Python pandas.core.tools.datetimes.to_datetime() Examples

def test_parse_tz_aware(self):
        # See gh-1693
        import pytz
        data = StringIO("Date,x\n2012-06-13T01:39:00Z,0.5")

        # it works
        result = self.read_csv(data, index_col=0, parse_dates=True)
        stamp = result.index[0]
        assert stamp.minute == 39
        try:
            assert result.index.tz is pytz.utc
        except AssertionError:  # hello Yaroslav
            arr = result.index.to_pydatetime()
            result = tools.to_datetime(arr, utc=True)[0]
            assert stamp.minute == result.minute
            assert stamp.hour == result.hour
            assert stamp.day == result.day 

def _handle_date_column(col, utc=None, format=None):
    if isinstance(format, dict):
        return to_datetime(col, errors='ignore', **format)
    else:
        # Allow passing of formatting string for integers
        # GH17855
        if format is None and (issubclass(col.dtype.type, np.floating) or
                               issubclass(col.dtype.type, np.integer)):
            format = 's'
        if format in ['D', 'd', 'h', 'm', 's', 'ms', 'us', 'ns']:
            return to_datetime(col, errors='coerce', unit=format, utc=utc)
        elif is_datetime64tz_dtype(col):
            # coerce to UTC timezone
            # GH11216
            return to_datetime(col, utc=True)
        else:
            return to_datetime(col, errors='coerce', format=format, utc=utc) 

def _handle_date_column(col, utc=None, format=None):
    if isinstance(format, dict):
        return to_datetime(col, errors='ignore', **format)
    else:
        # Allow passing of formatting string for integers
        # GH17855
        if format is None and (issubclass(col.dtype.type, np.floating) or
                               issubclass(col.dtype.type, np.integer)):
            format = 's'
        if format in ['D', 'd', 'h', 'm', 's', 'ms', 'us', 'ns']:
            return to_datetime(col, errors='coerce', unit=format, utc=utc)
        elif is_datetime64tz_dtype(col):
            # coerce to UTC timezone
            # GH11216
            return (to_datetime(col, errors='coerce')
                    .astype('datetime64[ns, UTC]'))
        else:
            return to_datetime(col, errors='coerce', format=format, utc=utc) 

def test_parse_tz_aware(self):
        # See gh-1693
        import pytz
        data = StringIO("Date,x\n2012-06-13T01:39:00Z,0.5")

        # it works
        result = self.read_csv(data, index_col=0, parse_dates=True)
        stamp = result.index[0]
        assert stamp.minute == 39
        try:
            assert result.index.tz is pytz.utc
        except AssertionError:  # hello Yaroslav
            arr = result.index.to_pydatetime()
            result = tools.to_datetime(arr, utc=True)[0]
            assert stamp.minute == result.minute
            assert stamp.hour == result.hour
            assert stamp.day == result.day 

def _handle_date_column(col, utc=None, format=None):
    if isinstance(format, dict):
        return to_datetime(col, errors='ignore', **format)
    else:
        if format in ['D', 's', 'ms', 'us', 'ns']:
            return to_datetime(col, errors='coerce', unit=format, utc=utc)
        elif (issubclass(col.dtype.type, np.floating) or
              issubclass(col.dtype.type, np.integer)):
            # parse dates as timestamp
            format = 's' if format is None else format
            return to_datetime(col, errors='coerce', unit=format, utc=utc)
        elif is_datetime64tz_dtype(col):
            # coerce to UTC timezone
            # GH11216
            return (to_datetime(col, errors='coerce')
                    .astype('datetime64[ns, UTC]'))
        else:
            return to_datetime(col, errors='coerce', format=format, utc=utc) 

def test_parse_tz_aware(self):
        # See gh-1693
        import pytz
        data = StringIO("Date,x\n2012-06-13T01:39:00Z,0.5")

        # it works
        result = self.read_csv(data, index_col=0, parse_dates=True)
        stamp = result.index[0]
        assert stamp.minute == 39
        try:
            assert result.index.tz is pytz.utc
        except AssertionError:  # hello Yaroslav
            arr = result.index.to_pydatetime()
            result = tools.to_datetime(arr, utc=True)[0]
            assert stamp.minute == result.minute
            assert stamp.hour == result.hour
            assert stamp.day == result.day 

def _handle_date_column(col, utc=None, format=None):
    if isinstance(format, dict):
        return to_datetime(col, errors='ignore', **format)
    else:
        # Allow passing of formatting string for integers
        # GH17855
        if format is None and (issubclass(col.dtype.type, np.floating) or
                               issubclass(col.dtype.type, np.integer)):
            format = 's'
        if format in ['D', 'd', 'h', 'm', 's', 'ms', 'us', 'ns']:
            return to_datetime(col, errors='coerce', unit=format, utc=utc)
        elif is_datetime64tz_dtype(col):
            # coerce to UTC timezone
            # GH11216
            return to_datetime(col, utc=True)
        else:
            return to_datetime(col, errors='coerce', format=format, utc=utc) 

def test_non_datetimeindex(self):
        dates = to_datetime(['1/1/2000', '1/2/2000', '1/3/2000'])
        assert frequencies.infer_freq(dates) == 'D' 

def _make_date_converter(date_parser=None, dayfirst=False,
                         infer_datetime_format=False):
    def converter(*date_cols):
        if date_parser is None:
            strs = _concat_date_cols(date_cols)

            try:
                return tools.to_datetime(
                    ensure_object(strs),
                    utc=None,
                    box=False,
                    dayfirst=dayfirst,
                    errors='ignore',
                    infer_datetime_format=infer_datetime_format
                )
            except ValueError:
                return tools.to_datetime(
                    parsing.try_parse_dates(strs, dayfirst=dayfirst))
        else:
            try:
                result = tools.to_datetime(
                    date_parser(*date_cols), errors='ignore')
                if isinstance(result, datetime.datetime):
                    raise Exception('scalar parser')
                return result
            except Exception:
                try:
                    return tools.to_datetime(
                        parsing.try_parse_dates(_concat_date_cols(date_cols),
                                                parser=date_parser,
                                                dayfirst=dayfirst),
                        errors='ignore')
                except Exception:
                    return generic_parser(date_parser, *date_cols)

    return converter 

def time2num(d):
    if isinstance(d, compat.string_types):
        parsed = tools.to_datetime(d)
        if not isinstance(parsed, datetime):
            raise ValueError('Could not parse time %s' % d)
        return _to_ordinalf(parsed.time())
    if isinstance(d, pydt.time):
        return _to_ordinalf(d)
    return d 

def _convert_1d(values, unit, axis):
        def try_parse(values):
            try:
                return _dt_to_float_ordinal(tools.to_datetime(values))
            except Exception:
                return values

        if isinstance(values, (datetime, pydt.date)):
            return _dt_to_float_ordinal(values)
        elif isinstance(values, np.datetime64):
            return _dt_to_float_ordinal(lib.Timestamp(values))
        elif isinstance(values, pydt.time):
            return dates.date2num(values)
        elif (is_integer(values) or is_float(values)):
            return values
        elif isinstance(values, compat.string_types):
            return try_parse(values)
        elif isinstance(values, (list, tuple, np.ndarray, Index)):
            if isinstance(values, Index):
                values = values.values
            if not isinstance(values, np.ndarray):
                values = com._asarray_tuplesafe(values)

            if is_integer_dtype(values) or is_float_dtype(values):
                return values

            try:
                values = tools.to_datetime(values)
                if isinstance(values, Index):
                    values = _dt_to_float_ordinal(values)
                else:
                    values = [_dt_to_float_ordinal(x) for x in values]
            except Exception:
                values = _dt_to_float_ordinal(values)

        return values 

def to_datetime(self, dayfirst=False):
        return self.copy() 

def _generate_regular_range(start, end, periods, offset):
    if isinstance(offset, Tick):
        stride = offset.nanos
        if periods is None:
            b = Timestamp(start).value
            # cannot just use e = Timestamp(end) + 1 because arange breaks when
            # stride is too large, see GH10887
            e = (b + (Timestamp(end).value - b) // stride * stride +
                 stride // 2 + 1)
            # end.tz == start.tz by this point due to _generate implementation
            tz = start.tz
        elif start is not None:
            b = Timestamp(start).value
            e = b + np.int64(periods) * stride
            tz = start.tz
        elif end is not None:
            e = Timestamp(end).value + stride
            b = e - np.int64(periods) * stride
            tz = end.tz
        else:
            raise ValueError("at least 'start' or 'end' should be specified "
                             "if a 'period' is given.")

        data = np.arange(b, e, stride, dtype=np.int64)
        data = DatetimeIndex._simple_new(data, None, tz=tz)
    else:
        if isinstance(start, Timestamp):
            start = start.to_pydatetime()

        if isinstance(end, Timestamp):
            end = end.to_pydatetime()

        xdr = generate_range(start=start, end=end,
                             periods=periods, offset=offset)

        dates = list(xdr)
        # utc = len(dates) > 0 and dates[0].tzinfo is not None
        data = tools.to_datetime(dates)

    return data 

def _make_date_converter(date_parser=None, dayfirst=False,
                         infer_datetime_format=False):
    def converter(*date_cols):
        if date_parser is None:
            strs = _concat_date_cols(date_cols)

            try:
                return tools.to_datetime(
                    _ensure_object(strs),
                    utc=None,
                    box=False,
                    dayfirst=dayfirst,
                    errors='ignore',
                    infer_datetime_format=infer_datetime_format
                )
            except:
                return tools.to_datetime(
                    parsing.try_parse_dates(strs, dayfirst=dayfirst))
        else:
            try:
                result = tools.to_datetime(
                    date_parser(*date_cols), errors='ignore')
                if isinstance(result, datetime.datetime):
                    raise Exception('scalar parser')
                return result
            except Exception:
                try:
                    return tools.to_datetime(
                        parsing.try_parse_dates(_concat_date_cols(date_cols),
                                                parser=date_parser,
                                                dayfirst=dayfirst),
                        errors='ignore')
                except Exception:
                    return generic_parser(date_parser, *date_cols)

    return converter 

def time2num(d):
    if isinstance(d, compat.string_types):
        parsed = tools.to_datetime(d)
        if not isinstance(parsed, datetime):
            raise ValueError('Could not parse time %s' % d)
        return _to_ordinalf(parsed.time())
    if isinstance(d, pydt.time):
        return _to_ordinalf(d)
    return d 

def _convert_1d(values, unit, axis):
        def try_parse(values):
            try:
                return _dt_to_float_ordinal(tools.to_datetime(values))
            except Exception:
                return values

        if isinstance(values, (datetime, pydt.date)):
            return _dt_to_float_ordinal(values)
        elif isinstance(values, np.datetime64):
            return _dt_to_float_ordinal(lib.Timestamp(values))
        elif isinstance(values, pydt.time):
            return dates.date2num(values)
        elif (is_integer(values) or is_float(values)):
            return values
        elif isinstance(values, compat.string_types):
            return try_parse(values)
        elif isinstance(values, (list, tuple, np.ndarray, Index)):
            if isinstance(values, Index):
                values = values.values
            if not isinstance(values, np.ndarray):
                values = com._asarray_tuplesafe(values)

            if is_integer_dtype(values) or is_float_dtype(values):
                return values

            try:
                values = tools.to_datetime(values)
                if isinstance(values, Index):
                    values = _dt_to_float_ordinal(values)
                else:
                    values = [_dt_to_float_ordinal(x) for x in values]
            except Exception:
                values = _dt_to_float_ordinal(values)

        return values 

def test_combine_first_dt64(self):
        from pandas.core.tools.datetimes import to_datetime
        s0 = to_datetime(Series(["2010", np.NaN]))
        s1 = to_datetime(Series([np.NaN, "2011"]))
        rs = s0.combine_first(s1)
        xp = to_datetime(Series(['2010', '2011']))
        assert_series_equal(rs, xp)

        s0 = to_datetime(Series(["2010", np.NaN]))
        s1 = Series([np.NaN, "2011"])
        rs = s0.combine_first(s1)
        xp = Series([datetime(2010, 1, 1), '2011'])
        assert_series_equal(rs, xp) 

def test_combine_first_dt64(self):
        from pandas.core.tools.datetimes import to_datetime
        s0 = to_datetime(Series(["2010", np.NaN]))
        s1 = to_datetime(Series([np.NaN, "2011"]))
        rs = s0.combine_first(s1)
        xp = to_datetime(Series(['2010', '2011']))
        assert_series_equal(rs, xp)

        s0 = to_datetime(Series(["2010", np.NaN]))
        s1 = Series([np.NaN, "2011"])
        rs = s0.combine_first(s1)
        xp = Series([datetime(2010, 1, 1), '2011'])
        assert_series_equal(rs, xp) 

def test_non_datetimeindex(self):
        dates = to_datetime(['1/1/2000', '1/2/2000', '1/3/2000'])
        assert frequencies.infer_freq(dates) == 'D' 

def _convert_1d(values, unit, axis):
        def try_parse(values):
            try:
                return _dt_to_float_ordinal(tools.to_datetime(values))
            except Exception:
                return values

        if isinstance(values, (datetime, pydt.date)):
            return _dt_to_float_ordinal(values)
        elif isinstance(values, np.datetime64):
            return _dt_to_float_ordinal(tslibs.Timestamp(values))
        elif isinstance(values, pydt.time):
            return dates.date2num(values)
        elif (is_integer(values) or is_float(values)):
            return values
        elif isinstance(values, compat.string_types):
            return try_parse(values)
        elif isinstance(values, (list, tuple, np.ndarray, Index, ABCSeries)):
            if isinstance(values, ABCSeries):
                # https://github.com/matplotlib/matplotlib/issues/11391
                # Series was skipped. Convert to DatetimeIndex to get asi8
                values = Index(values)
            if isinstance(values, Index):
                values = values.values
            if not isinstance(values, np.ndarray):
                values = com.asarray_tuplesafe(values)

            if is_integer_dtype(values) or is_float_dtype(values):
                return values

            try:
                values = tools.to_datetime(values)
                if isinstance(values, Index):
                    values = _dt_to_float_ordinal(values)
                else:
                    values = [_dt_to_float_ordinal(x) for x in values]
            except Exception:
                values = _dt_to_float_ordinal(values)

        return values 

def _generate_regular_range(start, end, periods, offset):
    if isinstance(offset, Tick):
        stride = offset.nanos
        if periods is None:
            b = Timestamp(start).value
            # cannot just use e = Timestamp(end) + 1 because arange breaks when
            # stride is too large, see GH10887
            e = (b + (Timestamp(end).value - b) // stride * stride +
                 stride // 2 + 1)
            # end.tz == start.tz by this point due to _generate implementation
            tz = start.tz
        elif start is not None:
            b = Timestamp(start).value
            e = b + np.int64(periods) * stride
            tz = start.tz
        elif end is not None:
            e = Timestamp(end).value + stride
            b = e - np.int64(periods) * stride
            tz = end.tz
        else:
            raise ValueError("at least 'start' or 'end' should be specified "
                             "if a 'period' is given.")

        data = np.arange(b, e, stride, dtype=np.int64)
        data = DatetimeIndex._simple_new(data, None, tz=tz)
    else:
        if isinstance(start, Timestamp):
            start = start.to_pydatetime()

        if isinstance(end, Timestamp):
            end = end.to_pydatetime()

        xdr = generate_range(start=start, end=end,
                             periods=periods, offset=offset)

        dates = list(xdr)
        # utc = len(dates) > 0 and dates[0].tzinfo is not None
        data = tools.to_datetime(dates)

    return data 

def _convert_1d(values, unit, axis):
        def try_parse(values):
            try:
                return _dt_to_float_ordinal(tools.to_datetime(values))
            except Exception:
                return values

        if isinstance(values, (datetime, pydt.date)):
            return _dt_to_float_ordinal(values)
        elif isinstance(values, np.datetime64):
            return _dt_to_float_ordinal(tslib.Timestamp(values))
        elif isinstance(values, pydt.time):
            return dates.date2num(values)
        elif (is_integer(values) or is_float(values)):
            return values
        elif isinstance(values, compat.string_types):
            return try_parse(values)
        elif isinstance(values, (list, tuple, np.ndarray, Index)):
            if isinstance(values, Index):
                values = values.values
            if not isinstance(values, np.ndarray):
                values = com._asarray_tuplesafe(values)

            if is_integer_dtype(values) or is_float_dtype(values):
                return values

            try:
                values = tools.to_datetime(values)
                if isinstance(values, Index):
                    values = _dt_to_float_ordinal(values)
                else:
                    values = [_dt_to_float_ordinal(x) for x in values]
            except Exception:
                values = _dt_to_float_ordinal(values)

        return values 

def _make_date_converter(date_parser=None, dayfirst=False,
                         infer_datetime_format=False):
    def converter(*date_cols):
        if date_parser is None:
            strs = _concat_date_cols(date_cols)

            try:
                return tools.to_datetime(
                    _ensure_object(strs),
                    utc=None,
                    box=False,
                    dayfirst=dayfirst,
                    errors='ignore',
                    infer_datetime_format=infer_datetime_format
                )
            except:
                return tools.to_datetime(
                    parsing.try_parse_dates(strs, dayfirst=dayfirst))
        else:
            try:
                result = tools.to_datetime(
                    date_parser(*date_cols), errors='ignore')
                if isinstance(result, datetime.datetime):
                    raise Exception('scalar parser')
                return result
            except Exception:
                try:
                    return tools.to_datetime(
                        parsing.try_parse_dates(_concat_date_cols(date_cols),
                                                parser=date_parser,
                                                dayfirst=dayfirst),
                        errors='ignore')
                except Exception:
                    return generic_parser(date_parser, *date_cols)

    return converter 

def time2num(d):
    if isinstance(d, compat.string_types):
        parsed = tools.to_datetime(d)
        if not isinstance(parsed, datetime):
            raise ValueError('Could not parse time {d}'.format(d=d))
        return _to_ordinalf(parsed.time())
    if isinstance(d, pydt.time):
        return _to_ordinalf(d)
    return d 

def _convert_1d(values, unit, axis):
        def try_parse(values):
            try:
                return _dt_to_float_ordinal(tools.to_datetime(values))
            except Exception:
                return values

        if isinstance(values, (datetime, pydt.date)):
            return _dt_to_float_ordinal(values)
        elif isinstance(values, np.datetime64):
            return _dt_to_float_ordinal(tslibs.Timestamp(values))
        elif isinstance(values, pydt.time):
            return dates.date2num(values)
        elif (is_integer(values) or is_float(values)):
            return values
        elif isinstance(values, compat.string_types):
            return try_parse(values)
        elif isinstance(values, (list, tuple, np.ndarray, Index, ABCSeries)):
            if isinstance(values, ABCSeries):
                # https://github.com/matplotlib/matplotlib/issues/11391
                # Series was skipped. Convert to DatetimeIndex to get asi8
                values = Index(values)
            if isinstance(values, Index):
                values = values.values
            if not isinstance(values, np.ndarray):
                values = com.asarray_tuplesafe(values)

            if is_integer_dtype(values) or is_float_dtype(values):
                return values

            try:
                values = tools.to_datetime(values)
                if isinstance(values, Index):
                    values = _dt_to_float_ordinal(values)
                else:
                    values = [_dt_to_float_ordinal(x) for x in values]
            except Exception:
                values = _dt_to_float_ordinal(values)

        return values 

def test_non_datetimeindex(self):
        dates = to_datetime(['1/1/2000', '1/2/2000', '1/3/2000'])
        assert frequencies.infer_freq(dates) == 'D' 

def time2num(d):
    if isinstance(d, compat.string_types):
        parsed = tools.to_datetime(d)
        if not isinstance(parsed, datetime):
            raise ValueError('Could not parse time {d}'.format(d=d))
        return _to_ordinalf(parsed.time())
    if isinstance(d, pydt.time):
        return _to_ordinalf(d)
    return d 

def _generate_regular_range(start, end, periods, freq):
    if isinstance(freq, Tick):
        stride = freq.nanos
        if periods is None:
            b = Timestamp(start).value
            # cannot just use e = Timestamp(end) + 1 because arange breaks when
            # stride is too large, see GH10887
            e = (b + (Timestamp(end).value - b) // stride * stride +
                 stride // 2 + 1)
            # end.tz == start.tz by this point due to _generate implementation
            tz = start.tz
        elif start is not None:
            b = Timestamp(start).value
            e = b + np.int64(periods) * stride
            tz = start.tz
        elif end is not None:
            e = Timestamp(end).value + stride
            b = e - np.int64(periods) * stride
            tz = end.tz
        else:
            raise ValueError("at least 'start' or 'end' should be specified "
                             "if a 'period' is given.")

        data = np.arange(b, e, stride, dtype=np.int64)
        data = DatetimeIndex._simple_new(data, None, tz=tz)
    else:
        if isinstance(start, Timestamp):
            start = start.to_pydatetime()

        if isinstance(end, Timestamp):
            end = end.to_pydatetime()

        xdr = generate_range(start=start, end=end,
                             periods=periods, offset=freq)

        dates = list(xdr)
        # utc = len(dates) > 0 and dates[0].tzinfo is not None
        data = tools.to_datetime(dates)

    return data 

def time2num(d):
    if isinstance(d, compat.string_types):
        parsed = tools.to_datetime(d)
        if not isinstance(parsed, datetime):
            raise ValueError('Could not parse time {d}'.format(d=d))
        return _to_ordinalf(parsed.time())
    if isinstance(d, pydt.time):
        return _to_ordinalf(d)
    return d 

def test_non_datetimeindex(self):
        dates = to_datetime(['1/1/2000', '1/2/2000', '1/3/2000'])
        assert frequencies.infer_freq(dates) == 'D'