polars_dataframe_filter_select_groupby_aggregation_quickstart.py

1import polars as pl
2from datetime import datetime
3
4# 1. 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# 2. Filter and Select
21# Select 'integer' and 'date' columns where 'integer' is greater than 2
22out = df.filter(pl.col("integer") > 2).select(["integer", "date"])
23
24# 3. Group By and Aggregate
25# Group by 'string' and calculate the sum of 'float'
26group_out = df.group_by("string").agg(pl.col("float").sum())
27
28print("Filtered DataFrame:")
29print(out)
30print("\nGrouped DataFrame:")
31print(group_out)