Quickstart examples for getting up and running with great expectations

great_expecations_examples.py

## 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")
validation_results = test.validate(expectation_suite="npi_csv_expectations.json")

if validation_results["success"]:
    print ("giddy up!")
else:
    raise Exception("oh shit.")
    
## SQLAlchemy
import os
from great_expectations.dataset import SqlAlchemyDataset
from sqlalchemy import create_engine

db_string = "postgres://{user}:{password}@{host}:{port}/{dbname}".format(
    user=os.environ["DB_USER"],
    password=os.environ["DB_PASSWORD"],
    port=os.environ["DB_PORT"],
    dbname=os.environ["DB_DBNAME"],
    host=os.environ["DB_HOST"],
)

db_engine = create_engine(db_string)

# Build up expectations on a table and save them
sql_dataset = SqlAlchemyDataset(table_name='my_table', engine=db_engine)
sql_dataset.expect_column_values_to_not_be_null("id")
sql_dataset.save_expectation_suite("postgres_expectations.json")

# Load in a subset of the table and test it
sql_query = """
    select *
    from my_table
    where created_at between date'2019-11-07' and date'2019-11-08'
"""
new_sql_dataset = SqlAlchemyDataset(custom_sql=sql_query, engine=db_engine)
validation_results = new_sql_dataset.validate(
    expectation_suite="postgres_expectations.json"
)

if validation_results["success"]:
    ...

Put together for this post: https://discuss.greatexpectations.io/t/a-super-simple-alternative-introduction-to-great-expectations/27?u=abegong