Files
HighCostDrugsDemo/config/snowflake.toml
T
2026-02-04 13:04:29 +00:00

129 lines
4.2 KiB
TOML

# Snowflake Configuration for NHS Patient Pathway Analysis
#
# This file contains connection settings for the Snowflake data warehouse.
# IMPORTANT: This file should NOT be committed to version control if it contains
# sensitive information. However, with externalbrowser auth, no passwords are stored.
#
# For NHS SSO authentication, the 'externalbrowser' authenticator opens a browser
# window for authentication via NHS identity management.
[connection]
# Snowflake account identifier (e.g., "xy12345.uk-south.azure")
# Ask your Snowflake administrator for the correct account name
account = ""
# Default warehouse to use for queries
# Common options: ANALYST_WH, COMPUTE_WH
warehouse = "ANALYST_WH"
# Default database for queries
# DATA_HUB is the primary analyst-curated data warehouse
database = "DATA_HUB"
# Default schema (optional, can be overridden per query)
schema = "DWH"
# Authentication method
# "externalbrowser" opens browser for NHS SSO (required for NHS environments)
# Other options: "snowflake" (username/password), "oauth", "okta"
authenticator = "externalbrowser"
# User principal (email address for externalbrowser auth)
# Leave empty to use current Windows user or prompt
user = ""
# Role to use (optional, uses default role if empty)
role = ""
[timeouts]
# Connection timeout in seconds
connection_timeout = 30
# Query execution timeout in seconds (for long-running queries)
# Set to 0 for no timeout
query_timeout = 300
# Login timeout in seconds (for SSO browser auth)
login_timeout = 120
[cache]
# Enable result caching
enabled = true
# Cache directory (relative to project root or absolute path)
# Defaults to data/cache/ if not specified
directory = "data/cache"
# Time-to-live for cached results in seconds
# 24 hours for historical data (86400 seconds)
ttl_seconds = 86400
# TTL for data that includes today's date (shorter)
ttl_current_data_seconds = 3600
# Maximum cache size in MB (oldest entries removed when exceeded)
max_size_mb = 500
[databases]
# Quick reference for database purposes (read-only documentation)
# DATA_HUB = "Analyst-curated data warehouse - primary source for most queries"
# PRIMARY_CARE = "Raw extracts from EMIS and TPP clinical systems"
# NATIONAL = "NHS England national datasets (SUS, ECDS, MHSDS, etc.)"
# FACTS_AND_DIMENSIONS_ALL_DATA = "External reference data (BNF, SNOMED, QOF clusters)"
# REPORTING_DATASETS_ICB = "Reporting outputs and analyst workspaces"
# Tables commonly used for high-cost drug analysis
[tables.activity]
# Main activity data source (high-cost drug interventions)
# Acute__Conmon__PatientLevelDrugs contains patient-level high-cost drug data
database = "DATA_HUB"
schema = "CDM"
table = "Acute__Conmon__PatientLevelDrugs"
key_columns = [
"PseudoNHSNoLinked", # Pseudonymised NHS number for patient linking
"ProviderCode", # NHS provider code (e.g., RM1, RGP)
"LocalPatientID", # Local patient identifier within provider
"InterventionDate", # Date of drug intervention
"DrugName", # Drug name (raw, needs standardization)
"DrugSNOMEDCode", # SNOMED code for drug
"PriceActual", # Actual cost of intervention
"TreatmentFunctionCode", # NHS treatment function code
"TreatmentFunctionDesc", # Treatment function description
"AdditionalDetail1", # Additional details (used for directory identification)
]
[tables.patient]
# Patient demographics
database = "DATA_HUB"
schema = "DWH"
view = "DimPerson"
key_columns = ["PatientPseudonym", "PersonKey", "CurrentGeneralPractice"]
[tables.medication]
# Medication reference data
database = "DATA_HUB"
schema = "DWH"
view = "DimMedicineAndDevice"
key_columns = ["ProductSnomedCode", "TherapeuticMoietySnomedCode", "ProductDescription"]
[tables.organization]
# NHS organizations and GP practices
database = "DATA_HUB"
schema = "DWH"
view = "DimOrganisationAndSite"
key_columns = ["SiteCode", "OrganisationName"]
[query]
# Default query behaviors
# Always double-quote identifiers for case-sensitivity
quote_identifiers = true
# Default row limit for test queries
test_limit = 20
# Maximum rows to fetch in a single query (prevents runaway queries)
max_rows = 100000
# Chunk size for large result sets
chunk_size = 10000