Polars-readme-2.py
· 1.2 KiB · Python
Raw
>>> df = pl.scan_csv("docs/assets/data/iris.csv")
>>> ## OPTION 1
>>> # run SQL queries on frame-level
>>> df.sql("""
... SELECT species,
... AVG(sepal_length) AS avg_sepal_length
... FROM self
... GROUP BY species
... """).collect()
shape: (3, 2)
┌────────────┬──────────────────┐
│ species ┆ avg_sepal_length │
│ --- ┆ --- │
│ str ┆ f64 │
╞════════════╪══════════════════╡
│ Virginica ┆ 6.588 │
│ Versicolor ┆ 5.936 │
│ Setosa ┆ 5.006 │
└────────────┴──────────────────┘
>>> ## OPTION 2
>>> # use pl.sql() to operate on the global context
>>> df2 = pl.LazyFrame({
... "species": ["Setosa", "Versicolor", "Virginica"],
... "blooming_season": ["Spring", "Summer", "Fall"]
...})
>>> pl.sql("""
... SELECT df.species,
... AVG(df.sepal_length) AS avg_sepal_length,
... df2.blooming_season
... FROM df
... LEFT JOIN df2 ON df.species = df2.species
... GROUP BY df.species, df2.blooming_season
... """).collect()
| 1 | >>> df = pl.scan_csv("docs/assets/data/iris.csv") |
| 2 | >>> ## OPTION 1 |
| 3 | >>> # run SQL queries on frame-level |
| 4 | >>> df.sql(""" |
| 5 | ... SELECT species, |
| 6 | ... AVG(sepal_length) AS avg_sepal_length |
| 7 | ... FROM self |
| 8 | ... GROUP BY species |
| 9 | ... """).collect() |
| 10 | shape: (3, 2) |
| 11 | ┌────────────┬──────────────────┐ |
| 12 | │ species ┆ avg_sepal_length │ |
| 13 | │ --- ┆ --- │ |
| 14 | │ str ┆ f64 │ |
| 15 | ╞════════════╪══════════════════╡ |
| 16 | │ Virginica ┆ 6.588 │ |
| 17 | │ Versicolor ┆ 5.936 │ |
| 18 | │ Setosa ┆ 5.006 │ |
| 19 | └────────────┴──────────────────┘ |
| 20 | >>> ## OPTION 2 |
| 21 | >>> # use pl.sql() to operate on the global context |
| 22 | >>> df2 = pl.LazyFrame({ |
| 23 | ... "species": ["Setosa", "Versicolor", "Virginica"], |
| 24 | ... "blooming_season": ["Spring", "Summer", "Fall"] |
| 25 | ...}) |
| 26 | >>> pl.sql(""" |
| 27 | ... SELECT df.species, |
| 28 | ... AVG(df.sepal_length) AS avg_sepal_length, |
| 29 | ... df2.blooming_season |
| 30 | ... FROM df |
| 31 | ... LEFT JOIN df2 ON df.species = df2.species |
| 32 | ... GROUP BY df.species, df2.blooming_season |
| 33 | ... """).collect() |