Data Input/Output

import pandas as pd
from pandas import read_csv, read_excel, read_json, read_sql

def read_csv(filepath_or_buffer, sep=',', delimiter=None, header='infer', names=None, index_col=None, usecols=None, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skipinitialspace=False, skiprows=None, skipfooter=0, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True, parse_dates=False, infer_datetime_format=False, keep_date_col=False, date_parser=None, date_format=None, dayfirst=False, cache_dates=True, iterator=False, chunksize=None, compression='infer', thousands=None, decimal='.', lineterminator=None, quotechar='"', quoting=0, doublequote=True, escapechar=None, comment=None, encoding=None, encoding_errors='strict', dialect=None, on_bad_lines='error', delim_whitespace=False, low_memory=True, memory_map=False, float_precision=None, storage_options=None, dtype_backend='numpy_nullable'):
    """
    Read a comma-separated values (CSV) file into DataFrame.
    
    Parameters:
    - filepath_or_buffer: str, path object, or file-like object
    - sep: str, delimiter to use
    - header: int, list of int, default 'infer', row(s) to use as column names
    - names: array-like, list of column names to use
    - index_col: int, str, sequence of int/str, or False, column(s) to use as row labels
    - usecols: list-like or callable, return subset of columns
    - dtype: type name or dict of column -> type, data type for data or columns
    - na_values: scalar, str, list-like, or dict, additional strings to recognize as NA/NaN
    - parse_dates: bool or list of int or names or list of lists or dict
    - chunksize: int, return TextFileReader object for iteration
    
    Returns:
    DataFrame or TextFileReader
    """

def read_table(filepath_or_buffer, sep='\\t', delimiter=None, header='infer', names=None, index_col=None, usecols=None, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skipinitialspace=False, skiprows=None, skipfooter=0, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True, parse_dates=False, infer_datetime_format=False, keep_date_col=False, date_parser=None, date_format=None, dayfirst=False, cache_dates=True, iterator=False, chunksize=None, compression='infer', thousands=None, decimal='.', lineterminator=None, quotechar='"', quoting=0, doublequote=True, escapechar=None, comment=None, encoding=None, encoding_errors='strict', dialect=None, on_bad_lines='error', delim_whitespace=False, low_memory=True, memory_map=False, float_precision=None, storage_options=None, dtype_backend='numpy_nullable'):
    """
    Read general delimited file into DataFrame.
    
    Similar to read_csv but with tab delimiter by default.
    """

def read_fwf(filepath_or_buffer, colspecs='infer', widths=None, infer_nrows=100, dtype_backend='numpy_nullable', iterator=False, chunksize=None, **kwargs):
    """
    Read a table of fixed-width formatted lines into DataFrame.
    
    Parameters:
    - filepath_or_buffer: str, path object, or file-like object
    - colspecs: list of tuple (int, int) or 'infer', column specifications
    - widths: list of int, width of each field
    - infer_nrows: int, number of rows to consider when letting the parser determine colspecs
    
    Returns:
    DataFrame or TextFileReader
    """

def read_excel(io, sheet_name=0, header=0, names=None, index_col=None, usecols=None, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skiprows=None, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, parse_dates=False, date_parser=None, date_format=None, thousands=None, decimal='.', comment=None, skipfooter=0, storage_options=None, dtype_backend='numpy_nullable', engine_kwargs=None):
    """
    Read an Excel file into a pandas DataFrame.
    
    Parameters:
    - io: str, bytes, ExcelFile, xlrd.Book, path object, or file-like object
    - sheet_name: str, int, list, or None, names of sheets or sheet positions to read
    - header: int, list of int, default 0, row(s) to use as column names
    - names: array-like, list of column names to use
    - index_col: int, str, list of int, default None, column(s) to use as row labels
    - usecols: str, list-like, or callable, return subset of columns
    - dtype: type name or dict of column -> type, data type for data or columns
    - skiprows: list-like, rows to skip at the beginning
    - nrows: int, number of rows to parse
    
    Returns:
    DataFrame or dict of DataFrames
    """

class ExcelFile:
    def __init__(self, path_or_buffer, engine=None, storage_options=None, engine_kwargs=None):
        """
        Class for parsing tabular Excel sheets into DataFrame objects.
        
        Parameters:
        - path_or_buffer: str, bytes, path object, or file-like object
        - engine: str, engine to use for reading ('openpyxl', 'xlrd', 'odf', 'pyxlsb')
        """
    
    def parse(self, sheet_name=0, header=0, names=None, index_col=None, usecols=None, converters=None, dtype=None, true_values=None, false_values=None, skiprows=None, nrows=None, na_values=None, verbose=False, parse_dates=False, date_parser=None, thousands=None, comment=None, skipfooter=0, convert_float=None, mangle_dupe_cols=True, dtype_backend='numpy_nullable', **kwds):
        """Parse specified sheet(s) into DataFrame."""
    
    def sheet_names(self):
        """Property returning list of sheet names."""

class ExcelWriter:
    def __init__(self, path, engine=None, date_format=None, datetime_format=None, mode='w', storage_options=None, if_sheet_exists=None, engine_kwargs=None):
        """
        Class for writing DataFrame objects into Excel sheets.
        
        Parameters:
        - path: str or file-like object, file path or existing ExcelWriter
        - engine: str, engine to use for writing ('openpyxl', 'xlsxwriter')
        - mode: str, file mode to use (write or append)
        """
    
    def close(self):
        """Close the contained workbook."""
    
    def save(self):
        """Save workbook to disk."""

def read_json(path_or_buf=None, orient=None, typ='frame', dtype=None, convert_axes=None, convert_dates=True, keep_default_dates=True, precise_float=False, date_unit=None, encoding=None, encoding_errors='strict', lines=False, chunksize=None, compression='infer', nrows=None, storage_options=None, dtype_backend='numpy_nullable', engine='ujson'):
    """
    Convert a JSON string to pandas object.
    
    Parameters:
    - path_or_buf: str, path object, file-like object, or None
    - orient: str, indication of expected JSON string format
    - typ: str, type of object to recover ('frame' or 'series')
    - dtype: bool or dict, data type for data or columns
    - convert_dates: bool or list of str, dates to parse
    - lines: bool, read file as one JSON object per line
    - chunksize: int, return JsonReader object for iteration
    
    Returns:
    Series, DataFrame, or JsonReader
    """

def json_normalize(data, record_path=None, meta=None, meta_prefix=None, record_prefix=None, errors='raise', sep='.', max_level=None):
    """
    Normalize semi-structured JSON data into a flat table.
    
    Parameters:
    - data: dict or list of dicts, unserialized JSON objects
    - record_path: str or list of str, path in each object to list of records
    - meta: list of str, fields to use as metadata for each record
    - sep: str, nested record separator
    - max_level: int, max number of levels to normalize
    
    Returns:
    DataFrame
    """

def read_sql(sql, con, index_col=None, coerce_float=True, params=None, parse_dates=None, columns=None, chunksize=None, dtype_backend='numpy_nullable', dtype=None):
    """
    Read SQL query or database table into a DataFrame.
    
    Parameters:
    - sql: str or SQLAlchemy Selectable, SQL query or table name
    - con: ADBC Connection, SQLAlchemy connectable, str, or sqlite3 connection
    - index_col: str or list of str, column(s) to use as row labels
    - coerce_float: bool, attempts to convert values of non-string, non-numeric objects to floating point
    - params: list, tuple, mapping or None, parameters to pass to execute method
    - parse_dates: list or dict, columns to parse as dates
    - chunksize: int, number of rows to include in each chunk
    
    Returns:
    DataFrame or Iterator[DataFrame]
    """

def read_sql_query(sql, con, index_col=None, coerce_float=True, params=None, parse_dates=None, chunksize=None, dtype=None, dtype_backend='numpy_nullable'):
    """
    Read SQL query into a DataFrame.
    
    Parameters:
    - sql: str or SQLAlchemy Selectable, SQL query to be executed
    - con: ADBC Connection, SQLAlchemy connectable, str, or sqlite3 connection
    
    Returns:
    DataFrame or Iterator[DataFrame]
    """

def read_sql_table(table_name, con, schema=None, index_col=None, coerce_float=True, parse_dates=None, columns=None, chunksize=None, dtype_backend='numpy_nullable'):
    """
    Read SQL database table into a DataFrame.
    
    Parameters:
    - table_name: str, name of SQL table in database
    - con: ADBC Connection, SQLAlchemy connectable, str, or sqlite3 connection
    - schema: str, name of SQL schema in database to query
    - columns: list, list of column names to select from SQL table
    
    Returns:
    DataFrame or Iterator[DataFrame]
    """

def read_pickle(filepath_or_buffer, compression='infer', storage_options=None):
    """
    Load pickled pandas object (or any object) from file.
    
    Parameters:
    - filepath_or_buffer: str, path object, or file-like object
    - compression: str or dict, compression type and options
    
    Returns:
    unpickled object
    """

def to_pickle(obj, filepath_or_buffer, compression='infer', protocol=5, storage_options=None):
    """
    Pickle (serialize) object to file.
    
    Parameters:
    - obj: any object, object to pickle
    - filepath_or_buffer: str, path object, or file-like object
    - compression: str or dict, compression type and options
    - protocol: int, pickle protocol to use
    """

def read_hdf(path_or_buf, key=None, mode='r', errors='strict', where=None, start=None, stop=None, columns=None, iterator=False, chunksize=None, dtype_backend='numpy_nullable', **kwargs):
    """
    Read from the store, close it if we opened it.
    
    Parameters:
    - path_or_buf: str, path object, pandas.HDFStore, or file-like object
    - key: str, identifier for group in store
    - mode: str, mode to open file
    - where: list of Term, criteria to select
    - start: int, row number to start selection
    - stop: int, row number to stop selection
    - columns: list, list of columns to return
    
    Returns:
    DataFrame or Series
    """

class HDFStore:
    def __init__(self, path, mode='r', complevel=None, complib=None, fletcher32=False, **kwargs):
        """
        Dict-like IO interface for storing pandas objects in PyTables.
        
        Parameters:
        - path: str, file path to HDF5 file
        - mode: str, mode to open file
        - complevel: int, compression level (0-9)
        - complib: str, compression library
        """
    
    def put(self, key, value, format=None, index=True, append=False, complib=None, complevel=None, min_itemsize=None, nan_rep=None, data_columns=None, encoding=None, errors='strict', track_times=True, dropna=False):
        """Store object in HDFStore."""
    
    def get(self, key):
        """Retrieve pandas object stored in file."""
    
    def keys(self):
        """Return list of keys in the store."""
    
    def close(self):
        """Close the store."""

def read_parquet(path, engine='auto', columns=None, storage_options=None, use_nullable_dtypes=False, dtype_backend='numpy_nullable', filesystem=None, filters=None, **kwargs):
    """
    Load a parquet object, returning a DataFrame.
    
    Parameters:
    - path: str, path object, or file-like object
    - engine: str, parquet library to use ('auto', 'pyarrow', 'fastparquet')
    - columns: list, columns to read
    - filters: list of tuples, row group filters
    
    Returns:
    DataFrame
    """

def read_feather(path, columns=None, use_threads=True, storage_options=None, dtype_backend='numpy_nullable'):
    """
    Load a feather-format object into a DataFrame.
    
    Parameters:
    - path: str, path object, or file-like object
    - columns: sequence, columns to read
    - use_threads: bool, whether to parallelize reading
    
    Returns:
    DataFrame
    """

def read_orc(path, columns=None, dtype_backend='numpy_nullable', filesystem=None, **kwargs):
    """
    Load an ORC object, returning a DataFrame.
    
    Parameters:
    - path: str, path object, or file-like object
    - columns: list, columns to read
    
    Returns:
    DataFrame
    """

def read_html(io, match='.+', header=None, index_col=None, skiprows=None, attrs=None, parse_dates=False, thousands=',', encoding=None, decimal='.', converters=None, na_values=None, keep_default_na=True, displayed_only=True, extract_links=None, dtype_backend='numpy_nullable', storage_options=None):
    """
    Read HTML tables into a list of DataFrame objects.
    
    Parameters:
    - io: str, path object, file-like object, or raw string containing HTML
    - match: str or compiled regex, set of table attributes to match
    - header: int or list-like, row(s) to use to make column headers
    - index_col: int or list-like, column(s) to use to make row index
    - skiprows: int, list-like or slice, rows to skip
    - attrs: dict, attributes to match in table tag
    
    Returns:
    list of DataFrames
    """

def read_xml(path_or_buffer, xpath='./*', namespaces=None, elems_only=False, attrs_only=False, names=None, dtype=None, converters=None, parse_dates=None, encoding='utf-8', parser='lxml', tree_builder=None, stylesheet=None, iterparse=None, compression='infer', storage_options=None, dtype_backend='numpy_nullable'):
    """
    Read XML document into a DataFrame object.
    
    Parameters:
    - path_or_buffer: str, path object, or file-like object
    - xpath: str, XPath expression to parse desired element(s)
    - namespaces: dict, namespace prefixes and URIs
    - elems_only: bool, parse child elements only
    - attrs_only: bool, parse attributes only
    - encoding: str, encoding of document
    
    Returns:
    DataFrame
    """

def read_clipboard(sep='\\s+', dtype_backend='numpy_nullable', **kwargs):
    """
    Read text from clipboard and pass to read_csv.
    
    Parameters:
    - sep: str, delimiter for splitting clipboard contents
    
    Returns:
    DataFrame
    """

def read_stata(filepath_or_buffer, convert_dates=True, convert_categoricals=True, encoding=None, index_col=None, convert_missing=False, preserve_dtypes=True, columns=None, order_categoricals=True, chunksize=None, iterator=False, compression='infer', storage_options=None, dtype_backend='numpy_nullable'):
    """
    Read Stata file into DataFrame.
    
    Parameters:
    - filepath_or_buffer: str, path object, or file-like object
    - convert_dates: bool, convert date variables to pandas datetime
    - convert_categoricals: bool, convert categorical variables to pandas Categorical
    - encoding: str, encoding used to decode text strings
    - preserve_dtypes: bool, preserve Stata data types
    
    Returns:
    DataFrame or StataReader
    """

def read_sas(filepath_or_buffer, format=None, index=None, encoding=None, chunksize=None, iterator=False, compression='infer', storage_options=None, dtype_backend='numpy_nullable'):
    """
    Read SAS files stored as either XPORT or SAS7BDAT format files.
    
    Parameters:
    - filepath_or_buffer: str, path object, or file-like object
    - format: str, file format ('xport' or 'sas7bdat')
    - encoding: str, encoding for text data
    - chunksize: int, rows to read at a time
    
    Returns:
    DataFrame or SAS Reader
    """

def read_spss(path, usecols=None, convert_categoricals=True, dtype_backend='numpy_nullable', storage_options=None):
    """
    Load an SPSS file from the file path, returning a DataFrame.
    
    Parameters:
    - path: str, path object, or file-like object
    - usecols: list-like, return subset of columns
    - convert_categoricals: bool, convert categorical variables to pandas Categorical
    
    Returns:
    DataFrame
    """

def read_gbq(query, project_id=None, index_col=None, col_order=None, reauth=False, auth_local_webserver=True, dialect=None, location=None, configuration=None, credentials=None, use_bqstorage_api=None, max_results=None, progress_bar_type=None, dtype_backend='numpy_nullable'):
    """
    Load data from Google BigQuery.
    
    Parameters:
    - query: str, SQL-Like Query to return data values
    - project_id: str, Google BigQuery Account project ID
    - index_col: str, name of result column to use for index
    - col_order: list(str), list of BigQuery column names in desired order
    - reauth: bool, force Google BigQuery to re-authenticate user
    - dialect: str, SQL dialect for BigQuery ('legacy' or 'standard')
    
    Returns:
    DataFrame
    """

# File reader classes for chunked reading
class TextFileReader:
    """Iterator for reading CSV files in chunks."""
    def __iter__(self): ...
    def __next__(self): ...
    def get_chunk(self, size=None): ...
    def close(self): ...

class JsonReader:
    """Iterator for reading JSON files in chunks."""
    def __iter__(self): ...
    def __next__(self): ...
    def close(self): ...

# Storage format constants
class ExcelWriterMode:
    WRITE = 'w'
    APPEND = 'a'

class JSONOrient:
    SPLIT = 'split'
    RECORDS = 'records'
    INDEX = 'index'
    COLUMNS = 'columns'
    VALUES = 'values'
    TABLE = 'table'