tessl/pypi-polars-u64-idx
Blazingly fast DataFrame library with 64-bit index support for handling datasets with more than 4.2 billion rows
—
Pending
selectors.mddocs/
Column Selectors
Powerful column selection system for efficiently selecting columns by name patterns, data types, or column positions. Selectors provide a concise and type-safe way to work with subsets of DataFrame columns without hard-coding column names.
Capabilities
Basic Selectors
Core selectors for fundamental column selection operations.
def all() -> Selector:
"""
Select all columns.
Returns:
Selector for all columns
"""
def first(*, strict: bool = True) -> Selector:
"""
Select the first column.
Parameters:
- strict: Raise error if no columns match
Returns:
Selector for first column
"""
def last(*, strict: bool = True) -> Selector:
"""
Select the last column.
Parameters:
- strict: Raise error if no columns match
Returns:
Selector for last column
"""
def by_name(*names: str | Collection[str], require_all: bool = True) -> Selector:
"""
Select columns by exact name match.
Parameters:
- names: Column names to select
- require_all: Require all specified names to exist
Returns:
Selector for named columns
"""
def by_index(*indices: int | Collection[int]) -> Selector:
"""
Select columns by index position.
Parameters:
- indices: Column indices to select (supports negative indexing)
Returns:
Selector for columns at specified indices
"""
def by_dtype(*dtypes: PolarsDataType | Collection[PolarsDataType]) -> Selector:
"""
Select columns by data type.
Parameters:
- dtypes: Data types to select
Returns:
Selector for columns with matching data types
"""Pattern Selectors
Selectors for matching columns by name patterns.
def contains(*substring: str) -> Selector:
"""
Select columns containing substring in name.
Parameters:
- substring: Substrings to match
Returns:
Selector for columns containing any substring
"""
def starts_with(*prefix: str) -> Selector:
"""
Select columns starting with prefix.
Parameters:
- prefix: Prefixes to match
Returns:
Selector for columns starting with any prefix
"""
def ends_with(*suffix: str) -> Selector:
"""
Select columns ending with suffix.
Parameters:
- suffix: Suffixes to match
Returns:
Selector for columns ending with any suffix
"""
def matches(pattern: str) -> Selector:
"""
Select columns matching regex pattern.
Parameters:
- pattern: Regular expression pattern
Returns:
Selector for columns matching pattern
"""Numeric Type Selectors
Selectors for numeric column types.
def numeric() -> Selector:
"""
Select all numeric columns (integers, floats, decimals).
Returns:
Selector for numeric columns
"""
def integer() -> Selector:
"""
Select integer columns (signed and unsigned).
Returns:
Selector for integer columns
"""
def signed_integer() -> Selector:
"""
Select signed integer columns (Int8, Int16, Int32, Int64, Int128).
Returns:
Selector for signed integer columns
"""
def unsigned_integer() -> Selector:
"""
Select unsigned integer columns (UInt8, UInt16, UInt32, UInt64).
Returns:
Selector for unsigned integer columns
"""
def float() -> Selector:
"""
Select floating-point columns (Float32, Float64).
Returns:
Selector for float columns
"""
def decimal() -> Selector:
"""
Select decimal columns.
Returns:
Selector for decimal columns
"""Text Type Selectors
Selectors for text and string-based column types.
def string(*, include_categorical: bool = False) -> Selector:
"""
Select string columns.
Parameters:
- include_categorical: Include categorical columns
Returns:
Selector for string columns
"""
def binary() -> Selector:
"""
Select binary columns.
Returns:
Selector for binary columns
"""
def categorical() -> Selector:
"""
Select categorical columns.
Returns:
Selector for categorical columns
"""
def enum() -> Selector:
"""
Select enum columns.
Returns:
Selector for enum columns
"""
def alpha(ascii_only: bool = False, *, ignore_spaces: bool = False) -> Selector:
"""
Select columns containing only alphabetic characters.
Parameters:
- ascii_only: Consider ASCII alphabetic characters only
- ignore_spaces: Ignore whitespace characters
Returns:
Selector for alphabetic string columns
"""
def alphanumeric(ascii_only: bool = False, *, ignore_spaces: bool = False) -> Selector:
"""
Select columns containing only alphanumeric characters.
Parameters:
- ascii_only: Consider ASCII characters only
- ignore_spaces: Ignore whitespace characters
Returns:
Selector for alphanumeric string columns
"""
def digit(ascii_only: bool = False) -> Selector:
"""
Select columns containing only numeric digit characters.
Parameters:
- ascii_only: Consider ASCII digit characters only
Returns:
Selector for digit string columns
"""Temporal Type Selectors
Selectors for date, time, and duration column types.
def temporal() -> Selector:
"""
Select all temporal columns (Date, Datetime, Time, Duration).
Returns:
Selector for temporal columns
"""
def date() -> Selector:
"""
Select date columns.
Returns:
Selector for date columns
"""
def datetime(time_unit: TimeUnit | None = None, time_zone: str | None = None) -> Selector:
"""
Select datetime columns, optionally filtering by time unit or timezone.
Parameters:
- time_unit: Filter by time unit ("ns", "us", "ms", "s")
- time_zone: Filter by timezone string
Returns:
Selector for datetime columns
"""
def time() -> Selector:
"""
Select time columns.
Returns:
Selector for time columns
"""
def duration(time_unit: TimeUnit | None = None) -> Selector:
"""
Select duration columns, optionally filtering by time unit.
Parameters:
- time_unit: Filter by time unit ("ns", "us", "ms", "s")
Returns:
Selector for duration columns
"""Complex Type Selectors
Selectors for nested and complex column types.
def nested() -> Selector:
"""
Select all nested columns (List, Array, Struct).
Returns:
Selector for nested columns
"""
def list(inner: Selector | None = None) -> Selector:
"""
Select list columns, optionally filtering by inner type.
Parameters:
- inner: Selector for inner list element type
Returns:
Selector for list columns
"""
def array(inner: Selector | None = None, *, width: int | None = None) -> Selector:
"""
Select array columns, optionally filtering by inner type or width.
Parameters:
- inner: Selector for inner array element type
- width: Filter by array width
Returns:
Selector for array columns
"""
def struct() -> Selector:
"""
Select struct columns.
Returns:
Selector for struct columns
"""
def boolean() -> Selector:
"""
Select boolean columns.
Returns:
Selector for boolean columns
"""Selector Operations
Utility functions for working with selectors.
def exclude(*selectors: Selector) -> Selector:
"""
Invert selector to exclude matching columns.
Parameters:
- selectors: Selectors to exclude
Returns:
Inverted selector
"""
def is_selector(obj: Any) -> bool:
"""
Check if object is a selector.
Parameters:
- obj: Object to check
Returns:
True if object is a selector
"""
def expand_selector(frame: DataFrame | LazyFrame, *selectors: Selector) -> list[str]:
"""
Expand selectors to concrete column names for a frame.
Parameters:
- frame: DataFrame or LazyFrame to evaluate selectors against
- selectors: Selectors to expand
Returns:
List of column names matching selectors
"""
class Selector:
"""
Column selector for advanced column selection operations.
Supports logical operations (|, &, ~) for combining selectors.
"""
def __or__(self, other: Selector) -> Selector:
"""Combine selectors with OR logic (union)."""
def __and__(self, other: Selector) -> Selector:
"""Combine selectors with AND logic (intersection)."""
def __invert__(self) -> Selector:
"""Invert selector to exclude matching columns."""
def exclude(self, *selectors: Selector) -> Selector:
"""Exclude other selectors from this selector."""Usage Examples
Basic Column Selection
import polars as pl
import polars.selectors as cs
df = pl.DataFrame({
"name": ["Alice", "Bob"],
"age": [25, 30],
"height": [5.5, 6.0],
"is_student": [True, False],
"graduation_date": [pl.date(2020, 5, 15), pl.date(2018, 12, 10)]
})
# Select numeric columns
numeric_cols = df.select(cs.numeric())
# Select columns by pattern
name_cols = df.select(cs.contains("name"))
# Combine selectors
text_and_bool = df.select(cs.string() | cs.boolean())
# Exclude columns
non_temporal = df.select(cs.all() & ~cs.temporal())Advanced Selector Combinations
# Complex selector logic
result = df.select(
cs.numeric() & ~cs.float(), # Integer columns only
cs.starts_with("is_") | cs.ends_with("_date"), # Boolean flags or dates
cs.by_index(0, -1) # First and last columns
)Install with Tessl CLI
npx tessl i tessl/pypi-polars-u64-idx@1.33.1