Skip to content

Updates PBM notebook and data.databricks.DatabricksNational #317

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yiwen-h merged 1 commit into from
Mar 17, 2025
Merged

Updates PBM notebook and data.databricks.DatabricksNational #317

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions model/data/databricks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,7 +226,7 @@ def get_op(self) -> pd.DataFrame:
.withColumn("dataset", F.lit("NATIONAL"))
.withColumn("sitetret", F.lit("NATIONAL"))
.groupBy(
op.drop("index", "fyear", "attendances", "tele_attendances").columns
op.drop("index", "fyear", "attendances", "tele_attendances", "sushrg_trimmed", "imd_quintile").columns
)
.agg(
(F.sum("attendances") * self._sample_rate).alias("attendances"),
Expand Down Expand Up @@ -270,7 +270,7 @@ def get_birth_factors(self) -> pd.DataFrame:

return (
self._spark.read.parquet(
"/Volumes/su_data/nhp/population-projections/birth_data"
"/Volumes/nhp/population_projections/files/birth_data/"
)
.filter(F.col("area_code").rlike("^E0[6-9]"))
.withColumn("sex", F.lit(2))
Expand All @@ -290,8 +290,9 @@ def get_demographic_factors(self) -> pd.DataFrame:

return (
self._spark.read.parquet(
"/Volumes/su_data/nhp/population-projections/demographic_data"
"/Volumes/nhp/population_projections/files/demographic_data/projection=principal_proj"
)
.withColumn("projection", F.lit("principal_proj"))
.filter(F.col("area_code").rlike("^E0[6-9]"))
.groupBy("projection", "age", "sex")
.pivot("year")
Expand All @@ -307,7 +308,7 @@ def get_hsa_activity_table(self) -> pd.DataFrame:
:rtype: pd.DataFrame
"""
return (
self._spark.read.table("hsa_activity_tables_NATIONAL")
self._spark.read.table("nhp.default.hsa_activity_tables_national")
.filter(F.col("fyear") == self._year * 100 + (self._year + 1) % 100)
.groupBy("hsagrp", "sex", "age")
.agg(F.mean("activity").alias("activity"))
Expand Down
12 changes: 3 additions & 9 deletions notebooks/national_run.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@

# COMMAND ----------

dbutils.widgets.text("data_path", "/Volumes/su_data/nhp/old_nhp_data", "Data Path")
dbutils.widgets.text("data_path", "/Volumes/nhp/model_data/files", "Data Path")
dbutils.widgets.text("data_version", "dev", "Data Version")
dbutils.widgets.text("params_file", "sample_params.json", "Params File")
dbutils.widgets.text("sample_rate", "0.01", "Sample Rate")
Expand Down Expand Up @@ -66,14 +66,8 @@

# COMMAND ----------

# Check that the version is the same in the params and in the data_version variable above

assert dbutils.widgets.get('data_version').rsplit('.', 1)[0] == params["app_version"]

# COMMAND ----------

spark.catalog.setCurrentCatalog("su_data")
spark.catalog.setCurrentDatabase("nhp")
spark.catalog.setCurrentCatalog("nhp")
spark.catalog.setCurrentDatabase("default")

# COMMAND ----------

Expand Down
Loading