Python data._is_using_pandas函数代码示例

def handle_formula_data(Y, X, formula, depth=0, missing='drop'):
    """
    Returns endog, exog, and the model specification from arrays and formula

    Parameters
    ----------
    Y : array-like
        Either endog (the LHS) of a model specification or all of the data.
        Y must define __getitem__ for now.
    X : array-like
        Either exog or None. If all the data for the formula is provided in
        Y then you must explicitly set X to None.
    formula : str or patsy.model_desc
        You can pass a handler by import formula_handler and adding a
        key-value pair where the key is the formula object class and
        the value is a function that returns endog, exog, formula object

    Returns
    -------
    endog : array-like
        Should preserve the input type of Y,X
    exog : array-like
        Should preserve the input type of Y,X. Could be None.
    """
    # half ass attempt to handle other formula objects
    if isinstance(formula, tuple(iterkeys(formula_handler))):
        return formula_handler[type(formula)]

    na_action = NAAction(on_NA=missing)

    if X is not None:
        if data_util._is_using_pandas(Y, X):
            result = dmatrices(formula, (Y, X), depth,
                               return_type='dataframe', NA_action=na_action)
        else:
            result = dmatrices(formula, (Y, X), depth,
                               return_type='dataframe', NA_action=na_action)
    else:
        if data_util._is_using_pandas(Y, None):
            result = dmatrices(formula, Y, depth, return_type='dataframe',
                               NA_action=na_action)
        else:
            result = dmatrices(formula, Y, depth, return_type='dataframe',
                               NA_action=na_action)

    # if missing == 'raise' there's not missing_mask
    missing_mask = getattr(na_action, 'missing_mask', None)
    if not np.any(missing_mask):
        missing_mask = None
    if len(result) > 1:  # have RHS design
        design_info = result[1].design_info  # detach it from DataFrame
    else:
        design_info = None
    # NOTE: is there ever a case where we'd need LHS design_info?
    return result, missing_mask, design_info

    def __init__(self, fname, data, convert_dates=None, encoding="latin-1",
                 byteorder=None):

        self._convert_dates = convert_dates
        # attach nobs, nvars, data, varlist, typlist
        if data_util._is_using_pandas(data, None):
            self._prepare_pandas(data)

        elif data_util._is_array_like(data, None):
            data = np.asarray(data)
            if data_util._is_structured_ndarray(data):
                self._prepare_structured_array(data)
            else:
                if convert_dates is not None:
                    raise ValueError("Not able to convert dates in a plain"
                                     " ndarray.")
                self._prepare_ndarray(data)

        else: # pragma : no cover
            raise ValueError("Type %s for data not understood" % type(data))


        if byteorder is None:
            byteorder = sys.byteorder
        self._byteorder = _set_endianness(byteorder)
        self._encoding = encoding
        self._file = _open_file_binary_write(fname, encoding)

def handle_data(endog, exog):
    """
    Given inputs
    """
    # deal with lists and tuples up-front
    if isinstance(endog, (list, tuple)):
        endog = np.asarray(endog)
    if isinstance(exog, (list, tuple)):
        exog = np.asarray(exog)

    if data_util._is_using_pandas(endog, exog):
        klass = PandasData
    elif data_util._is_using_larry(endog, exog):
        klass = LarryData
    elif data_util._is_using_timeseries(endog, exog):
        klass = TimeSeriesData
    elif data_util._is_using_patsy(endog, exog):
        klass = PatsyData
    # keep this check last
    elif data_util._is_using_ndarray(endog, exog):
        klass = ModelData
    else:
        raise ValueError("unrecognized data structures: %s / %s" % (type(endog), type(exog)))

    return klass(endog, exog=exog)

    def __init__(self, fname, data, convert_dates=None, encoding="latin-1",
                 byteorder=None):
        warnings.warn(
            "StataWriter is deprecated as of 0.10.0 and will be removed in a "
            "future version.  Use pandas.DataFrame.to_stata or "
            "pandas.io.stata.StatWriter instead.",
            FutureWarning)

        self._convert_dates = convert_dates
        # attach nobs, nvars, data, varlist, typlist
        if data_util._is_using_pandas(data, None):
            self._prepare_pandas(data)

        elif data_util._is_array_like(data, None):
            data = np.asarray(data)
            if data_util._is_structured_ndarray(data):
                self._prepare_structured_array(data)
            else:
                if convert_dates is not None:
                    raise ValueError("Not able to convert dates in a plain"
                                     " ndarray.")
                self._prepare_ndarray(data)

        else: # pragma : no cover
            raise ValueError("Type %s for data not understood" % type(data))


        if byteorder is None:
            byteorder = sys.byteorder
        self._byteorder = _set_endianness(byteorder)
        self._encoding = encoding
        self._file = get_file_obj(fname, 'wb', encoding)

def auto_arima(endog, freq=None, d=None, D=None, max_p=5, max_q=5, max_P=2, max_Q=2, max_order=5, max_d=2, max_D=1, start_p=2, start_q=2, start_P=1, start_Q=1, stationary=False,
               ic="aic", stepwise=True, trace=False, approximation=None,
               test="adf", seasonal_test="ch", allowdrift=True, allowmean=True, lambda_parameter=None, *args, **kwargs):
        # Parameter Validity Check
    if np.any(np.isnan(endog)):
        raise ValueError("Missing Values in Series")
    origin_endog = endog
    if _is_using_pandas(endog, None):
        endog = np.asarray(endog)
    if len(endog) <= 10:
        raise ValueError("There are too few observations.")
    if np.any(np.isnan(endog)):
        raise ValueError("NaN values in endogenous not allowed")
    if np.all(endog == endog[0]):
        raise ValueError("The endogenous variable is a constant")
    if (not isinstance(freq, int)) or freq <= 1:
        raise ValueError("The frequency parameter must be a integer greater than 1")
    if lambda_parameter is not None:
        if lambda_parameter < 0:
            raise ValueError("The Lambda parameter must be positive")
        if not np.all(endog > 0):
            raise ValueError("Box-Cox Transformation can be only used on positive series.")
        endog = boxcox(endog, lambda_parameter)

    max_p = max_p if max_p <= floor(len(endog) / 3) else floor(len(endog) / 3)
    max_q = max_q if max_q <= floor(len(endog) / 3) else floor(len(endog) / 3)
    max_P = max_P if max_P <= floor(len(endog) / 3 / freq) else floor(len(endog) / 3 / freq)
    max_Q = max_Q if max_Q <= floor(len(endog) / 3 / freq) else floor(len(endog) / 3 / freq)
    if stationary:
        D = 0
        d = 0
    if freq == 1:

def concat(series, axis=0, allow_mix=False):
    """
    Concatenate a set of series.

    Parameters
    ----------
    series : iterable
        An iterable of series to be concatenated
    axis : int, optional
        The axis along which to concatenate. Default is 1 (columns).
    allow_mix : bool
        Whether or not to allow a mix of pandas and non-pandas objects. Default
        is False. If true, the returned object is an ndarray, and additional
        pandas metadata (e.g. column names, indices, etc) is lost.

    Returns
    -------
    concatenated : array or pd.DataFrame
        The concatenated array. Will be a DataFrame if series are pandas
        objects.
    """
    is_pandas = np.r_[[_is_using_pandas(s, None) for s in series]]

    if np.all(is_pandas):
        concatenated = pd.concat(series, axis=axis)
    elif np.all(~is_pandas) or allow_mix:
        concatenated = np.concatenate(series, axis=axis)
    else:
        raise ValueError('Attempted to concatenate Pandas objects with'
                         ' non-Pandas objects with `allow_mix=False`.')

    return concatenated

    def sort(self, data, index=None):
        '''Applies a (potentially hierarchical) sort operation on a numpy array
        or pandas series/dataframe based on the grouping index or a
        user-supplied index.  Returns an object of the same type as the
        original data as well as the matching (sorted) Pandas index.
        '''

        if index is None:
            index = self.index
        if data_util._is_using_ndarray_type(data, None):
            if data.ndim == 1:
                out = pd.Series(data, index=index, copy=True)
                out = out.sort_index()
            else:
                out = pd.DataFrame(data, index=index)
                out = out.sort(inplace=False)  # copies
            return np.array(out), out.index
        elif data_util._is_using_pandas(data, None):
            out = data
            out = out.reindex(index)  # copies?
            out = out.sort_index()
            return out, out.index
        else:
            msg = 'data must be a Numpy array or a Pandas Series/DataFrame'
            raise ValueError(msg)

def _maybe_get_pandas_wrapper_freq(X, trim=None):
    if _is_using_pandas(X, None):
        index = X.index
        func = _get_pandas_wrapper(X, trim)
        freq = index.inferred_freq
        return func, freq
    else:
        return lambda x : x, None

    def new_func(X, *args, **kwargs):
        # quick pass-through for do nothing case
        if not _is_using_pandas(X, None):
            return func(X, *args, **kwargs)

        wrapper_func = _get_pandas_wrapper(X, trim_head, trim_tail, names)
        ret = func(X, *args, **kwargs)
        ret = wrapper_func(ret)
        return ret

def add_constant(data, prepend=True, has_constant='skip'):
    '''
    This appends a column of ones to an array if prepend==False.

    Parameters
    ----------
    data : array-like
        `data` is the column-ordered design matrix
    prepend : bool
        True and the constant is prepended rather than appended.
    has_constant : str {'raise', 'add', 'skip'}
        Behavior if ``data'' already has a constant. The default will return
        data without adding another constant. If 'raise', will raise an
        error if a constant is present. Using 'add' will duplicate the
        constant, if one is present. Has no effect for structured or
        recarrays. There is no checking for a constant in this case.

    Returns
    -------
    data : array
        The original array with a constant (column of ones) as the first or
        last column.
    '''
    if _is_using_pandas(data, None):
        # work on a copy
        return _pandas_add_constant(data.copy(), prepend, has_constant)
    else:
        data = np.asarray(data)
    if not data.dtype.names:
        var0 = data.var(0) == 0
        if np.any(var0):
            if has_constant == 'raise':
                raise ValueError("data already contains a constant.")
            elif has_constant == 'skip':
                return data
            elif has_constant == 'add':
                pass
            else:
                raise ValueError("Option {0} not understood for "
                                 "has_constant.".format(has_constant))
        data = np.column_stack((data, np.ones((data.shape[0], 1))))
        if prepend:
            return np.roll(data, 1, 1)
    else:
        return_rec = data.__class__ is np.recarray
        if prepend:
            ones = np.ones((data.shape[0], 1), dtype=[('const', float)])
            data = nprf.append_fields(ones, data.dtype.names,
                                      [data[i] for i in data.dtype.names],
                                      usemask=False, asrecarray=return_rec)
        else:
            data = nprf.append_fields(data, 'const', np.ones(data.shape[0]),
                                      usemask=False, asrecarray=return_rec)
    return data

def diff(series, k_diff=1, k_seasonal_diff=None, k_seasons=1):
    r"""
    Difference a series simply and/or seasonally along the zero-th axis.

    Given a series (denoted :math:`y_t`), performs the differencing operation

    .. math::

        \Delta^d \Delta_s^D y_t

    where :math:`d =` `diff`, :math:`s =` `k_seasons`,
    :math:`D =` `seasonal\_diff`, and :math:`\Delta` is the difference
    operator.

    Parameters
    ----------
    series : array_like
        The series to be differenced.
    diff : int, optional
        The number of simple differences to perform. Default is 1.
    seasonal_diff : int or None, optional
        The number of seasonal differences to perform. Default is no seasonal
        differencing.
    k_seasons : int, optional
        The seasonal lag. Default is 1. Unused if there is no seasonal
        differencing.

    Returns
    -------
    differenced : array
        The differenced array.
    """
    pandas = _is_using_pandas(series, None)
    differenced = np.asanyarray(series) if not pandas else series

    # Seasonal differencing
    if k_seasonal_diff is not None:
        while k_seasonal_diff > 0:
            if not pandas:
                differenced = (
                    differenced[k_seasons:] - differenced[:-k_seasons]
                )
            else:
                differenced = differenced.diff(k_seasons)[k_seasons:]
            k_seasonal_diff -= 1

    # Simple differencing
    if not pandas:
        differenced = np.diff(differenced, k_diff, axis=0)
    else:
        while k_diff > 0:
            differenced = differenced.diff()[1:]
            k_diff -= 1
    return differenced

def _maybe_get_pandas_wrapper(X, trim_head=None, trim_tail=None):
    """
    If using pandas returns a function to wrap the results, e.g., wrapper(X)
    trim is an integer for the symmetric truncation of the series in some
    filters.
    otherwise returns None
    """
    if _is_using_pandas(X, None):
        return _get_pandas_wrapper(X, trim_head, trim_tail)
    else:
        return lambda x : x

def handle_formula_data(Y, X, formula, depth=0):
    """
    Returns endog, exog, and the model specification from arrays and formula

    Parameters
    ----------
    Y : array-like
        Either endog (the LHS) of a model specification or all of the data.
        Y must define __getitem__ for now.
    X : array-like
        Either exog or None. If all the data for the formula is provided in
        Y then you must explicitly set X to None.
    formula : str or patsy.model_desc
        You can pass a handler by import formula_handler and adding a
        key-value pair where the key is the formula object class and
        the value is a function that returns endog, exog, formula object

    Returns
    -------
    endog : array-like
        Should preserve the input type of Y,X
    exog : array-like
        Should preserve the input type of Y,X. Could be None.
    """
    # half ass attempt to handle other formula objects
    if isinstance(formula, tuple(iterkeys(formula_handler))):
        return formula_handler[type(formula)]

    if X is not None:
        if data_util._is_using_pandas(Y, X):
            return dmatrices(formula, (Y, X), 2, return_type='dataframe')
        else:
            return dmatrices(formula, (Y, X), 2, return_type='dataframe')
    else:
        if data_util._is_using_pandas(Y, None):
            return dmatrices(formula, Y, 2, return_type='dataframe')
        else:
            return dmatrices(formula, Y, 2, return_type='dataframe')

def add_constant(data, prepend=True, has_constant='skip'):
    """
    Adds a column of ones to an array

    Parameters
    ----------
    data : array-like
        `data` is the column-ordered design matrix
    prepend : bool
        If true, the constant is in the first column.  Else the constant is
        appended (last column).
    has_constant : str {'raise', 'add', 'skip'}
        Behavior if ``data'' already has a constant. The default will return
        data without adding another constant. If 'raise', will raise an
        error if a constant is present. Using 'add' will duplicate the
        constant, if one is present.

    Returns
    -------
    data : array, recarray or DataFrame
        The original values with a constant (column of ones) as the first or
        last column. Returned value depends on input type.

    Notes
    -----
    When the input is recarray or a pandas Series or DataFrame, the added
    column's name is 'const'.
    """
    if _is_using_pandas(data, None) or _is_recarray(data):
        from statsmodels.tsa.tsatools import add_trend
        return add_trend(data, trend='c', prepend=prepend, has_constant=has_constant)

    # Special case for NumPy
    x = np.asanyarray(data)
    if x.ndim == 1:
        x = x[:,None]
    elif x.ndim > 2:
        raise ValueError('Only implementd 2-dimensional arrays')

    is_nonzero_const = np.ptp(x, axis=0) == 0
    is_nonzero_const &= np.all(x != 0.0, axis=0)
    if is_nonzero_const.any():
        if has_constant == 'skip':
            return x
        elif has_constant == 'raise':
            raise ValueError("data already contains a constant")

    x = [np.ones(x.shape[0]), x]
    x = x if prepend else x[::-1]
    return np.column_stack(x)

    def __init__(self, endog, exog, **kwargs):
        # Standardize data
        if not _is_using_pandas(endog, None):
            endog = np.asanyarray(endog)

        exog_is_using_pandas = _is_using_pandas(exog, None)
        if not exog_is_using_pandas:
            exog = np.asarray(exog)

        # Make sure we have 2-dimensional array
        if exog.ndim == 1:
            if not exog_is_using_pandas:
                exog = exog[:, None]
            else:
                exog = pd.DataFrame(exog)

        self.k_exog = exog.shape[1]

        # Handle coefficient initialization
        # By default, do not calculate likelihood while it is controlled by
        # diffuse initial conditions.
        kwargs.setdefault('loglikelihood_burn', self.k_exog)
        kwargs.setdefault('initialization', 'approximate_diffuse')
        kwargs.setdefault('initial_variance', 1e9)

        # Initialize the state space representation
        super(RecursiveLS, self).__init__(
            endog, k_states=self.k_exog, exog=exog, **kwargs
        )

        # Setup the state space representation
        self['design'] = self.exog[:, :, None].T
        self['transition'] = np.eye(self.k_states)

        # Notice that the filter output does not depend on the measurement
        # variance, so we set it here to 1
        self['obs_cov', 0, 0] = 1.