polars_dataframe_filter_groupby_aggregation_quickstart.py

1import polars as pl
2from datetime import datetime
3
4# Create a DataFrame
5df = pl.DataFrame(
6    {
7        "integer": [1, 2, 3, 4, 5],
8        "date": [
9            datetime(2025, 1, 1),
10            datetime(2025, 1, 2),
11            datetime(2025, 1, 3),
12            datetime(2025, 1, 4),
13            datetime(2025, 1, 5),
14        ],
15        "float": [4.0, 5.0, 6.0, 7.0, 8.0],
16        "string": ["a", "b", "c", "d", "e"],
17    }
18)
19
20# Perform basic operations: filter rows and select columns
21out = df.filter(pl.col("integer") > 2).select(
22    pl.col("date"),
23    pl.col("float") * 2
24)
25
26# Perform a group-by and aggregation
27group_out = df.group_by("string").agg(
28    pl.col("integer").sum().alias("sum_integer")
29)
30
31print("Filtered DataFrame:")
32print(out)
33print("\nGrouped Aggregation:")
34print(group_out)