the-algorithm/src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/README
twitter-team ef4c5eb65e Twitter Recommendation Algorithm
Please note we have force-pushed a new initial commit in order to remove some publicly-available Twitter user information. Note that this process may be required in the future.
2023-03-31 17:36:31 -05:00

96 lines
4.5 KiB
Plaintext

To run iikf-tweets-ann-adhoc-job (adhoc):
bin/d6w create \
${GCP_PROJECT_NAME}/us-central1/iikf-tweets-ann-adhoc-job \
src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/iikf-tweets-ann-adhoc-job.d6w \
--jar dist/iikf-tweets-ann-adhoc-job.jar \
--bind=profile.project=${GCP_PROJECT_NAME} \
--bind=profile.user_name=your_ldap \
--bind=profile.date="2022-03-28" \
--bind=profile.machine="n2-highmem-4" \
--bind=profile.job_name="iikf-tweets-ann-adhoc-job" --ignore-existing
To run iikf-hl-8-el-50-tweets-ann-adhoc-job (adhoc):
bin/d6w create \
${GCP_PROJECT_NAME}/us-central1/iikf-hl-8-el-50-tweets-ann-adhoc-job \
src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/iikf-hl-8-el-50-tweets-ann-adhoc-job.d6w \
--jar dist/iikf-hl-8-el-50-tweets-ann-adhoc-job.jar \
--bind=profile.project=${GCP_PROJECT_NAME} \
--bind=profile.user_name=your_ldap \
--bind=profile.date="2022-03-28" \
--bind=profile.machine="n2-highmem-4" \
--bind=profile.job_name="iikf-hl-8-el-50-tweets-ann-adhoc-job" --ignore-existing
To run mts-consumer-embeddings-tweets-ann-adhoc-job (adhoc)
bin/d6w create \
${GCP_PROJECT_NAME}/us-central1/mts-consumer-embeddings-tweets-ann-adhoc-job \
src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/mts-consumer-embeddings-tweets-ann-adhoc-job.d6w \
--jar dist/mts-consumer-embeddings-tweets-ann-adhoc-job.jar \
--bind=profile.project=${GCP_PROJECT_NAME} \
--bind=profile.user_name=your_ldap \
--bind=profile.date="2022-03-28" \
--bind=profile.machine="n2-highmem-4" \
--bind=profile.job_name="mts-consumer-embeddings-tweets-ann-adhoc-job" --ignore-existing
To schedule iikf-tweets-ann-batch-job (batch)
bin/d6w schedule \
${GCP_PROJECT_NAME}/us-central1/iikf-tweets-ann-batch-job \
src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/iikf-tweets-ann-batch-job.d6w \
--bind=profile.project=${GCP_PROJECT_NAME} \
--bind=profile.user_name=cassowary \
--bind=profile.date="2022-03-26" \
--bind=profile.machine="n2-highmem-4" \
--bind=profile.job_name="iikf-tweets-ann-batch-job"
To schedule iikf-hl-0-el-15-tweets-ann-batch-job (batch)
bin/d6w schedule \
${GCP_PROJECT_NAME}/us-central1/iikf-hl-0-el-15-tweets-ann-batch-job \
src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/iikf-hl-0-el-15-tweets-ann-batch-job.d6w \
--bind=profile.project=${GCP_PROJECT_NAME} \
--bind=profile.user_name=cassowary \
--bind=profile.date="2022-03-26" \
--bind=profile.machine="n2-highmem-4" \
--bind=profile.job_name="iikf-hl-0-el-15-tweets-ann-batch-job"
To schedule iikf-hl-2-el-15-tweets-ann-batch-job (batch)
bin/d6w schedule \
${GCP_PROJECT_NAME}/us-central1/iikf-hl-2-el-15-tweets-ann-batch-job \
src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/iikf-hl-2-el-15-tweets-ann-batch-job.d6w \
--bind=profile.project=${GCP_PROJECT_NAME} \
--bind=profile.user_name=cassowary \
--bind=profile.date="2022-03-26" \
--bind=profile.machine="n2-highmem-4" \
--bind=profile.job_name="iikf-hl-2-el-15-tweets-ann-batch-job"
To schedule iikf-hl-2-el-50-tweets-ann-batch-job (batch)
bin/d6w schedule \
${GCP_PROJECT_NAME}/us-central1/iikf-hl-2-el-50-tweets-ann-batch-job \
src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/iikf-hl-2-el-50-tweets-ann-batch-job.d6w \
--bind=profile.project=${GCP_PROJECT_NAME} \
--bind=profile.user_name=cassowary \
--bind=profile.date="2022-03-26" \
--bind=profile.machine="n2-highmem-4" \
--bind=profile.job_name="iikf-hl-2-el-50-tweets-ann-batch-job"
To schedule iikf-hl-8-el-50-tweets-ann-batch-job (batch)
bin/d6w schedule \
${GCP_PROJECT_NAME}/us-central1/iikf-hl-8-el-50-tweets-ann-batch-job \
src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/iikf-hl-8-el-50-tweets-ann-batch-job.d6w \
--bind=profile.project=${GCP_PROJECT_NAME} \
--bind=profile.user_name=cassowary \
--bind=profile.date="2022-03-26" \
--bind=profile.machine="n2-highmem-4" \
--bind=profile.job_name="iikf-hl-8-el-50-tweets-ann-batch-job"
To schedule mts-consumer-embeddings-tweets-ann-batch-job(batch)
bin/d6w schedule \
${GCP_PROJECT_NAME}/us-central1/mts-consumer-embeddings-tweets-ann-batch-job \
src/scala/com/twitter/simclusters_v2/scio/bq_generation/tweets_ann/mts-consumer-embeddings-tweets-ann-batch-job.d6w \
--bind=profile.project=${GCP_PROJECT_NAME} \
--bind=profile.user_name=cassowary \
--bind=profile.date="2022-03-26" \
--bind=profile.machine="n2-highmem-4" \
--bind=profile.job_name="mts-consumer-embeddings-tweets-ann-batch-job"