def pca_eigenvalues(x_adult, x_wine):
warnings.simplefilter(action='ignore', category=FutureWarning)
pca = PCA(n_components=10)
pca.fit(x_adult)
y_adult = pca.explained_variance_
pca = PCA(n_components=10)
pca.fit(x_wine)
y_wine = pca.explained_variance_
mca = MCA(n_components=10)
mca.fit(x_wine)
y_wine2 = 100 * np.array(mca.eigenvalues_)
x_axis = [k + 1 for k in range(10)]
plot.style.use('seaborn-darkgrid')
plot.title(f'Eigen values distributions')
plot.xlabel('Eigen value index')
plot.ylabel('Eigen value')
plot.xticks(x_axis, x_axis)
plot.plot(x_axis, np.transpose([y_adult, y_wine, y_wine2]), 'o-')
plot.legend(['Adult', 'Wine reviews (PCA)', 'Wine reviews (MCA) x100'],
loc='upper right')
plot.show()
class DFMCA(BaseEstimator, TransformerMixin):
# NOTE:
# - DFMCA(n_components=df[columns].apply(lambda x: len(x.unique())).sum()) to remain every dimensions
# - Ensure to convert binary encoded features as string, to ensure prince.MCA() will generate new one-hot encoded features by calling pd.get_dummies()
def __init__(self, columns=None, prefix='mca_', **kwargs):
self.columns = columns
self.prefix = prefix
self.model = MCA(**kwargs)
self.transform_cols = None
self.stat_df = None
def fit(self, X, y=None):
self.columns = X.columns if self.columns is None else self.columns
self.transform_cols = [x for x in X.columns if x in self.columns]
self.model.fit(X[self.transform_cols])
# Reference: Reference: https://www.appliedaicourse.com/lecture/11/applied-machine-learning-online-course/2896/pca-for-dimensionality-reduction-not-visualization/0/free-videos
self.stat_df = pd.DataFrame({
'dimension': [x+1 for x in range(len(self.model.eigenvalues_))],
'eigenvalues': self.model.eigenvalues_,
'explained_inertia': self.model.explained_inertia_,
'cumsum_explained_inertia': np.cumsum(self.model.explained_inertia_)
})
return self
def transform(self, X):
if self.transform_cols is None:
raise NotFittedError(f"This {self.__class__.__name__} instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator.")
new_X = self.model.transform(X[self.transform_cols])
new_X.rename(columns=dict(zip(new_X.columns, [f'{self.prefix}{x}' for x in new_X.columns])), inplace=True)
new_X = pd.concat([X.drop(columns=self.transform_cols), new_X], axis=1)
return new_X
def fit_transform(self, X, y=None):
return self.fit(X).transform(X)