def create_classifier(x, z, toe, window=40, min_buffer=40, max_buffer=200):
"""
Create dune toe classifier.
...
Parameters
----------
x : ndarray
Array of cross-shore locations of size (m,).
z : ndarray
Array of elevations matching x. May be of size (m,) or (m,n).
toe : ndarray
Array of dune toe locations of size (n,).
window : int, default 40
Size of the window for training data.
min_buffer : int, default 40
Minimum buffer around the real dune toe.
max_buffer : int, default 200
Maximum buffer range.
Returns
-------
clf : scikit-learn classifier
Created random forest classifier.
"""
# Pre-processing
z = ds.interp_nan(x, z) # interp nan
xx = np.arange(np.min(x), np.max(x) + 0.5, 0.5)
z = ds.interp_to_grid(x, xx, z) # interp to grid
toe = ds.interp_toe_to_grid(x, xx, toe)
z = ds.moving_average(z, 5) # apply moving average to smooth
z = ds.diff_data(z, 1) # differentiate
# Create data
features, labels = create_training_data(xx, z, toe, window, min_buffer,
max_buffer)
# Build classifier
clf = RandomForestClassifier(n_estimators=100,
criterion="gini",
random_state=123).fit(features,
labels.ravel())
return clf
def __init__(self, x, z, window_size=5):
"""
A class used to represent a 2D beach profile transect.
...
Parameters
----------
x : ndarray
Array of cross-shore locations of size (m,).
z : ndarray
Array of elevations matching x. May be of size (m,) or (m,n).
window_size : int, default 5
Size of window used to smooth z with a moving average.
Attributes
----------
x_orig : ndarray
Original input array of cross-shore locations.
z_orig : ndarray
Original array of profile elevations matching x_orig.
x : ndarray
x_orig interpolated to 0.5 m grid.
z : ndarray
z_orig interpolated to 0.5 m grid and smoothed by a moving average with
window size smooth_window.
Methods
-------
predict_dunetoe_ml(self, clf_name, no_of_output=1, dune_crest='rr', **kwargs)
predict_dunetoe_mc(self, dune_crest='rr', shoreline=True, window_size=None, **kwargs)
predict_dunetoe_pd(self, dune_crest=None, shoreline=None, **kwargs)
predict_dunetoe_rr(self, window_size=11, threshold=0.2, water_level=0)
predict_dunecrest(self, method="max", window_size=50, threshold=0.8, water_level=0)
predict_shoreline(self, water_level=0, dune_crest='rr', **kwargs)
"""
assert isinstance(x, np.ndarray) & (
np.ndim(x) == 1), 'x should be of type ndarray and shape (m,).'
assert (np.ndim(x) == 1), 'x should be a 1-d array of size (m,).'
assert (len(x) > 1), 'x should have length > 1.'
assert isinstance(z, np.ndarray), 'z should be of type ndarray.'
assert isinstance(window_size, int) & \
(window_size > 0) & \
(window_size < len(x)), f'window_size must be int between 0 and {len(x)}.'
# Ensure inputs are row vectors
x = np.atleast_1d(x)
z = np.atleast_2d(z)
if len(x) not in z.shape:
raise ValueError(
f'Input x of shape ({x.shape[0]},) must share a dimension with input z which has shape {z.shape[0], z.shape[1]}.'
)
if x.shape[0] != z.shape[1]:
z = z.T
# Store original inputs
self.x = x
self.z = z
# Interp nan values
z = ds.interp_nan(x, z)
flag = np.polyfit(x, z.T, 1)[0]
if np.any(flag > 0):
#raise Warning(f'Input profiles should be oriented from landward (left) to seaward (right), '
# f'some inputted profiles appear to have the sea on the left. This may cause errors.')
print(
f'Input profiles should be oriented from landward (left) to seaward (right), '
f'some inputted profiles appear to have the sea on the left. This may cause errors.'
)
# Interp to 0.5 m grid
self.x_interp = np.arange(np.min(x), np.max(x) + 0.5, 0.5)
z = ds.interp_to_grid(x, self.x_interp, z)
# Apply moving average to smooth data
z = ds.moving_average(z, window_size)
# Store transformed inputs
self.z_interp = z