alt Hacker NewsIt’s just the lazy/expression part of the API, which is really the bread and butter of polars, rather than just being “replacement syntax” for pandas. This allows you to tap into abstraction that SQL can’t keep up with:
import polars as pl
# 1. Base Dataset
lazy_df = pl.LazyFrame(
{
"store_id": ["S01", "S02", "S03", "S04", "S05"],
"revenue": [5000.0, 2400.0, 15000.0, 900.0, 3200.0],
"margin": [0.45, 0.30, 0.60, 0.15, 0.50],
"tx_count": [120, 45, 300, 20, 85],
"returns": [5, 12, 45, 2, 8],
}
)
# 2. Define Layer Abstractions
def get_kpi_layer() -> list[pl.Expr]:
return [
(pl.col("returns") / pl.col("tx_count")).alias("return_rate"),
(pl.col("revenue") / pl.col("tx_count")).alias("avg_order_value"),
]
def get_threshold_layer(thresholds: dict[str, list[float]]) -> list[pl.Expr]:
return [
(pl.col(col) > limit).alias(f"is_{col}above{int(limit)}")
for col, limits in thresholds.items()
for limit in limits
]
def get_interaction_layer(numeric_cols: list[str]) -> list[pl.Expr]:
return [
(pl.col(a) / (pl.col(b) + 1e-5)).alias(f"ratio_{a}per{b}")
for i, a in enumerate(numeric_cols)
for b in numeric_cols[i + 1 :]
]
def get_segmentation_layer() -> list[pl.Expr]:
return [
pl.when(pl.col("margin") > 0.4)
.then(pl.literal("High"))
.otherwise(pl.literal("Low"))
.alias("margin_profile")
]
# 3. Consolidate and Execute Single Graph Pass
thresholds = {"revenue": [1000.0, 5000.0, 10000.0], "tx_count": [50, 100, 200]}
numeric_cols = ["revenue", "margin", "tx_count", "returns"]
expr_pool = [
*get_kpi_layer(),
*get_threshold_layer(thresholds),
*get_interaction_layer(numeric_cols),
*get_segmentation_layer(),
]
final_df = lazy_df.with_columns(expr_pool).collect()Replies
_zoltan_ • today at 11:47 AM
I'm sorry but this looks much better:
WITH raw_data AS (
SELECT * FROM (
VALUES
('S01', 5000.0, 0.45, 120, 5),
('S02', 2400.0, 0.30, 45, 12),
('S03', 15000.0, 0.60, 300, 45),
('S04', 900.0, 0.15, 20, 2),
('S05', 3200.0, 0.50, 85, 8)
) AS t(store_id, revenue, margin, tx_count, returns)),
base_data AS (
SELECT
store_id,
revenue,
margin,
CAST(tx_count AS DOUBLE) AS tx_count,
CAST(returns AS DOUBLE) AS returns
FROM raw_data
)
SELECT
store_id,
revenue,
margin,
CAST(tx_count AS BIGINT) AS tx_count,
CAST(returns AS BIGINT) AS returns,
-- KPI Layer
returns / tx_count AS return_rate,
revenue / tx_count AS avg_order_value,
-- Threshold Layer (matching original alias names)
revenue > 1000.0 AS is_revenueabove1000,
revenue > 5000.0 AS is_revenueabove5000,
revenue > 10000.0 AS is_revenueabove10000,
tx_count > 50 AS is_tx_countabove50,
tx_count > 100 AS is_tx_countabove100,
tx_count > 200 AS is_tx_countabove200,
-- Interaction Layer (preserving exact numeric formula & aliases)
revenue / (margin + 1e-5) AS ratio_revenuepermargin,
revenue / (tx_count + 1e-5) AS ratio_revenuepertx_count,
revenue / (returns + 1e-5) AS ratio_revenueperreturns,
margin / (tx_count + 1e-5) AS ratio_marginpertx_count,
margin / (returns + 1e-5) AS ratio_marginperreturns,
tx_count / (returns + 1e-5) AS ratio_tx_countperreturns,
-- Segmentation Layer
CASE WHEN margin > 0.4 THEN 'High' ELSE 'Low' END AS margin_profile
FROM base_data;➕ show 2 replies
awesome, thanks!