Struct DataFrameAnalyzer 

pub struct DataFrameAnalyzer { /* private fields */ }

Implementations

impl DataFrameAnalyzer

pub fn new(df: DataFrame) -> Self

pub fn get_dataframe(&self) -> &DataFrame

pub fn get_descriptive_statistics(&self) -> Result<DataFrame>

pub fn get_value_counts(&self, column_name: &str) -> Result<DataFrame>

pub fn get_null_counts(&self) -> Result<DataFrame>

pub fn get_histogram(&self, column_name: &str, bins: usize) -> Result<DataFrame>

pub fn rank_by_column(&self, column_name: &str) -> Result<DataFrame>

pub fn detect_anomalies( &self, column_name: &str, threshold: f64, ) -> Result<(DataFrame, usize)>

pub fn perform_kmeans_clustering( &self, column_names: &[&str], k: usize, max_iterations: usize, ) -> Result<DataFrame>

pub fn group_and_aggregate( &self, group_by_column: &str, aggregations: &[(&str, &str)], ) -> Result<DataFrame>

Performs a group-by operation followed by aggregation on specified columns.

Arguments

• group_by_column - The name of the column to group the DataFrame by.
• aggregations - A slice of tuples, where each tuple contains:
  • The name of the column to aggregate.
  • The type of aggregation to perform (“sum”, “mean”, “min”, “max”, “count”).

Returns

A Result containing the aggregated DataFrame or an anyhow::Error if the operation fails.

Errors

Returns an error if the specified columns are not found or if an unsupported aggregation type is provided.

pub fn get_correlation_matrix(&self, column_names: &[&str]) -> Result<DataFrame>

Trait Implementations

impl Debug for DataFrameAnalyzer

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.