|
| 1 | +### Setup Snowflake Data |
| 2 | + |
| 3 | +instance -> https://supypql-om48075.snowflakecomputing.com/console/login |
| 4 | + |
| 5 | + |
| 6 | +```sql |
| 7 | +-- Use an admin role |
| 8 | +USE ROLE ACCOUNTADMIN; |
| 9 | + |
| 10 | +-- Create the `transform` role |
| 11 | +CREATE ROLE IF NOT EXISTS transform; |
| 12 | +GRANT ROLE TRANSFORM TO ROLE ACCOUNTADMIN; |
| 13 | + |
| 14 | +-- Create the default warehouse if necessary |
| 15 | +CREATE WAREHOUSE IF NOT EXISTS COMPUTE_WH; |
| 16 | +GRANT OPERATE ON WAREHOUSE COMPUTE_WH TO ROLE TRANSFORM; |
| 17 | + |
| 18 | +-- Create the `dbt` user and assign to role |
| 19 | +CREATE USER IF NOT EXISTS dbt |
| 20 | + PASSWORD='dbtPassword123' |
| 21 | + LOGIN_NAME='dbt' |
| 22 | + MUST_CHANGE_PASSWORD=FALSE |
| 23 | + DEFAULT_WAREHOUSE='COMPUTE_WH' |
| 24 | + DEFAULT_ROLE='transform' |
| 25 | + DEFAULT_NAMESPACE='AIRBNB.RAW' |
| 26 | + COMMENT='DBT user used for data transformation'; |
| 27 | +GRANT ROLE transform to USER dbt; |
| 28 | + |
| 29 | +-- Create our database and schemas |
| 30 | +CREATE DATABASE IF NOT EXISTS AIRBNB; |
| 31 | +CREATE SCHEMA IF NOT EXISTS AIRBNB.RAW; |
| 32 | + |
| 33 | +-- Set up permissions to role `transform` |
| 34 | +GRANT ALL ON WAREHOUSE COMPUTE_WH TO ROLE transform; |
| 35 | +GRANT ALL ON DATABASE AIRBNB to ROLE transform; |
| 36 | +GRANT ALL ON ALL SCHEMAS IN DATABASE AIRBNB to ROLE transform; |
| 37 | +GRANT ALL ON FUTURE SCHEMAS IN DATABASE AIRBNB to ROLE transform; |
| 38 | +GRANT ALL ON ALL TABLES IN SCHEMA AIRBNB.RAW to ROLE transform; |
| 39 | +GRANT ALL ON FUTURE TABLES IN SCHEMA AIRBNB.RAW to ROLE transform; |
| 40 | + |
| 41 | +-- Set up the defaults |
| 42 | +USE WAREHOUSE COMPUTE_WH; |
| 43 | +USE DATABASE airbnb; |
| 44 | +USE SCHEMA RAW; |
| 45 | + |
| 46 | +-- Create our three tables and import the data from S3 |
| 47 | +CREATE OR REPLACE TABLE raw_listings |
| 48 | + (id integer, |
| 49 | + listing_url string, |
| 50 | + name string, |
| 51 | + room_type string, |
| 52 | + minimum_nights integer, |
| 53 | + host_id integer, |
| 54 | + price string, |
| 55 | + created_at datetime, |
| 56 | + updated_at datetime); |
| 57 | + |
| 58 | +COPY INTO raw_listings (id, |
| 59 | + listing_url, |
| 60 | + name, |
| 61 | + room_type, |
| 62 | + minimum_nights, |
| 63 | + host_id, |
| 64 | + price, |
| 65 | + created_at, |
| 66 | + updated_at) |
| 67 | + from 's3://dbtlearn/listings.csv' |
| 68 | + FILE_FORMAT = (type = 'CSV' skip_header = 1 |
| 69 | + FIELD_OPTIONALLY_ENCLOSED_BY = '"'); |
| 70 | + |
| 71 | + |
| 72 | +CREATE OR REPLACE TABLE raw_reviews |
| 73 | + (listing_id integer, |
| 74 | + date datetime, |
| 75 | + reviewer_name string, |
| 76 | + comments string, |
| 77 | + sentiment string); |
| 78 | + |
| 79 | +COPY INTO raw_reviews (listing_id, date, reviewer_name, comments, sentiment) |
| 80 | + from 's3://dbtlearn/reviews.csv' |
| 81 | + FILE_FORMAT = (type = 'CSV' skip_header = 1 |
| 82 | + FIELD_OPTIONALLY_ENCLOSED_BY = '"'); |
| 83 | + |
| 84 | + |
| 85 | +CREATE OR REPLACE TABLE raw_hosts |
| 86 | + (id integer, |
| 87 | + name string, |
| 88 | + is_superhost string, |
| 89 | + created_at datetime, |
| 90 | + updated_at datetime); |
| 91 | + |
| 92 | +COPY INTO raw_hosts (id, name, is_superhost, created_at, updated_at) |
| 93 | + from 's3://dbtlearn/hosts.csv' |
| 94 | + FILE_FORMAT = (type = 'CSV' skip_header = 1 |
| 95 | + FIELD_OPTIONALLY_ENCLOSED_BY = '"'); |
| 96 | + |
| 97 | +``` |
| 98 | + |
| 99 | +## Setup local python |
| 100 | +Install python 3.11 and install virtualenv. **Create the folder for the course and install on it!** |
| 101 | +```python |
| 102 | +pip install virtualenv |
| 103 | +``` |
| 104 | +create python venv |
| 105 | +```python |
| 106 | +virtual env --python=python3.11 |
| 107 | +``` |
| 108 | +activated venv (be in the folder) |
| 109 | +```python |
| 110 | +. venv/bin/activate |
| 111 | +``` |
0 commit comments