None):
_subtypes[rtype or rsubclass.__name__] = rsubclass _subtypes[rtype or rsubclass.__name__] = rsubclass
def from_dict(indict, cls=None): def from_dict(indict):
if not cls: target = indict.get('@type', None)
target = indict.get('@type', None) if target and target in _subtypes:
try: cls = _subtypes[target]
if target and target in _subtypes: else:
cls = _subtypes[target] cls = BaseModel
else: return cls(**indict)
cls = BaseModel
except Exception:
cls = BaseModel
outdict = dict()
for k, v in indict.items():
if k == '@context':
pass
elif isinstance(v, dict):
v = from_dict(indict[k])
elif isinstance(v, list):
for ix, v2 in enumerate(v):
if isinstance(v2, dict):
v[ix] = from_dict(v2)
outdict[k] = v
return cls(**outdict)
def from_string(string, **kwargs):
return from_dict(json.loads(string), **kwargs)
def from_json(injson): def from_json(injson):
@@ -331,7 +308,7 @@ for i in [
_ErrorModel = from_schema('error') _ErrorModel = from_schema('error')
class Error(SenpyMixin, Exception): class Error(SenpyMixin, BaseException):
def __init__(self, message, *args, **kwargs): def __init__(self, message, *args, **kwargs):
super(Error, self).__init__(self, message, message) super(Error, self).__init__(self, message, message)
self._error = _ErrorModel(message=message, *args, **kwargs) self._error = _ErrorModel(message=message, *args, **kwargs)
@@ -360,8 +337,5 @@ class Error(SenpyMixin, Exception):
def __delattr__(self, key): def __delattr__(self, key):
delattr(self._error, key) delattr(self._error, key)
def __str__(self):
return str(self.to_JSON(with_context=False))
register(Error, 'error') register(Error, 'error')

View File

@@ -3,18 +3,16 @@ standard_library.install_aliases()
import inspect import inspect
import os.path import os.path
import os
import pickle import pickle
import logging import logging
import tempfile import tempfile
import copy import copy
from .. import models from . import models
from ..api import API_PARAMS
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
class Plugin(models.Plugin): class SenpyPlugin(models.Plugin):
def __init__(self, info=None): def __init__(self, info=None):
""" """
Provides a canonical name for plugins and serves as base for other Provides a canonical name for plugins and serves as base for other
@@ -25,24 +23,12 @@ class Plugin(models.Plugin):
"information for the plugin.")) "information for the plugin."))
logger.debug("Initialising {}".format(info)) logger.debug("Initialising {}".format(info))
id = 'plugins/{}_{}'.format(info['name'], info['version']) id = 'plugins/{}_{}'.format(info['name'], info['version'])
super(Plugin, self).__init__(id=id, **info) super(SenpyPlugin, self).__init__(id=id, **info)
self.is_activated = False self.is_activated = False
def get_folder(self): def get_folder(self):
return os.path.dirname(inspect.getfile(self.__class__)) return os.path.dirname(inspect.getfile(self.__class__))
def activate(self):
pass
def deactivate(self):
pass
SenpyPlugin = Plugin
class AnalysisPlugin(Plugin):
def analyse(self, *args, **kwargs): def analyse(self, *args, **kwargs):
raise NotImplemented( raise NotImplemented(
'Your method should implement either analyse or analyse_entry') 'Your method should implement either analyse or analyse_entry')
@@ -61,33 +47,30 @@ class AnalysisPlugin(Plugin):
for i in results.entries: for i in results.entries:
yield i yield i
def analyse_entries(self, entries, parameters): def activate(self):
for entry in entries: pass
logger.debug('Analysing entry with plugin {}: {}'.format(self, entry))
for result in self.analyse_entry(entry, parameters): def deactivate(self):
yield result pass
class ConversionPlugin(Plugin): class SentimentPlugin(models.SentimentPlugin, SenpyPlugin):
pass
class SentimentPlugin(models.SentimentPlugin, AnalysisPlugin):
def __init__(self, info, *args, **kwargs): def __init__(self, info, *args, **kwargs):
super(SentimentPlugin, self).__init__(info, *args, **kwargs) super(SentimentPlugin, self).__init__(info, *args, **kwargs)
self.minPolarityValue = float(info.get("minPolarityValue", 0)) self.minPolarityValue = float(info.get("minPolarityValue", 0))
self.maxPolarityValue = float(info.get("maxPolarityValue", 1)) self.maxPolarityValue = float(info.get("maxPolarityValue", 1))
class EmotionPlugin(models.EmotionPlugin, AnalysisPlugin): class EmotionPlugin(models.EmotionPlugin, SenpyPlugin):
def __init__(self, info, *args, **kwargs): def __init__(self, info, *args, **kwargs):
super(EmotionPlugin, self).__init__(info, *args, **kwargs) super(EmotionPlugin, self).__init__(info, *args, **kwargs)
self.minEmotionValue = float(info.get("minEmotionValue", -1)) self.minEmotionValue = float(info.get("minEmotionValue", -1))
self.maxEmotionValue = float(info.get("maxEmotionValue", 1)) self.maxEmotionValue = float(info.get("maxEmotionValue", 1))
class EmotionConversionPlugin(models.EmotionConversionPlugin, ConversionPlugin): class EmotionConversionPlugin(models.EmotionConversionPlugin, SenpyPlugin):
pass def __init__(self, info, *args, **kwargs):
super(EmotionConversionPlugin, self).__init__(info, *args, **kwargs)
class ShelfMixin(object): class ShelfMixin(object):
@@ -96,12 +79,7 @@ class ShelfMixin(object):
if not hasattr(self, '_sh') or self._sh is None: if not hasattr(self, '_sh') or self._sh is None:
self.__dict__['_sh'] = {} self.__dict__['_sh'] = {}
if os.path.isfile(self.shelf_file): if os.path.isfile(self.shelf_file):
try: self.__dict__['_sh'] = pickle.load(open(self.shelf_file, 'rb'))
self.__dict__['_sh'] = pickle.load(open(self.shelf_file, 'rb'))
except (IndexError, EOFError, pickle.UnpicklingError):
logger.warning('{} has a corrupted shelf file!'.format(self.id))
if not self.get('force_shelf', False):
raise
return self._sh return self._sh
@sh.deleter @sh.deleter
@@ -114,8 +92,8 @@ class ShelfMixin(object):
@property @property
def shelf_file(self): def shelf_file(self):
if 'shelf_file' not in self or not self['shelf_file']: if 'shelf_file' not in self or not self['shelf_file']:
sd = os.environ.get('SENPY_DATA', tempfile.gettempdir()) self.shelf_file = os.path.join(tempfile.gettempdir(),
self.shelf_file = os.path.join(sd, self.name + '.p') self.name + '.p')
return self['shelf_file'] return self['shelf_file']
def save(self): def save(self):
@@ -123,40 +101,3 @@ class ShelfMixin(object):
if hasattr(self, '_sh') and self._sh is not None: if hasattr(self, '_sh') and self._sh is not None:
with open(self.shelf_file, 'wb') as f: with open(self.shelf_file, 'wb') as f:
pickle.dump(self._sh, f) pickle.dump(self._sh, f)
default_plugin_type = API_PARAMS['plugin_type']['default']
def pfilter(plugins, **kwargs):
""" Filter plugins by different criteria """
if isinstance(plugins, models.Plugins):
plugins = plugins.plugins
elif isinstance(plugins, dict):
plugins = plugins.values()
ptype = kwargs.pop('plugin_type', default_plugin_type)
logger.debug('#' * 100)
logger.debug('ptype {}'.format(ptype))
if ptype:
try:
ptype = ptype[0].upper() + ptype[1:]
pclass = globals()[ptype]
logger.debug('Class: {}'.format(pclass))
candidates = filter(lambda x: isinstance(x, pclass),
plugins)
except KeyError:
raise models.Error('{} is not a valid type'.format(ptype))
else:
candidates = plugins
logger.debug(candidates)
def matches(plug):
res = all(getattr(plug, k, None) == v for (k, v) in kwargs.items())
logger.debug(
"matching {} with {}: {}".format(plug.name, kwargs, res))
return res
if kwargs:
candidates = filter(matches, candidates)
return {p.name: p for p in candidates}

View File

@@ -1,80 +0,0 @@
from senpy.plugins import EmotionConversionPlugin
from senpy.models import EmotionSet, Emotion, Error
import logging
logger = logging.getLogger(__name__)
class CentroidConversion(EmotionConversionPlugin):
def __init__(self, info):
if 'centroids' not in info:
raise Error('Centroid conversion plugins should provide '
'the centroids in their senpy file')
if 'onyx:doesConversion' not in info:
if 'centroids_direction' not in info:
raise Error('Please, provide centroids direction')
cf, ct = info['centroids_direction']
info['onyx:doesConversion'] = [{
'onyx:conversionFrom': cf,
'onyx:conversionTo': ct
}, {
'onyx:conversionFrom': ct,
'onyx:conversionTo': cf
}]
if 'aliases' in info:
aliases = info['aliases']
ncentroids = {}
for k1, v1 in info['centroids'].items():
nv1 = {}
for k2, v2 in v1.items():
nv1[aliases.get(k2, k2)] = v2
ncentroids[aliases.get(k1, k1)] = nv1
info['centroids'] = ncentroids
super(CentroidConversion, self).__init__(info)
def _forward_conversion(self, original):
"""Sum the VAD value of all categories found."""
res = Emotion()
for e in original.onyx__hasEmotion:
category = e.onyx__hasEmotionCategory
if category in self.centroids:
for dim, value in self.centroids[category].items():
try:
res[dim] += value
except Exception:
res[dim] = value
return res
def _backwards_conversion(self, original):
"""Find the closest category"""
dimensions = list(self.centroids.values())[0]
def distance(e1, e2):
return sum((e1[k] - e2.get(k, 0)) for k in dimensions)
emotion = ''
mindistance = 10000000000000000000000.0
for state in self.centroids:
d = distance(self.centroids[state], original)
if d < mindistance:
mindistance = d
emotion = state
result = Emotion(onyx__hasEmotionCategory=emotion)
return result
def convert(self, emotionSet, fromModel, toModel, params):
cf, ct = self.centroids_direction
logger.debug(
'{}\n{}\n{}\n{}'.format(emotionSet, fromModel, toModel, params))
e = EmotionSet()
if fromModel == cf and toModel == ct:
e.onyx__hasEmotion.append(self._forward_conversion(emotionSet))
elif fromModel == ct and toModel == cf:
for i in emotionSet.onyx__hasEmotion:
e.onyx__hasEmotion.append(self._backwards_conversion(i))
else:
raise Error('EMOTION MODEL NOT KNOWN')
yield e

View File

@@ -1,39 +0,0 @@
---
name: Ekman2FSRE
module: senpy.plugins.conversion.centroids
description: Plugin to convert emotion sets from Ekman to VAD
version: 0.1
# No need to specify onyx:doesConversion because centroids.py adds it automatically from centroids_direction
centroids:
anger:
A: 6.95
D: 5.1
V: 2.7
disgust:
A: 5.3
D: 8.05
V: 2.7
fear:
A: 6.5
D: 3.6
V: 3.2
happiness:
A: 7.22
D: 6.28
V: 8.6
sadness:
A: 5.21
D: 2.82
V: 2.21
centroids_direction:
- emoml:big6
- emoml:fsre-dimensions
aliases: # These are aliases for any key in the centroid, to avoid repeating a long name several times
A: emoml:arousal
V: emoml:valence
D: emoml:dominance
anger: emoml:big6anger
disgust: emoml:big6disgust
fear: emoml:big6fear
happiness: emoml:big6happiness
sadness: emoml:big6sadness

View File

@@ -0,0 +1,56 @@
from senpy.plugins import EmotionConversionPlugin
from senpy.models import EmotionSet, Emotion, Error
import logging
logger = logging.getLogger(__name__)
import math
class WNA2VAD(EmotionConversionPlugin):
def _ekman_to_vad(self, ekmanSet):
potency = 0
arousal = 0
dominance = 0
for e in ekmanSet.onyx__hasEmotion:
category = e.onyx__hasEmotionCategory
centroid = self.centroids[category]
potency += centroid['V']
arousal += centroid['A']
dominance += centroid['D']
e = Emotion({'emoml:potency': potency,
'emoml:arousal': arousal,
'emoml:dominance': dominance})
return e
def _vad_to_ekman(self, VADEmotion):
V = VADEmotion['emoml:valence']
A = VADEmotion['emoml:potency']
D = VADEmotion['emoml:dominance']
emotion = ''
value = 10000000000000000000000.0
for state in self.centroids:
valence = V - self.centroids[state]['V']
arousal = A - self.centroids[state]['A']
dominance = D - self.centroids[state]['D']
new_value = math.sqrt((valence**2) +
(arousal**2) +
(dominance**2))
if new_value < value:
value = new_value
emotion = state
result = Emotion(onyx__hasEmotionCategory=emotion)
return result
def convert(self, emotionSet, fromModel, toModel, params):
logger.debug('{}\n{}\n{}\n{}'.format(emotionSet, fromModel, toModel, params))
e = EmotionSet()
if fromModel == 'emoml:big6':
e.onyx__hasEmotion.append(self._ekman_to_vad(emotionSet))
elif fromModel == 'emoml:fsre-dimensions':
for i in emotionSet.onyx__hasEmotion:
e.onyx__hasEmotion.append(self._vad_to_ekman(e))
else:
raise Error('EMOTION MODEL NOT KNOWN')
yield e

View File

@@ -1,39 +1,35 @@
--- ---
name: Ekman2PAD name: Ekman2VAD
module: senpy.plugins.conversion.centroids module: ekman2vad
description: Plugin to convert emotion sets from Ekman to VAD description: Plugin to convert from Ekman to VAD
version: 0.1 version: 0.1
# No need to specify onyx:doesConversion because centroids.py adds it automatically from centroids_direction onyx:doesConversion:
- onyx:conversionFrom: emoml:big6
onyx:conversionTo: emoml:fsre-dimensions
- onyx:conversionFrom: emoml:fsre-dimensions
onyx:conversionTo: wna:WNAModel
centroids: centroids:
anger: emoml:big6anger:
A: 6.95 A: 6.95
D: 5.1 D: 5.1
V: 2.7 V: 2.7
disgust: emoml:big6disgust:
A: 5.3 A: 5.3
D: 8.05 D: 8.05
V: 2.7 V: 2.7
fear: emoml:big6fear:
A: 6.5 A: 6.5
D: 3.6 D: 3.6
V: 3.2 V: 3.2
happiness: emoml:big6happiness:
A: 7.22 A: 7.22
D: 6.28 D: 6.28
V: 8.6 V: 8.6
sadness: emoml:big6sadness:
A: 5.21 A: 5.21
D: 2.82 D: 2.82
V: 2.21 V: 2.21
centroids_direction: aliases:
- emoml:big6
- emoml:pad
aliases: # These are aliases for any key in the centroid, to avoid repeating a long name several times
A: emoml:arousal A: emoml:arousal
V: emoml:valence V: emoml:potency
D: emoml:dominance D: emoml:dominance
anger: emoml:big6anger
disgust: emoml:big6disgust
fear: emoml:big6fear
happiness: emoml:big6happiness
sadness: emoml:big6sadness

View File

@@ -37,12 +37,6 @@
"@type": "@id", "@type": "@id",
"@container": "@set" "@container": "@set"
}, },
"options": {
"@container": "@set"
},
"plugins": {
"@container": "@set"
},
"prov:wasGeneratedBy": { "prov:wasGeneratedBy": {
"@type": "@id" "@type": "@id"
}, },

View File

@@ -6,10 +6,11 @@
"properties": { "properties": {
"plugins": { "plugins": {
"type": "array", "type": "array",
"default": [],
"items": { "items": {
"$ref": "plugin.json" "$ref": "plugin.json"
} }
},
"@type": {
} }
} }
} }

View File

@@ -18,16 +18,10 @@
"type": "string" "type": "string"
}, },
"analysis": { "analysis": {
"default": [],
"type": "array", "type": "array",
"default": [],
"items": { "items": {
"anyOf": [ "$ref": "analysis.json"
{
"$ref": "analysis.json"
},{
"type": "string"
}
]
} }
}, },
"entries": { "entries": {

View File

@@ -47,7 +47,7 @@
This website is the senpy Playground, which allows you to test the instance of senpy in this server. It provides a user-friendly interface to the functions exposed by the senpy API. This website is the senpy Playground, which allows you to test the instance of senpy in this server. It provides a user-friendly interface to the functions exposed by the senpy API.
</p> </p>
<p> <p>
Once you get comfortable with the parameters and results, you are encouraged to issue your own requests to the API endpoint. You can find examples of API URL's when you try out a plugin with the "Analyse!" button on the "Test it" tab. Once you get comfortable with the parameters and results, you are encouraged to issue your own requests to the API endpoint, which should be <a href="/api">here</a>.
</p> </p>
<p> <p>
These are some of the things you can do with the API: These are some of the things you can do with the API:

View File

@@ -8,12 +8,8 @@ DEFAULT_FILE = os.path.join(ROOT, 'VERSION')
def read_version(versionfile=DEFAULT_FILE): def read_version(versionfile=DEFAULT_FILE):
try: with open(versionfile) as f:
with open(versionfile) as f: return f.read().strip()
return f.read().strip()
except IOError:
logger.error('Running an unknown version of senpy. Be careful!.')
return '0.0'
__version__ = read_version() __version__ = read_version()

View File

@@ -9,6 +9,4 @@ test=pytest
ignore = E402 ignore = E402
max-line-length = 100 max-line-length = 100
[bdist_wheel] [bdist_wheel]
universal=1 universal=1
[tool:pytest]
addopts = --cov=senpy --cov-report term-missing

View File

@@ -1,3 +1,3 @@
pytest
mock mock
pytest-cov pytest-cov
pytest

View File

@@ -1,23 +0,0 @@
from senpy.plugins import AnalysisPlugin
import multiprocessing
def _train(process_number):
return process_number
class AsyncPlugin(AnalysisPlugin):
def _do_async(self, num_processes):
pool = multiprocessing.Pool(processes=num_processes)
values = pool.map(_train, range(num_processes))
return values
def activate(self):
self.value = self._do_async(4)
def analyse_entry(self, entry, params):
values = self._do_async(2)
entry.async_values = values
yield entry

View File

@@ -1,8 +0,0 @@
---
name: Async
module: asyncplugin
description: I am async
author: "@balkian"
version: '0.1'
async: true
extra_params: {}

View File

@@ -4,5 +4,4 @@ from senpy.plugins import SentimentPlugin
class DummyPlugin(SentimentPlugin): class DummyPlugin(SentimentPlugin):
def analyse_entry(self, entry, params): def analyse_entry(self, entry, params):
entry.text = entry.text[::-1] entry.text = entry.text[::-1]
entry.reversed = entry.get('reversed', 0) + 1
yield entry yield entry

View File

@@ -1,8 +1,8 @@
from senpy.plugins import AnalysisPlugin from senpy.plugins import SenpyPlugin
from time import sleep from time import sleep
class SleepPlugin(AnalysisPlugin): class SleepPlugin(SenpyPlugin):
def activate(self, *args, **kwargs): def activate(self, *args, **kwargs):
sleep(self.timeout) sleep(self.timeout)

View File

@@ -1,68 +0,0 @@
import logging
logger = logging.getLogger(__name__)
from unittest import TestCase
from senpy.api import parse_params, API_PARAMS, NIF_PARAMS, WEB_PARAMS
from senpy.models import Error
class APITest(TestCase):
def test_api_params(self):
"""The API should not define any required parameters without a default"""
parse_params({}, spec=API_PARAMS)
def test_web_params(self):
"""The WEB should not define any required parameters without a default"""
parse_params({}, spec=WEB_PARAMS)
def test_basic(self):
a = {}
try:
parse_params(a, spec=NIF_PARAMS)
raise AssertionError()
except Error:
pass
a = {'input': 'hello'}
p = parse_params(a, spec=NIF_PARAMS)
assert 'input' in p
b = {'i': 'hello'}
p = parse_params(b, spec=NIF_PARAMS)
assert 'input' in p
def test_plugin(self):
query = {}
plug_params = {
'hello': {
'aliases': ['hello', 'hiya'],
'required': True
}
}
try:
parse_params(query, spec=plug_params)
raise AssertionError()
except Error:
pass
query['hello'] = 'world'
p = parse_params(query, spec=plug_params)
assert 'hello' in p
assert p['hello'] == 'world'
del query['hello']
query['hiya'] = 'dlrow'
p = parse_params(query, spec=plug_params)
assert 'hello' in p
assert 'hiya' in p
assert p['hello'] == 'dlrow'
def test_default(self):
spec = {
'hello': {
'required': True,
'default': 1
}
}
p = parse_params({}, spec=spec)
assert 'hello' in p
assert p['hello'] == 1

View File

@@ -19,7 +19,6 @@ def parse_resp(resp):
class BlueprintsTest(TestCase): class BlueprintsTest(TestCase):
def setUp(self): def setUp(self):
self.app = Flask("test_extensions") self.app = Flask("test_extensions")
self.app.debug = False
self.client = self.app.test_client() self.client = self.app.test_client()
self.senpy = Senpy() self.senpy = Senpy()
self.senpy.init_app(self.app) self.senpy.init_app(self.app)

View File

@@ -4,21 +4,18 @@ try:
except ImportError: except ImportError:
from mock import patch from mock import patch
import json
from senpy.client import Client from senpy.client import Client
from senpy.models import Results, Plugins, Error from senpy.models import Results, Error
from senpy.plugins import AnalysisPlugin, default_plugin_type
class Call(dict): class Call(dict):
def __init__(self, obj): def __init__(self, obj):
self.obj = obj.serialize() self.obj = obj.jsonld()
self.status_code = 200 self.status_code = 200
self.content = self.json() self.content = self.json()
def json(self): def json(self):
return json.loads(self.obj) return self.obj
class ModelsTest(TestCase): class ModelsTest(TestCase):
@@ -37,29 +34,10 @@ class ModelsTest(TestCase):
url=endpoint + '/', method='GET', params={'input': 'hello'}) url=endpoint + '/', method='GET', params={'input': 'hello'})
error = Call(Error('Nothing')) error = Call(Error('Nothing'))
with patch('requests.request', return_value=error) as patched: with patch('requests.request', return_value=error) as patched:
try: resp = client.analyse(input='hello', algorithm='NONEXISTENT')
client.analyse(input='hello', algorithm='NONEXISTENT') assert isinstance(resp, Error)
raise Exception('Exceptions should be raised. This is not golang')
except Error:
pass
patched.assert_called_with( patched.assert_called_with(
url=endpoint + '/', url=endpoint + '/',
method='GET', method='GET',
params={'input': 'hello', params={'input': 'hello',
'algorithm': 'NONEXISTENT'}) 'algorithm': 'NONEXISTENT'})
def test_plugins(self):
endpoint = 'http://dummy/'
client = Client(endpoint)
plugins = Plugins()
p1 = AnalysisPlugin({'name': 'AnalysisP1', 'version': 0, 'description': 'No'})
plugins.plugins = [p1, ]
success = Call(plugins)
with patch('requests.request', return_value=success) as patched:
response = client.plugins()
assert isinstance(response, dict)
assert len(response) == 1
assert "AnalysisP1" in response
patched.assert_called_with(
url=endpoint + '/plugins', method='GET',
params={'plugin_type': default_plugin_type})

View File

@@ -1,6 +1,5 @@
from __future__ import print_function from __future__ import print_function
import os import os
from copy import deepcopy
import logging import logging
try: try:
@@ -10,7 +9,7 @@ except ImportError:
from functools import partial from functools import partial
from senpy.extensions import Senpy from senpy.extensions import Senpy
from senpy.models import Error, Results, Entry, EmotionSet, Emotion, Plugin from senpy.models import Error
from flask import Flask from flask import Flask
from unittest import TestCase from unittest import TestCase
@@ -43,7 +42,6 @@ class ExtensionsTest(TestCase):
info = { info = {
'name': 'TestPip', 'name': 'TestPip',
'module': 'dummy', 'module': 'dummy',
'description': None,
'requirements': ['noop'], 'requirements': ['noop'],
'version': 0 'version': 0
} }
@@ -53,7 +51,6 @@ class ExtensionsTest(TestCase):
assert module assert module
import noop import noop
dir(noop) dir(noop)
self.senpy.install_deps()
def test_installing(self): def test_installing(self):
""" Enabling a plugin """ """ Enabling a plugin """
@@ -61,19 +58,6 @@ class ExtensionsTest(TestCase):
assert len(self.senpy.plugins) >= 3 assert len(self.senpy.plugins) >= 3
assert self.senpy.plugins["Sleep"].is_activated assert self.senpy.plugins["Sleep"].is_activated
def test_installing_nonexistent(self):
""" Fail if the dependencies cannot be met """
info = {
'name': 'TestPipFail',
'module': 'dummy',
'description': None,
'requirements': ['IAmMakingThisPackageNameUpToFail'],
'version': 0
}
root = os.path.join(self.dir, 'plugins', 'dummy_plugin')
with self.assertRaises(Error):
name, module = self.senpy._load_plugin_from_info(info, root=root)
def test_disabling(self): def test_disabling(self):
""" Disabling a plugin """ """ Disabling a plugin """
self.senpy.deactivate_all(sync=True) self.senpy.deactivate_all(sync=True)
@@ -109,49 +93,19 @@ class ExtensionsTest(TestCase):
assert r2.analysis[0] == "plugins/Dummy_0.1" assert r2.analysis[0] == "plugins/Dummy_0.1"
assert r1.entries[0].text == 'input' assert r1.entries[0].text == 'input'
def test_analyse_jsonld(self):
""" Using a plugin with JSON-LD input"""
js_input = '''{
"@id": "prueba",
"@type": "results",
"entries": [
{"@id": "entry1",
"text": "tupni",
"@type": "entry"
}
]
}'''
r1 = self.senpy.analyse(algorithm="Dummy",
input=js_input,
informat="json-ld",
output="tuptuo")
r2 = self.senpy.analyse(input="tupni", output="tuptuo")
assert r1.analysis[0] == "plugins/Dummy_0.1"
assert r2.analysis[0] == "plugins/Dummy_0.1"
assert r1.entries[0].text == 'input'
def test_analyse_error(self): def test_analyse_error(self):
mm = mock.MagicMock() mm = mock.MagicMock()
mm.id = 'magic_mock' mm.analyse_entry.side_effect = Error('error on analysis', status=900)
mm.analyse_entries.side_effect = Error('error on analysis', status=500)
self.senpy.plugins['MOCK'] = mm self.senpy.plugins['MOCK'] = mm
try: resp = self.senpy.analyse(input='nothing', algorithm='MOCK')
self.senpy.analyse(input='nothing', algorithm='MOCK') assert resp['message'] == 'error on analysis'
assert False assert resp['status'] == 900
except Error as ex:
assert ex['message'] == 'error on analysis'
assert ex['status'] == 500
mm.analyse.side_effect = Exception('generic exception on analysis') mm.analyse.side_effect = Exception('generic exception on analysis')
mm.analyse_entries.side_effect = Exception( mm.analyse_entry.side_effect = Exception(
'generic exception on analysis') 'generic exception on analysis')
resp = self.senpy.analyse(input='nothing', algorithm='MOCK')
try: assert resp['message'] == 'generic exception on analysis'
self.senpy.analyse(input='nothing', algorithm='MOCK') assert resp['status'] == 500
assert False
except Error as ex:
assert ex['message'] == 'generic exception on analysis'
assert ex['status'] == 500
def test_filtering(self): def test_filtering(self):
""" Filtering plugins """ """ Filtering plugins """
@@ -165,55 +119,3 @@ class ExtensionsTest(TestCase):
def test_load_default_plugins(self): def test_load_default_plugins(self):
senpy = Senpy(plugin_folder=self.dir, default_plugins=True) senpy = Senpy(plugin_folder=self.dir, default_plugins=True)
assert len(senpy.plugins) > 1 assert len(senpy.plugins) > 1
def test_convert_emotions(self):
self.senpy.activate_all(sync=True)
plugin = Plugin({
'id': 'imaginary',
'onyx:usesEmotionModel': 'emoml:fsre-dimensions'
})
eSet1 = EmotionSet()
eSet1.prov__wasGeneratedBy = plugin['id']
eSet1['onyx:hasEmotion'].append(Emotion({
'emoml:arousal': 1,
'emoml:potency': 0,
'emoml:valence': 0
}))
response = Results({
'entries': [Entry({
'text': 'much ado about nothing',
'emotions': [eSet1]
})]
})
params = {'emotionModel': 'emoml:big6',
'conversion': 'full'}
r1 = deepcopy(response)
self.senpy.convert_emotions(r1,
[plugin, ],
params)
assert len(r1.entries[0].emotions) == 2
params['conversion'] = 'nested'
r2 = deepcopy(response)
self.senpy.convert_emotions(r2,
[plugin, ],
params)
assert len(r2.entries[0].emotions) == 1
assert r2.entries[0].emotions[0]['prov:wasDerivedFrom'] == eSet1
params['conversion'] = 'filtered'
r3 = deepcopy(response)
self.senpy.convert_emotions(r3,
[plugin, ],
params)
assert len(r3.entries[0].emotions) == 1
r3.jsonld()
# def test_async_plugin(self):
# """ We should accept multiprocessing plugins with async=False"""
# thread1 = self.senpy.activate_plugin("Async", sync=False)
# thread1.join(timeout=1)
# assert len(self.senpy.plugins['Async'].value) == 4
# resp = self.senpy.analyse(input='nothing', algorithm='Async')
# assert len(resp.entries[0].async_values) == 2
# self.senpy.activate_plugin("Async", sync=True)

View File

@@ -11,12 +11,8 @@ from senpy.models import (Emotion,
Entry, Entry,
Error, Error,
Results, Results,
Sentiment, Sentiment)
Plugins, from senpy.plugins import SenpyPlugin
Plugin,
from_string,
from_dict)
from senpy import plugins
from pprint import pprint from pprint import pprint
@@ -57,8 +53,8 @@ class ModelsTest(TestCase):
assert (received["entries"][0]["nif:isString"] != "Not testing") assert (received["entries"][0]["nif:isString"] != "Not testing")
def test_id(self): def test_id(self):
""" Adding the id after creation should overwrite the automatic ID ''' Adding the id after creation should overwrite the automatic ID
""" '''
r = Entry() r = Entry()
j = r.jsonld() j = r.jsonld()
assert '@id' in j assert '@id' in j
@@ -98,32 +94,20 @@ class ModelsTest(TestCase):
r.validate() r.validate()
def test_plugins(self): def test_plugins(self):
self.assertRaises(Error, plugins.Plugin) self.assertRaises(Error, SenpyPlugin)
p = plugins.Plugin({"name": "dummy", p = SenpyPlugin({"name": "dummy", "version": 0})
"version": 0,
"extra_params": {
"none": {
"options": ["es", ],
"required": False,
"default": "0"
}
}})
c = p.jsonld() c = p.jsonld()
assert '@type' in c assert "info" not in c
assert c['@type'] == 'plugin' assert "repo" not in c
assert 'info' not in c assert "extra_params" in c
assert 'repo' not in c logging.debug("Framed:")
assert 'extra_params' in c
logging.debug('Framed:')
logging.debug(c) logging.debug(c)
p.validate() p.validate()
assert 'es' in c['extra_params']['none']['options']
assert isinstance(c['extra_params']['none']['options'], list)
def test_str(self): def test_str(self):
"""The string representation shouldn't include private variables""" """The string representation shouldn't include private variables"""
r = Results() r = Results()
p = plugins.Plugin({"name": "STR test", "version": 0}) p = SenpyPlugin({"name": "STR test", "version": 0})
p._testing = 0 p._testing = 0
s = str(p) s = str(p)
assert "_testing" not in s assert "_testing" not in s
@@ -160,39 +144,6 @@ class ModelsTest(TestCase):
g = rdflib.Graph().parse(data=t, format='turtle') g = rdflib.Graph().parse(data=t, format='turtle')
assert len(g) == len(triples) assert len(g) == len(triples)
def test_plugin_list(self): def test_convert_emotions(self):
"""The plugin list should be of type \"plugins\"""" """It should be possible to convert between different emotion models"""
plugs = Plugins() pass
c = plugs.jsonld()
assert '@type' in c
assert c['@type'] == 'plugins'
def test_single_plugin(self):
"""A response with a single plugin should still return a list"""
plugs = Plugins()
p = Plugin({'id': str(1),
'version': 0,
'description': 'dummy'})
plugs.plugins.append(p)
assert isinstance(plugs.plugins, list)
js = plugs.jsonld()
assert isinstance(js['plugins'], list)
def test_from_string(self):
results = {
'@type': 'results',
'@id': 'prueba',
'entries': [{
'@id': 'entry1',
'@type': 'entry',
'text': 'TEST'
}]
}
recovered = from_dict(results)
assert isinstance(recovered, Results)
assert isinstance(recovered.entries[0], Entry)
string = json.dumps(results)
recovered = from_string(string)
assert isinstance(recovered, Results)
assert isinstance(recovered.entries[0], Entry)

View File

@@ -83,39 +83,7 @@ class PluginsTest(TestCase):
res2 = a.analyse(input=1) res2 = a.analyse(input=1)
assert res2.entries[0].nif__isString == 2 assert res2.entries[0].nif__isString == 2
def test_corrupt_shelf(self): def test_two(self):
''' Reusing the values of a previous shelf '''
emptyfile = os.path.join(self.shelf_dir, "emptyfile")
invalidfile = os.path.join(self.shelf_dir, "invalid_file")
with open(emptyfile, 'w+b'), open(invalidfile, 'w+b') as inf:
inf.write(b'ohno')
files = {emptyfile: ['empty file', (EOFError, IndexError)],
invalidfile: ['invalid file', (pickle.UnpicklingError, IndexError)]}
for fn in files:
with open(fn, 'rb') as f:
msg, error = files[fn]
a = ShelfDummyPlugin(info={
'name': 'shelve',
'version': 'test',
'shelf_file': f.name
})
assert os.path.isfile(a.shelf_file)
print('Shelf file: %s' % a.shelf_file)
with self.assertRaises(error):
a.sh['a'] = 'fromA'
a.save()
del a._sh
assert os.path.isfile(a.shelf_file)
a.force_shelf = True
a.sh['a'] = 'fromA'
a.save()
b = pickle.load(f)
assert b['a'] == 'fromA'
def test_reuse_shelf(self):
''' Reusing the values of a previous shelf ''' ''' Reusing the values of a previous shelf '''
a = ShelfDummyPlugin(info={ a = ShelfDummyPlugin(info={
'name': 'shelve', 'name': 'shelve',

2
version.sh Executable file
View File

@@ -0,0 +1,2 @@
#!/bin/sh
git describe --long --tags --dirty