Struct GroupedData 

pub struct GroupedData { /* private fields */ }

GroupedData - represents a DataFrame grouped by certain columns. Similar to PySpark’s GroupedData

Implementations

impl GroupedData

pub fn count(&self) -> Result<DataFrame, PolarsError>

Count rows in each group

pub fn sum(&self, column: &str) -> Result<DataFrame, PolarsError>

Sum a column in each group

pub fn avg(&self, column: &str) -> Result<DataFrame, PolarsError>

Average (mean) of a column in each group

pub fn min(&self, column: &str) -> Result<DataFrame, PolarsError>

Minimum value of a column in each group

pub fn max(&self, column: &str) -> Result<DataFrame, PolarsError>

Maximum value of a column in each group

pub fn first(&self, column: &str) -> Result<DataFrame, PolarsError>

First value of a column in each group (order not guaranteed unless explicitly sorted).

pub fn last(&self, column: &str) -> Result<DataFrame, PolarsError>

Last value of a column in each group (order not guaranteed unless explicitly sorted).

pub fn approx_count_distinct( &self, column: &str, ) -> Result<DataFrame, PolarsError>

Approximate count of distinct values in each group (uses n_unique; same as count_distinct for exact).

pub fn any_value(&self, column: &str) -> Result<DataFrame, PolarsError>

Any value from the group (PySpark any_value). Uses first value.

pub fn bool_and(&self, column: &str) -> Result<DataFrame, PolarsError>

Boolean AND across group (PySpark bool_and / every).

pub fn bool_or(&self, column: &str) -> Result<DataFrame, PolarsError>

Boolean OR across group (PySpark bool_or / some).

pub fn product(&self, column: &str) -> Result<DataFrame, PolarsError>

Product of column values in each group (PySpark product).

pub fn collect_list(&self, column: &str) -> Result<DataFrame, PolarsError>

Collect column values into list per group (PySpark collect_list).

pub fn collect_set(&self, column: &str) -> Result<DataFrame, PolarsError>

Collect distinct column values into list per group (PySpark collect_set).

pub fn count_if(&self, column: &str) -> Result<DataFrame, PolarsError>

Count rows where condition column is true (PySpark count_if).

pub fn percentile(&self, column: &str, p: f64) -> Result<DataFrame, PolarsError>

Percentile of column (PySpark percentile). p in 0.0..=1.0.

pub fn max_by( &self, value_col: &str, ord_col: &str, ) -> Result<DataFrame, PolarsError>

Value of value_col where ord_col is maximum (PySpark max_by).

pub fn min_by( &self, value_col: &str, ord_col: &str, ) -> Result<DataFrame, PolarsError>

Value of value_col where ord_col is minimum (PySpark min_by).

pub fn covar_pop( &self, col1: &str, col2: &str, ) -> Result<DataFrame, PolarsError>

Population covariance between two columns in each group (PySpark covar_pop).

pub fn covar_samp( &self, col1: &str, col2: &str, ) -> Result<DataFrame, PolarsError>

Sample covariance between two columns in each group (PySpark covar_samp). ddof=1.

pub fn corr(&self, col1: &str, col2: &str) -> Result<DataFrame, PolarsError>

Pearson correlation between two columns in each group (PySpark corr).

pub fn regr_count( &self, y_col: &str, x_col: &str, ) -> Result<DataFrame, PolarsError>

Regression count of (y, x) pairs where both non-null (PySpark regr_count).

pub fn regr_avgx( &self, y_col: &str, x_col: &str, ) -> Result<DataFrame, PolarsError>

Regression average of x (PySpark regr_avgx).

pub fn regr_avgy( &self, y_col: &str, x_col: &str, ) -> Result<DataFrame, PolarsError>

Regression average of y (PySpark regr_avgy).

pub fn regr_slope( &self, y_col: &str, x_col: &str, ) -> Result<DataFrame, PolarsError>

Regression slope (PySpark regr_slope).

pub fn regr_intercept( &self, y_col: &str, x_col: &str, ) -> Result<DataFrame, PolarsError>

Regression intercept (PySpark regr_intercept).

pub fn regr_r2( &self, y_col: &str, x_col: &str, ) -> Result<DataFrame, PolarsError>

Regression R-squared (PySpark regr_r2).

pub fn regr_sxx( &self, y_col: &str, x_col: &str, ) -> Result<DataFrame, PolarsError>

Regression sum (x - avg_x)^2 (PySpark regr_sxx).

pub fn regr_syy( &self, y_col: &str, x_col: &str, ) -> Result<DataFrame, PolarsError>

Regression sum (y - avg_y)^2 (PySpark regr_syy).

pub fn regr_sxy( &self, y_col: &str, x_col: &str, ) -> Result<DataFrame, PolarsError>

Regression sum (x - avg_x)(y - avg_y) (PySpark regr_sxy).

pub fn kurtosis(&self, column: &str) -> Result<DataFrame, PolarsError>

Kurtosis of a column in each group (PySpark kurtosis). Fisher definition, bias=true.

pub fn skewness(&self, column: &str) -> Result<DataFrame, PolarsError>

Skewness of a column in each group (PySpark skewness). bias=true.

pub fn agg(&self, aggregations: Vec<Expr>) -> Result<DataFrame, PolarsError>

Apply multiple aggregations at once (generic agg method)

pub fn grouping_columns(&self) -> &[String]

Get grouping columns