knox / Polars-readme-1.py

>>> import polars as pl >>> df = pl.DataFrame( ... { ... "A": [1, 2, 3, 4, 5], ... "fruits": ["banana", "banana", "apple", "apple", "banana"], ... "B": [5, 4, 3, 2, 1], ... "cars": ["beetle", "audi", "beetle", "beetle", "beetle"], ... } ... ) # embarrassingly parallel execution & very expressive query language >>> df.sort("fruits").select( ... "fruits", ... "cars", ... pl.lit("fruits").alias("literal_string_fruits"), ... pl.col("B").filter(pl.col("cars") == "beetle").sum(), ... pl.col("A").filter(pl.col("B") > 2).sum().over("cars").alias("sum_A_by_cars"), ... pl.col("A").sum().over("fruits").alias("sum_A_by_fruits"), ... pl.col("A").reverse().over("fruits").alias("rev_A_by_fruits"), ... pl.col("A").sort_by("B").over("fruits").alias("sort_A_by_B_by_fruits"), ... ) shape: (5, 8) ┌──────────┬──────────┬──────────────┬─────┬─────────────┬─────────────┬─────────────┬─────────────┐ │ fruits ┆ cars ┆ literal_stri ┆ B ┆ sum_A_by_ca ┆ sum_A_by_fr ┆ rev_A_by_fr ┆ sort_A_by_B │ │ --- ┆ --- ┆ ng_fruits ┆ --- ┆ rs ┆ uits ┆ uits ┆ _by_fruits │ │ str ┆ str ┆ --- ┆ i64 ┆ --- ┆ --- ┆ --- ┆ --- │ │ ┆ ┆ str ┆ ┆ i64 ┆ i64 ┆ i64 ┆ i64 │ ╞══════════╪══════════╪══════════════╪═════╪═════════════╪═════════════╪═════════════╪═════════════╡ │ "apple" ┆ "beetle" ┆ "fruits" ┆ 11 ┆ 4 ┆ 7 ┆ 4 ┆ 4 │ │ "apple" ┆ "beetle" ┆ "fruits" ┆ 11 ┆ 4 ┆ 7 ┆ 3 ┆ 3 │ │ "banana" ┆ "beetle" ┆ "fruits" ┆ 11 ┆ 4 ┆ 8 ┆ 5 ┆ 5 │ │ "banana" ┆ "audi" ┆ "fruits" ┆ 11 ┆ 2 ┆ 8 ┆ 2 ┆ 2 │ │ "banana" ┆ "beetle" ┆ "fruits" ┆ 11 ┆ 4 ┆ 8 ┆ 1 ┆ 1 │ └──────────┴──────────┴──────────────┴─────┴─────────────┴─────────────┴─────────────┴─────────────┘