ian-whitestone

with sample_data as (
    select *
    from snowflake_sample_data.tpch_sf1.customer
),

nation_14_customers as (
    select *
    from sample_data
    where c_nationkey = 14
),

ian-whitestone

Presto Specific

• Don’t SELECT *, Specify explicit column names (columnar store)
• Avoid large JOINs (filter each table first)
  • In PRESTO tables are joined in the order they are listed!!
  • Join small tables earlier in the plan and leave larger fact tables to the end
  • Avoid cross joins or 1 to many joins as these can degrade performance
• Order by and group by take time
  • only use order by in subqueries if it is really necessary
• When using GROUP BY, order the columns by the highest cardinality (that is, most number of unique values) to the lowest.

ian-whitestone

{% macro set_query_tag() -%}
    {# Start with any model-configured dict #}
    {% set tag_dict = config.get('query_tag', default={}) %}

    {# Regardless of resource type, we can always access the config via the 'model' variable #}
    {%- do tag_dict.update(
        dbt_snowflake_query_tags_version='1.1.3',
        app='dbt',
        dbt_version=dbt_version,
        project_name=project_name,

ian-whitestone

# Let's add an row number to indicate the first message per app & microservice
# This code is analagous to the SQL: row_number() over (partition by id, topic order by msg_ts asc)
df['row_num'] = df.sort_values(['id', 'msg_ts'], ascending=True).groupby(['id', 'topic']).cumcount() + 1

ian-whitestone

<script src="https://cdn.jsdelivr.net/npm/canvas-confetti@1.4.0/dist/confetti.browser.min.js"></script>
 <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.6.0/jquery.min.js"></script>
 
 
 <div id="bottom_of_page">Thanks for scrolling to the bottom 🙌</div>
 
 <div>Enjoy some confetti 🎉</div>
 
 <script>
 

ian-whitestone

## Pandas
import great_expectations as ge

# Build up expectations on a sample dataset and save them
train = ge.read_csv("data/npi.csv")
train.expect_column_values_to_not_be_null("NPI")
train.save_expectation_suite("npi_csv_expectations.json")

# Load in a new dataset and test them
test = ge.read_csv("data/npi_new.csv")

ian-whitestone

"""
Read accompanying blog post: https://ianwhitestone.work/Zappa-Zip-Callbacks
"""
import os
import re
import shutil
import tarfile
import zipfile

ian-whitestone

import os

from jinja2 import Environment, meta, Template
import pandas as pd
from pandas.testing import assert_frame_equal
import pandas.io.sql as psql
import psycopg2

# All these constants would likely live in separate files
CONNECTION = psycopg2.connect(

ian-whitestone

ian-whitestone