Python Client API

Search Shortcut cmd + k | ctrl + k

Documentation / Client APIs / Python

Python Client API

duckdb.threadsafety bool¶: Indicates that this package is threadsafe

duckdb.apilevel int¶: Indicates which Python DBAPI version this package implements

duckdb.paramstyle str¶: Indicates which parameter style duckdb supports

duckdb.default_connection duckdb.DuckDBPyConnection¶: The connection that is used by default if you don’t explicitly pass one to the root methods in this module

class duckdb.BinaryValue(object: Any)¶: Bases: Value

exception duckdb.BinderException¶: Bases: ProgrammingError

class duckdb.BitValue(object: Any)¶: Bases: Value

class duckdb.BlobValue(object: Any)¶: Bases: Value

class duckdb.BooleanValue(object: Any)¶: Bases: Value

duckdb.CaseExpression(condition: duckdb.duckdb.Expression, value: duckdb.duckdb.Expression) → duckdb.duckdb.Expression¶

exception duckdb.CatalogException¶: Bases: ProgrammingError

duckdb.CoalesceOperator(*args) → duckdb.duckdb.Expression¶

duckdb.ColumnExpression(name: str) → duckdb.duckdb.Expression¶: Create a column reference from the provided column name

exception duckdb.ConnectionException¶: Bases: OperationalError

duckdb.ConstantExpression(value: object) → duckdb.duckdb.Expression¶: Create a constant expression from the provided value

exception duckdb.ConstraintException¶: Bases: IntegrityError

exception duckdb.ConversionException¶: Bases: DataError

exception duckdb.DataError¶: Bases: DatabaseError

class duckdb.DateValue(object: Any)¶: Bases: Value

class duckdb.DecimalValue(object: Any, width: int, scale: int)¶: Bases: Value

class duckdb.DoubleValue(object: Any)¶: Bases: Value

class duckdb.DuckDBPyConnection¶

Bases: pybind11_object

append(self: duckdb.duckdb.DuckDBPyConnection, table_name: str, df: pandas.DataFrame, *, by_name: bool = False) → duckdb.duckdb.DuckDBPyConnection¶: Append the passed DataFrame to the named table

array_type(self: duckdb.duckdb.DuckDBPyConnection, type: duckdb.duckdb.typing.DuckDBPyType, size: int) → duckdb.duckdb.typing.DuckDBPyType¶: Create an array type object of ‘type’

arrow(self: duckdb.duckdb.DuckDBPyConnection, rows_per_batch: int = 1000000) → pyarrow.lib.Table¶: Fetch a result as Arrow table following execute()

begin(self: duckdb.duckdb.DuckDBPyConnection) → duckdb.duckdb.DuckDBPyConnection¶: Start a new transaction

checkpoint(self: duckdb.duckdb.DuckDBPyConnection) → duckdb.duckdb.DuckDBPyConnection¶: Synchronizes data in the write-ahead log (WAL) to the database data file (no-op for in-memory connections)

close(self: duckdb.duckdb.DuckDBPyConnection) → None¶: Close the connection

commit(self: duckdb.duckdb.DuckDBPyConnection) → duckdb.duckdb.DuckDBPyConnection¶: Commit changes performed within a transaction

create_function(self: duckdb.duckdb.DuckDBPyConnection, name: str, function: Callable, parameters: object = None, return_type: duckdb.duckdb.typing.DuckDBPyType = None, *, type: duckdb.duckdb.functional.PythonUDFType = <PythonUDFType.NATIVE: 0>, null_handling: duckdb.duckdb.functional.FunctionNullHandling = <FunctionNullHandling.DEFAULT: 0>, exception_handling: duckdb.duckdb.PythonExceptionHandling = <PythonExceptionHandling.DEFAULT: 0>, side_effects: bool = False) → duckdb.duckdb.DuckDBPyConnection¶: Create a DuckDB function out of the passing in Python function so it can be used in queries

cursor(self: duckdb.duckdb.DuckDBPyConnection) → duckdb.duckdb.DuckDBPyConnection¶: Create a duplicate of the current connection

decimal_type(self: duckdb.duckdb.DuckDBPyConnection, width: int, scale: int) → duckdb.duckdb.typing.DuckDBPyType¶: Create a decimal type with ‘width’ and ‘scale’

property description¶: Get result set attributes, mainly column names

df(self: duckdb.duckdb.DuckDBPyConnection, *, date_as_object: bool = False) → pandas.DataFrame¶: Fetch a result as DataFrame following execute()

dtype(self: duckdb.duckdb.DuckDBPyConnection, type_str: str) → duckdb.duckdb.typing.DuckDBPyType¶: Create a type object by parsing the ‘type_str’ string

duplicate(self: duckdb.duckdb.DuckDBPyConnection) → duckdb.duckdb.DuckDBPyConnection¶: Create a duplicate of the current connection

enum_type(self: duckdb.duckdb.DuckDBPyConnection, name: str, type: duckdb.duckdb.typing.DuckDBPyType, values: list) → duckdb.duckdb.typing.DuckDBPyType¶: Create an enum type of underlying ‘type’, consisting of the list of ‘values’

execute(self: duckdb.duckdb.DuckDBPyConnection, query: object, parameters: object = None) → duckdb.duckdb.DuckDBPyConnection¶: Execute the given SQL query, optionally using prepared statements with parameters set

executemany(self: duckdb.duckdb.DuckDBPyConnection, query: object, parameters: object = None) → duckdb.duckdb.DuckDBPyConnection¶: Execute the given prepared statement multiple times using the list of parameter sets in parameters

extract_statements(self: duckdb.duckdb.DuckDBPyConnection, query: str) → list¶: Parse the query string and extract the Statement object(s) produced

fetch_arrow_table(self: duckdb.duckdb.DuckDBPyConnection, rows_per_batch: int = 1000000) → pyarrow.lib.Table¶: Fetch a result as Arrow table following execute()

fetch_df(self: duckdb.duckdb.DuckDBPyConnection, *, date_as_object: bool = False) → pandas.DataFrame¶: Fetch a result as DataFrame following execute()

fetch_df_chunk(self: duckdb.duckdb.DuckDBPyConnection, vectors_per_chunk: int = 1, *, date_as_object: bool = False) → pandas.DataFrame¶: Fetch a chunk of the result as DataFrame following execute()

fetch_record_batch(self: duckdb.duckdb.DuckDBPyConnection, rows_per_batch: int = 1000000) → pyarrow.lib.RecordBatchReader¶: Fetch an Arrow RecordBatchReader following execute()

fetchall(self: duckdb.duckdb.DuckDBPyConnection) → list¶: Fetch all rows from a result following execute

fetchdf(self: duckdb.duckdb.DuckDBPyConnection, *, date_as_object: bool = False) → pandas.DataFrame¶: Fetch a result as DataFrame following execute()

fetchmany(self: duckdb.duckdb.DuckDBPyConnection, size: int = 1) → list¶: Fetch the next set of rows from a result following execute

fetchnumpy(self: duckdb.duckdb.DuckDBPyConnection) → dict¶: Fetch a result as list of NumPy arrays following execute

fetchone(self: duckdb.duckdb.DuckDBPyConnection) → Optional[tuple]¶: Fetch a single row from a result following execute

filesystem_is_registered(self: duckdb.duckdb.DuckDBPyConnection, name: str) → bool¶: Check if a filesystem with the provided name is currently registered

from_arrow(self: duckdb.duckdb.DuckDBPyConnection, arrow_object: object) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from an Arrow object

from_csv_auto(self: duckdb.duckdb.DuckDBPyConnection, path_or_buffer: object, **kwargs) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the CSV file in ‘name’

from_df(self: duckdb.duckdb.DuckDBPyConnection, df: pandas.DataFrame) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the DataFrame in df

from_parquet(*args, **kwargs)¶

Overloaded function.

from_parquet(self: duckdb.duckdb.DuckDBPyConnection, file_glob: str, binary_as_string: bool = False, *, file_row_number: bool = False, filename: bool = False, hive_partitioning: bool = False, union_by_name: bool = False, compression: object = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from the Parquet files in file_glob

from_parquet(self: duckdb.duckdb.DuckDBPyConnection, file_globs: list[str], binary_as_string: bool = False, *, file_row_number: bool = False, filename: bool = False, hive_partitioning: bool = False, union_by_name: bool = False, compression: object = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from the Parquet files in file_globs

from_query(self: duckdb.duckdb.DuckDBPyConnection, query: object, *, alias: str = '', params: object = None) → duckdb.duckdb.DuckDBPyRelation¶: Run a SQL query. If it is a SELECT statement, create a relation object from the given SQL query, otherwise run the query as-is.

from_substrait(self: duckdb.duckdb.DuckDBPyConnection, proto: bytes) → duckdb.duckdb.DuckDBPyRelation¶: Create a query object from protobuf plan

from_substrait_json(self: duckdb.duckdb.DuckDBPyConnection, json: str) → duckdb.duckdb.DuckDBPyRelation¶: Create a query object from a JSON protobuf plan

get_substrait(self: duckdb.duckdb.DuckDBPyConnection, query: str, *, enable_optimizer: bool = True) → duckdb.duckdb.DuckDBPyRelation¶: Serialize a query to protobuf

get_substrait_json(self: duckdb.duckdb.DuckDBPyConnection, query: str, *, enable_optimizer: bool = True) → duckdb.duckdb.DuckDBPyRelation¶: Serialize a query to protobuf on the JSON format

get_table_names(self: duckdb.duckdb.DuckDBPyConnection, query: str) → set[str]¶: Extract the required table names from a query

install_extension(self: duckdb.duckdb.DuckDBPyConnection, extension: str, *, force_install: bool = False, repository: object = None, repository_url: object = None, version: object = None) → None¶: Install an extension by name, with an optional version and/or repository to get the extension from

interrupt(self: duckdb.duckdb.DuckDBPyConnection) → None¶: Interrupt pending operations

list_filesystems(self: duckdb.duckdb.DuckDBPyConnection) → list¶: List registered filesystems, including builtin ones

list_type(self: duckdb.duckdb.DuckDBPyConnection, type: duckdb.duckdb.typing.DuckDBPyType) → duckdb.duckdb.typing.DuckDBPyType¶: Create a list type object of ‘type’

load_extension(self: duckdb.duckdb.DuckDBPyConnection, extension: str) → None¶: Load an installed extension

map_type(self: duckdb.duckdb.DuckDBPyConnection, key: duckdb.duckdb.typing.DuckDBPyType, value: duckdb.duckdb.typing.DuckDBPyType) → duckdb.duckdb.typing.DuckDBPyType¶: Create a map type object from ‘key_type’ and ‘value_type’

pl(self: duckdb.duckdb.DuckDBPyConnection, rows_per_batch: int = 1000000) → duckdb::PolarsDataFrame¶: Fetch a result as Polars DataFrame following execute()

query(self: duckdb.duckdb.DuckDBPyConnection, query: object, *, alias: str = '', params: object = None) → duckdb.duckdb.DuckDBPyRelation¶: Run a SQL query. If it is a SELECT statement, create a relation object from the given SQL query, otherwise run the query as-is.

read_csv(self: duckdb.duckdb.DuckDBPyConnection, path_or_buffer: object, **kwargs) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the CSV file in ‘name’

read_json(self: duckdb.duckdb.DuckDBPyConnection, path_or_buffer: object, *, columns: Optional[object] = None, sample_size: Optional[object] = None, maximum_depth: Optional[object] = None, records: Optional[str] = None, format: Optional[str] = None, date_format: Optional[object] = None, timestamp_format: Optional[object] = None, compression: Optional[object] = None, maximum_object_size: Optional[object] = None, ignore_errors: Optional[object] = None, convert_strings_to_integers: Optional[object] = None, field_appearance_threshold: Optional[object] = None, map_inference_threshold: Optional[object] = None, maximum_sample_files: Optional[object] = None, filename: Optional[object] = None, hive_partitioning: Optional[object] = None, union_by_name: Optional[object] = None, hive_types: Optional[object] = None, hive_types_autocast: Optional[object] = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the JSON file in ‘name’

read_parquet(*args, **kwargs)¶

Overloaded function.

read_parquet(self: duckdb.duckdb.DuckDBPyConnection, file_glob: str, binary_as_string: bool = False, *, file_row_number: bool = False, filename: bool = False, hive_partitioning: bool = False, union_by_name: bool = False, compression: object = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from the Parquet files in file_glob

read_parquet(self: duckdb.duckdb.DuckDBPyConnection, file_globs: list[str], binary_as_string: bool = False, *, file_row_number: bool = False, filename: bool = False, hive_partitioning: bool = False, union_by_name: bool = False, compression: object = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from the Parquet files in file_globs

register(self: duckdb.duckdb.DuckDBPyConnection, view_name: str, python_object: object) → duckdb.duckdb.DuckDBPyConnection¶: Register the passed Python Object value for querying with a view

register_filesystem(self: duckdb.duckdb.DuckDBPyConnection, filesystem: fsspec.AbstractFileSystem) → None¶: Register a fsspec compliant filesystem

remove_function(self: duckdb.duckdb.DuckDBPyConnection, name: str) → duckdb.duckdb.DuckDBPyConnection¶: Remove a previously created function

rollback(self: duckdb.duckdb.DuckDBPyConnection) → duckdb.duckdb.DuckDBPyConnection¶: Roll back changes performed within a transaction

row_type(self: duckdb.duckdb.DuckDBPyConnection, fields: object) → duckdb.duckdb.typing.DuckDBPyType¶: Create a struct type object from ‘fields’

property rowcount¶: Get result set row count

sql(self: duckdb.duckdb.DuckDBPyConnection, query: object, *, alias: str = '', params: object = None) → duckdb.duckdb.DuckDBPyRelation¶: Run a SQL query. If it is a SELECT statement, create a relation object from the given SQL query, otherwise run the query as-is.

sqltype(self: duckdb.duckdb.DuckDBPyConnection, type_str: str) → duckdb.duckdb.typing.DuckDBPyType¶: Create a type object by parsing the ‘type_str’ string

string_type(self: duckdb.duckdb.DuckDBPyConnection, collation: str = '') → duckdb.duckdb.typing.DuckDBPyType¶: Create a string type with an optional collation

struct_type(self: duckdb.duckdb.DuckDBPyConnection, fields: object) → duckdb.duckdb.typing.DuckDBPyType¶: Create a struct type object from ‘fields’

table(self: duckdb.duckdb.DuckDBPyConnection, table_name: str) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object for the named table

table_function(self: duckdb.duckdb.DuckDBPyConnection, name: str, parameters: object = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the named table function with given parameters

tf(self: duckdb.duckdb.DuckDBPyConnection) → dict¶: Fetch a result as dict of TensorFlow Tensors following execute()

torch(self: duckdb.duckdb.DuckDBPyConnection) → dict¶: Fetch a result as dict of PyTorch Tensors following execute()

type(self: duckdb.duckdb.DuckDBPyConnection, type_str: str) → duckdb.duckdb.typing.DuckDBPyType¶: Create a type object by parsing the ‘type_str’ string

union_type(self: duckdb.duckdb.DuckDBPyConnection, members: object) → duckdb.duckdb.typing.DuckDBPyType¶: Create a union type object from ‘members’

unregister(self: duckdb.duckdb.DuckDBPyConnection, view_name: str) → duckdb.duckdb.DuckDBPyConnection¶: Unregister the view name

unregister_filesystem(self: duckdb.duckdb.DuckDBPyConnection, name: str) → None¶: Unregister a filesystem

values(self: duckdb.duckdb.DuckDBPyConnection, values: object) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the passed values

view(self: duckdb.duckdb.DuckDBPyConnection, view_name: str) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object for the named view

class duckdb.DuckDBPyRelation¶

Bases: pybind11_object

aggregate(self: duckdb.duckdb.DuckDBPyRelation, aggr_expr: object, group_expr: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Compute the aggregate aggr_expr by the optional groups group_expr on the relation

property alias¶: Get the name of the current alias

any_value(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Returns the first non-null value from a given column

apply(self: duckdb.duckdb.DuckDBPyRelation, function_name: str, function_aggr: str, group_expr: str = '', function_parameter: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Compute the function of a single column or a list of columns by the optional groups on the relation

arg_max(self: duckdb.duckdb.DuckDBPyRelation, arg_column: str, value_column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Finds the row with the maximum value for a value column and returns the value of that row for an argument column

arg_min(self: duckdb.duckdb.DuckDBPyRelation, arg_column: str, value_column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Finds the row with the minimum value for a value column and returns the value of that row for an argument column

arrow(self: duckdb.duckdb.DuckDBPyRelation, batch_size: int = 1000000) → pyarrow.lib.Table¶: Execute and fetch all rows as an Arrow Table

avg(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the average on a given column

bit_and(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the bitwise AND of all bits present in a given column

bit_or(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the bitwise OR of all bits present in a given column

bit_xor(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the bitwise XOR of all bits present in a given column

bitstring_agg(self: duckdb.duckdb.DuckDBPyRelation, column: str, min: Optional[object] = None, max: Optional[object] = None, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes a bitstring with bits set for each distinct value in a given column

bool_and(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the logical AND of all values present in a given column

bool_or(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the logical OR of all values present in a given column

close(self: duckdb.duckdb.DuckDBPyRelation) → None¶: Closes the result

property columns¶: Return a list containing the names of the columns of the relation.

count(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the number of elements present in a given column

create(self: duckdb.duckdb.DuckDBPyRelation, table_name: str) → None¶: Creates a new table named table_name with the contents of the relation object

create_view(self: duckdb.duckdb.DuckDBPyRelation, view_name: str, replace: bool = True) → duckdb.duckdb.DuckDBPyRelation¶: Creates a view named view_name that refers to the relation object

cume_dist(self: duckdb.duckdb.DuckDBPyRelation, window_spec: str, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the cumulative distribution within the partition

dense_rank(self: duckdb.duckdb.DuckDBPyRelation, window_spec: str, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the dense rank within the partition

describe(self: duckdb.duckdb.DuckDBPyRelation) → duckdb.duckdb.DuckDBPyRelation¶: Gives basic statistics (e.g., min, max) and if `NULL` exists for each column of the relation.

property description¶: Return the description of the result

df(self: duckdb.duckdb.DuckDBPyRelation, *, date_as_object: bool = False) → pandas.DataFrame¶: Execute and fetch all rows as a pandas DataFrame

distinct(self: duckdb.duckdb.DuckDBPyRelation) → duckdb.duckdb.DuckDBPyRelation¶: Retrieve distinct rows from this relation object

property dtypes¶: Return a list containing the types of the columns of the relation.

except_(self: duckdb.duckdb.DuckDBPyRelation, other_rel: duckdb.duckdb.DuckDBPyRelation) → duckdb.duckdb.DuckDBPyRelation¶: Create the set except of this relation object with another relation object in other_rel

execute(self: duckdb.duckdb.DuckDBPyRelation) → duckdb.duckdb.DuckDBPyRelation¶: Transform the relation into a result set

explain(self: duckdb.duckdb.DuckDBPyRelation, type: duckdb.duckdb.ExplainType = 'standard') → str¶

favg(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the average of all values present in a given column using a more accurate floating point summation (Kahan Sum)

fetch_arrow_reader(self: duckdb.duckdb.DuckDBPyRelation, batch_size: int = 1000000) → pyarrow.lib.RecordBatchReader¶: Execute and return an Arrow Record Batch Reader that yields all rows

fetch_arrow_table(self: duckdb.duckdb.DuckDBPyRelation, batch_size: int = 1000000) → pyarrow.lib.Table¶: Execute and fetch all rows as an Arrow Table

fetch_df_chunk(self: duckdb.duckdb.DuckDBPyRelation, vectors_per_chunk: int = 1, *, date_as_object: bool = False) → pandas.DataFrame¶: Execute and fetch a chunk of the rows

fetchall(self: duckdb.duckdb.DuckDBPyRelation) → list¶: Execute and fetch all rows as a list of tuples

fetchdf(self: duckdb.duckdb.DuckDBPyRelation, *, date_as_object: bool = False) → pandas.DataFrame¶: Execute and fetch all rows as a pandas DataFrame

fetchmany(self: duckdb.duckdb.DuckDBPyRelation, size: int = 1) → list¶: Execute and fetch the next set of rows as a list of tuples

fetchnumpy(self: duckdb.duckdb.DuckDBPyRelation) → dict¶: Execute and fetch all rows as a Python dict mapping each column to one numpy arrays

fetchone(self: duckdb.duckdb.DuckDBPyRelation) → Optional[tuple]¶: Execute and fetch a single row as a tuple

filter(self: duckdb.duckdb.DuckDBPyRelation, filter_expr: object) → duckdb.duckdb.DuckDBPyRelation¶: Filter the relation object by the filter in filter_expr

first(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Returns the first value of a given column

first_value(self: duckdb.duckdb.DuckDBPyRelation, column: str, window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the first value within the group or partition

fsum(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the sum of all values present in a given column using a more accurate floating point summation (Kahan Sum)

geomean(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the geometric mean over all values present in a given column

histogram(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the histogram over all values present in a given column

insert(self: duckdb.duckdb.DuckDBPyRelation, values: object) → None¶: Inserts the given values into the relation

insert_into(self: duckdb.duckdb.DuckDBPyRelation, table_name: str) → None¶: Inserts the relation object into an existing table named table_name

intersect(self: duckdb.duckdb.DuckDBPyRelation, other_rel: duckdb.duckdb.DuckDBPyRelation) → duckdb.duckdb.DuckDBPyRelation¶: Create the set intersection of this relation object with another relation object in other_rel

join(self: duckdb.duckdb.DuckDBPyRelation, other_rel: duckdb.duckdb.DuckDBPyRelation, condition: object, how: str = 'inner') → duckdb.duckdb.DuckDBPyRelation¶: Join the relation object with another relation object in other_rel using the join condition expression in join_condition. Types supported are ‘inner’ and ‘left’

lag(self: duckdb.duckdb.DuckDBPyRelation, column: str, window_spec: str, offset: int = 1, default_value: str = 'NULL', ignore_nulls: bool = False, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the lag within the partition

last(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Returns the last value of a given column

last_value(self: duckdb.duckdb.DuckDBPyRelation, column: str, window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the last value within the group or partition

lead(self: duckdb.duckdb.DuckDBPyRelation, column: str, window_spec: str, offset: int = 1, default_value: str = 'NULL', ignore_nulls: bool = False, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the lead within the partition

limit(self: duckdb.duckdb.DuckDBPyRelation, n: int, offset: int = 0) → duckdb.duckdb.DuckDBPyRelation¶: Only retrieve the first n rows from this relation object, starting at offset

list(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Returns a list containing all values present in a given column

map(self: duckdb.duckdb.DuckDBPyRelation, map_function: Callable, *, schema: Optional[object] = None) → duckdb.duckdb.DuckDBPyRelation¶: Calls the passed function on the relation

max(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Returns the maximum value present in a given column

mean(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the average on a given column

median(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the median over all values present in a given column

min(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Returns the minimum value present in a given column

mode(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the mode over all values present in a given column

n_tile(self: duckdb.duckdb.DuckDBPyRelation, window_spec: str, num_buckets: int, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Divides the partition as equally as possible into num_buckets

nth_value(self: duckdb.duckdb.DuckDBPyRelation, column: str, window_spec: str, offset: int, ignore_nulls: bool = False, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the nth value within the partition

order(self: duckdb.duckdb.DuckDBPyRelation, order_expr: str) → duckdb.duckdb.DuckDBPyRelation¶: Reorder the relation object by order_expr

percent_rank(self: duckdb.duckdb.DuckDBPyRelation, window_spec: str, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the relative rank within the partition

pl(self: duckdb.duckdb.DuckDBPyRelation, batch_size: int = 1000000) → duckdb::PolarsDataFrame¶: Execute and fetch all rows as a Polars DataFrame

product(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Returns the product of all values present in a given column

project(self: duckdb.duckdb.DuckDBPyRelation, *args, groups: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Project the relation object by the projection in project_expr

quantile(self: duckdb.duckdb.DuckDBPyRelation, column: str, q: object = 0.5, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the exact quantile value for a given column

quantile_cont(self: duckdb.duckdb.DuckDBPyRelation, column: str, q: object = 0.5, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the interpolated quantile value for a given column

quantile_disc(self: duckdb.duckdb.DuckDBPyRelation, column: str, q: object = 0.5, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the exact quantile value for a given column

query(self: duckdb.duckdb.DuckDBPyRelation, virtual_table_name: str, sql_query: str) → duckdb.duckdb.DuckDBPyRelation¶: Run the given SQL query in sql_query on the view named virtual_table_name that refers to the relation object

rank(self: duckdb.duckdb.DuckDBPyRelation, window_spec: str, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the rank within the partition

rank_dense(self: duckdb.duckdb.DuckDBPyRelation, window_spec: str, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the dense rank within the partition

record_batch(self: duckdb.duckdb.DuckDBPyRelation, batch_size: int = 1000000) → pyarrow.lib.RecordBatchReader¶: Execute and return an Arrow Record Batch Reader that yields all rows

row_number(self: duckdb.duckdb.DuckDBPyRelation, window_spec: str, projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the row number within the partition

select(self: duckdb.duckdb.DuckDBPyRelation, *args, groups: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Project the relation object by the projection in project_expr

select_dtypes(self: duckdb.duckdb.DuckDBPyRelation, types: object) → duckdb.duckdb.DuckDBPyRelation¶: Select columns from the relation, by filtering based on type(s)

select_types(self: duckdb.duckdb.DuckDBPyRelation, types: object) → duckdb.duckdb.DuckDBPyRelation¶: Select columns from the relation, by filtering based on type(s)

set_alias(self: duckdb.duckdb.DuckDBPyRelation, alias: str) → duckdb.duckdb.DuckDBPyRelation¶: Rename the relation object to new alias

property shape¶: Tuple of # of rows, # of columns in relation.

show(self: duckdb.duckdb.DuckDBPyRelation, *, max_width: Optional[int] = None, max_rows: Optional[int] = None, max_col_width: Optional[int] = None, null_value: Optional[str] = None, render_mode: object = None) → None¶: Display a summary of the data

sort(self: duckdb.duckdb.DuckDBPyRelation, *args) → duckdb.duckdb.DuckDBPyRelation¶: Reorder the relation object by the provided expressions

sql_query(self: duckdb.duckdb.DuckDBPyRelation) → str¶: Get the SQL query that is equivalent to the relation

std(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the sample standard deviation for a given column

stddev(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the sample standard deviation for a given column

stddev_pop(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the population standard deviation for a given column

stddev_samp(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the sample standard deviation for a given column

string_agg(self: duckdb.duckdb.DuckDBPyRelation, column: str, sep: str = ',', groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Concatenates the values present in a given column with a separator

sum(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the sum of all values present in a given column

tf(self: duckdb.duckdb.DuckDBPyRelation) → dict¶: Fetch a result as dict of TensorFlow Tensors

to_arrow_table(self: duckdb.duckdb.DuckDBPyRelation, batch_size: int = 1000000) → pyarrow.lib.Table¶: Execute and fetch all rows as an Arrow Table

to_csv(self: duckdb.duckdb.DuckDBPyRelation, file_name: str, *, sep: object = None, na_rep: object = None, header: object = None, quotechar: object = None, escapechar: object = None, date_format: object = None, timestamp_format: object = None, quoting: object = None, encoding: object = None, compression: object = None, overwrite: object = None, per_thread_output: object = None, use_tmp_file: object = None, partition_by: object = None, write_partition_columns: object = None) → None¶: Write the relation object to a CSV file in ‘file_name’

to_df(self: duckdb.duckdb.DuckDBPyRelation, *, date_as_object: bool = False) → pandas.DataFrame¶: Execute and fetch all rows as a pandas DataFrame

to_parquet(self: duckdb.duckdb.DuckDBPyRelation, file_name: str, *, compression: object = None, field_ids: object = None, row_group_size_bytes: object = None, row_group_size: object = None) → None¶: Write the relation object to a Parquet file in ‘file_name’

to_table(self: duckdb.duckdb.DuckDBPyRelation, table_name: str) → None¶: Creates a new table named table_name with the contents of the relation object

to_view(self: duckdb.duckdb.DuckDBPyRelation, view_name: str, replace: bool = True) → duckdb.duckdb.DuckDBPyRelation¶: Creates a view named view_name that refers to the relation object

torch(self: duckdb.duckdb.DuckDBPyRelation) → dict¶: Fetch a result as dict of PyTorch Tensors

property type¶: Get the type of the relation.

property types¶: Return a list containing the types of the columns of the relation.

union(self: duckdb.duckdb.DuckDBPyRelation, union_rel: duckdb.duckdb.DuckDBPyRelation) → duckdb.duckdb.DuckDBPyRelation¶: Create the set union of this relation object with another relation object in other_rel

unique(self: duckdb.duckdb.DuckDBPyRelation, unique_aggr: str) → duckdb.duckdb.DuckDBPyRelation¶: Number of distinct values in a column.

value_counts(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the number of elements present in a given column, also projecting the original column

var(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the sample variance for a given column

var_pop(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the population variance for a given column

var_samp(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the sample variance for a given column

variance(self: duckdb.duckdb.DuckDBPyRelation, column: str, groups: str = '', window_spec: str = '', projected_columns: str = '') → duckdb.duckdb.DuckDBPyRelation¶: Computes the sample variance for a given column

write_csv(self: duckdb.duckdb.DuckDBPyRelation, file_name: str, *, sep: object = None, na_rep: object = None, header: object = None, quotechar: object = None, escapechar: object = None, date_format: object = None, timestamp_format: object = None, quoting: object = None, encoding: object = None, compression: object = None, overwrite: object = None, per_thread_output: object = None, use_tmp_file: object = None, partition_by: object = None, write_partition_columns: object = None) → None¶: Write the relation object to a CSV file in ‘file_name’

write_parquet(self: duckdb.duckdb.DuckDBPyRelation, file_name: str, *, compression: object = None, field_ids: object = None, row_group_size_bytes: object = None, row_group_size: object = None) → None¶: Write the relation object to a Parquet file in ‘file_name’

exception duckdb.Error¶: Bases: Exception

class duckdb.ExplainType¶

Bases: pybind11_object

Members:

STANDARD

ANALYZE

ANALYZE = <ExplainType.ANALYZE: 1>¶

STANDARD = <ExplainType.STANDARD: 0>¶

property name¶

property value¶

class duckdb.Expression¶

Bases: pybind11_object

alias(self: duckdb.duckdb.Expression, arg0: str) → duckdb.duckdb.Expression¶

Create a copy of this expression with the given alias.

Parameters:: name: The alias to use for the expression, this will affect how it can be referenced.
Returns:: Expression: self with an alias.

asc(self: duckdb.duckdb.Expression) → duckdb.duckdb.Expression¶: Set the order by modifier to ASCENDING.

cast(self: duckdb.duckdb.Expression, type: duckdb.duckdb.typing.DuckDBPyType) → duckdb.duckdb.Expression¶

Create a CastExpression to type from self

Parameters:: type: The type to cast to
Returns:: CastExpression: self::type

desc(self: duckdb.duckdb.Expression) → duckdb.duckdb.Expression¶: Set the order by modifier to DESCENDING.

isin(self: duckdb.duckdb.Expression, *args) → duckdb.duckdb.Expression¶

Return an IN expression comparing self to the input arguments.

Returns:: DuckDBPyExpression: The compare IN expression

isnotin(self: duckdb.duckdb.Expression, *args) → duckdb.duckdb.Expression¶

Return a NOT IN expression comparing self to the input arguments.

Returns:: DuckDBPyExpression: The compare NOT IN expression

isnotnull(self: duckdb.duckdb.Expression) → duckdb.duckdb.Expression¶

Create a binary IS NOT NULL expression from self

Returns:: DuckDBPyExpression: self IS NOT NULL

isnull(self: duckdb.duckdb.Expression) → duckdb.duckdb.Expression¶

Create a binary IS NULL expression from self

Returns:: DuckDBPyExpression: self IS NULL

nulls_first(self: duckdb.duckdb.Expression) → duckdb.duckdb.Expression¶: Set the NULL order by modifier to NULLS FIRST.

nulls_last(self: duckdb.duckdb.Expression) → duckdb.duckdb.Expression¶: Set the NULL order by modifier to NULLS LAST.

otherwise(self: duckdb.duckdb.Expression, value: duckdb.duckdb.Expression) → duckdb.duckdb.Expression¶

Add an ELSE <value> clause to the CaseExpression.

Parameters:: value: The value to use if none of the WHEN conditions are met.
Returns:: CaseExpression: self with an ELSE clause.

show(self: duckdb.duckdb.Expression) → None¶: Print the stringified version of the expression.

when(self: duckdb.duckdb.Expression, condition: duckdb.duckdb.Expression, value: duckdb.duckdb.Expression) → duckdb.duckdb.Expression¶

Add an additional WHEN <condition> THEN <value> clause to the CaseExpression.

Parameters:: condition: The condition that must be met. value: The value to use if the condition is met.
Returns:: CaseExpression: self with an additional WHEN clause.

exception duckdb.FatalException¶: Bases: DatabaseError

class duckdb.FloatValue(object: Any)¶: Bases: Value

duckdb.FunctionExpression(function_name: str, *args) → duckdb.duckdb.Expression¶

exception duckdb.HTTPException¶

Bases: IOException

Thrown when an error occurs in the httpfs extension, or whilst downloading an extension.

body: str¶

headers: Dict[str, str]¶

reason: str¶

status_code: int¶

class duckdb.HugeIntegerValue(object: Any)¶: Bases: Value

exception duckdb.IOException¶: Bases: OperationalError

class duckdb.IntegerValue(object: Any)¶: Bases: Value

exception duckdb.IntegrityError¶: Bases: DatabaseError

exception duckdb.InternalError¶: Bases: DatabaseError

exception duckdb.InternalException¶: Bases: InternalError

exception duckdb.InterruptException¶: Bases: DatabaseError

class duckdb.IntervalValue(object: Any)¶: Bases: Value

exception duckdb.InvalidInputException¶: Bases: ProgrammingError

exception duckdb.InvalidTypeException¶: Bases: ProgrammingError

class duckdb.LongValue(object: Any)¶: Bases: Value

exception duckdb.NotImplementedException¶: Bases: NotSupportedError

exception duckdb.NotSupportedError¶: Bases: DatabaseError

class duckdb.NullValue¶: Bases: Value

exception duckdb.OperationalError¶: Bases: DatabaseError

exception duckdb.OutOfMemoryException¶: Bases: OperationalError

exception duckdb.OutOfRangeException¶: Bases: DataError

exception duckdb.ParserException¶: Bases: ProgrammingError

exception duckdb.PermissionException¶: Bases: DatabaseError

exception duckdb.ProgrammingError¶: Bases: DatabaseError

class duckdb.PythonExceptionHandling¶

Bases: pybind11_object

Members:

DEFAULT

RETURN_NULL

DEFAULT = <PythonExceptionHandling.DEFAULT: 0>¶

RETURN_NULL = <PythonExceptionHandling.RETURN_NULL: 1>¶

property name¶

property value¶

exception duckdb.SequenceException¶: Bases: DatabaseError

exception duckdb.SerializationException¶: Bases: OperationalError

class duckdb.ShortValue(object: Any)¶: Bases: Value

duckdb.StarExpression(*args, **kwargs)¶

Overloaded function.

StarExpression(*, exclude: object = None) -> duckdb.duckdb.Expression
StarExpression() -> duckdb.duckdb.Expression

class duckdb.StringValue(object: Any)¶: Bases: Value

exception duckdb.SyntaxException¶: Bases: ProgrammingError

class duckdb.TimeTimeZoneValue(object: Any)¶: Bases: Value

class duckdb.TimeValue(object: Any)¶: Bases: Value

class duckdb.TimestampMilisecondValue(object: Any)¶: Bases: Value

class duckdb.TimestampNanosecondValue(object: Any)¶: Bases: Value

class duckdb.TimestampSecondValue(object: Any)¶: Bases: Value

class duckdb.TimestampTimeZoneValue(object: Any)¶: Bases: Value

class duckdb.TimestampValue(object: Any)¶: Bases: Value

exception duckdb.TransactionException¶: Bases: OperationalError

exception duckdb.TypeMismatchException¶: Bases: DataError

class duckdb.UUIDValue(object: Any)¶: Bases: Value

class duckdb.UnsignedBinaryValue(object: Any)¶: Bases: Value

class duckdb.UnsignedIntegerValue(object: Any)¶: Bases: Value

class duckdb.UnsignedLongValue(object: Any)¶: Bases: Value

class duckdb.UnsignedShortValue(object: Any)¶: Bases: Value

class duckdb.Value(object: Any, type: DuckDBPyType)¶: Bases: object

exception duckdb.Warning¶: Bases: Exception

duckdb.aggregate(df: pandas.DataFrame, aggr_expr: object, group_expr: str = '', *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Compute the aggregate aggr_expr by the optional groups group_expr on the relation

duckdb.alias(df: pandas.DataFrame, alias: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Rename the relation object to new alias

duckdb.append(table_name: str, df: pandas.DataFrame, *, by_name: bool = False, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Append the passed DataFrame to the named table

duckdb.array_type(type: duckdb.duckdb.typing.DuckDBPyType, size: int, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create an array type object of ‘type’

duckdb.arrow(*args, **kwargs)¶

Overloaded function.

arrow(rows_per_batch: int = 1000000, *, connection: duckdb.DuckDBPyConnection = None) -> pyarrow.lib.Table

Fetch a result as Arrow table following execute()

arrow(rows_per_batch: int = 1000000, *, connection: duckdb.DuckDBPyConnection = None) -> pyarrow.lib.Table

Fetch a result as Arrow table following execute()

arrow(arrow_object: object, *, connection: duckdb.DuckDBPyConnection = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from an Arrow object

duckdb.begin(*, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Start a new transaction

duckdb.checkpoint(*, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Synchronizes data in the write-ahead log (WAL) to the database data file (no-op for in-memory connections)

duckdb.close(*, connection: duckdb.DuckDBPyConnection = None) → None¶: Close the connection

duckdb.commit(*, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Commit changes performed within a transaction

duckdb.connect(database: object = ':memory:', read_only: bool = False, config: dict = None) → duckdb.DuckDBPyConnection¶: Create a DuckDB database instance. Can take a database file name to read/write persistent data and a read_only flag if no changes are desired

duckdb.create_function(name: str, function: Callable, parameters: object = None, return_type: duckdb.duckdb.typing.DuckDBPyType = None, *, type: duckdb.duckdb.functional.PythonUDFType = <PythonUDFType.NATIVE: 0>, null_handling: duckdb.duckdb.functional.FunctionNullHandling = <FunctionNullHandling.DEFAULT: 0>, exception_handling: duckdb.duckdb.PythonExceptionHandling = <PythonExceptionHandling.DEFAULT: 0>, side_effects: bool = False, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Create a DuckDB function out of the passing in Python function so it can be used in queries

duckdb.cursor(*, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Create a duplicate of the current connection

duckdb.decimal_type(width: int, scale: int, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a decimal type with ‘width’ and ‘scale’

duckdb.description(*, connection: duckdb.DuckDBPyConnection = None) → Optional[list]¶: Get result set attributes, mainly column names

duckdb.df(*args, **kwargs)¶

Overloaded function.

df(*, date_as_object: bool = False, connection: duckdb.DuckDBPyConnection = None) -> pandas.DataFrame

Fetch a result as DataFrame following execute()

df(*, date_as_object: bool = False, connection: duckdb.DuckDBPyConnection = None) -> pandas.DataFrame

Fetch a result as DataFrame following execute()

df(df: pandas.DataFrame, *, connection: duckdb.DuckDBPyConnection = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from the DataFrame df

duckdb.distinct(df: pandas.DataFrame, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Retrieve distinct rows from this relation object

duckdb.dtype(type_str: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a type object by parsing the ‘type_str’ string

duckdb.duplicate(*, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Create a duplicate of the current connection

duckdb.enum_type(name: str, type: duckdb.duckdb.typing.DuckDBPyType, values: list, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create an enum type of underlying ‘type’, consisting of the list of ‘values’

duckdb.execute(query: object, parameters: object = None, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Execute the given SQL query, optionally using prepared statements with parameters set

duckdb.executemany(query: object, parameters: object = None, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Execute the given prepared statement multiple times using the list of parameter sets in parameters

duckdb.extract_statements(query: str, *, connection: duckdb.DuckDBPyConnection = None) → list¶: Parse the query string and extract the Statement object(s) produced

duckdb.fetch_arrow_table(rows_per_batch: int = 1000000, *, connection: duckdb.DuckDBPyConnection = None) → pyarrow.lib.Table¶: Fetch a result as Arrow table following execute()

duckdb.fetch_df(*, date_as_object: bool = False, connection: duckdb.DuckDBPyConnection = None) → pandas.DataFrame¶: Fetch a result as DataFrame following execute()

duckdb.fetch_df_chunk(vectors_per_chunk: int = 1, *, date_as_object: bool = False, connection: duckdb.DuckDBPyConnection = None) → pandas.DataFrame¶: Fetch a chunk of the result as DataFrame following execute()

duckdb.fetch_record_batch(rows_per_batch: int = 1000000, *, connection: duckdb.DuckDBPyConnection = None) → pyarrow.lib.RecordBatchReader¶: Fetch an Arrow RecordBatchReader following execute()

duckdb.fetchall(*, connection: duckdb.DuckDBPyConnection = None) → list¶: Fetch all rows from a result following execute

duckdb.fetchdf(*, date_as_object: bool = False, connection: duckdb.DuckDBPyConnection = None) → pandas.DataFrame¶: Fetch a result as DataFrame following execute()

duckdb.fetchmany(size: int = 1, *, connection: duckdb.DuckDBPyConnection = None) → list¶: Fetch the next set of rows from a result following execute

duckdb.fetchnumpy(*, connection: duckdb.DuckDBPyConnection = None) → dict¶: Fetch a result as list of NumPy arrays following execute

duckdb.fetchone(*, connection: duckdb.DuckDBPyConnection = None) → Optional[tuple]¶: Fetch a single row from a result following execute

duckdb.filesystem_is_registered(name: str, *, connection: duckdb.DuckDBPyConnection = None) → bool¶: Check if a filesystem with the provided name is currently registered

duckdb.filter(df: pandas.DataFrame, filter_expr: object, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Filter the relation object by the filter in filter_expr

duckdb.from_arrow(arrow_object: object, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from an Arrow object

duckdb.from_csv_auto(path_or_buffer: object, **kwargs) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the CSV file in ‘name’

duckdb.from_df(df: pandas.DataFrame, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the DataFrame in df

duckdb.from_parquet(*args, **kwargs)¶

Overloaded function.

from_parquet(file_glob: str, binary_as_string: bool = False, *, file_row_number: bool = False, filename: bool = False, hive_partitioning: bool = False, union_by_name: bool = False, compression: object = None, connection: duckdb.DuckDBPyConnection = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from the Parquet files in file_glob

from_parquet(file_globs: list[str], binary_as_string: bool = False, *, file_row_number: bool = False, filename: bool = False, hive_partitioning: bool = False, union_by_name: bool = False, compression: object = None, connection: duckdb.DuckDBPyConnection = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from the Parquet files in file_globs

duckdb.from_query(query: object, *, alias: str = '', params: object = None, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Run a SQL query. If it is a SELECT statement, create a relation object from the given SQL query, otherwise run the query as-is.

duckdb.from_substrait(proto: bytes, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a query object from protobuf plan

duckdb.from_substrait_json(json: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a query object from a JSON protobuf plan

duckdb.get_substrait(query: str, *, enable_optimizer: bool = True, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Serialize a query to protobuf

duckdb.get_substrait_json(query: str, *, enable_optimizer: bool = True, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Serialize a query to protobuf on the JSON format

duckdb.get_table_names(query: str, *, connection: duckdb.DuckDBPyConnection = None) → set[str]¶: Extract the required table names from a query

duckdb.install_extension(extension: str, *, force_install: bool = False, repository: object = None, repository_url: object = None, version: object = None, connection: duckdb.DuckDBPyConnection = None) → None¶: Install an extension by name, with an optional version and/or repository to get the extension from

duckdb.interrupt(*, connection: duckdb.DuckDBPyConnection = None) → None¶: Interrupt pending operations

duckdb.limit(df: pandas.DataFrame, n: int, offset: int = 0, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Only retrieve the first n rows from this relation object, starting at offset

duckdb.list_filesystems(*, connection: duckdb.DuckDBPyConnection = None) → list¶: List registered filesystems, including builtin ones

duckdb.list_type(type: duckdb.duckdb.typing.DuckDBPyType, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a list type object of ‘type’

duckdb.load_extension(extension: str, *, connection: duckdb.DuckDBPyConnection = None) → None¶: Load an installed extension

duckdb.map_type(key: duckdb.duckdb.typing.DuckDBPyType, value: duckdb.duckdb.typing.DuckDBPyType, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a map type object from ‘key_type’ and ‘value_type’

duckdb.order(df: pandas.DataFrame, order_expr: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Reorder the relation object by order_expr

duckdb.pl(rows_per_batch: int = 1000000, *, connection: duckdb.DuckDBPyConnection = None) → duckdb::PolarsDataFrame¶: Fetch a result as Polars DataFrame following execute()

duckdb.project(df: pandas.DataFrame, *args, groups: str = '', connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Project the relation object by the projection in project_expr

duckdb.query(query: object, *, alias: str = '', params: object = None, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Run a SQL query. If it is a SELECT statement, create a relation object from the given SQL query, otherwise run the query as-is.

duckdb.query_df(df: pandas.DataFrame, virtual_table_name: str, sql_query: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Run the given SQL query in sql_query on the view named virtual_table_name that refers to the relation object

duckdb.read_csv(path_or_buffer: object, **kwargs) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the CSV file in ‘name’

duckdb.read_json(path_or_buffer: object, *, columns: Optional[object] = None, sample_size: Optional[object] = None, maximum_depth: Optional[object] = None, records: Optional[str] = None, format: Optional[str] = None, date_format: Optional[object] = None, timestamp_format: Optional[object] = None, compression: Optional[object] = None, maximum_object_size: Optional[object] = None, ignore_errors: Optional[object] = None, convert_strings_to_integers: Optional[object] = None, field_appearance_threshold: Optional[object] = None, map_inference_threshold: Optional[object] = None, maximum_sample_files: Optional[object] = None, filename: Optional[object] = None, hive_partitioning: Optional[object] = None, union_by_name: Optional[object] = None, hive_types: Optional[object] = None, hive_types_autocast: Optional[object] = None, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the JSON file in ‘name’

duckdb.read_parquet(*args, **kwargs)¶

Overloaded function.

read_parquet(file_glob: str, binary_as_string: bool = False, *, file_row_number: bool = False, filename: bool = False, hive_partitioning: bool = False, union_by_name: bool = False, compression: object = None, connection: duckdb.DuckDBPyConnection = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from the Parquet files in file_glob

read_parquet(file_globs: list[str], binary_as_string: bool = False, *, file_row_number: bool = False, filename: bool = False, hive_partitioning: bool = False, union_by_name: bool = False, compression: object = None, connection: duckdb.DuckDBPyConnection = None) -> duckdb.duckdb.DuckDBPyRelation

Create a relation object from the Parquet files in file_globs

duckdb.register(view_name: str, python_object: object, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Register the passed Python Object value for querying with a view

duckdb.register_filesystem(filesystem: fsspec.AbstractFileSystem, *, connection: duckdb.DuckDBPyConnection = None) → None¶: Register a fsspec compliant filesystem

duckdb.remove_function(name: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Remove a previously created function

duckdb.rollback(*, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Roll back changes performed within a transaction

duckdb.row_type(fields: object, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a struct type object from ‘fields’

duckdb.rowcount(*, connection: duckdb.DuckDBPyConnection = None) → int¶: Get result set row count

duckdb.sql(query: object, *, alias: str = '', params: object = None, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Run a SQL query. If it is a SELECT statement, create a relation object from the given SQL query, otherwise run the query as-is.

duckdb.sqltype(type_str: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a type object by parsing the ‘type_str’ string

duckdb.string_type(collation: str = '', *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a string type with an optional collation

duckdb.struct_type(fields: object, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a struct type object from ‘fields’

duckdb.table(table_name: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object for the named table

duckdb.table_function(name: str, parameters: object = None, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the named table function with given parameters

duckdb.tf(*, connection: duckdb.DuckDBPyConnection = None) → dict¶: Fetch a result as dict of TensorFlow Tensors following execute()

class duckdb.token_type¶

Bases: pybind11_object

Members:

identifier

numeric_const

string_const

operator

keyword

comment

comment = <token_type.comment: 5>¶

identifier = <token_type.identifier: 0>¶

keyword = <token_type.keyword: 4>¶

property name¶

numeric_const = <token_type.numeric_const: 1>¶

operator = <token_type.operator: 3>¶

string_const = <token_type.string_const: 2>¶

property value¶

duckdb.tokenize(query: str) → list¶: Tokenizes a SQL string, returning a list of (position, type) tuples that can be used for e.g., syntax highlighting

duckdb.torch(*, connection: duckdb.DuckDBPyConnection = None) → dict¶: Fetch a result as dict of PyTorch Tensors following execute()

duckdb.type(type_str: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a type object by parsing the ‘type_str’ string

duckdb.union_type(members: object, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.typing.DuckDBPyType¶: Create a union type object from ‘members’

duckdb.unregister(view_name: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.DuckDBPyConnection¶: Unregister the view name

duckdb.unregister_filesystem(name: str, *, connection: duckdb.DuckDBPyConnection = None) → None¶: Unregister a filesystem

duckdb.values(values: object, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object from the passed values

duckdb.view(view_name: str, *, connection: duckdb.DuckDBPyConnection = None) → duckdb.duckdb.DuckDBPyRelation¶: Create a relation object for the named view

duckdb.write_csv(df: pandas.DataFrame, filename: str, *, sep: object = None, na_rep: object = None, header: object = None, quotechar: object = None, escapechar: object = None, date_format: object = None, timestamp_format: object = None, quoting: object = None, encoding: object = None, compression: object = None, overwrite: object = None, per_thread_output: object = None, use_tmp_file: object = None, partition_by: object = None, write_partition_columns: object = None, connection: duckdb.DuckDBPyConnection = None) → None¶: Write the relation object to a CSV file in ‘file_name’

About this page