API surface

class Blade:

Convenience facade for common datablade workflows. Stores default options that are threaded through to the underlying functions.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\blade.py:30

def try_cast_string_columns_to_numeric(df=None, convert_partial=False, verbose=False):

Attempt to cast DataFrame string columns to numeric values where possible. Args: df: The DataFrame to process. If None, returns None. convert_partial: If Tru...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\frames.py:71

def clean_dataframe_columns(df=None, verbose=False):

Clean the DataFrame columns by flattening MultiIndex, converting to strings, and removing duplicates. Args: df: The DataFrame to clean. If None, returns None...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\frames.py:128

def generate_parquet_schema(df=None, verbose=False):

Generate a PyArrow Schema from a pandas DataFrame with optimized data types. Args: df: The DataFrame to generate the schema from. If None, returns None. verb...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\frames.py:171

def pandas_to_parquet_table(df=None, convert=True, partial=False, preserve_index=False, verbose=False):

Generate a PyArrow Table from a pandas DataFrame with automatic type conversion. Args: df: The DataFrame to convert. If None, returns None. convert: If True,...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\frames.py:264

def generate_sql_server_create_table_string(df=None, catalog='database', schema='dbo', table='table', dropexisting=True, verbose=False):

Generate a SQL Server CREATE TABLE statement from a pandas DataFrame. Args: df: The DataFrame to generate the schema from. If None, returns None. catalog: Th...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\frames.py:350

def write_to_file_and_sql(df, file_path, table_name, sql_server, database, username, password, verbose=False):

Write a DataFrame to a CSV file and import it to SQL Server using BCP. Args: df: The DataFrame to write. file_path: Path where the CSV file will be saved. ta...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\frames.py:402

def read_file_chunked(file_path, chunksize=None, memory_fraction=0.5, verbose=False, **read_kwargs):

Read a file in chunks, automatically determining chunk size based on available memory. Args: file_path: Path to the file to read. chunksize: Optional explici...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\readers.py:138

def read_file_iter(file_path, chunksize=None, memory_fraction=0.5, verbose=False, **read_kwargs):

Stream a file as an iterator of DataFrame chunks. This is the "never materialize" API: unlike read_file_smart(), this function does not concatenate chunks in...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\readers.py:219

def read_file_to_parquets(file_path, output_dir, output_prefix='part', rows_per_file=None, memory_fraction=0.5, convert_types=True, verbose=False, **read_kwargs):

Read a large file and write it to multiple Parquet files if it doesn't fit in memory. Args: file_path: Path to the input file. output_dir: Directory where Pa...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\readers.py:315

def stream_to_parquets(file_path, output_dir, output_prefix='part', rows_per_file=None, memory_fraction=0.5, convert_types=True, verbose=False, **read_kwargs):

Stream a file and write it to Parquet partitions without materializing. This helper is the "no concat" companion to read_file_to_parquets(). It uses read_fil...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\readers.py:376

def read_file_smart(file_path, use_polars=True, memory_fraction=0.5, verbose=False, **read_kwargs):

Intelligently read a file, using Polars for large files if available. For files that fit in memory, reads directly. For large files, uses Polars lazy evaluat...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\dataframes\readers.py:441

def list_docs():

List docs.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\docs\__init__.py:17

def read_doc(name):

Read doc.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\docs\__init__.py:22

def write_docs(target_dir):

Write docs.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\docs\__init__.py:34

def write_site(target_dir):

Write site.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\docs\__init__.py:47

def main(argv=None):

Main.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\docs\__init__.py:100

def get(url, verbose=False, **kwargs):

Get JSON data from a URL using HTTP GET request. Args: url: The URL to fetch JSON data from (must be non-empty string). verbose: If True, prints error messag...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\io\json.py:10

def get(url, path=None, verbose=False, **kwargs):

Download a ZIP file from a URL and either extract it to a path or return as BytesIO. Args: url: The URL of the ZIP file to download. path: Optional path wher...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\io\zip.py:13

def bulk_load_sqlserver(file_path, table_name, database, server, username, password, schema='dbo', delimiter=',', verbose=False):

Bulk load a file into SQL Server using BCP. Args: file_path: Path to the data file. table_name: Target table name. database: Database name. server: SQL Serve...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\bulk_load.py:52

def bulk_load_postgres(file_path, table_name, database, schema='public', connection_string=None, delimiter=',', header=True, verbose=False):

Generate a PostgreSQL COPY command for bulk loading. Args: file_path: Path to the data file. table_name: Target table name. database: Database name. schema:...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\bulk_load.py:125

def bulk_load_mysql(file_path, table_name, database, delimiter=',', enclosed_by='"', lines_terminated_by='\\n', ignore_lines=1, verbose=False):

Generate a MySQL LOAD DATA command for bulk loading. Args: file_path: Path to the data file. table_name: Target table name. database: Database name. delimite...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\bulk_load.py:170

def bulk_load_duckdb(file_path, table_name, database='memory', schema='main', verbose=False):

Generate a DuckDB COPY command for bulk loading. Args: file_path: Path to the data file. table_name: Target table name. database: Database name (default: mem...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\bulk_load.py:218

def bulk_load(file_path, table_name, database, dialect=Dialect.SQLSERVER, schema=None, server=None, username=None, password=None, delimiter=',', verbose=False):

Bulk load a file to a database table using the appropriate dialect method. Args: file_path: Path to the data file. table_name: Target table name. database: D...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\bulk_load.py:260

def write_dataframe_and_load(df, file_path, table_name, database, dialect=Dialect.SQLSERVER, schema=None, server=None, username=None, password=None, delimiter=',', verbose=False):

Write a DataFrame to a file and bulk load it to a database. Args: df: The DataFrame to write. file_path: Path where the file will be saved. table_name: Targe...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\bulk_load.py:340

def generate_create_table(df, catalog=None, schema=None, table='table', drop_existing=True, dialect=Dialect.SQLSERVER, verbose=False):

Generate a CREATE TABLE statement for the given dialect. Args: df: Source DataFrame. catalog: Optional catalog/database name. schema: Optional schema name (d...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\ddl.py:162

def generate_create_table_from_parquet(parquet_path, catalog=None, schema=None, table='table', drop_existing=True, dialect=Dialect.SQLSERVER, verbose=False):

Generate a CREATE TABLE statement from a Parquet file schema. This reads the Parquet schema only (via PyArrow) and does not materialize data. Columns whose P...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\ddl_pyarrow.py:209

class Dialect(str, Enum):

Supported SQL dialects for datablade DDL helpers.

No public methods listed.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\dialects.py:6

def quote_identifier(name, dialect=Dialect.SQLSERVER):

Quote an identifier for the given SQL dialect. Args: name: Identifier to quote; must be non-empty string. dialect: Target SQL dialect. Returns: Quoted identi...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\sql\quoting.py:8

def flatten(nest):

Flatten a nested list recursively to a single-level list. Args: nest: A potentially nested list structure. Returns: A flat list containing all elements from...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\lists.py:6

def get_logger():

Get the datablade logger instance. Returns: The configured datablade logger.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\logging.py:34

def configure_logging(level=logging.INFO, handler=None, format_string=None, *, log_file=None, format=None):

Configure the datablade logger. Args: level: Logging level (e.g., logging.DEBUG, logging.INFO). handler: Optional custom handler. If None, uses StreamHandler...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\logging.py:45

def log(message, level=logging.INFO, verbose=True):

Log a message at the specified level if verbose is True. Args: message: The message to log (converted to string). level: Logging level (default: INFO). verbo...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\logging.py:102

def log_debug(message, verbose=True):

Log a DEBUG level message.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\logging.py:125

def log_info(message, verbose=True):

Log an INFO level message.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\logging.py:130

def log_warning(message, verbose=True):

Log a WARNING level message.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\logging.py:135

def log_error(message, verbose=True):

Log an ERROR level message.

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\logging.py:140

def print_verbose(message, verbose=True):

Print a message if verbose is True. This is a backward-compatible alias for log_info. Args: message: The message to print (converted to string). verbose: If...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\logging.py:146

def sql_quotename(name=None, brackets=True, ticks=False, verbose=False):

Quote a SQL Server name string with brackets or ticks. Args: name: The name to quote. Must be a non-empty string. brackets: If True, wraps the name in square...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\strings.py:9

def pathing(input, verbose=False):

Standardize and validate a path string or Path object. Args: input: The path to standardize (string or pathlib.Path). Must not be None. verbose: If True, pri...

Source: C:\Users\BrentCarpenetti\Documents\repositories\datablade\src\datablade\utils\strings.py:55