Struct PyDataFrame

#[repr(transparent)]
pub struct PyDataFrame {
    pub df: DataFrame,
}

Fields

df: DataFrame

Implementations

impl PyDataFrame

pub fn from_rows( py: Python<'_>, data: Vec<Wrap<Row<'_>>>, schema: Option<Wrap<Schema>>, infer_schema_length: Option<usize>, ) -> PyResult<Self>

pub fn from_dicts( py: Python<'_>, data: &Bound<'_, PyAny>, schema: Option<Wrap<Schema>>, schema_overrides: Option<Wrap<Schema>>, strict: bool, infer_schema_length: Option<usize>, ) -> PyResult<Self>

pub fn from_arrow_record_batches( py: Python<'_>, rb: Vec<Bound<'_, PyAny>>, schema: Bound<'_, PyAny>, ) -> PyResult<Self>

impl PyDataFrame

pub fn row_tuple<'py>( &self, idx: i64, py: Python<'py>, ) -> PyResult<Bound<'py, PyTuple>>

pub fn row_tuples<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyList>>

pub fn to_arrow( &mut self, py: Python<'_>, compat_level: PyCompatLevel, ) -> PyResult<Vec<PyObject>>

pub fn to_pandas(&mut self, py: Python<'_>) -> PyResult<Vec<PyObject>>

Create a Vec of PyArrow RecordBatch instances.

Note this will give bad results for columns with dtype pl.Object, since those can’t be converted correctly via PyArrow. The calling Python code should make sure these are not included.

impl PyDataFrame

pub fn __init__(columns: Vec<PySeries>) -> PyResult<Self>

pub fn estimated_size(&self) -> usize

pub fn dtype_strings(&self) -> Vec<String>

pub fn add(&self, py: Python<'_>, s: &PySeries) -> PyResult<Self>

pub fn sub(&self, py: Python<'_>, s: &PySeries) -> PyResult<Self>

pub fn div(&self, py: Python<'_>, s: &PySeries) -> PyResult<Self>

pub fn mul(&self, py: Python<'_>, s: &PySeries) -> PyResult<Self>

pub fn rem(&self, py: Python<'_>, s: &PySeries) -> PyResult<Self>

pub fn add_df(&self, py: Python<'_>, s: &Self) -> PyResult<Self>

pub fn sub_df(&self, py: Python<'_>, s: &Self) -> PyResult<Self>

pub fn div_df(&self, py: Python<'_>, s: &Self) -> PyResult<Self>

pub fn mul_df(&self, py: Python<'_>, s: &Self) -> PyResult<Self>

pub fn rem_df(&self, py: Python<'_>, s: &Self) -> PyResult<Self>

pub fn sample_n( &self, py: Python<'_>, n: &PySeries, with_replacement: bool, shuffle: bool, seed: Option<u64>, ) -> PyResult<Self>

pub fn sample_frac( &self, py: Python<'_>, frac: &PySeries, with_replacement: bool, shuffle: bool, seed: Option<u64>, ) -> PyResult<Self>

pub fn rechunk(&self, py: Python<'_>) -> Self

pub fn as_str(&self) -> String

Format DataFrame as String

pub fn get_columns(&self) -> Vec<PySeries>

pub fn columns(&self) -> Vec<&str>

Get column names

pub fn set_column_names(&mut self, names: Vec<PyBackedStr>) -> PyResult<()>

set column names

pub fn dtypes<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyList>>

Get datatypes

pub fn n_chunks(&self) -> usize

pub fn shape(&self) -> (usize, usize)

pub fn height(&self) -> usize

pub fn width(&self) -> usize

pub fn is_empty(&self) -> bool

pub fn hstack(&self, py: Python<'_>, columns: Vec<PySeries>) -> PyResult<Self>

pub fn hstack_mut( &mut self, py: Python<'_>, columns: Vec<PySeries>, ) -> PyResult<()>

pub fn vstack(&self, py: Python<'_>, other: &PyDataFrame) -> PyResult<Self>

pub fn vstack_mut( &mut self, py: Python<'_>, other: &PyDataFrame, ) -> PyResult<()>

pub fn extend(&mut self, py: Python<'_>, other: &PyDataFrame) -> PyResult<()>

pub fn drop_in_place(&mut self, name: &str) -> PyResult<PySeries>

pub fn to_series(&self, index: isize) -> PyResult<PySeries>

pub fn get_column_index(&self, name: &str) -> PyResult<usize>

pub fn get_column(&self, name: &str) -> PyResult<PySeries>

pub fn select( &self, py: Python<'_>, columns: Vec<PyBackedStr>, ) -> PyResult<Self>

pub fn gather( &self, py: Python<'_>, indices: Wrap<Vec<IdxSize>>, ) -> PyResult<Self>

pub fn gather_with_series( &self, py: Python<'_>, indices: &PySeries, ) -> PyResult<Self>

pub fn replace(&mut self, column: &str, new_col: PySeries) -> PyResult<()>

pub fn replace_column( &mut self, index: usize, new_column: PySeries, ) -> PyResult<()>

pub fn insert_column(&mut self, index: usize, column: PySeries) -> PyResult<()>

pub fn slice(&self, py: Python<'_>, offset: i64, length: Option<usize>) -> Self

pub fn head(&self, py: Python<'_>, n: usize) -> Self

pub fn tail(&self, py: Python<'_>, n: usize) -> Self

pub fn is_unique(&self, py: Python<'_>) -> PyResult<PySeries>

pub fn is_duplicated(&self, py: Python<'_>) -> PyResult<PySeries>

pub fn equals( &self, py: Python<'_>, other: &PyDataFrame, null_equal: bool, ) -> bool

pub fn with_row_index( &self, py: Python<'_>, name: &str, offset: Option<IdxSize>, ) -> PyResult<Self>

pub fn _to_metadata(&self) -> Self

pub fn group_by_map_groups( &self, by: Vec<PyBackedStr>, lambda: PyObject, maintain_order: bool, ) -> PyResult<Self>

pub fn clone(&self) -> Self

pub fn unpivot( &self, py: Python<'_>, on: Vec<PyBackedStr>, index: Vec<PyBackedStr>, value_name: Option<&str>, variable_name: Option<&str>, ) -> PyResult<Self>

pub fn pivot_expr( &self, py: Python<'_>, on: Vec<String>, index: Option<Vec<String>>, values: Option<Vec<String>>, maintain_order: bool, sort_columns: bool, aggregate_expr: Option<PyExpr>, separator: Option<&str>, ) -> PyResult<Self>

pub fn partition_by( &self, py: Python<'_>, by: Vec<String>, maintain_order: bool, include_key: bool, ) -> PyResult<Vec<Self>>

pub fn lazy(&self) -> PyLazyFrame

pub fn to_dummies( &self, py: Python<'_>, columns: Option<Vec<String>>, separator: Option<&str>, drop_first: bool, ) -> PyResult<Self>

pub fn null_count(&self, py: Python<'_>) -> Self

pub fn map_rows( &mut self, lambda: Bound<'_, PyAny>, output_type: Option<Wrap<DataType>>, inference_size: usize, ) -> PyResult<(PyObject, bool)>

pub fn shrink_to_fit(&mut self, py: Python<'_>)

pub fn hash_rows( &mut self, py: Python<'_>, k0: u64, k1: u64, k2: u64, k3: u64, ) -> PyResult<PySeries>

pub fn transpose( &mut self, py: Python<'_>, keep_names_as: Option<&str>, column_names: &Bound<'_, PyAny>, ) -> PyResult<Self>

pub fn upsample( &self, py: Python<'_>, by: Vec<String>, index_column: &str, every: &str, stable: bool, ) -> PyResult<Self>

pub fn to_struct( &self, py: Python<'_>, name: &str, invalid_indices: Vec<usize>, ) -> PySeries

pub fn clear(&self, py: Python<'_>) -> Self

pub fn into_raw_parts(&mut self) -> (usize, usize, usize)

impl PyDataFrame

pub fn read_csv( py: Python<'_>, py_f: Bound<'_, PyAny>, infer_schema_length: Option<usize>, chunk_size: usize, has_header: bool, ignore_errors: bool, n_rows: Option<usize>, skip_rows: usize, skip_lines: usize, projection: Option<Vec<usize>>, separator: &str, rechunk: bool, columns: Option<Vec<String>>, encoding: Wrap<CsvEncoding>, n_threads: Option<usize>, path: Option<String>, overwrite_dtype: Option<Vec<(PyBackedStr, Wrap<DataType>)>>, overwrite_dtype_slice: Option<Vec<Wrap<DataType>>>, low_memory: bool, comment_prefix: Option<&str>, quote_char: Option<&str>, null_values: Option<Wrap<NullValues>>, missing_utf8_is_empty_string: bool, try_parse_dates: bool, skip_rows_after_header: usize, row_index: Option<(String, IdxSize)>, eol_char: &str, raise_if_empty: bool, truncate_ragged_lines: bool, decimal_comma: bool, schema: Option<Wrap<Schema>>, ) -> PyResult<Self>

pub fn read_parquet( py: Python<'_>, py_f: PyObject, columns: Option<Vec<String>>, projection: Option<Vec<usize>>, n_rows: Option<usize>, row_index: Option<(String, IdxSize)>, low_memory: bool, parallel: Wrap<ParallelStrategy>, use_statistics: bool, rechunk: bool, ) -> PyResult<Self>

pub fn read_json( py: Python<'_>, py_f: Bound<'_, PyAny>, infer_schema_length: Option<usize>, schema: Option<Wrap<Schema>>, schema_overrides: Option<Wrap<Schema>>, ) -> PyResult<Self>

pub fn read_ndjson( py: Python<'_>, py_f: Bound<'_, PyAny>, ignore_errors: bool, schema: Option<Wrap<Schema>>, schema_overrides: Option<Wrap<Schema>>, ) -> PyResult<Self>

pub fn read_ipc( py: Python<'_>, py_f: Bound<'_, PyAny>, columns: Option<Vec<String>>, projection: Option<Vec<usize>>, n_rows: Option<usize>, row_index: Option<(String, IdxSize)>, memory_map: bool, ) -> PyResult<Self>

pub fn read_ipc_stream( py: Python<'_>, py_f: Bound<'_, PyAny>, columns: Option<Vec<String>>, projection: Option<Vec<usize>>, n_rows: Option<usize>, row_index: Option<(String, IdxSize)>, rechunk: bool, ) -> PyResult<Self>

pub fn read_avro( py: Python<'_>, py_f: PyObject, columns: Option<Vec<String>>, projection: Option<Vec<usize>>, n_rows: Option<usize>, ) -> PyResult<Self>

pub fn write_csv( &mut self, py: Python<'_>, py_f: PyObject, include_bom: bool, include_header: bool, separator: u8, line_terminator: String, quote_char: u8, batch_size: NonZeroUsize, datetime_format: Option<String>, date_format: Option<String>, time_format: Option<String>, float_scientific: Option<bool>, float_precision: Option<usize>, null_value: Option<String>, quote_style: Option<Wrap<QuoteStyle>>, cloud_options: Option<Vec<(String, String)>>, credential_provider: Option<PyObject>, retries: usize, ) -> PyResult<()>

pub fn write_parquet( &mut self, py: Python<'_>, py_f: PyObject, compression: &str, compression_level: Option<i32>, statistics: Wrap<StatisticsOptions>, row_group_size: Option<usize>, data_page_size: Option<usize>, partition_by: Option<Vec<String>>, partition_chunk_size_bytes: usize, cloud_options: Option<Vec<(String, String)>>, credential_provider: Option<PyObject>, retries: usize, ) -> PyResult<()>

pub fn write_json(&mut self, py_f: PyObject) -> PyResult<()>

pub fn write_ndjson(&mut self, py_f: PyObject) -> PyResult<()>

pub fn write_ipc( &mut self, py: Python<'_>, py_f: PyObject, compression: Wrap<Option<IpcCompression>>, compat_level: PyCompatLevel, cloud_options: Option<Vec<(String, String)>>, credential_provider: Option<PyObject>, retries: usize, ) -> PyResult<()>

pub fn write_ipc_stream( &mut self, py: Python<'_>, py_f: PyObject, compression: Wrap<Option<IpcCompression>>, compat_level: PyCompatLevel, ) -> PyResult<()>

pub fn write_avro( &mut self, py: Python<'_>, py_f: PyObject, compression: Wrap<Option<AvroCompression>>, name: String, ) -> PyResult<()>

impl PyDataFrame

pub fn serialize_json(&mut self, py: Python<'_>, py_f: PyObject) -> PyResult<()>

Serialize into a JSON string.

pub fn deserialize_json( py: Python<'_>, py_f: Bound<'_, PyAny>, ) -> PyResult<Self>

Deserialize a file-like object containing JSON string data into a DataFrame.

Trait Implementations

impl Clone for PyDataFrame

fn clone(&self) -> PyDataFrame

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl From<DataFrame> for PyDataFrame

fn from(df: DataFrame) -> Self

Converts to this type from the input type.

impl IntoPy<Py<PyAny>> for PyDataFrame

fn into_py(self, py: Python<'_>) -> PyObject

👎Deprecated since 0.23.0: IntoPy is going to be replaced by IntoPyObject. See the migration guide (https://pyo3.rs/v0.23.0/migration) for more information.

Performs the conversion.

impl<'py> IntoPyObject<'py> for PyDataFrame

type Target = PyDataFrame

The Python output type

type Output = Bound<'py, <PyDataFrame as IntoPyObject<'py>>::Target>

The smart pointer type to use.

type Error = PyErr

The type returned in the event of a conversion error.

fn into_pyobject( self, py: Python<'py>, ) -> Result<<Self as IntoPyObject<'_>>::Output, <Self as IntoPyObject<'_>>::Error>

Performs the conversion.

impl PyClass for PyDataFrame

type Frozen = False

Whether the pyclass is frozen.

impl PyClassImpl for PyDataFrame

const IS_BASETYPE: bool = false

#[pyclass(subclass)]

const IS_SUBCLASS: bool = false

#[pyclass(extends=…)]

const IS_MAPPING: bool = false

#[pyclass(mapping)]

const IS_SEQUENCE: bool = false

#[pyclass(sequence)]

type BaseType = PyAny

Base class

type ThreadChecker = SendablePyClass<PyDataFrame>

This handles following two situations:

type Inventory = Pyo3MethodsInventoryForPyDataFrame

type PyClassMutability = <<PyAny as PyClassBaseType>::PyClassMutability as PyClassMutability>::MutableChild

Immutable or mutable

type Dict = PyClassDummySlot

Specify this class has #[pyclass(dict)] or not.

type WeakRef = PyClassDummySlot

Specify this class has #[pyclass(weakref)] or not.

type BaseNativeType = PyAny

The closest native ancestor. This is PyAny by default, and when you declare #[pyclass(extends=PyDict)], it’s PyDict.

fn items_iter() -> PyClassItemsIter

fn doc(py: Python<'_>) -> PyResult<&'static CStr>

Rendered class doc

fn lazy_type_object() -> &'static LazyTypeObject<Self>

fn dict_offset() -> Option<isize>

fn weaklist_offset() -> Option<isize>

impl PyClassNewTextSignature<PyDataFrame> for PyClassImplCollector<PyDataFrame>

fn new_text_signature(self) -> Option<&'static str>

impl<'a, 'py> PyFunctionArgument<'a, 'py> for &'a PyDataFrame

type Holder = Option<PyRef<'py, PyDataFrame>>

fn extract( obj: &'a Bound<'py, PyAny>, holder: &'a mut Self::Holder, ) -> PyResult<Self>

impl<'a, 'py> PyFunctionArgument<'a, 'py> for &'a mut PyDataFrame

type Holder = Option<PyRefMut<'py, PyDataFrame>>

fn extract( obj: &'a Bound<'py, PyAny>, holder: &'a mut Self::Holder, ) -> PyResult<Self>

impl PyTypeInfo for PyDataFrame

const NAME: &'static str = "PyDataFrame"

Class name.

const MODULE: Option<&'static str> = ::core::option::Option::None

Module name, if any.

fn type_object_raw(py: Python<'_>) -> *mut PyTypeObject

Returns the PyTypeObject instance for this type.

fn type_object(py: Python<'_>) -> Bound<'_, PyType>

Returns the safe abstraction over the type object.

fn type_object_bound(py: Python<'_>) -> Bound<'_, PyType>

👎Deprecated since 0.23.0: renamed to PyTypeInfo::type_object

Deprecated name for PyTypeInfo::type_object.

fn is_type_of(object: &Bound<'_, PyAny>) -> bool

Checks if object is an instance of this type or a subclass of this type.

fn is_type_of_bound(object: &Bound<'_, PyAny>) -> bool

👎Deprecated since 0.23.0: renamed to PyTypeInfo::is_type_of

Deprecated name for PyTypeInfo::is_type_of.

fn is_exact_type_of(object: &Bound<'_, PyAny>) -> bool

Checks if object is an instance of this type.

fn is_exact_type_of_bound(object: &Bound<'_, PyAny>) -> bool

👎Deprecated since 0.23.0: renamed to PyTypeInfo::is_exact_type_of

Deprecated name for PyTypeInfo::is_exact_type_of.

impl DerefToPyAny for PyDataFrame