Feature View

...
entities:
  - name: user
    id_types:
      - main_id
      - user_id
    feature_views:
      using_ids:
        - id: email # primary key for features_by_email view
          name: features_by_email
        - id: salesforce_id # primary key for salesforce_id_stitched_features view
          name: salesforce_id_stitched_features
      features:
        - from: models/feature_table_1 # include everything from `feature_table_1` (default behaviour if `include` is not specified)
          include: ["*"]
        - from: models/feature_table_2 # exclude 'middle_name' feature from `feature_table_2`
          exclude: ["middle_name"] 

# Project name
name: sample_id_stitching
# Project's yaml schema version
schema_version: 72
# Warehouse connection
connection: test
# Folder containing models
model_folders:
  - models
# Entities in this project and their ids.
entities:
  - name: user
    id_types:
      - main_id # You need to add `main_id` to the list only if you have defined `main_id_type: main_id` in the id stitcher spec.
      - user_id # one of the identifier from your data source.
      - email
# lib packages can be imported in project signifying that this project inherits its properties from there
packages:
  - name: corelib
    url: "https://github.com/rudderlabs/profiles-corelib/tag/schema_{{best_schema_version}}"
    # if required then you can extend the package definition such as for ID types.

inputs:
- name: rsIdentifies
  contract: # constraints that a model adheres to
    is_optional: false
    is_event_stream: true
    with_entity_ids:
      - user
    with_columns:
      - name: timestamp
      - name: user_id
      - name: anonymous_id
      - name: email
  app_defaults:
    table: rudder_events_production.web.identifies # one of the WH table RudderStack generates when processing identify or track events.
    occurred_at_col: timestamp
    ids:
      - select: "user_id" # kind of identity sql to pick this column from above table.
        type: user_id
        entity: user # as defined in project file
        to_default_stitcher: true
      - select: "anonymous_id"
        type: anonymous_id
        entity: user
        to_default_stitcher: true
      - select: "lower(email)" # can use sql.
        type: email
        entity: user
        to_default_stitcher: true
- name: rsTracks
  contract:
    is_optional: false
    is_event_stream: true
    with_entity_ids:
      - user
    with_columns:
      - name: timestamp
      - name: user_id
      - name: anonymous_id
  app_defaults:
    table: rudder_events_production.web.tracks # another table in WH maintained by RudderStack processing track events.
    occurred_at_col: timestamp
    ids:
      - select: "user_id"
        type: user_id
        entity: user
        to_default_stitcher: true
      - select: "anonymous_id"
        type: anonymous_id
        entity: user
        to_default_stitcher: true

var_groups:
  - name: first_group
    entity_key: user
    vars:
      - entity_var:
          name: first_seen
          select: min(timestamp::date)
          from: inputs/rsTracks
          where: properties_country is not null and properties_country != ''
      - entity_var:
          name: last_seen
          select: max(timestamp::date)
          from: inputs/rsTracks
          is_feature: false # Specifies the entity_var is not a feature
      - entity_var:
          name: user_lifespan
          select: '{{user.Var("last_seen")}} - {{user.Var("first_seen")}}'
          description: Life Time Value of a customer
      - entity_var:
          name: days_active
          select: count(distinct timestamp::date)
          from: inputs/rsTracks
          description: No. of days a customer was active
      - entity_var:
          name: campaign_source
          default: "'organic'"
      - entity_var:
          name: user_rank
          default: -1
      - entity_var:
          name: campaign_source_first_touch
          select: first_value(context_campaign_source)
          window:
              order_by:
                  - timestamp asc
              partition_by:
                  - main_id
          from: inputs/rsIdentifies
          where: context_campaign_source is not null and context_campaign_source != ''
      - input_var:
          name: num_c_rank_num_b_partition
          select: rank()
          from: inputs/tbl_c
          default: -1
          window:
            partition_by:
              - '{{tbl_c}}.num_b'
            order_by:
              - '{{tbl_c}}.num_c asc'
          where: '{{tbl_c}}.num_b >= 10'
      - entity_var:
          name: min_num_c_rank_num_b_partition
          select: min(num_c_rank_num_b_partition)
          from: inputs/tbl_c