Skip to content
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

PIPELINE-1863 Normalize and standardize input fields on normalization #11

Merged
merged 5 commits into from
Jul 5, 2024
Merged

PIPELINE-1863 Normalize and standardize input fields on normalization #11

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
bb91da0
standardize input data using shipdataprocess
rdgfuentes Jul 4, 2024
4cac2ba
Normalized shipname and callsign to calculate ssvid
rdgfuentes Jul 4, 2024
d8c8e3d
Added missing dependency on pyproject-build.toml
rdgfuentes Jul 4, 2024
dad4e91
Use specific version of shipdataprocess
rdgfuentes Jul 5, 2024
37cedd3
Updated poetry.lock
rdgfuentes Jul 5, 2024
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
868 changes: 492 additions & 376 deletions packages/pipe-vms-ingestion/poetry.lock
View file
Open in desktop

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions packages/pipe-vms-ingestion/pyproject-build.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,8 @@ packages = [
python = ">=3.9,<3.11"
apache-beam = {extras = ["gcp"], version = "2.56.0"}
jinja2 = "^3.0.3"
shipdataprocess = "0.8.6"
pandas = "^2.2.2"

[tool.poetry.group.dev.dependencies]
autopep8 = "2.0.2"
Expand Down
2 changes: 2 additions & 0 deletions packages/pipe-vms-ingestion/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,8 @@ readme = 'README.md'
python = ">=3.9,<3.11"
apache-beam = {extras = ["gcp"], version = "2.56.0"}
jinja2 = "^3.0.3"
shipdataprocess = "0.8.6"
pandas = "^2.2.2"

[tool.poetry.dependencies.bigquery]
path = "../libs/bigquery"
Expand Down
24 changes: 17 additions & 7 deletions packages/pipe-vms-ingestion/tests/vms_ingestion/normalization/feeds/test_bra_normalize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,13 @@
class TestBRANormalize(unittest.TestCase):

options = build_pipeline_options_with_defaults(
argv=["--country_code=bra", '--source=""', '--destination=""', '--start_date=""', '--end_date=""']
argv=[
"--country_code=bra",
'--source=""',
'--destination=""',
'--start_date=""',
'--end_date=""',
]
)

# Our input data, which will make up the initial PCollection.
Expand All @@ -34,7 +40,7 @@ class TestBRANormalize(unittest.TestCase):
# Our output data, which is the expected data that the final PCollection must match.
EXPECTED = [
{
"msgid": "bb84c21c72cb41d85d724245b52cf2ab",
"msgid": "5411260da7a997217b865007b51e7295",
"source": "ONYXSAT_BRAZIL_VMS",
"source_type": "VMS",
"source_tenant": "BRA",
Expand All @@ -43,18 +49,18 @@ class TestBRANormalize(unittest.TestCase):
"source_ssvid": "4961089",
"type": "VMS",
"internal_id": "4961089",
"ssvid": "BRA|i:4961089|s:Cibradep X",
"ssvid": "BRA|i:4961089|s:CIBRADEP10",
"timestamp": datetime.fromisoformat("2024-05-01 05:35:45+00:00"),
"lat": -1.21861112117767,
"lon": -48.4911117553711,
"speed": 9.1792656587473,
"course": 192.0,
"heading": None,
"shipname": "Cibradep X",
"shipname": "CIBRADEP X",
"callsign": None,
"destination": None,
"imo": None,
"shiptype": "fishing",
"shiptype": "FISHING",
"receiver_type": None,
"receiver": None,
"length": None,
Expand All @@ -63,7 +69,9 @@ class TestBRANormalize(unittest.TestCase):
"class_b_cs_flag": None,
"received_at": None,
"ingested_at": None,
"timestamp_date": datetime.date(datetime.fromisoformat("2024-05-01 05:35:45+00:00")),
"timestamp_date": datetime.date(
datetime.fromisoformat("2024-05-01 05:35:45+00:00")
),
}
]

Expand All @@ -78,4 +86,6 @@ def test_normalize(self):
output: pvalue.PCollection = input | BRANormalize(feed="bra")

# Assert that the output PCollection matches the EXPECTED data.
assert_that(output, pcol_equal_to(TestBRANormalize.EXPECTED), label="CheckOutput")
assert_that(
output, pcol_equal_to(TestBRANormalize.EXPECTED), label="CheckOutput"
)
24 changes: 17 additions & 7 deletions packages/pipe-vms-ingestion/tests/vms_ingestion/normalization/feeds/test_chl_normalize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,13 @@
class TestCHLNormalize(unittest.TestCase):

options = build_pipeline_options_with_defaults(
argv=["--country_code=chl", '--source=""', '--destination=""', '--start_date=""', '--end_date=""']
argv=[
"--country_code=chl",
'--source=""',
'--destination=""',
'--start_date=""',
'--end_date=""',
]
)

# Our input data, which will make up the initial PCollection.
Expand All @@ -33,15 +39,15 @@ class TestCHLNormalize(unittest.TestCase):
# Our output data, which is the expected data that the final PCollection must match.
EXPECTED = [
{
"msgid": "1d4e4dde1f0178df0f396c14587feb04",
"source": "chile_vms_some_fleet",
"msgid": "c8de2f410ae274c94fbd6583f722fc6b",
"source": "CHILE_VMS_SOME_FLEET",
"source_type": "VMS",
"source_tenant": "CHL",
"source_provider": "SERNAPESCA",
"source_fleet": "some_fleet",
"source_fleet": "SOME_FLEET",
"source_ssvid": None,
"type": "VMS",
"ssvid": "CHL|s:AUSTRAL TRAVELER|c:ABC123",
"ssvid": "CHL|s:AUSTRALTRAVELER|c:ABC123",
"timestamp": datetime.fromisoformat("2020-01-01 20:23:01+00:00"),
"lat": -52.546,
"lon": -71.947,
Expand All @@ -62,7 +68,9 @@ class TestCHLNormalize(unittest.TestCase):
"class_b_cs_flag": None,
"received_at": None,
"ingested_at": None,
"timestamp_date": datetime.date(datetime.fromisoformat("2020-01-01 20:23:01+00:00")),
"timestamp_date": datetime.date(
datetime.fromisoformat("2020-01-01 20:23:01+00:00")
),
}
]

Expand All @@ -77,4 +85,6 @@ def test_normalize(self):
output: pvalue.PCollection = input | CHLNormalize(feed="chl")

# Assert that the output PCollection matches the EXPECTED data.
assert_that(output, pcol_equal_to(TestCHLNormalize.EXPECTED), label="CheckOutput")
assert_that(
output, pcol_equal_to(TestCHLNormalize.EXPECTED), label="CheckOutput"
)
24 changes: 17 additions & 7 deletions packages/pipe-vms-ingestion/tests/vms_ingestion/normalization/feeds/test_cri_normalize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,13 @@
class TestCRINormalize(unittest.TestCase):

options = build_pipeline_options_with_defaults(
argv=["--country_code=cri", '--source=""', '--destination=""', '--start_date=""', '--end_date=""']
argv=[
"--country_code=cri",
'--source=""',
'--destination=""',
'--start_date=""',
'--end_date=""',
]
)

# Our input data, which will make up the initial PCollection.
Expand Down Expand Up @@ -51,24 +57,26 @@ class TestCRINormalize(unittest.TestCase):
"lat": 9.9798,
"length": None,
"lon": -84.8221,
"msgid": "758d0202a1b6b7166ddb9851e6731091",
"msgid": "0df1eb16d80e0b61fb9639177b3c71fb",
"received_at": None,
"receiver": None,
"receiver_type": None,
"registry_number": None,
"shipname": "K'IN",
"shiptype": None,
"source": "costarica_vms_sardineros",
"source_fleet": "sardineros",
"source": "COSTARICA_VMS_SARDINEROS",
"source_fleet": "SARDINEROS",
"source_provider": "INCOPESCA",
"source_tenant": "CRI",
"source_ssvid": None,
"source_type": "VMS",
"speed": 0.0,
"ssvid": "CRI|s:K'IN",
"ssvid": "CRI|s:KIN",
"status": None,
"timestamp": datetime.fromisoformat("2024-05-01 12:15:01+00:00"),
"timestamp_date": datetime.date(datetime.fromisoformat("2024-05-01 12:15:01+00:00")),
"timestamp_date": datetime.date(
datetime.fromisoformat("2024-05-01 12:15:01+00:00")
),
"type": "VMS",
"width": None,
},
Expand All @@ -85,4 +93,6 @@ def test_normalize(self):
output: pvalue.PCollection = input | CRINormalize(feed="cri")

# Assert that the output PCollection matches the EXPECTED data.
assert_that(output, pcol_equal_to(TestCRINormalize.EXPECTED), label="CheckOutput")
assert_that(
output, pcol_equal_to(TestCRINormalize.EXPECTED), label="CheckOutput"
)
39 changes: 25 additions & 14 deletions packages/pipe-vms-ingestion/vms_ingestion/normalization/transforms/map_normalized_message.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,12 @@
from datetime import datetime

import apache_beam as beam
from shipdataprocess.normalize import normalize_callsign, normalize_shipname
from shipdataprocess.standardize import (
standardize_imo,
standardize_int_str,
standardize_str,
)
from vms_ingestion.normalization.transforms.calculate_msgid import get_message_id
from vms_ingestion.normalization.transforms.calculate_ssvid import encode_ssvid

Expand All @@ -9,33 +15,33 @@ def map_normalized_message(msg, feed, source_provider, source_format):
result = {
**msg,
"source_type": "VMS",
"source_tenant": feed.upper(),
"source_provider": source_provider,
"source_fleet": msg.get("fleet"),
"source_tenant": standardize_str(feed),
"source_provider": standardize_str(source_provider),
"source_fleet": standardize_str(msg.get("fleet")),
"source_ssvid": msg.get("internal_id"),
"type": msg.get("type", "VMS"),
"type": standardize_str(msg.get("type", "VMS")),
"timestamp": msg["timestamp"],
"lat": msg["lat"],
"lon": msg["lon"],
"speed": msg.get("speed"),
"course": msg.get("course"),
"heading": msg.get("heading"),
"shipname": msg["shipname"],
"callsign": msg["callsign"] if msg["callsign"] else None,
"shipname": standardize_str(msg["shipname"]),
"callsign": standardize_str(msg["callsign"]) if msg["callsign"] else None,
"destination": msg.get("destination"),
"imo": msg.get("imo"),
"shiptype": msg.get("shiptype"),
"imo": standardize_imo(msg.get("imo")),
"shiptype": standardize_str(msg.get("shiptype")),
"receiver_type": msg.get("receiver_type"),
"receiver": msg.get("receiver"),
"length": msg.get("length"),
"width": msg.get("width"),
"status": msg.get("status"),
"class_b_cs_flag": msg.get("class_b_cs_flag"),
"status": standardize_int_str(msg.get("status")),
"class_b_cs_flag": standardize_int_str(msg.get("class_b_cs_flag")),
"received_at": msg.get("received_at"),
"ingested_at": msg.get("ingested_at"),
"timestamp_date": datetime.date(msg["timestamp"]),
}
return {**result, "source": source_format.format(**result)}
return {**result, "source": standardize_str(source_format.format(**result))}


class MapNormalizedMessage(beam.PTransform):
Expand All @@ -46,7 +52,12 @@ def __init__(self, feed, source_provider, source_format):
self.source_format = source_format

def expand(self, pcoll):
return pcoll | self.map_normalized_message() | self.calculate_ssvid() | self.calculate_message_id()
return (
pcoll
| self.map_normalized_message()
| self.calculate_ssvid()
| self.calculate_message_id()
)

def map_normalized_message(self):
return beam.Map(
Expand Down Expand Up @@ -81,8 +92,8 @@ def calculate_ssvid(self):
"ssvid": encode_ssvid(
country=msg["source_tenant"],
internal_id=msg.get("internal_id"),
shipname=msg.get("shipname"),
callsign=msg.get("callsign"),
shipname=normalize_shipname(msg.get("shipname")),
callsign=normalize_callsign(msg.get("callsign")),
licence=msg.get("licence"),
),
}
Expand Down
Loading