Merge final release (#1)

* adding initial skeleton

* updating .gitignore

* updating dev dependencies

* adding report.py

* updating notes

* adding prospector.yaml

* updating beam to install gcp extras

* adding documentation

* adding data exploration report + code

* adding latest beam pipeline code

* adding latest beam pipeline code

* adding debug.py

* adding latesty beam pipeline code

* adding latest beam pipeline code

* adding latest beam pipeline code

* updating .gitignore

* updating folder structure for data input/output

* updating prospector.yaml

* adding latest beam pipeline code

* updating prospector.yaml

* migrate beam pipeline to main.py

* updating .gitignore

* updating .gitignore

* adding download script for data set

* adding initial docs

* moving inputs/outputs to use pathlib

* removing shard_name_template from output file

* adding pyenv 3.7.9

* removing requirements.txt for documentation

* updating README.md

* updating download data script for new location in GCS

* adding latest beam pipeline code for dataflow

* adding latest beam pipeline code for dataflow

* adding latest beam pipeline code for dataflow

* moving dataflow notes

* updating prospector.yaml

* adding latest beam pipeline code for dataflow

* updating beam pipeline to use GroupByKey

* updating download_data script with new bucket

* update prospector.yaml

* update dataflow documentation with new commands for vpc

* adding latest beam pipeline code for dataflow with group optimisation

* updating dataflow documentation

* adding latest beam pipeline code for dataflow with group optimisation

* updating download_data script with pp-2020 dataset

* adding temporary notes

* updating dataflow notes

* adding latest beam pipeline code

* updating dataflow notes

* adding latest beam pipeline code for dataflow

* adding debug print

* moving panda-profiling report into docs

* updating report.py

* adding entrypoint command

* adding initial docs

* adding commands.md to notes

* commenting out debug imports

* updating documentation

* updating latest beam pipeline with default inputs

* updating poetry

* adding requirements.txt

* updating documentation
This commit is contained in:
dtomlinson91
2021-09-28 00:31:09 +01:00
committed by GitHub
parent 8a22bfebe1
commit 80376a662e
34 changed files with 5667 additions and 1 deletions

53
requirements.txt Normal file
View File

@@ -0,0 +1,53 @@
apache-beam==2.32.0; python_version >= "3.6"
avro-python3==1.9.2.1; python_version >= "3.6"
cachetools==4.2.2; python_version >= "3.6" and python_version < "4.0" and (python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0")
certifi==2021.5.30; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6"
charset-normalizer==2.0.6; python_full_version >= "3.6.0" and python_version >= "3.6"
crcmod==1.7; python_version >= "3.6"
dill==0.3.1.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.1.0" and python_version >= "3.6"
docopt==0.6.2; python_version >= "3.6"
fastavro==1.4.5; python_version >= "3.6"
fasteners==0.16.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.5.0"
future==0.18.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.6"
google-api-core==1.31.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
google-apitools==0.5.31; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.5.0"
google-auth==1.35.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
google-cloud-bigquery==2.6.1; python_version >= "3.6"
google-cloud-bigtable==1.7.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.4.0"
google-cloud-core==1.7.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
google-cloud-datastore==1.15.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.4.0"
google-cloud-dlp==1.0.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.4.0"
google-cloud-language==1.3.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.4.0"
google-cloud-pubsub==1.7.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.5.0"
google-cloud-recommendations-ai==0.2.0; python_version >= "3.6"
google-cloud-spanner==1.19.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.4.0"
google-cloud-videointelligence==1.16.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.4.0"
google-cloud-vision==1.0.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.4.0"
google-crc32c==1.2.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
google-resumable-media==1.3.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
googleapis-common-protos==1.53.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
grpc-google-iam-v1==0.12.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.5.0"
grpcio-gcp==0.2.2; python_version >= "3.6"
grpcio==1.41.0; python_version >= "3.6" and (python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.4.0")
hdfs==2.6.0; python_version >= "3.6"
httplib2==0.19.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.5.0"
idna==3.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6"
numpy==1.20.3; python_version >= "3.7"
oauth2client==4.1.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.5.0"
orjson==3.6.3; python_version >= "3.7"
packaging==21.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
proto-plus==1.19.0; python_version >= "3.6"
protobuf==3.18.0; python_version >= "3.6" and (python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0")
pyarrow==4.0.1; python_version >= "3.6"
pyasn1-modules==0.2.8; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
pyasn1==0.4.8; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "4" and (python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0") or python_version >= "3.6" and python_full_version >= "3.6.0" and python_version < "4" and (python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0")
pydot==1.4.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
pymongo==3.12.0; python_version >= "3.6"
pyparsing==2.4.7; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6"
python-dateutil==2.8.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.6"
pytz==2021.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
requests==2.26.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6"
rsa==4.7.2; python_version >= "3.6" and python_version < "4" and (python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0")
six==1.16.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_version >= "3.6" and python_full_version >= "3.6.0"
typing-extensions==3.7.4.3; python_version >= "3.6"
urllib3==1.26.7; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version < "4" and python_version >= "3.6"