NSAPH Data Platform
Contents
Introduction
What is Data Platform
Data Domains
Data Processing Pipelines
Python Packages
Data Platform Internals
Adding more data
Terms and Acronyms
Indices
NSAPH Data Platform
The pg_export_parquet Module
View page source
The pg_export_parquet Module
A command line utility to export results of SQL query as Parquet files
result_set
(
conn
:
connection
,
sql
:
str
,
cursor_name
:
str
,
batch_size
:
int
)
[source]
index_of
(
text
:
str
,
token
:
str
)
[source]
class
PgPqBase
(
cnxn
:
connection
,
sql
:
str
,
destination
:
str
)
[source]
setup_schema
(
)
[source]
static
type_pg2pq
(
vtype
:
str
)
[source]
metadata_sql
(
)
→
str
[source]
get_metadata
(
)
→
List
[
Tuple
]
[source]
set_partitioning
(
columns
:
List
[
str
]
)
[source]
abstract
export
(
)
[source]
classmethod
run
(
)
[source]
classmethod
export_sql
(
arguments
,
sql
)
[source]
classmethod
export_table
(
arguments
,
table
:
str
)
[source]
classmethod
export_schema
(
arguments
)
[source]
class
PgPqSingleQuery
(
cnxn
:
connection
,
sql
:
str
,
destination
:
str
,
mode
:
str
,
schema
:
Optional
[
Schema
]
=
None
)
[source]
static
normalize_value
(
v
)
[source]
transform
(
row
:
Dict
)
→
Dict
[source]
set_partitioning
(
columns
:
List
[
str
]
,
values
:
Optional
[
List
]
=
None
)
[source]
export
(
)
[source]
batch
(
data
:
List
[
Dict
]
)
[source]
batches
(
)
[source]
class
PgPqPartitionedQuery
(
cnxn
:
connection
,
sql
:
str
,
destination
:
str
,
partition
:
List
[
str
]
)
[source]
static
qualify_column
(
sql
:
str
,
column
:
str
,
idx_select
:
int
)
[source]
set_partition_values
(
)
[source]
set_partitioning
(
partition
:
List
[
str
]
)
[source]
export
(
)
[source]