Python DataFrame.iteritems方法代碼示例

# 需要導入模塊: from pandas.core.frame import DataFrame [as 別名]
# 或者: from pandas.core.frame.DataFrame import iteritems [as 別名]
class VAR(object):
    """
    Estimates VAR(p) regression on multivariate time series data
    presented in pandas data structures.

    Parameters
    ----------
    data : DataFrame or dict of Series
    p : lags to include

    """

    def __init__(self, data, p=1, intercept=True):
        try:
            import statsmodels.tsa.vector_ar.api as sm_var
        except ImportError:
            import scikits.statsmodels.tsa.var as sm_var

        self._data = DataFrame(_combine_rhs(data))
        self._p = p

        self._columns = self._data.columns
        self._index = self._data.index

        self._intercept = intercept

    @cache_readonly
    def aic(self):
        """Returns the Akaike information criterion."""
        return self._ic['aic']

    @cache_readonly
    def bic(self):
        """Returns the Bayesian information criterion."""
        return self._ic['bic']

    @cache_readonly
    def beta(self):
        """
        Returns a DataFrame, where each column x1 contains the betas
        calculated by regressing the x1 column of the VAR input with
        the lagged input.

        Returns
        -------
        DataFrame
        """
        d = dict([(key, value.beta)
                  for (key, value) in self.ols_results.iteritems()])
        return DataFrame(d)

    def forecast(self, h):
        """
        Returns a DataFrame containing the forecasts for 1, 2, ..., n time
        steps.  Each column x1 contains the forecasts of the x1 column.

        Parameters
        ----------
        n: int
            Number of time steps ahead to forecast.

        Returns
        -------
        DataFrame
        """
        forecast = self._forecast_raw(h)[:, 0, :]
        return DataFrame(forecast, index=xrange(1, 1 + h),
                         columns=self._columns)

    def forecast_cov(self, h):
        """
        Returns the covariance of the forecast residuals.

        Returns
        -------
        DataFrame
        """
        return [DataFrame(value, index=self._columns, columns=self._columns)
                for value in self._forecast_cov_raw(h)]

    def forecast_std_err(self, h):
        """
        Returns the standard errors of the forecast residuals.

        Returns
        -------
        DataFrame
        """
        return DataFrame(self._forecast_std_err_raw(h),
                         index=xrange(1, 1 + h), columns=self._columns)

    @cache_readonly
    def granger_causality(self):
        """Returns the f-stats and p-values from the Granger Causality Test.

        If the data consists of columns x1, x2, x3, then we perform the
        following regressions:

        x1 ~ L(x2, x3)
        x1 ~ L(x1, x3)
#.........這裏部分代碼省略.........

# 需要導入模塊: from pandas.core.frame import DataFrame [as 別名]
# 或者: from pandas.core.frame.DataFrame import iteritems [as 別名]
    def get_chunk(self, rows=None):
        if rows is not None and self.skip_footer:
            raise ValueError('skip_footer not supported for iteration')

        try:
            content = self._get_lines(rows)
        except StopIteration:
            if self._first_chunk:
                content = []
            else:
                raise

        # done with first read, next time raise StopIteration
        self._first_chunk = False

        if len(content) == 0: # pragma: no cover
            if self.index_col is not None:
                if np.isscalar(self.index_col):
                    index = Index([], name=self.index_name)
                else:
                    index = MultiIndex.from_arrays([[]] * len(self.index_col),
                                                   names=self.index_name)
            else:
                index = Index([])

            return DataFrame(index=index, columns=self.columns)

        zipped_content = list(lib.to_object_array(content).T)

        if not self._has_complex_date_col and self.index_col is not None:
            index = self._get_simple_index(zipped_content)
            index = self._agg_index(index)
        else:
            index = Index(np.arange(len(content)))

        col_len, zip_len = len(self.columns), len(zipped_content)
        if col_len != zip_len:
            row_num = -1
            for (i, l) in enumerate(content):
                if len(l) != col_len:
                    break

            footers = 0
            if self.skip_footer:
                footers = self.skip_footer
            row_num = self.pos - (len(content) - i + footers)

            msg = ('Expecting %d columns, got %d in row %d' %
                   (col_len, zip_len, row_num))
            raise ValueError(msg)

        data = dict((k, v) for k, v in izip(self.columns, zipped_content))

        # apply converters
        for col, f in self.converters.iteritems():
            if isinstance(col, int) and col not in self.columns:
                col = self.columns[col]
            data[col] = lib.map_infer(data[col], f)

        columns = list(self.columns)
        if self.parse_dates is not None:
            data, columns = self._process_date_conversion(data)

        data = _convert_to_ndarrays(data, self.na_values, self.verbose)

        df = DataFrame(data=data, columns=columns, index=index)
        if self._has_complex_date_col and self.index_col is not None:
            if not self._name_processed:
                self.index_name = self._get_index_name(list(columns))
                self._name_processed = True
            data = dict(((k, v) for k, v in df.iteritems()))
            index = self._get_complex_date_index(data, col_names=columns,
                                                 parse_dates=False)
            index = self._agg_index(index, False)
            data = dict(((k, v.values) for k, v in data.iteritems()))
            df = DataFrame(data=data, columns=columns, index=index)

        if self.squeeze and len(df.columns) == 1:
            return df[df.columns[0]]
        return df