def fit(self, X, y=None, **kwargs):
"""
The fit method is the primary drawing input for the parallel coords
visualization since it has both the X and y data required for the
viz and the transform method does not.
Parameters
----------
X : ndarray or DataFrame of shape n x m
A matrix of n instances with 2 features
y : ndarray or Series of length n
An array or series of target or class values
kwargs : dict
Pass generic arguments to the drawing method
Returns
-------
self : instance
Returns the instance of the transformer/visualizer
"""
_, ncols = X.shape
if ncols == 2:
X_two_cols = X
if self.features_ is None:
self.features_ = ["Feature One", "Feature Two"]
# Handle the feature names if they're None.
elif self.features_ is not None and is_dataframe(X):
X_two_cols = X[self.features_].as_matrix()
# handle numpy named/ structured array
elif self.features_ is not None and is_structured_array(X):
X_selected = X[self.features_]
X_two_cols = X_selected.view((np.float64, len(X_selected.dtype.names)))
# handle features that are numeric columns in ndarray matrix
elif self.features_ is not None and has_ndarray_int_columns(self.features_, X):
f_one, f_two = self.features_
X_two_cols = X[:, [int(f_one), int(f_two)]]
else:
raise YellowbrickValueError("""
ScatterVisualizer only accepts two features, please
explicitly set these two features in the init kwargs or
pass a matrix/ dataframe in with only two columns.""")
# Store the classes for the legend if they're None.
if self.classes_ is None:
# TODO: Is this the most efficient method?
self.classes_ = [str(label) for label in np.unique(y)]
# Draw the instances
self.draw(X_two_cols, y, **kwargs)
# Fit always returns self.
return self
def fit(self, X, y=None, **kwargs):
"""
The fit method is the primary drawing input for the parallel coords
visualization since it has both the X and y data required for the
viz and the transform method does not.
Parameters
----------
X : ndarray or DataFrame of shape n x m
A matrix of n instances with 2 features
y : ndarray or Series of length n
An array or series of target or class values
kwargs : dict
Pass generic arguments to the drawing method
Returns
-------
self : instance
Returns the instance of the transformer/visualizer
"""
_, ncols = X.shape
if ncols == 2:
X_two_cols = X
if self.features_ is None:
self.features_ = ["Feature One", "Feature Two"]
# Handle the feature names if they're None.
elif self.features_ is not None and is_dataframe(X):
X_two_cols = X[self.features_].as_matrix()
# handle numpy named/ structured array
elif self.features_ is not None and is_structured_array(X):
X_selected = X[self.features_]
X_two_cols = X_selected.copy().view((np.float64, len(X_selected.dtype.names)))
# handle features that are numeric columns in ndarray matrix
elif self.features_ is not None and has_ndarray_int_columns(self.features_, X):
f_one, f_two = self.features_
X_two_cols = X[:, [int(f_one), int(f_two)]]
else:
raise YellowbrickValueError("""
ScatterVisualizer only accepts two features, please
explicitly set these two features in the init kwargs or
pass a matrix/ dataframe in with only two columns.""")
# Store the classes for the legend if they're None.
if self.classes_ is None:
# TODO: Is this the most efficient method?
self.classes_ = [str(label) for label in np.unique(y)]
# Draw the instances
self.draw(X_two_cols, y, **kwargs)
# Fit always returns self.
return self
def _select_feature_columns(self, X):
""" """
if len(X.shape) == 1:
X_flat = X.view(np.float64).reshape(len(X), -1)
else:
X_flat = X
_, ncols = X_flat.shape
if ncols == 2:
X_two_cols = X
if self.features_ is None:
self.features_ = ["Feature One", "Feature Two"]
# Handle the feature names if they're None.
elif self.features_ is not None and is_dataframe(X):
X_two_cols = X[self.features_].as_matrix()
# handle numpy named/ structured array
elif self.features_ is not None and is_structured_array(X):
X_selected = X[self.features_]
X_two_cols = X_selected.view(np.float64).reshape(
len(X_selected), -1)
# handle features that are numeric columns in ndarray matrix
elif self.features_ is not None and has_ndarray_int_columns(
self.features_, X):
f_one, f_two = self.features_
X_two_cols = X[:, [int(f_one), int(f_two)]]
else:
raise YellowbrickValueError("""
ScatterVisualizer only accepts two features, please
explicitly set these two features in the init kwargs or
pass a matrix/ dataframe in with only two columns.""")
return X_two_cols
def _select_feature_columns(self, X):
""" """
if len(X.shape) == 1:
X_flat = X.copy().view(np.float64).reshape(len(X), -1)
else:
X_flat = X
_, ncols = X_flat.shape
if ncols == 2:
X_two_cols = X
if self.features_ is None:
self.features_ = ["Feature One", "Feature Two"]
# Handle the feature names if they're None.
elif self.features_ is not None and is_dataframe(X):
X_two_cols = X[self.features_].as_matrix()
# handle numpy named/ structured array
elif self.features_ is not None and is_structured_array(X):
X_selected = X[self.features_]
X_two_cols = X_selected.copy().view(np.float64).reshape(len(X_selected), -1)
# handle features that are numeric columns in ndarray matrix
elif self.features_ is not None and has_ndarray_int_columns(self.features_, X):
f_one, f_two = self.features_
X_two_cols = X[:, [int(f_one), int(f_two)]]
else:
raise YellowbrickValueError("""
ScatterVisualizer only accepts two features, please
explicitly set these two features in the init kwargs or
pass a matrix/ dataframe in with only two columns.""")
return X_two_cols
