# Human-authored augmentation for the BIRD `financial` dataset.
#
# The warehouse STRUCTURE (tables/columns/types/nullability) is extracted
# from Postgres into extracted_schema.json by `make recon`. This file only
# carries what humans add on top: table/column descriptions and relationships.
# (Metrics live in metrics.yaml.)
#
# Format:
#   tables.<name>:           one-line description.
#   columns.<table>.<col>:   one-line description. Sparse — only the ones
#                            worth describing. Undescribed columns just have
#                            no description in the recon.
#   relationships:           declared FKs (BIRD ships SQLite without them).

schema: financial

tables:
  account: One row per bank account. The pivot table — most facts hang off account_id.
  client: One row per bank customer.
  disp: Disposition — many-to-many link between client and account. Type tells you whether the client is the OWNER or just a USER of the account.
  district: Demographic and economic data for each Czech district. The A-columns are infamous — most analysis questions referencing demographics use these.
  loan: One row per loan granted to an account.
  card: One row per credit/debit card issued to a disposition.
  trans: Transaction history. Largest table by far (~1M rows). Every credit, debit, transfer.
  order: Standing payment orders (recurring debits). Note the table name collides with a SQL keyword and must be quoted.

columns:
  account.district_id: Geographic district the account belongs to (joins to district).
  account.frequency: Statement issuance frequency. "POPLATEK MESICNE" = monthly, "POPLATEK TYDNE" = weekly, "POPLATEK PO OBRATU" = on transaction.
  account.date: Date the account was opened (YYMMDD as integer).

  client.gender: '"M" or "F". Derived from birth_number.'
  client.birth_date: Date of birth, normalised. Original birth_number encoded gender by adding 50 to the month field for women.
  client.district_id: District the client lives in (joins to district).

  disp.client_id: Joins to client.
  disp.account_id: Joins to account.
  disp.type: '"OWNER" or "DISPONENT" (USER). Only owners can request loans / cards.'

  district.A2: District name.
  district.A3: Region (a grouping of districts).
  district.A4: Number of inhabitants.
  district.A5: Number of municipalities with population < 499.
  district.A6: Number of municipalities with population 500-1999.
  district.A7: Number of municipalities with population 2000-9999.
  district.A8: Number of municipalities with population > 10000.
  district.A9: Number of cities.
  district.A10: Ratio of urban inhabitants (percent).
  district.A11: Average salary (in CZK).
  district.A12: Unemployment rate in 1995 (percent). NULL means missing data.
  district.A13: Unemployment rate in 1996 (percent).
  district.A14: Number of entrepreneurs per 1000 inhabitants.
  district.A15: Number of crimes committed in 1995. NULL means missing data.
  district.A16: Number of crimes committed in 1996.

  loan.account_id: The account the loan was granted to.
  loan.date: Loan grant date (YYMMDD as integer).
  loan.amount: Total amount of the loan (CZK).
  loan.duration: Loan duration in months.
  loan.payments: Monthly payment (CZK).
  loan.status: Loan status code. "A" = contract finished, no problems. "B" = contract finished, loan not paid (DEFAULT). "C" = running contract, payments on time. "D" = running contract, client in debt (AT RISK).

  card.disp_id: The disposition (and via it, the account) the card belongs to.
  card.type: '"junior", "classic", or "gold".'
  card.issued: Date the card was issued.

  trans.account_id: The account the transaction belongs to.
  trans.date: Transaction date (YYMMDD as integer).
  trans.type: '"PRIJEM" (credit) or "VYDAJ" (debit).'
  trans.operation: Mode of operation, e.g. "VKLAD" (cash credit), "VYBER" (cash withdrawal), "PREVOD Z UCTU" (transfer from another bank).
  trans.amount: Amount (CZK).
  trans.balance: Account balance after the transaction.
  trans.k_symbol: Characterisation of the payment. "POJISTNE" = insurance, "SLUZBY" = household, "UROK" = interest credited, "SANKC. UROK" = penalty interest, "SIPO" = household payment, "DUCHOD" = old-age pension, "UVER" = loan payment.
  trans.bank: Counterparty bank code (only set for inter-bank transfers).
  trans.account: Counterparty account number (only set for inter-bank transfers).

  order.account_id: The originating account.
  order.bank_to: Recipient bank.
  order.account_to: Recipient account.
  order.amount: Order amount (CZK).
  order.k_symbol: Purpose, same vocabulary as trans.k_symbol.

relationships:
  - from: account.district_id
    to: district.district_id
  - from: client.district_id
    to: district.district_id
  - from: disp.client_id
    to: client.client_id
  - from: disp.account_id
    to: account.account_id
  - from: loan.account_id
    to: account.account_id
  - from: card.disp_id
    to: disp.disp_id
  - from: trans.account_id
    to: account.account_id
  - from: order.account_id
    to: account.account_id