pydatafabric 0.1.2

SHINSEGAE DataFabric Python Package

SHINSEGAE DataFabric Python Package

This is highly site dependent package. Resources are abstracted into package structure.

Usage

Work with spark-bigquery-connector

# SELECT
from pydatafabric.gcp import bq_table_to_pandas 
pandas_df = bq_table_to_pandas("dataset", "table_name", ["col_1", "col_2"], "2020-01-01", "cust_id is not null")
# INSERT 
from pydatafabric.gcp import pandas_to_bq_table
pandas_to_bq_table(pandas_df, "dataset", "table_name", "2020-03-01")

Send slack message

from pydatafabric.ye import slack_send
text = 'Hello'
username = 'airflow'
channel = '#leavemealone'
slack_send(text=text, username=username, channel=channel)
# Send dataframe as text
df = pd.DataFrame(data={'col1': [1, 2], 'col2': [3, 4]})
slack_send(text=df, username=username, channel=channel, dataframe=True)

Get bigquery client

from pydatafabric.gcp import get_bigquery_client
bq = get_bigquery_client()
bq.query(query)

IPython BigQuery Magic

from pydatafabric.gcp import import_bigquery_ipython_magic

import_bigquery_ipython_magic()

query_params = {
    "p_1": "v_1",
    "dataset": "common_dev",
}

%% bq --params $query_params

SELECT c_1 
FROM {dataset}.user_logs
WHERE c_1 = @p_1

Use github util

from pydatafabric.ye import get_github_util
g = get_github_util
# query graphql
res = g.query_gql(graph_ql)
# get file in github repository
byte_object = g.download_from_git(github_url_path)

Installation

$ pip install pydatafabric --upgrade

If you would like to install submodules for AIR

$ pip install pydatafabric[emart] --upgrade