def test_pi_sub_period(self):
# GH#13071
idx = PeriodIndex(['2011-01', '2011-02', '2011-03', '2011-04'],
freq='M',
name='idx')
result = idx - pd.Period('2012-01', freq='M')
off = idx.freq
exp = pd.Index([-12 * off, -11 * off, -10 * off, -9 * off], name='idx')
tm.assert_index_equal(result, exp)
result = np.subtract(idx, pd.Period('2012-01', freq='M'))
tm.assert_index_equal(result, exp)
result = pd.Period('2012-01', freq='M') - idx
exp = pd.Index([12 * off, 11 * off, 10 * off, 9 * off], name='idx')
tm.assert_index_equal(result, exp)
result = np.subtract(pd.Period('2012-01', freq='M'), idx)
tm.assert_index_equal(result, exp)
exp = pd.TimedeltaIndex([np.nan, np.nan, np.nan, np.nan], name='idx')
tm.assert_index_equal(idx - pd.Period('NaT', freq='M'), exp)
tm.assert_index_equal(pd.Period('NaT', freq='M') - idx, exp)
def mu_max(curves,
norm_eqs=None,
time_range=['2.5 hours', '15 hours'],
blank='BLK'):
if norm_eqs:
for strain, norm_eq in norm_eqs.items():
try:
curves.update(
curves.assign(OD595norm=norm_eq(curves[
curves.name.str.contains(strain)].OD595)))
except (Exception):
curves = curves.assign(OD595norm=norm_eq(curves[
curves.name.str.contains(strain)].OD595))
curves.OD595 = curves.OD595norm
#curves = curves.reset_index()
#curves.rename(columns={'index': 'indexer'})
window_size = 12
curves.Time = pd.TimedeltaIndex(curves.Time, unit='h').round('T')
data = curves.set_index(['Time', 'name',
'well']).unstack([1, 2]).resample('5T').mean()
blank_val = data['OD595'][blank].mean()
try:
blank_val = blank_val.mean()
except:
pass
data = data - blank_val
rolling = data.rolling(window_size)
growth_rates = (rolling.apply(lambda x: np.log(x[-1]/x[0])).OD595[time_range[0]:time_range[-1]]\
.max()/(window_size/12)).reset_index()
# growth_rates = growth_rates.assign(Strain = growth_rates.name.apply(lambda x: str(x).split(' ')[0]),
# Treatment = growth_rates.name.apply(lambda x: ' '.join(str(x).split(' ')[1:])))
# #data.pH = pd.to_numeric(data.pH, errors='ignore')
# data = growth_rates.rename(columns={0: 'Max growth rate'})
# sns.barplot(data=growth_rates, y='Treatment', x='Max growth rate', hue='Strain')
return growth_rates
def _nonempty_index(idx):
typ = type(idx)
if typ is pd.RangeIndex:
return pd.RangeIndex(2, name=idx.name)
elif typ in (pd.Int64Index, pd.Float64Index):
return typ([1, 2], name=idx.name)
elif typ is pd.Index:
return pd.Index(['a', 'b'], name=idx.name)
elif typ is pd.DatetimeIndex:
start = '1970-01-01'
data = [start, start] if idx.freq is None else None
return pd.DatetimeIndex(data, start=start, periods=2, freq=idx.freq,
tz=idx.tz, name=idx.name)
elif typ is pd.PeriodIndex:
return pd.PeriodIndex(start='1970-01-01', periods=2, freq=idx.freq,
name=idx.name)
elif typ is pd.TimedeltaIndex:
start = np.timedelta64(1, 'D')
data = [start, start] if idx.freq is None else None
return pd.TimedeltaIndex(data, start=start, periods=2, freq=idx.freq,
name=idx.name)
elif typ is pd.CategoricalIndex:
if len(idx.categories):
data = [idx.categories[0]] * 2
cats = idx.categories
else:
data = _nonempty_index(idx.categories)
cats = None
return pd.CategoricalIndex(data, categories=cats,
ordered=idx.ordered, name=idx.name)
elif typ is pd.MultiIndex:
levels = [_nonempty_index(i) for i in idx.levels]
labels = [[0, 0] for i in idx.levels]
return pd.MultiIndex(levels=levels, labels=labels, names=idx.names)
raise TypeError("Don't know how to handle index of "
"type {0}".format(type(idx).__name__))
def day_counts(index):
"""Days between DatetimeIndex values as a :any:`pandas.Series`.
Parameters
----------
index : :any:`pandas.DatetimeIndex`
The index for which to get day counts.
Returns
-------
day_counts : :any:`pandas.Series`
A :any:`pandas.Series` with counts of days between periods. Counts are
given on start dates of periods.
"""
# dont affect the original data
index = index.copy()
if len(index) == 0:
return pd.Series([], index=index)
timedeltas = (index[1:] - index[:-1]).append(pd.TimedeltaIndex([pd.NaT]))
timedelta_days = timedeltas.total_seconds() / (60 * 60 * 24)
return pd.Series(timedelta_days, index=index)
def test_pi_sub_period(self):
# GH#13071
idx = PeriodIndex(["2011-01", "2011-02", "2011-03", "2011-04"],
freq="M",
name="idx")
result = idx - pd.Period("2012-01", freq="M")
off = idx.freq
exp = pd.Index([-12 * off, -11 * off, -10 * off, -9 * off], name="idx")
tm.assert_index_equal(result, exp)
result = np.subtract(idx, pd.Period("2012-01", freq="M"))
tm.assert_index_equal(result, exp)
result = pd.Period("2012-01", freq="M") - idx
exp = pd.Index([12 * off, 11 * off, 10 * off, 9 * off], name="idx")
tm.assert_index_equal(result, exp)
result = np.subtract(pd.Period("2012-01", freq="M"), idx)
tm.assert_index_equal(result, exp)
exp = pd.TimedeltaIndex([np.nan, np.nan, np.nan, np.nan], name="idx")
tm.assert_index_equal(idx - pd.Period("NaT", freq="M"), exp)
tm.assert_index_equal(pd.Period("NaT", freq="M") - idx, exp)
def calc_baseline_dumb(training_data, similar_moments, prediction_window):
if type(prediction_window) is not timedelta:
prediction_window = timedelta(minutes=prediction_window)
k = len(similar_moments)
r = np.zeros((49, 1))
for i in similar_moments:
similar_day = (1 /
k) * training_data[i:i + prediction_window].resample(
timedelta(minutes=15)).mean()
similar_day = similar_day[0:49]
r += similar_day
# r += (1 / k) * training_data[i:i + prediction_window].as_matrix
baseline = np.squeeze(r)
b = pd.DataFrame(baseline).set_index(
pd.TimedeltaIndex(freq='15T', start=0,
periods=49)).resample(timedelta(minutes=1)).ffill()
baseline = np.squeeze(b.as_matrix())
baseline = np.concatenate((baseline, np.atleast_1d(baseline[-1])))
return baseline
def test_timedelta_other_units(self):
idx = pd.TimedeltaIndex(['1 days', 'NaT', '2 days'])
exp = np.array([False, True, False])
tm.assert_numpy_array_equal(isnull(idx), exp)
tm.assert_numpy_array_equal(notnull(idx), ~exp)
tm.assert_numpy_array_equal(isnull(idx.values), exp)
tm.assert_numpy_array_equal(notnull(idx.values), ~exp)
for dtype in ['timedelta64[D]', 'timedelta64[h]', 'timedelta64[m]',
'timedelta64[s]', 'timedelta64[ms]', 'timedelta64[us]',
'timedelta64[ns]']:
values = idx.values.astype(dtype)
exp = np.array([False, True, False])
tm.assert_numpy_array_equal(isnull(values), exp)
tm.assert_numpy_array_equal(notnull(values), ~exp)
exp = pd.Series([False, True, False])
s = pd.Series(values)
tm.assert_series_equal(isnull(s), exp)
tm.assert_series_equal(notnull(s), ~exp)
s = pd.Series(values, dtype=object)
tm.assert_series_equal(isnull(s), exp)
tm.assert_series_equal(notnull(s), ~exp)
def test_construction_discrete(data, time, interpolation, shape_exp):
"""Test the construction of the TimeSeries class."""
# set expected values
if isinstance(time, pint.Quantity):
time_exp = pd.TimedeltaIndex(time.magnitude, unit="s")
else:
time_exp = time
# create instance
ts = TimeSeries(data=data, time=time, interpolation=interpolation)
# check
assert np.all(ts.data == data)
assert np.all(ts.time == time_exp)
assert ts.interpolation == interpolation
assert ts.shape == shape_exp
assert data.check(UREG.get_dimensionality(ts.units))
assert np.all(ts.data_array.data == data)
assert ts.data_array.attrs["interpolation"] == interpolation
if time_exp is None:
assert "time" not in ts.data_array
else:
assert np.all(ts.data_array.time == time_exp)
def test_add_dti_td(self):
# GH 17558
# Check that tz-aware DatetimeIndex + np.array(dtype="timedelta64")
# and DatetimeIndex + TimedeltaIndex work as expected
dti = pd.DatetimeIndex([pd.Timestamp("2017/01/01")],
name="x").tz_localize('US/Eastern')
expected = pd.DatetimeIndex([pd.Timestamp("2017/01/01 01:00")],
name="x").tz_localize('US/Eastern')
td_np = np.array([np.timedelta64(1, 'h')], dtype="timedelta64[ns]")
results = [
dti + td_np, # add numpy array
dti + td_np.astype(dtype="timedelta64[m]"),
dti + pd.TimedeltaIndex(td_np, name=dti.name),
dti + td_np[0], # add timedelta scalar
dti + pd.to_timedelta(td_np[0]),
]
for actual in results:
tm.assert_index_equal(actual, expected)
errmsg = r"cannot add DatetimeIndex and np.ndarray\[float64\]"
with tm.assert_raises_regex(TypeError, errmsg):
dti + np.array([0.1], dtype=np.float64)
def mean_std_model(data):
"""
function to build mean and standard deviation model
args :
data : onehot encoded dataframe
return :
df : dataframe containing mean and standard deviation
"""
df = data.copy()
df["minute"] = df['D'].map(lambda x: x.minute)
df["hour"] = df['D'].map(lambda x: x.hour)
#get mean and standard deviation of each columnn
df_g = df.groupby(['hour', 'minute']).agg(['mean', std])
df = df_g.reset_index()
#set the mean as the predction
df['minutes'] = df['minute'] + df['hour'] * 60
df['time'] = datetime.combine(
date.today(), datetime.min.time()) + pd.TimedeltaIndex(df['minutes'],
unit='m')
df.drop(['minutes', 'hour', 'minute'], axis=1, inplace=True)
return df
