# Validating Data Freshness
Pointblank Validation
2026-07-13|17:44:49 Polars
STEP COLUMNS VALUES TBL EVAL UNITS PASS FAIL W E C EXT
#4CA64C 1
MC4wNzk0MzQ4LDE4LjQ4MDM1MDcgNDkuOTUwNDU0OSwxOC4wODczNTE2IEM0OS44MjE0NzUsMTcuNjk0MzUyNCA0OS40NjM4NzUzLDE3LjQyMTMwMTQgNDkuMDUwNzgxLDE3LjQwMDM5MSBMMzIuMDk3NjU2LDE2LjUzNTE1NiBMMjUuOTMxNjQxLDAuNjM4NjcxOSBDMjUuNzgyNTQ4MywwLjI1NDAwMjg0NyAyNS40MTI1NTE2LDAgMjUsMCBaIE0yNSwzLjc2MzY3MTkgTDMwLjQ2Njc5NywxNy44NjEzMjggQzMwLjYwOTY4OSwxOC4yMjkxNDE2IDMwLjk1NTQ5NjIsMTguNDc4NTUxNSAzMS4zNDk2MDksMTguNDk4MDQ3IEw0Ni4zNTkzNzUsMTkuMjY1NjI1IEwzNC42Njc5NjksMjguODI2MTcyIEMzNC4zNjQ2MDU0LDI5LjA3NDIxMTQgMzQuMjM0MDQ5MywyOS40NzY1Njc5IDM0LjMzMzk4NCwyOS44NTU0NjkgTDM4LjE3NTc4MSw0NC4zNjkxNDEgTDI1LjU0MTAxNiwzNi4yNTc4MTIgQzI1LjIxMTQ3ODksMzYuMDQ1ODUzNiAyNC43ODg1MjExLDM2LjA0NTg1MzYgMjQuNDU4OTg0LDM2LjI1NzgxMiBMMTEuODI0MjE5LDQ0LjM2OTE0MSBMMTUuNjY2MDE2LDI5Ljg1NTQ2OSBDMTUuNzY1OTUwNywyOS40NzY1Njc5IDE1LjYzNTM5NDYsMjkuMDc0MjExNCAxNS4zMzIwMzEsMjguODI2MTcyIEwzLjY0MDYyNSwxOS4yNjU2MjUgTDE4LjY1MDM5MSwxOC40OTgwNDcgQzE5LjA0NDUwMzgsMTguNDc4NTUxNSAxOS4zOTAzMTEsMTguMjI5MTQxNiAxOS41MzMyMDMsMTcuODYxMzI4IEwyNSwzLjc2MzY3MTkgWiIgaWQ9IlNoYXBlIiAvPgogICAgICAgICAgICA8L2c+CiAgICAgICAgPC9nPgogICAgPC9nPgo8L3N2Zz4=" /> specially()

Recent data available (within 2 days of 2023-12-31)

 EXPR ✓ 1 1
1.00		 0
0.00		 -- -- -- --
#4CA64C 2
col_vals_ge()

All data points are from the last week

 data_timestamp 2023-12-24 ✓ 4 4
1.00		 0
0.00		 -- -- -- --
#4CA64C 3
specially()

Most recent data is from today

 EXPR ✓ 1 1
1.00		 0
0.00		 -- -- -- --
#4CA64C 4
col_vals_not_null()

No missing timestamps

 data_timestamp -- ✓ 4 4
1.00		 0
0.00		 -- -- -- --
2026-07-13 17:44:49 UTC< 1 s2026-07-13 17:44:49 UTC
``` python import pointblank as pb import polars as pl from datetime import date, datetime, timedelta # Create sample data with mixed freshness levels freshness_data = pl.DataFrame({ "data_timestamp": [ datetime(2023, 12, 28, 10, 30), # 3 days ago from Dec 31 datetime(2023, 12, 29, 14, 15), # 2 days ago datetime(2023, 12, 30, 9, 45), # 1 day ago datetime(2023, 12, 31, 16, 20), # Today ], "sensor_id": ["TEMP_01", "TEMP_02", "TEMP_01", "TEMP_03"], "reading": [22.5, 21.8, 23.1, 22.9], "quality_score": [0.95, 0.88, 0.92, 0.97] }) # Assuming today is 2023-12-31, check for data freshness current_date = date(2023, 12, 31) freshness_cutoff = current_date - timedelta(days=2) # Data should be within 2 days validation = ( pb.Validate(freshness_data) .specially( expr=lambda df: df.filter( pl.col("data_timestamp").dt.date() >= freshness_cutoff ).height > 0, brief=f"Recent data available (within 2 days of {current_date})" ) .col_vals_ge( columns="data_timestamp", value=current_date - timedelta(days=7), # Within last week brief="All data points are from the last week" ) .specially( expr=lambda df: ( df.select(pl.col("data_timestamp").max()).item().date() >= current_date ), brief="Most recent data is from today" ) .col_vals_not_null( columns="data_timestamp", brief="No missing timestamps" ) .interrogate() ) validation ``` Preview of Input Table
PolarsRows4Columns4
data_timestamp Datetime
sensor_id String
reading Float64
quality_score Float64
1 2023-12-28 10:30:00 TEMP_01 22.5 0.95
2 2023-12-29 14:15:00 TEMP_02 21.8 0.88
3 2023-12-30 09:45:00 TEMP_01 23.1 0.92
4 2023-12-31 16:20:00 TEMP_03 22.9 0.97