Bump spaCy version, bugfixes, codestyle

This commit is contained in:
Patrick Jentsch
2022-01-27 16:50:22 +01:00
parent 29ccfac4f6
commit a2e8e72e54
9 changed files with 699 additions and 509 deletions

View File

@ -9,7 +9,14 @@ ENV LANG=C.UTF-8
RUN apt-get update \
&& apt-get install --no-install-recommends --yes \
wget
procps \
python3.7 \
python3-pip \
wget \
&& python3 -m pip install \
chardet \
setuptools \
wheel
# Install the NLP pipeline and it's dependencies #
## Install pyFlow ##
@ -21,12 +28,12 @@ RUN wget --no-check-certificate --quiet \
&& apt-get install --no-install-recommends --yes \
python2.7 \
&& python2.7 setup.py build install \
&& cd .. \
&& cd - > /dev/null \
&& rm -r "pyflow-${PYFLOW_VERSION}" "pyflow-${PYFLOW_VERSION}.tar.gz"
## Install spaCy ##
ENV SPACY_VERSION=3.0.5
ENV SPACY_VERSION=3.2.1
RUN apt-get install --no-install-recommends --yes \
python3.7 \
python3-pip \
@ -38,23 +45,14 @@ RUN apt-get install --no-install-recommends --yes \
&& pip3 install "spacy==${SPACY_VERSION}"
# Only models that include the following components are compatibel:
# lemmatizer, ner, parser, senter, tagger,
ENV SPACY_MODELS="de_core_news_md,en_core_web_md,it_core_news_md,nl_core_news_md,pl_core_news_md,zh_core_web_md"
ENV SPACY_MODELS_VERSION=3.0.0
ENV SPACY_MODELS="de_core_news_md,en_core_web_md,it_core_news_md,pl_core_news_md,zh_core_web_md"
ENV SPACY_MODELS_VERSION=3.2.0
RUN for spacy_model in $(echo ${SPACY_MODELS} | tr "," "\n"); do python3 -m spacy download "${spacy_model}-${SPACY_MODELS_VERSION}" --direct; done
## Further dependencies ##
RUN apt-get install --no-install-recommends --yes \
procps \
zip
COPY packages .
RUN cd stand-off-data-py \
&& python3 setup.py build \
&& python3 setup.py install \
&& python3 -m pip install . \
&& cd -