numeric.py

import numpy as np

from pandas._libs import lib

from pandas.core.dtypes.cast import maybe_downcast_numeric
from pandas.core.dtypes.common import (
    ensure_object,
    is_datetime_or_timedelta_dtype,
    is_decimal,
    is_extension_array_dtype,
    is_float_dtype,
    is_integer_dtype,
    is_number,
    is_numeric_dtype,
    is_scalar,
    needs_i8_conversion,
)
from pandas.core.dtypes.generic import ABCIndex, ABCSeries

import pandas as pd
from pandas.core.arrays.numeric import NumericArray
from pandas.core.construction import extract_array


def to_numeric(arg, errors="raise", downcast=None):
    """
    Convert argument to a numeric type.

    The default return dtype is `float64` or `int64`
    depending on the data supplied. Use the `downcast` parameter
    to obtain other dtypes.

    Please note that precision loss may occur if really large numbers
    are passed in. Due to the internal limitations of `ndarray`, if
    numbers smaller than `-9223372036854775808` (np.iinfo(np.int64).min)
    or larger than `18446744073709551615` (np.iinfo(np.uint64).max) are
    passed in, it is very likely they will be converted to float so that
    they can stored in an `ndarray`. These warnings apply similarly to
    `Series` since it internally leverages `ndarray`.

    Parameters
    ----------
    arg : scalar, list, tuple, 1-d array, or Series
        Argument to be converted.
    errors : {'ignore', 'raise', 'coerce'}, default 'raise'
        - If 'raise', then invalid parsing will raise an exception.
        - If 'coerce', then invalid parsing will be set as NaN.
        - If 'ignore', then invalid parsing will return the input.
    downcast : {'integer', 'signed', 'unsigned', 'float'}, default None
        If not None, and if the data has been successfully cast to a
        numerical dtype (or if the data was numeric to begin with),
        downcast that resulting data to the smallest numerical dtype
        possible according to the following rules:

        - 'integer' or 'signed': smallest signed int dtype (min.: np.int8)
        - 'unsigned': smallest unsigned int dtype (min.: np.uint8)
        - 'float': smallest float dtype (min.: np.float32)

        As this behaviour is separate from the core conversion to
        numeric values, any errors raised during the downcasting
        will be surfaced regardless of the value of the 'errors' input.

        In addition, downcasting will only occur if the size
        of the resulting data's dtype is strictly larger than
        the dtype it is to be cast to, so if none of the dtypes
        checked satisfy that specification, no downcasting will be
        performed on the data.

    Returns
    -------
    ret
        Numeric if parsing succeeded.
        Return type depends on input.  Series if Series, otherwise ndarray.

    See Also
    --------
    DataFrame.astype : Cast argument to a specified dtype.
    to_datetime : Convert argument to datetime.
    to_timedelta : Convert argument to timedelta.
    numpy.ndarray.astype : Cast a numpy array to a specified type.
    DataFrame.convert_dtypes : Convert dtypes.

    Examples
    --------
    Take separate series and convert to numeric, coercing when told to

    >>> s = pd.Series(['1.0', '2', -3])
    >>> pd.to_numeric(s)
    0    1.0
    1    2.0
    2   -3.0
    dtype: float64
    >>> pd.to_numeric(s, downcast='float')
    0    1.0
    1    2.0
    2   -3.0
    dtype: float32
    >>> pd.to_numeric(s, downcast='signed')
    0    1
    1    2
    2   -3
    dtype: int8
    >>> s = pd.Series(['apple', '1.0', '2', -3])
    >>> pd.to_numeric(s, errors='ignore')
    0    apple
    1      1.0
    2        2
    3       -3
    dtype: object
    >>> pd.to_numeric(s, errors='coerce')
    0    NaN
    1    1.0
    2    2.0
    3   -3.0
    dtype: float64
    """
    if downcast not in (None, "integer", "signed", "unsigned", "float"):
        raise ValueError("invalid downcasting method provided")

    if errors not in ("ignore", "raise", "coerce"):
        raise ValueError("invalid error value specified")

    is_series = False
    is_index = False
    is_scalars = False
    is_numeric_extension_dtype = False

    if isinstance(arg, ABCSeries):
        is_series = True
        values = arg.values
        if is_extension_array_dtype(arg) and isinstance(values, NumericArray):
            is_numeric_extension_dtype = True
            values = extract_array(arg)
    elif isinstance(arg, ABCIndex):
        is_index = True
        if needs_i8_conversion(arg.dtype):
            values = arg.asi8
        else:
            values = arg.values
    elif isinstance(arg, (list, tuple)):
        values = np.array(arg, dtype="O")
    elif is_scalar(arg):
        if is_decimal(arg):
            return float(arg)
        if is_number(arg):
            return arg
        is_scalars = True
        values = np.array([arg], dtype="O")
    elif getattr(arg, "ndim", 1) > 1:
        raise TypeError("arg must be a list, tuple, 1-d array, or Series")
    else:
        values = arg

    if is_numeric_extension_dtype or (
        is_extension_array_dtype(arg) and isinstance(values, NumericArray)
    ):
        is_numeric_extension_dtype = True
        mask, values = values._mask, values._data

    values_dtype = getattr(values, "dtype", None)
    if is_numeric_dtype(values_dtype):
        pass
    elif is_datetime_or_timedelta_dtype(values_dtype):
        values = values.astype(np.int64)
    else:
        values = ensure_object(values)
        coerce_numeric = errors not in ("ignore", "raise")
        try:
            values = lib.maybe_convert_numeric(
                values, set(), coerce_numeric=coerce_numeric
            )
        except (ValueError, TypeError):
            if errors == "raise":
                raise

    # attempt downcast only if the data has been successfully converted
    # to a numerical dtype and if a downcast method has been specified
    if downcast is not None and is_numeric_dtype(values.dtype):
        typecodes = None

        if downcast in ("integer", "signed"):
            typecodes = np.typecodes["Integer"]
        elif downcast == "unsigned" and (not len(values) or np.min(values) >= 0):
            typecodes = np.typecodes["UnsignedInteger"]
        elif downcast == "float":
            typecodes = np.typecodes["Float"]

            # pandas support goes only to np.float32,
            # as float dtypes smaller than that are
            # extremely rare and not well supported
            float_32_char = np.dtype(np.float32).char
            float_32_ind = typecodes.index(float_32_char)
            typecodes = typecodes[float_32_ind:]

        if typecodes is not None:
            # from smallest to largest
            for dtype in typecodes:
                dtype = np.dtype(dtype)
                if dtype.itemsize <= values.dtype.itemsize:
                    values = maybe_downcast_numeric(values, dtype)

                    # successful conversion
                    if values.dtype == dtype:
                        break

    if is_numeric_extension_dtype:
        if is_integer_dtype(values):
            from pandas.core.arrays import IntegerArray

            values = IntegerArray(values, mask)
        elif is_float_dtype(values):
            from pandas.core.arrays import FloatingArray

            values = FloatingArray(values, mask)

    if is_series:
        return arg._constructor(values, index=arg.index, name=arg.name)
    elif is_index:
        # because we want to coerce to numeric if possible,
        # do not use _shallow_copy
        return pd.Index(values, name=arg.name)
    elif is_scalars:
        return values[0]
    else:
        return values