Polars

Misc

Also see Python, Polars
Packages
- {tidypolars}
Resources
- Cookbook Polars for R
Coerce an existing dataframe into a polars dataframe
```
pl$
  DataFrame(D)$
  # do stuff
```

Mutate

Example: 10-day and 50-day Moving Average (source)

moving_average_pl <- 
  long_pl$with_columns(
    pl$
      col("Price")$
      rolling_mean(10)$
      over("Stock")$
      alias("Price_MA10"),
    pl$
      col("Price")$
      rolling_mean(50)$
      over("Stock")$
      alias("Price_MA50")
)
moving_average_pl

moving_average_pl |> 
    as_tibble() |> 
    tidyr::pivot_longer(
        cols = Price:Price_MA50
    ) %>%
    group_by(Stock) |> 
    plot_time_series(as_date(Date), value, .color_var = name, .facet_ncol = 4, .smooth = FALSE)

Summarize

Example: min, max, mean by group

df <- pl$scan_csv(file_name)$
    group_by("state")$
    agg(
        pl$
          col("measurement")$
          min()$
          alias("min_m"),
        pl$
          col("measurement")$
          max()$
          alias("max_m"),
        pl$
          col("measurement")$
          mean()$
          alias("mean_m")
    )$
    collect()

Pivoting

Example: pivot_longer (source)

long_pl = stock_data_pl$unpivot(
    index         = "Date",
    value_name    = "Price",
    variable_name = "Stock"
)
long_pl

long_pl %>%
    as_tibble() |> 
    group_by(Stock)  |> 
    timetk::plot_time_series(as_date(Date), Price, .facet_ncol = 4, .smooth = FALSE)

SQL

Example: min, max, mean by group

lf <- pl$LazyFrame(D) 

pl$
  SQLContext(frame = lf)$
  execute(
    "select min(measurement) as min_m, 
            max(measurement) as max_m, 
            avg(measurement) as mean_m 
    from frame 
    group by state"
  )$
  collect()