Python pandas 模块，RangeIndex() 实例源码

def setattributeindex(self, instance, value):
        bus_name = instance.bus.index
        instance.branch['F_BUS'] = instance.branch['F_BUS'].apply(lambda x: value[bus_name.get_loc(x)])
        instance.branch['T_BUS'] = instance.branch['T_BUS'].apply(lambda x: value[bus_name.get_loc(x)])
        instance.gen['GEN_BUS'] = instance.gen['GEN_BUS'].apply(lambda x: value[bus_name.get_loc(x)])

        try:
            instance.load.columns = [v for b, v in zip(instance.bus_name.isin(instance.load.columns), value) if b == True]
        except ValueError:
            instance.load.columns = value
        except AttributeError:
            instance.load = pd.DataFrame(0, index=range(0, 1), columns=value, dtype='float')

        instance.bus.index = value

        if isinstance(instance.bus_name, pd.RangeIndex) or isinstance(instance.bus_name, pd.Int64Index):
            logger.debug('Forcing string types for all bus names')
            instance.bus_name = ['Bus{}'.format(b) for b in instance.bus_name]

def test_check_exact_times_true(self):
        self.pm.check_timestamp(3600, exact_times=True)
        expected = pd.DataFrame(
            array([['', '', Timestamp('2016-10-17 02:05:00'),
                   Timestamp('2016-10-17 03:05:00'), 2,
                   'Missing timestamp']], dtype=object),
            columns=['System Name', 'Variable Name', 'Start Date', 'End Date', 'Timesteps', 'Error Flag'],
            index=RangeIndex(start=0, stop=1, step=1)
            )
        assert_frame_equal(expected, self.pm.test_results)

def test_check_exact_times_false(self):
        self.pm.check_timestamp(3600, exact_times=False)
        expected = pd.DataFrame(
            array([['', '', Timestamp('2016-10-17 02:00:00'),
                    Timestamp('2016-10-17 02:00:00'), 1, 'Missing timestamp']], dtype=object),
            columns=['System Name', 'Variable Name', 'Start Date', 'End Date', 'Timesteps', 'Error Flag'],
            index=RangeIndex(start=0, stop=1, step=1)
            )
        assert_frame_equal(expected, self.pm.test_results)

def test_check_exact_times_true_with_start_time(self):
        self.pm.check_timestamp(3600, expected_start_time=Timestamp('2016-10-17 01:00:00'), exact_times=True)
        expected = pd.DataFrame(
            array([['', '', Timestamp('2016-10-17 01:00:00'),
                   Timestamp('2016-10-17 03:00:00'), 3,
                   'Missing timestamp']], dtype=object),
            columns=['System Name', 'Variable Name', 'Start Date', 'End Date', 'Timesteps', 'Error Flag'],
            index=RangeIndex(start=0, stop=1, step=1)
            )
        assert_frame_equal(expected, self.pm.test_results)

def test_deadsensor(self):
        # dead sensor = < 1 in 5 hours
        self.pm.check_delta([1, None], window=5*3600+1, absolute_value=True)
        expected = pd.DataFrame(
            array([['Test', 'A', Timestamp('2017-01-01 00:00:00'), Timestamp('2017-01-01 05:00:00'), 6, '|Delta| < lower bound, 1'],
                   ['Test', 'A', Timestamp('2017-01-01 16:00:00'), Timestamp('2017-01-01 23:00:00'), 8, '|Delta| < lower bound, 1']], dtype=object),
            columns=['System Name', 'Variable Name', 'Start Date', 'End Date', 'Timesteps', 'Error Flag'],
            index=RangeIndex(start=0, stop=2, step=1)
            )
        assert_frame_equal(expected, self.pm.test_results)

def test_abrupt_change(self):
        # abrupt change = > 7 in 3 hours
        self.pm.check_delta([None, 7], window=3*3600+1, absolute_value=True)
        expected = pd.DataFrame(
            array([['Test', 'A', Timestamp('2017-01-01 13:00:00'), Timestamp('2017-01-01 16:00:00'), 4, '|Delta| > upper bound, 7'],
                   ['Test', 'B', Timestamp('2017-01-01 10:00:00'), Timestamp('2017-01-01 12:00:00'), 3, '|Delta| > upper bound, 7'],
                   ['Test', 'B', Timestamp('2017-01-01 16:00:00'), Timestamp('2017-01-01 19:00:00'), 4, '|Delta| > upper bound, 7']], dtype=object),
            columns=['System Name', 'Variable Name', 'Start Date', 'End Date', 'Timesteps', 'Error Flag'],
            index=RangeIndex(start=0, stop=3, step=1)
            )
        assert_frame_equal(expected, self.pm.test_results)

def test_abrupt_negative_change(self):
        # abrupt negative change = < -7 in 3 hours
        self.pm.check_delta([-7, None], window=3*3600+1, absolute_value=False)
        expected = pd.DataFrame(
            array([['Test', 'B', Timestamp('2017-01-01 10:00:00'), Timestamp('2017-01-01 12:00:00'), 3, 'Delta < lower bound, -7']], dtype=object),
            columns=['System Name', 'Variable Name', 'Start Date', 'End Date', 'Timesteps', 'Error Flag'],
            index=RangeIndex(start=0, stop=1, step=1)
            )
        assert_frame_equal(expected, self.pm.test_results)

def test_outlier(self):
        # outlier if stdev > 1.9
        self.pm.check_outlier([-1.9, 1.9], window=None, absolute_value=False)
        expected = pd.DataFrame(
            array([['Test', 'A', Timestamp('2017-01-01 19:00:00'), Timestamp('2017-01-01 19:00:00'), 1, 'Outlier < lower bound, -1.9'],
                   ['Test', 'A', Timestamp('2017-01-01 06:00:00'), Timestamp('2017-01-01 06:00:00'), 1, 'Outlier > upper bound, 1.9']], dtype=object),
            columns=['System Name', 'Variable Name', 'Start Date', 'End Date', 'Timesteps', 'Error Flag'],
            index=RangeIndex(start=0, stop=2, step=1)
            )
        assert_frame_equal(expected, self.pm.test_results)

def transform(self, dataframe, display_schema):
        csv_df = self._format_columns(dataframe, display_schema['metrics'], display_schema['dimensions'])

        if isinstance(dataframe.index, pd.RangeIndex):
            # If there are no dimensions, just serialize to csv without the index
            return csv_df.to_csv(index=False)

        csv_df = self._format_index(csv_df, display_schema['dimensions'])

        row_dimension_labels = self._format_row_dimension_labels(display_schema['dimensions'])
        return csv_df.to_csv(index_label=row_dimension_labels)

def calc_ladder(scores_df, year=2016):
    '''
    DataFrame with championship ladder with round-robin games for the given year.
    Wins, draws and losses are worth 4, 2 and 0 points respectively.
    '''
    # Select a subset of the rows
    # df.loc[] matches dates as strings like '20160506' or '2016'.
    # Note here rounds are simple strings so sort with R1 < R10 < R2 < .. < R9
    #      (we could change this with a CategoricalIndex)
    # Note also that pandas 0.18.0 has a bug with .loc on MultiIndexes
    #      if dates are the first level. It works as expected if we
    #      move the dates to the end before slicing
    scores2 = scores_df.reorder_levels([1, 2, 3, 0]).sort_index()
    x = scores2.loc(axis=0)[:, 'R1':'R9', :, str(year):str(year)]
    # Don't need to put levels back in order as we are about to drop 3 of them
    # x = x.reorder_levels([3, 0, 1, 2]).sort_index()

    # Just keep Team. This does a copy too, avoiding SettingWithCopy warning
    y = x.reset_index(['Date', 'Venue', 'Round'], drop=True)

    # Add cols with 0/1 for number of games played, won, drawn and lost
    y['P'] = 1
    y['W'] = (y['F'] > y['A']).astype(int)
    y['D'] = 0
    y.loc[y['F'] == y['A'], 'D'] = 1
    y.eval('L = 1*(A>F)', inplace=True)
    print(y)

    # Subtotal by team and then sort by Points/Percentage
    t = y.groupby(level='Team').sum()
    t['PCT'] = 100.0 * t.F / t.A
    t['PTS'] = 4 * t['W'] + 2 * t['D']
    ladder = t.sort_values(['PTS', 'PCT'], ascending=False)

    # Add ladder position (note: assumes no ties!)
    ladder['Pos'] = pd.RangeIndex(1, len(ladder) + 1)
    print(ladder)

    return ladder

def setattributeindex(self, instance, value):
        instance.gen.index = value
        instance.gencost.index = value

        if isinstance(instance.gen_name, pd.RangeIndex) or isinstance(instance.bus_name, pd.Int64Index):
            instance.gen_name = ['GenCo{}'.format(g) for g in instance.gen_name]

def make_meta(x):
    """Create an empty pygdf object containing the desired metadata.

    Parameters
    ----------
    x : dict, tuple, list, pd.Series, pd.DataFrame, pd.Index, dtype, scalar
        To create a DataFrame, provide a `dict` mapping of `{name: dtype}`, or
        an iterable of `(name, dtype)` tuples. To create a `Series`, provide a
        tuple of `(name, dtype)`. If a pygdf object, names, dtypes, and index
        should match the desired output. If a dtype or scalar, a scalar of the
        same dtype is returned.

    Examples
    --------
    >>> make_meta([('a', 'i8'), ('b', 'O')])
    Empty DataFrame
    Columns: [a, b]
    Index: []
    >>> make_meta(('a', 'f8'))
    Series([], Name: a, dtype: float64)
    >>> make_meta('i8')
    1
    """
    if hasattr(x, '_meta'):
        return x._meta
    if isinstance(x, (gd.Series, gd.DataFrame, gd.index.Index)):
        out = x[:2]
        return out.copy() if hasattr(out, 'copy') else out

    meta = dd.utils.make_meta(x)

    if isinstance(meta, (pd.DataFrame, pd.Series, pd.Index)):
        meta2 = dd.utils.meta_nonempty(meta)
        if isinstance(meta2, pd.DataFrame):
            return gd.DataFrame.from_pandas(meta2)
        elif isinstance(meta2, pd.Series):
            return gd.Series.from_any(meta2)
        else:
            if isinstance(meta2, pd.RangeIndex):
                return gd.index.RangeIndex(meta2.start, meta2.stop)
            return gd.index.GenericIndex(meta2)

    return meta