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.

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

feat: ⚡️ add job for dune upload #42

Merged
merged 1 commit into from
Jan 11, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
18 changes: 16 additions & 2 deletions ggdp/__init__.py
Original file line number Diff line number Diff line change
@@ -1,11 +1,12 @@
import os

from dagster import Definitions, load_assets_from_modules
from dagster import Definitions, load_assets_from_modules, define_asset_job
from dagster_dbt import dbt_cli_resource, load_assets_from_dbt_project
from dagster_duckdb import DuckDBResource
from dagster_duckdb_pandas import DuckDBPandasIOManager

from . import assets
from . import ops

DBT_PROJECT_DIR = os.path.dirname(os.path.abspath(__file__)) + "/../dbt/"

Expand All @@ -24,4 +25,17 @@
),
}

defs = Definitions(assets=[*dbt_assets, *all_assets], resources=resources)
build_all_assets = define_asset_job(
name="build_all", selection="*", description="Materialize all assets"
)
build_indexer_assets = define_asset_job(
name="build_light_assets",
selection=["++rounds", "++projects"],
description="Materialize downstream of Gitcoin indexer-provided rounds, projects",
)

job_definitions = [ops.refresh_dune, build_all_assets, build_indexer_assets]

defs = Definitions(
assets=[*dbt_assets, *all_assets], resources=resources, jobs=job_definitions
)
48 changes: 48 additions & 0 deletions ggdp/ops.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
import io
import json
import os

import pandas as pd
import requests as rq

from .assets import raw_allo_deployments
from dagster import op, job, OpExecutionContext


@op()
def tiny_upload_to_dune(context: OpExecutionContext, data: pd.DataFrame) -> None:
"""
Upload select dataframe to dune using API, needs DUNE_API_KEY envar to succeeed.
"""

DUNE_KEY = os.getenv("DUNE_API_KEY")
if DUNE_KEY is None:
raise ValueError("DUNE_API_KEY envar not set, cannot upload")

file_buffer = io.StringIO()
data.to_csv(file_buffer, index=False)
file_buffer.seek(0)
csv_content = file_buffer.getvalue()

upload_payload = json.dumps(
{"table_name": "allo_contract_deployments", "data": csv_content}
)

response = rq.post(
"https://api.dune.com/api/v1/table/upload/csv",
headers={"X-Dune-Api-Key": DUNE_KEY},
data=upload_payload,
)
context.log.info(
f"new data uploaded to dune, result:{str(response.status_code)} | {str(response.text)}"
)

response.raise_for_status()


@job
def refresh_dune():
"""
Refresh public dune dataset by materializing `raw_allo_deployments` and uploading new version.
"""
tiny_upload_to_dune(data=raw_allo_deployments())