great_expectations_quickstart_csv_validation_with_expectations.py

1import great_expectations as gx
2
3# 1. Create a Data Context
4context = gx.get_context()
5
6# 2. Connect to Data
7# For this example, we'll use a sample taxi data CSV file
8validator = context.sources.pandas_default.read_csv(
9    "https://raw.githubusercontent.com/great-expectations/gx_tutorials/main/data/yellow_tripdata_sample_2019-01.csv"
10)
11
12# 3. Create Expectations
13validator.expect_column_values_to_not_be_null("pickup_datetime")
14validator.expect_column_values_to_be_between(
15    "passenger_count", min_value=1, max_value=6
16)
17
18# 4. Validate Data
19checkpoint_result = validator.validate()
20
21# 5. Review Results
22print(checkpoint_result)
23
24# Optional: View results in Data Docs
25# context.build_data_docs()
26# context.open_data_docs()