Unverified Commit ece7ed36 authored by Raghupathi's avatar Raghupathi Committed by GitHub
Browse files

Update ingestion specs (#3677)

Showing with 3 additions and 3 deletions
+3 -3
......@@ -53,12 +53,12 @@ ml_analytics_project_output_dir: "{{ WORKDIR }}/source/projects/output"
ml_analytics_observation_status_output_dir: "{{ WORKDIR }}/source/observations/status/output"
ml_analytics_api_authorization_key: "{{ml_api_auth_token | default('sunbird_api_auth_token')}}"
ml_analytics_api_access_token: "{{ml_api_access_token | default('ml_core_internal_access_token')}}"
ml_analytics_druid_observation_status_injestion_spec : '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type": "azure","uris": ["azure://telemetry-data-store/observation/status/sl_observation_status.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"sl-observation-status","granularitySpec":{"type":"uniform","queryGranularity":"DAY","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"updatedAt","format":"auto"},"dimensionsSpec":{"dimensions":["status","entity_externalId","entity_id","entity_type","solution_id","solution_externalId","submission_id","entity_name","solution_name","role_title","school_name","school_code","school_externalId","state_name","state_code","state_externalId","district_name","district_code","district_externalId","block_name","block_code","block_externalId","cluster_name","cluster_code","cluster_externalId","completedDate","channel","parent_channel","program_id","program_externalId","program_name","app_name","user_id","private_program","solution_type","organisation_name","ecm_marked_na","board_name","updatedAt","organisation_id","user_type","observed_school_name","observed_school_id","observed_school_code","observed_state_name","observed_state_id","observed_state_code","observed_district_name","observed_district_id","observed_district_code","observed_block_name","observed_block_id","observed_block_code","observed_cluster_name","observed_cluster_id","observed_cluster_code"]},"metricsSpec":[]}}}'
ml_analytics_druid_observation_status_injestion_spec : '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type": "azure","uris": ["azure://telemetry-data-store/observation/status/sl_observation_status.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"sl-observation-status","granularitySpec":{"type":"uniform","queryGranularity":"DAY","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"updatedAt","format":"auto"},"dimensionsSpec":{"dimensions":["status","entity_externalId","entity_id","entity_type","solution_id","solution_externalId","submission_id","entity_name","solution_name","role_title","school_name","school_code","school_externalId","state_name","state_code","state_externalId","district_name","district_code","district_externalId","block_name","block_code","block_externalId","cluster_name","cluster_code","cluster_externalId","completedDate","channel","parent_channel","program_id","program_externalId","program_name","app_name","user_id","private_program","solution_type","organisation_name","ecm_marked_na","board_name","updatedAt","organisation_id","user_type","observed_school_name","observed_school_id","observed_school_code","observed_state_name","observed_state_id","observed_state_code","observed_district_name","observed_district_id","observed_district_code","observed_block_name","observed_block_id","observed_block_code","observed_cluster_name","observed_cluster_id","observed_cluster_code","isRubricDriven","criteriaLevelReport"]},"metricsSpec":[]}}}'
ml_analytics_druid_project_injestion_spec : '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type": "azure","uris": ["azure://telemetry-data-store/projects/sl_projects.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"sl-project","granularitySpec":{"type":"uniform","queryGranularity":"DAY","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"project_updated_date","format":"auto"},"dimensionsSpec":{"dimensions":[]},"metricsSpec":[]}}}'
ml_analytics_druid_distinctCnt_obs_injestion_spec: '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type":"azure","uris":["azure://telemetry-data-store/observation/distinctCount/ml_observation_distinctCount_status.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"ml-obs-status","granularitySpec":{"type":"uniform","queryGranularity":"none","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"time_stamp","format":"auto"},"dimensionsSpec":{"dimensions":[{"type":"string","name":"program_name"},{"type":"string","name":"program_id"},{"type":"string","name":"solution_name"},{"type":"string","name":"solution_id"},{"type":"string","name":"status"},{"type":"string","name":"state_name"},{"type":"string","name":"state_externalId"},{"type":"string","name":"district_name"},{"type":"string","name":"district_externalId"},{"type":"string","name":"block_name"},{"type":"string","name":"block_externalId"},{"type":"string","name":"organisation_name"},{"type":"string","name":"organisation_id"},{"type":"string","name":"parent_channel"},{"type":"string","name":"solution_type"},{"type":"string","name":"private_program"},{"type":"long","name":"unique_submissions"},{"type":"long","name":"unique_entities"},{"type":"long","name":"unique_users"},{"type":"long","name":"unique_solution"},{"type":"string","name":"time_stamp"}]},"metricsSpec":[]}}}'
ml_analytics_druid_distinctCnt_obs_domain_injestion_spec: '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type":"azure","uris":["azure://telemetry-data-store/observation/distinctCount_domain/ml_observation_distinctCount_domain.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"ml-obs-domain","granularitySpec":{"type":"uniform","queryGranularity":"none","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"time_stamp","format":"auto"},"dimensionsSpec":{"dimensions":[{"type":"string","name":"program_name"},{"type":"string","name":"program_id"},{"type":"string","name":"solution_name"},{"type":"string","name":"solution_id"},{"type":"string","name":"state_name"},{"type":"string","name":"state_externalId"},{"type":"string","name":"district_name"},{"type":"string","name":"district_externalId"},{"type":"string","name":"block_name"},{"type":"string","name":"block_externalId"},{"type":"string","name":"organisation_name"},{"type":"string","name":"organisation_id"},{"type":"string","name":"parent_channel"},{"type":"string","name":"solution_type"},{"type":"string","name":"private_program"},{"type":"string","name":"domain_name"},{"type":"string","name":"domain_externalId"},{"type":"string","name":"domain_level"},{"type":"long","name":"unique_submissions"},{"type":"long","name":"unique_entities"},{"type":"long","name":"unique_users"},{"type":"long","name":"unique_solution"},{"type":"string","name":"time_stamp"}]},"metricsSpec":[]}}}'
ml_analytics_druid_distinctCnt_obs_domain_criteria_injestion_spec: '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type":"azure","uris":["azure://telemetry-data-store/observation/distinctCount_domain_criteria/ml_observation_distinctCount_domain_criteria.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"ml-obs-domain-criteria","granularitySpec":{"type":"uniform","queryGranularity":"none","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"time_stamp","format":"auto"},"dimensionsSpec":{"dimensions":[{"type":"string","name":"program_name"},{"type":"string","name":"program_id"},{"type":"string","name":"solution_name"},{"type":"string","name":"solution_id"},{"type":"string","name":"state_name"},{"type":"string","name":"state_externalId"},{"type":"string","name":"district_name"},{"type":"string","name":"district_externalId"},{"type":"string","name":"block_name"},{"type":"string","name":"block_externalId"},{"type":"string","name":"organisation_name"},{"type":"string","name":"organisation_id"},{"type":"string","name":"parent_channel"},{"type":"string","name":"solution_type"},{"type":"string","name":"private_program"},{"type":"string","name":"domain_name"},{"type":"string","name":"domain_externalId"},{"type":"string","name":"domain_level"},{"type":"string","name":"criteria_name"},{"type":"string","name":"criteria_score"},{"type":"string","name":"criteria_id"},{"type":"long","name":"unique_submissions"},{"type":"long","name":"unique_entities"},{"type":"long","name":"unique_users"},{"type":"long","name":"unique_solution"},{"type":"string","name":"time_stamp"}]},"metricsSpec":[]}}}'
ml_analytics_druid_distinctCnt_projects_status_injestion_spec: '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type":"azure","uris":["azure://telemetry-data-store/projects/distinctCount/ml_projects_distinctCount.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"ml-project-status","granularitySpec":{"type":"uniform","queryGranularity":"none","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"time_stamp","format":"auto"},"dimensionsSpec":{"dimensions":[{"type":"string","name":"program_name"},{"type":"string","name":"program_id"},{"type":"string","name":"project_title"},{"type":"string","name":"solution_id"},{"type":"string","name":"status_of_project"},{"type":"string","name":"state_name"},{"type":"string","name":"state_externalId"},{"type":"string","name":"district_name"},{"type":"string","name":"district_externalId"},{"type":"string","name":"block_name"},{"type":"string","name":"block_externalId"},{"type":"string","name":"organisation_name"},{"type":"string","name":"organisation_id"},{"type":"string","name":"private_program"},{"type":"string","name":"project_created_type"},{"type":"string","name":"parent_channel"},{"type":"long","name":"unique_projects"},{"type":"long","name":"unique_users"},{"type":"long","name":"unique_solution"},{"type":"long","name":"no_of_imp_with_evidence"},{"type":"string","name":"time_stamp"}]},"metricsSpec":[]}}}'
ml_analytics_druid_distinctCnt_projects_status_injestion_spec: '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type":"azure","uris":["azure://telemetry-data-store/projects/distinctCount/ml_projects_distinctCount.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"ml-project-status","granularitySpec":{"type":"uniform","queryGranularity":"none","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"time_stamp","format":"auto"},"dimensionsSpec":{"dimensions":[{"type":"string","name":"program_name"},{"type":"string","name":"program_id"},{"type":"string","name":"project_title"},{"type":"string","name":"solution_id"},{"type":"string","name":"status_of_project"},{"type":"string","name":"state_name"},{"type":"string","name":"state_externalId"},{"type":"string","name":"district_name"},{"type":"string","name":"district_externalId"},{"type":"string","name":"block_name"},{"type":"string","name":"block_externalId"},{"type":"string","name":"organisation_name"},{"type":"string","name":"organisation_id"},{"type":"string","name":"private_program"},{"type":"string","name":"project_created_type"},{"type":"string","name":"parent_channel"},{"type":"long","name":"unique_projects"},{"type":"long","name":"unique_users"},{"type":"long","name":"unique_solution"},{"type":"long","name":"no_of_imp_with_evidence"},{"type":"string","name":"time_stamp"},{"type":"long","name":"no_of_certificate_issued"}]},"metricsSpec":[]}}}'
ml_analytics_obs_distinctCnt_cloud_blob_path: "observation/distinctCount/"
ml_analytics_obs_distinctCnt_domain_cloud_blob_path: "observation/distinctCount_domain/"
ml_analytics_obs_distinctCnt_domain_criteria_cloud_blob_path: "observation/distinctCount_domain_criteria/"
......@@ -77,7 +77,7 @@ ml_analytics_observation_status_rollup_output_dir: "/opt/sparkjobs/source/observ
ml_analytics_druid_project_rollup_injestion_spec: '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type":"azure","uris":["azure://telemetry-data-store/projects/rollup/projects_rollup.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"ml-project-status-rollup","granularitySpec":{"type":"uniform","queryGranularity":"DAY","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"project_updated_date","format":"iso"},"dimensionsSpec":{"dimensions":["project_title","project_goal","area_of_improvement","status_of_project","tasks_name","tasks_status","designation","task_evidence_status","project_id","task_id","project_created_type","parent_channel","program_id","program_name","project_updated_date","createdBy","program_externalId","private_program","task_deleted_flag","project_terms_and_condition","state_externalId","block_externalId","district_externalId","cluster_externalId","school_externalId","state_name","block_name","district_name","cluster_name","school_name","board_name","organisation_name","solution_id","organisation_id",{"name":"status_code","type":"long"}]},"metricsSpec":[{"name":"count","type":"count"},{"name":"sum___v","type":"longSum","fieldName":"__v"},{"name":"sum_status_code","type":"longMax","fieldName":"status_code"},{"type":"HLLSketchBuild","name":"count_of_createBy","fieldName":"createdBy"},{"type":"HLLSketchBuild","name":"count_of_project_id","fieldName":"project_id"},{"type":"HLLSketchBuild","name":"count_of_solution_id","fieldName":"solution_id"},{"type":"HLLSketchBuild","name":"count_of_program_id","fieldName":"program_id"}]}}}'
ml_analytics_druid_observation_status_rollup_injestion_spec: '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type":"azure","uris":["azure://telemetry-data-store/observation/rollup/observation_status_rollup.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"ml-observation-status-rollup","granularitySpec":{"type":"uniform","queryGranularity":"DAY","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"updatedAt","format":"iso"},"dimensionsSpec":{"dimensions":["status","user_id","solution_id","submission_id","entity_name","completedDate","program_id","private_program","solution_type","updatedAt","role_title","solution_name","program_name","channel","parent_channel","block_name","district_name","school_name","cluster_name","state_name","organisation_name","board_name","district_externalId","state_externalId","block_externalId","cluster_externalId","school_externalId","organisation_id",{"type":"long","name":"status_code"}]},"metricsSpec":[{"type":"count","name":"count"},{"type":"longSum","name":"sum___v","fieldName":"__v","expression":null},{"type":"HLLSketchBuild","name":"count_distinct_solution","fieldName":"solution_id","lgK":12,"tgtHllType":"HLL_4","round":false},{"type":"HLLSketchBuild","name":"count_distinct_submission_id","fieldName":"submission_id","lgK":12,"tgtHllType":"HLL_4","round":false},{"type":"HLLSketchBuild","name":"count_distinct_user_id","fieldName":"user_id","lgK":12,"tgtHllType":"HLL_4","round":false}]}}}'
ml_analytics_druid_rollup_url: "{{groups['druid'][0]}}:8081"
ml_analytics_druid_distinctCnt_prglevel_projects_status_injestion_spec : '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type":"azure","uris":["azure://telemetry-data-store/projects/distinctCountPrglevel/ml_projects_distinctCount_prgmlevel.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"ml-project-programLevel-status","granularitySpec":{"type":"uniform","queryGranularity":"none","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"time_stamp","format":"auto"},"dimensionsSpec":{"dimensions":[{"type":"string","name":"program_name"},{"type":"string","name":"program_id"},{"type":"string","name":"status_of_project"},{"type":"string","name":"state_name"},{"type":"string","name":"state_externalId"},{"type":"string","name":"private_program"},{"type":"string","name":"project_created_type"},{"type":"string","name":"parent_channel"},{"type":"long","name":"unique_projects"},{"type":"long","name":"unique_users"},{"type":"long","name":"no_of_imp_with_evidence"},{"type":"string","name":"time_stamp"}]},"metricsSpec":[]}}}'
ml_analytics_druid_distinctCnt_prglevel_projects_status_injestion_spec : '{"type":"index","spec":{"ioConfig":{"type":"index","inputSource":{"type":"azure","uris":["azure://telemetry-data-store/projects/distinctCountPrglevel/ml_projects_distinctCount_prgmlevel.json"]},"inputFormat":{"type":"json"}},"tuningConfig":{"type":"index","partitionsSpec":{"type":"dynamic"}},"dataSchema":{"dataSource":"ml-project-programLevel-status","granularitySpec":{"type":"uniform","queryGranularity":"none","rollup":false,"segmentGranularity":"DAY"},"timestampSpec":{"column":"time_stamp","format":"auto"},"dimensionsSpec":{"dimensions":[{"type":"string","name":"program_name"},{"type":"string","name":"program_id"},{"type":"string","name":"status_of_project"},{"type":"string","name":"state_name"},{"type":"string","name":"state_externalId"},{"type":"string","name":"private_program"},{"type":"string","name":"project_created_type"},{"type":"string","name":"parent_channel"},{"type":"long","name":"unique_projects"},{"type":"long","name":"unique_users"},{"type":"long","name":"no_of_imp_with_evidence"},{"type":"string","name":"time_stamp"},{"type":"long","name":"no_of_certificate_issued"}]},"metricsSpec":[]}}}'
ml_analytics_projects_distinctCnt_prglevel_output_dir: "{{ WORKDIR }}/source/projects/distinctCountPrglevel/output"
ml_analytics_projects_distinctCnt_prglevel_cloud_blob_path: "projects/distinctCountPrglevel/"
ml_analytics_survey_status_output_dir : "{{ WORKDIR }}/source/survey/status/output"
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment