def define_waterwork(self, array=empty, return_tubes=None, prefix=''):
"""Get the waterwork that completely describes the pour and pump transformations.
Parameters
----------
array : np.ndarray or empty
The array to be transformed.
Returns
-------
Waterwork
The waterwork with all the tanks (operations) added, and names set.
"""
# Convert the category values to indices.
cti, cti_slots = td.cat_to_index(
array, self.cat_val_to_index,
tube_plugs={'input_dtype': lambda z: self.input_dtype}
)
cti_slots['cats'].set_name('array')
cti['missing_vals'].set_name('missing_vals')
# Clone the indices so that a copy of 'indices' can be outputted as a tap.
cloned, _ = td.clone(cti['target'])
cloned['a'].set_name('indices')
# Convert the indices into one-hot vectors.
one_hots, _ = td.one_hot(
cloned['b'], len(self.cat_val_to_index),
tube_plugs={
'missing_vals': lambda z: np.ones(z[self._pre('indices', prefix)].shape)*-2
}
)
if self.norm_mode == 'mean_std':
one_hots, _ = td.sub(
one_hots['target'], self.mean,
tube_plugs={'a_is_smaller': False, 'smaller_size_array': self.mean}
)
one_hots, _ = td.div(
one_hots['target'], self.std,
tube_plugs={'a_is_smaller': False, 'smaller_size_array': self.std, 'missing_vals': np.array([]), 'remainder': np.array([])}
)
one_hots['target'].set_name('one_hots')
if return_tubes is not None:
ww = one_hots['target'].waterwork
r_tubes = []
for r_tube_key in return_tubes:
r_tubes.append(ww.maybe_get_tube(r_tube_key))
return r_tubes
def define_waterwork(self, array=empty, return_tubes=None, prefix=''):
"""Get the waterwork that completely describes the pour and pump transformations.
Parameters
----------
array : np.ndarray or empty
The array to be transformed.
Returns
-------
Waterwork
The waterwork with all the tanks (operations) added, and names set.
"""
# Replace all the NaN's with the inputted replace_with function.
nans, nans_slots = td.isnan(array)
nans_slots['a'].set_name('array')
nums, _ = td.replace(
nans['a'],
nans['target'],
slot_plugs={
'replace_with':
lambda z: self.fill_nan_func(z[self._pre('array', prefix)])
},
tube_plugs={
'replace_with': np.array([]),
'replaced_vals': np.array(np.nan)
})
nums['replaced_vals'].set_name('replaced_vals')
nums['mask'].set_name('nans')
# Do any additional normalization
if self.norm_mode == 'mean_std':
nums, _ = td.sub(nums['target'],
self.mean,
tube_plugs={
'a_is_smaller': False,
'smaller_size_array': self.mean
})
nums, _ = td.div(nums['target'],
self.std,
tube_plugs={
'a_is_smaller': False,
'smaller_size_array': self.std,
'missing_vals': np.array([]),
'remainder': np.array([])
})
elif self.norm_mode == 'min_max':
nums, _ = td.sub(nums['target'],
self.min,
tube_plugs={
'a_is_smaller': False,
'smaller_size_array': self.min
})
nums, _ = td.div(nums['target'], (self.max - self.min),
tube_plugs={
'a_is_smaller': False,
'smaller_size_array': (self.max - self.min),
'missing_vals': np.array([]),
'remainder': np.array([])
})
nums['target'].set_name('nums')
if return_tubes is not None:
ww = nums['target'].waterwork
r_tubes = []
for r_tube_key in return_tubes:
r_tubes.append(ww.maybe_get_tube(r_tube_key))
return r_tubes
def __sub__(self, other): """Define an add tank (operation) between two tubes.""" import wtrwrks.tanks.tank_defs as td return td.sub(a=self, b=other)
def define_waterwork(self, array=empty, return_tubes=None, prefix=''):
"""Get the waterwork that completely describes the pour and pump transformations.
Parameters
----------
array : np.ndarray or empty
The array to be transformed.
Returns
-------
Waterwork
The waterwork with all the tanks (operations) added, and names set.
"""
# Replace all the NaT's with the inputted replace_with.
nats, nats_slots = td.isnat(array)
nats_slots['a'].set_name('array')
replaced, _ = td.replace(
nats['a'], nats['target'],
slot_plugs={
'replace_with': lambda z: self.fill_nat_func(z[self._pre('array', prefix)])
},
tube_plugs={
'replace_with': np.array([]),
'replaced_vals': np.array([None], dtype=np.datetime64)
}
)
replaced['replaced_vals'].set_name('replaced_vals')
replaced['mask'].set_name('nats')
# Convert the datetimes to numbers
nums, _ = td.datetime_to_num(replaced['target'], self.zero_datetime, self.num_units, self.time_unit, name='dtn')
nums['diff'].set_name('diff')
if self.norm_mode == 'mean_std':
nums, _ = td.sub(
nums['target'], self.mean,
tube_plugs={'a_is_smaller': False, 'smaller_size_array': self.mean}
)
nums, _ = td.div(
nums['target'], self.std,
tube_plugs={'a_is_smaller': False, 'smaller_size_array': self.std, 'missing_vals': np.array([]), 'remainder': np.array([])}
)
elif self.norm_mode == 'min_max':
nums, _ = td.sub(
nums['target'], self.min,
tube_plugs={'a_is_smaller': False, 'smaller_size_array': self.min}
)
nums, _ = td.div(
nums['target'], (self.max - self.min),
tube_plugs={'a_is_smaller': False, 'smaller_size_array': (self.max - self.min), 'missing_vals': np.array([]), 'remainder': np.array([])}
)
nums['target'].set_name('nums')
if return_tubes is not None:
ww = nums['target'].waterwork
r_tubes = []
for r_tube_key in return_tubes:
r_tubes.append(ww.maybe_get_tube(r_tube_key))
return r_tubes