Python pandas.DatetimeIndex方法代码示例

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def match_times(stop_id, estimates, schedule):
    # This technique finds the closest scheduled time to actual arrivals
    # This is flawed since it does not account for scheduled arrivals where
    # a train never arrived.
    # It's difficult to search the other way around however, since our estimated
    # arrival times are incomplete (see "select.dropna" in "estimate_arrivals").
    # If we search for the closest estimated arrival to each scheduled stop,
    # we will get some that are far apart because the actual train was likely associated
    # with a different scheduled stop time.
    # This way seems to be fairer on Metro, but we are open to improvements!

    # Try clause is here because there was an unexplained bug occurring on April 10 2019 with data inputs from around 1:35pm. There was an index (-1) out of range error.
    # Exact cause of the issue is still uncertain but there was a vehicle position observation out of range on the blue line at that time.
    try:
        estimates.loc[:, "closest_scheduled"] = estimates.datetime_utc.apply(
            lambda x: schedule.index[schedule.index.get_loc(x, method="nearest")]
        )
        estimates.loc[:, "closest_scheduled"] = pd.DatetimeIndex(
            estimates["closest_scheduled"]
        )
        return estimates
    except:
        return None 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def match_arrivals_with_schedule(estimated_trips, schedule_direction):
    schedule_direction.loc[:,"datetime_utc"] = pd.to_datetime(schedule_direction["datetime"], utc=True)
    estimated_trips.loc[:,"datetime_utc"] = pd.to_datetime(estimated_trips["datetime"], utc=True)
    schedule_direction = schedule_direction.set_index(pd.DatetimeIndex(schedule_direction["datetime_utc"])).sort_index()
    matched_estimates = [
        match_times(
            stop_id,
            stop_estimates,
            schedule_direction[schedule_direction["stop_id"] == stop_id],
        )
        for stop_id, stop_estimates in estimated_trips.groupby(["stop_id"])
    ]
    matched_estimates = [x for x in matched_estimates if x is not None]
    matched_estimates = pd.concat(matched_estimates)
    matched_estimates["since_scheduled"] = (
        matched_estimates["datetime_utc"] - matched_estimates["closest_scheduled"]
    )
    return matched_estimates 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def _multi_index_to_records(index, empty_index):
    # array of tuples to numpy cols. copy copy copy
    if not empty_index:
        ix_vals = list(map(np.array, [index.get_level_values(i) for i in range(index.nlevels)]))
    else:
        # empty multi index has no size, create empty arrays for recarry.
        ix_vals = [np.array([]) for n in index.names]
    index_names = list(index.names)
    count = 0
    for i, n in enumerate(index_names):
        if n is None:
            index_names[i] = 'level_%d' % count
            count += 1
            log.info("Level in MultiIndex has no name, defaulting to %s" % index_names[i])
    index_tz = [get_timezone(i.tz) if isinstance(i, DatetimeIndex) else None for i in index.levels]
    return ix_vals, index_names, index_tz 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def _index_to_records(self, df):
        metadata = {}
        index = df.index
        index_tz = None

        if isinstance(index, MultiIndex):
            ix_vals, index_names, index_tz = _multi_index_to_records(index, len(df) == 0)
        else:
            ix_vals = [index.values]
            index_names = list(index.names)
            if index_names[0] is None:
                index_names = ['index']
                log.info("Index has no name, defaulting to 'index'")
            if isinstance(index, DatetimeIndex) and index.tz is not None:
                index_tz = get_timezone(index.tz)

        if index_tz is not None:
            metadata['index_tz'] = index_tz
        metadata['index'] = index_names

        return index_names, ix_vals, metadata 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def _index_from_records(self, recarr):
        index = recarr.dtype.metadata['index']

        if len(index) == 1:
            rtn = Index(np.copy(recarr[str(index[0])]), name=index[0])
            if isinstance(rtn, DatetimeIndex) and 'index_tz' in recarr.dtype.metadata:
                rtn = rtn.tz_localize('UTC').tz_convert(recarr.dtype.metadata['index_tz'])
        else:
            level_arrays = []
            index_tz = recarr.dtype.metadata.get('index_tz', [])
            for level_no, index_name in enumerate(index):
                # build each index level separately to ensure we end up with the right index dtype
                level = Index(np.copy(recarr[str(index_name)]))
                if level_no < len(index_tz):
                    tz = index_tz[level_no]
                    if tz is not None:
                        if not isinstance(level, DatetimeIndex) and len(level) == 0:
                            # index type information got lost during save as the index was empty, cast back
                            level = DatetimeIndex([], tz=tz)
                        else:
                            level = level.tz_localize('UTC').tz_convert(tz)
                level_arrays.append(level)
            rtn = MultiIndex.from_arrays(level_arrays, names=index)
        return rtn 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def to_mongo(self, range_obj):
        """
        takes the range object used for this chunker type
        and converts it into a string that can be use for a
        mongo query that filters by the range

        returns
        -------
        dict
        """
        if isinstance(range_obj, (pd.DatetimeIndex, tuple)):
            range_obj = DateRange(range_obj[0], range_obj[-1])
        if range_obj.start and range_obj.end:
            return {'$and': [{START: {'$lte': range_obj.end}}, {END: {'$gte': range_obj.start}}]}
        elif range_obj.start:
            return {END: {'$gte': range_obj.start}}
        elif range_obj.end:
            return {START: {'$lte': range_obj.end}}
        else:
            return {} 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def exclude(self, data, range_obj):
        """
        Removes data within the bounds of the range object (inclusive)

        returns
        -------
        data, filtered by range_obj
        """
        if isinstance(range_obj, (pd.DatetimeIndex, tuple)):
            range_obj = DateRange(range_obj[0], range_obj[-1])
        if 'date' in data.index.names:
            return data[(data.index.get_level_values('date') < range_obj.start) | (data.index.get_level_values('date') > range_obj.end)]
        elif 'date' in data.columns:
            return data[(data.date < range_obj.start) | (data.date > range_obj.end)]
        else:
            return data 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def test_missing_cols(chunkstore_lib):
    index = DatetimeIndex(pd.date_range('2019-01-01', periods=3, freq='D'), name='date')
    index2 = DatetimeIndex(pd.date_range('2019-01-04', periods=3, freq='D'), name='date')
    expected_index = DatetimeIndex(pd.date_range('2019-01-01', periods=6, freq='D'), name='date')
    expected_df = DataFrame({'A': [1, 2, 3, 40, 50, 60], 'B': [5.0,6.0,7.0, np.nan, np.nan, np.nan]}, index=expected_index)

    df = pd.DataFrame({'A': [1, 2, 3], 'B': [5,6,7]}, index=index)
    chunkstore_lib.write('test', df, chunk_size='D')

    df = pd.DataFrame({'A': [40, 50, 60]}, index=index2)
    chunkstore_lib.append('test', df, chunk_size='D')


    assert_frame_equal(chunkstore_lib.read('test'), expected_df)
    df = chunkstore_lib.read('test', columns=['B'])
    assert_frame_equal(df, expected_df['B'].to_frame()) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def test_dataframe_append_should_add_new_column(library):
    data = np.zeros((2,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a10')])
    data[:] = [(1, 2., 'Hello'), (2, 3., "World")]
    df = DataFrame(data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                       dt(2013, 1, 2)]).astype('datetime64[ns]'), name='DATETIME'))
    data2 = np.zeros((1,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a10'), ('D', 'f4')])
    data2[:] = [(4, 5., 'Hi', 6.)]
    df2 = DataFrame(data2, index=DatetimeIndex(np.array([dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))
    expected_data = np.zeros((3,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a10'), ('D', 'f4')])
    expected_data[:] = [(1, 2., 'Hello', np.nan), (2, 3., "World", np.nan), (4, 5., 'Hi', 6.)]
    expected = DataFrame(expected_data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                                       dt(2013, 1, 2),
                                                                       dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))

    library.write('pandas', df)
    library.append('pandas', df2)
    actual = library.read('pandas').data

    assert_frame_equal(expected, actual) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def test_dataframe_append_should_add_new_columns_and_reorder(library):
    data = np.zeros((2,), dtype=[('A', 'i4'), ('B', 'f4'), ('C', 'a10')])
    data[:] = [(1, 2., 'Hello'), (2, 3., "World")]
    df = DataFrame(data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                       dt(2013, 1, 2)]).astype('datetime64[ns]'), name='DATETIME'))
    data2 = np.zeros((1,), dtype=[('C', 'a10'), ('A', 'i4'), ('E', 'a1'), ('B', 'f4'), ('D', 'f4'), ('F', 'i4')])
    data2[:] = [('Hi', 4, 'Y', 5., 6., 7)]
    df2 = DataFrame(data2, index=DatetimeIndex(np.array([dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))
    expected_data = np.zeros((3,), dtype=[('C', 'a10'), ('A', 'i4'), ('E', 'a1'),
                                          ('B', 'f4'), ('D', 'f4'), ('F', 'i4')])
    expected_data[:] = [('Hello', 1, '', 2., np.nan, 0), ("World", 2, '', 3., np.nan, 0), ('Hi', 4, 'Y', 5., 6., 7)]
    expected = DataFrame(expected_data, index=DatetimeIndex(np.array([dt(2013, 1, 1),
                                                                       dt(2013, 1, 2),
                                                                       dt(2013, 1, 3)]).astype('datetime64[ns]'), name='DATETIME'))

    library.write('pandas', df)
    library.append('pandas', df2)
    actual = library.read('pandas').data

    assert_frame_equal(expected, actual)


# -- auto generated tests --- # 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def test_map_dictlike(self, mapper):
        expected = self.index + self.index.freq

        # don't compare the freqs
        if isinstance(expected, pd.DatetimeIndex):
            expected.freq = None

        result = self.index.map(mapper(expected, self.index))
        tm.assert_index_equal(result, expected)

        expected = pd.Index([pd.NaT] + self.index[1:].tolist())
        result = self.index.map(mapper(expected, self.index))
        tm.assert_index_equal(result, expected)

        # empty map; these map to np.nan because we cannot know
        # to re-infer things
        expected = pd.Index([np.nan] * len(self.index))
        result = self.index.map(mapper([], []))
        tm.assert_index_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def test_constructor_from_index_dtlike(self, cast_as_obj, index):
        if cast_as_obj:
            result = pd.Index(index.astype(object))
        else:
            result = pd.Index(index)

        tm.assert_index_equal(result, index)

        if isinstance(index, pd.DatetimeIndex):
            assert result.tz == index.tz
            if cast_as_obj:
                # GH#23524 check that Index(dti, dtype=object) does not
                #  incorrectly raise ValueError, and that nanoseconds are not
                #  dropped
                index += pd.Timedelta(nanoseconds=50)
                result = pd.Index(index, dtype=object)
                assert result.dtype == np.object_
                assert list(result) == list(index) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def test_constructor_from_frame_series_freq(self):
        # GH 6273
        # create from a series, passing a freq
        dts = ['1-1-1990', '2-1-1990', '3-1-1990', '4-1-1990', '5-1-1990']
        expected = DatetimeIndex(dts, freq='MS')

        df = pd.DataFrame(np.random.rand(5, 3))
        df['date'] = dts
        result = DatetimeIndex(df['date'], freq='MS')

        assert df['date'].dtype == object
        expected.name = 'date'
        tm.assert_index_equal(result, expected)

        expected = pd.Series(dts, name='date')
        tm.assert_series_equal(df['date'], expected)

        # GH 6274
        # infer freq of same
        freq = pd.infer_freq(df['date'])
        assert freq == 'MS' 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def test_union(self, tz):
        rng1 = pd.date_range('1/1/2000', freq='D', periods=5, tz=tz)
        other1 = pd.date_range('1/6/2000', freq='D', periods=5, tz=tz)
        expected1 = pd.date_range('1/1/2000', freq='D', periods=10, tz=tz)

        rng2 = pd.date_range('1/1/2000', freq='D', periods=5, tz=tz)
        other2 = pd.date_range('1/4/2000', freq='D', periods=5, tz=tz)
        expected2 = pd.date_range('1/1/2000', freq='D', periods=8, tz=tz)

        rng3 = pd.date_range('1/1/2000', freq='D', periods=5, tz=tz)
        other3 = pd.DatetimeIndex([], tz=tz)
        expected3 = pd.date_range('1/1/2000', freq='D', periods=5, tz=tz)

        for rng, other, expected in [(rng1, other1, expected1),
                                     (rng2, other2, expected2),
                                     (rng3, other3, expected3)]:

            result_union = rng.union(other)
            tm.assert_index_equal(result_union, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import DatetimeIndex [as 别名]
def test_difference(self, tz, sort):
        rng_dates = ['1/2/2000', '1/3/2000', '1/1/2000', '1/4/2000',
                     '1/5/2000']

        rng1 = pd.DatetimeIndex(rng_dates, tz=tz)
        other1 = pd.date_range('1/6/2000', freq='D', periods=5, tz=tz)
        expected1 = pd.DatetimeIndex(rng_dates, tz=tz)

        rng2 = pd.DatetimeIndex(rng_dates, tz=tz)
        other2 = pd.date_range('1/4/2000', freq='D', periods=5, tz=tz)
        expected2 = pd.DatetimeIndex(rng_dates[:3], tz=tz)

        rng3 = pd.DatetimeIndex(rng_dates, tz=tz)
        other3 = pd.DatetimeIndex([], tz=tz)
        expected3 = pd.DatetimeIndex(rng_dates, tz=tz)

        for rng, other, expected in [(rng1, other1, expected1),
                                     (rng2, other2, expected2),
                                     (rng3, other3, expected3)]:
            result_diff = rng.difference(other, sort)
            if sort is None:
                expected = expected.sort_values()
            tm.assert_index_equal(result_diff, expected)