flowfile_version: 0.12.8
flowfile_id: 1
flowfile_name: Language profitability
flowfile_settings:
  description: null
  execution_mode: Performance
  execution_location: local
  auto_save: false
  show_detailed_progress: true
  max_parallel_workers: 4
  source_registration_id: null
  parameters: []
nodes:
- id: 1
  type: database_reader
  is_start_node: true
  description: Read from public.movies
  node_reference: null
  x_position: 0
  y_position: 100
  group_id: null
  left_input_id: null
  right_input_id: null
  input_ids: null
  outputs: [3]
  output_handles: [output-0]
  input_connections: null
  setting_input:
    cache_results: false
    output_field_config: null
    database_settings:
      connection_mode: reference
      database_connection: null
      database_connection_name: analytics-postgres
      schema_name: public
      table_name: movies
      query: null
      query_mode: table
    fields:
    - name: budget
      data_type: Int64
    - name: genres
      data_type: String
    - name: homepage
      data_type: String
    - name: id
      data_type: Int32
    - name: keywords
      data_type: String
    - name: original_language
      data_type: String
    - name: original_title
      data_type: String
    - name: overview
      data_type: String
    - name: popularity
      data_type: Float64
    - name: production_companies
      data_type: String
    - name: production_countries
      data_type: String
    - name: release_date
      data_type: Datetime(time_unit='us', time_zone=None)
    - name: revenue
      data_type: Int64
    - name: runtime
      data_type: Float64
    - name: spoken_languages
      data_type: String
    - name: status
      data_type: String
    - name: tagline
      data_type: String
    - name: title
      data_type: String
    - name: vote_average
      data_type: Float64
    - name: vote_count
      data_type: Int32
- id: 3
  type: formula
  is_start_node: false
  description: profit = ([revenue] - [budget])
  node_reference: null
  x_position: 200
  y_position: 100
  group_id: null
  left_input_id: null
  right_input_id: null
  input_ids: [1]
  outputs: [4]
  output_handles: [output-0]
  input_connections: null
  setting_input:
    cache_results: false
    output_field_config: null
    function:
      field:
        name: profit
        data_type: Auto
      function: ([revenue] - [budget])
- id: 4
  type: polars_code
  is_start_node: false
  description: input_df.filter((((pl.col('budget') > 0) & (pl.col('revenue') > 0))))
  node_reference: null
  x_position: 400
  y_position: 100
  group_id: null
  left_input_id: null
  right_input_id: null
  input_ids: [3]
  outputs: [5]
  output_handles: [output-0]
  input_connections: null
  setting_input:
    cache_results: false
    output_field_config: null
    polars_code_input:
      polars_code: input_df.filter((((pl.col('budget') > 0) & (pl.col('revenue') >
        0))))
- id: 5
  type: group_by
  is_start_node: false
  description: Aggregate after grouping by "original_language"
  node_reference: null
  x_position: 600
  y_position: 100
  group_id: null
  left_input_id: null
  right_input_id: null
  input_ids: [4]
  outputs: [6]
  output_handles: [output-0]
  input_connections: null
  setting_input:
    cache_results: false
    output_field_config: null
    groupby_input:
      agg_cols:
      - old_name: original_language
        agg: groupby
        new_name: original_language
        output_type: null
      - old_name: title
        agg: count
        new_name: films
        output_type: Int64
      - old_name: vote_average
        agg: mean
        new_name: avg_score
        output_type: Float64
      - old_name: profit
        agg: sum
        new_name: total_profit
        output_type: null
      - old_name: profit
        agg: median
        new_name: median_profit
        output_type: Float64
- id: 6
  type: polars_code
  is_start_node: false
  description: input_df.filter(((pl.col('films') >= 10)))
  node_reference: null
  x_position: 800
  y_position: 100
  group_id: null
  left_input_id: null
  right_input_id: null
  input_ids: [5]
  outputs: [7]
  output_handles: [output-0]
  input_connections: null
  setting_input:
    cache_results: false
    output_field_config: null
    polars_code_input:
      polars_code: input_df.filter(((pl.col('films') >= 10)))
- id: 7
  type: sort
  is_start_node: false
  description: Sort by total_profit
  node_reference: null
  x_position: 1000
  y_position: 100
  group_id: null
  left_input_id: null
  right_input_id: null
  input_ids: [6]
  outputs: [8]
  output_handles: [output-0]
  input_connections: null
  setting_input:
    cache_results: false
    output_field_config: null
    sort_input:
    - column: total_profit
      how: desc
- id: 8
  type: database_writer
  is_start_node: false
  description: Write to public.language_profitability (replace)
  node_reference: null
  x_position: 1200
  y_position: 100
  group_id: null
  left_input_id: null
  right_input_id: null
  input_ids: [7]
  outputs: []
  output_handles: []
  input_connections: null
  setting_input:
    cache_results: false
    output_field_config: null
    database_write_settings:
      connection_mode: reference
      database_connection: null
      database_connection_name: analytics-postgres
      table_name: language_profitability
      schema_name: public
      if_exists: replace
groups: []