def test_pca_on_uncentered_data():
pca1 = PCA(solver='svd')
pca1.fit(X)
pca2 = PCA(solver='eigen')
pca2.fit(X)
assert_almost_equal(pca1.e_vals_normalized_, pca2.e_vals_normalized_)
def test_evals():
pca = PCA(n_components=2, solver='eigen')
pca.fit(X_std)
assert_almost_equal(pca.e_vals_, [2.9, 0.9, 0.2, 0.02], decimal=1)
pca = PCA(n_components=2, solver='svd')
pca.fit(X_std)
assert_almost_equal(pca.e_vals_, [2.9, 0.9, 0.2, 0.02], decimal=1)
def test_whitening():
pca = PCA(n_components=2)
res = pca.fit(X_std).transform(X_std)
diagonals_sum = np.sum(np.diagonal(np.cov(res.T)))
assert round(diagonals_sum, 1) == 3.9, diagonals_sum
pca = PCA(n_components=2, whitening=True)
res = pca.fit(X_std).transform(X_std)
diagonals_sum = np.sum(np.diagonal(np.cov(res.T)))
assert round(diagonals_sum, 1) == 2.0, diagonals_sum
def test_evals():
pca = PCA(n_components=2, solver='eigen')
pca.fit(X_std)
expected = [2.93035378, 0.92740362, 0.14834223, 0.02074601]
assert_almost_equal(pca.e_vals_, expected, decimal=5)
pca = PCA(n_components=2, solver='svd')
pca.fit(X_std)
assert_almost_equal(pca.e_vals_, expected, decimal=5)
def test_loadings():
expect = np.array([[0.9, -0.4, -0.3, 0.], [-0.5, -0.9, 0.1, -0.],
[1., -0., 0.1, -0.1], [1., -0.1, 0.2, 0.1]])
pca = PCA(solver='eigen')
pca.fit(X_std)
assert_almost_equal(pca.loadings_, expect, decimal=1)
expect = np.array([[-0.9, -0.4, 0.3, 0.], [0.4, -0.9, -0.1, -0.],
[-1., -0., -0.1, -0.1], [-1., -0.1, -0.2, 0.1]])
pca = PCA(solver='svd')
pca.fit(X_std)
assert_almost_equal(pca.loadings_, expect, decimal=1)
def extract_features(extraction_type, n_components):
if extraction_type == 'pca':
ext = PCA(n_components=n_components)
return ext
elif extraction_type == 'lda':
ext = LDA(n_discriminants=n_components)
return ext
else:
print("Input a valid method for (PCA or LDA)\n")
def extract_features(tipo, n):
if tipo == 'pca':
ext = PCA(n_components=n)
return ext
elif tipo == 'lda':
ext = LDA(n_discriminants=n)
return ext
else:
print ("Ingrese un método válido (pca o lda)\n")
def test_fail_array_transform():
pca = PCA(n_components=2)
pca.fit(X)
exp = pca.transform(X[1])
def test_variance_explained_ratio():
pca = PCA()
pca.fit(X_std)
assert math.isclose(np.sum(pca.e_vals_normalized_), 1.)
assert math.isclose(np.sum(pca.e_vals_normalized_ < 0.), 0, abs_tol=1e-10)
def test_default_components():
pca = PCA()
res = pca.fit(X_std).transform(X_std)
assert res.shape[1] == 4
def test_evals():
pca = PCA(n_components=2, solver='eigen')
pca.fit(X)
res = pca.fit(X).transform(X)
assert_almost_equal(pca.e_vals_, [2.93, 0.93, 0.15, 0.02], decimal=2)
def test_fail_array_fit():
pca = PCA(n_components=2)
pca.fit(X[1])
def test_default_2components():
pca = PCA(n_components=2)
res = pca.fit(X).transform(X)
assert res.shape[1] == 2
def test_variance_explained_ratio():
pca = PCA()
pca.fit(X_std)
assert np.sum(pca.e_vals_normalized_) == 1.
assert np.sum(pca.e_vals_normalized_ < 0.) == 0
bootstrap_features=False,
oob_score=False,
warm_start=False,
n_jobs=1,
random_state=0,
verbose=1)
scores = cross_val_score(bag, X, y, scoring='f1_micro', cv=5, verbose=5)
print scores.mean()
'''
trees estims f1
300 10 33.4
300 20
150 50
'''
pca = PCA(n_components=1000)
X_pca = pca.fit(X).transform(X)
et = ExtraTreesClassifier(n_estimators=300,
max_depth=None,
random_state=0,
verbose=1)
bag = BaggingClassifier(base_estimator=et,
n_estimators=20,
max_samples=1.0,
max_features=1.0,
bootstrap=True,
bootstrap_features=False,
oob_score=False,
warm_start=False,
n_jobs=1,
#extratrees from sklearn.ensemble import ExtraTreesClassifier from sklearn.model_selection import cross_val_score et = ExtraTreesClassifier(n_estimators=300, max_depth=None, random_state=0,verbose=5) scores = cross_val_score(et, X, y,scoring='f1_micro',cv=5,verbose=5) print scores.mean() #32% ,max depth=none, n_est=300 #kernel PCA from mlxtend.feature_extraction import PrincipalComponentAnalysis as PCA from sklearn.ensemble import ExtraTreesClassifier from sklearn.model_selection import cross_val_score pca = PCA(n_components=700) X_pca = pca.fit(X).transform(X) et = ExtraTreesClassifier(n_estimators=500, max_depth=None, random_state=0,verbose=5) scores = cross_val_score(et, X_pca, y,scoring='f1_micro',cv=5,verbose=5) print scores.mean() from mlxtend.feature_extraction import RBFKernelPCA as KPCA kpca = KPCA(gamma=1.0, n_components=700) kpca.fit(X) X_kpca = kpca.fit(X).transform(X) et = ExtraTreesClassifier(n_estimators=500, max_depth=None, random_state=0,verbose=5) scores = cross_val_score(et, X_pca, y,scoring='f1_micro',cv=5,verbose=5) print scores.mean()
color='blue',
marker='^', #triangle marker
alpha=0.5,
)
plt.title('BMI vs glucose by sex')
plt.ylabel('Serum glucose concentration')
plt.xlabel('BMI')
plt.legend([sex1, sex2], ['Sex 1', 'Sex 2'])
#plt.show()
plt.savefig('../../figs/bivariate/subsetkpca1_2')
plt.close()
"""
#PCA only takes 2D axis. Look into how to deal with that later.
pca = PCA(n_components=2) #2-component linear PCA
X_pca = pca.fit(X).transform(X)
#print(X_pca)
'''
#Graph after pca
#generate graph from matrix
for i in range(len(X)):
if sex[i] == 1:
#Sex 1 glucose v BMI
sex1 = plt.scatter(X_pca[i][0], #bmi
X_pca[i][1], #glucose
color ='red',
marker='o', #circle marker
alpha=0.5,
)
#Blue half moon
plt.scatter(X[y==1, 0], X[y==1, 1], # Start and peak/trough of each 'moon'.
color='blue', marker='^', alpha=0.5)
plt.xlabel('x coordinate')
plt.ylabel('y coordinate')
#plt.show()
plt.savefig('../figs/tutorial/mlxtendex1_1.png')
plt.close()
# Moons are linearly inseperable so standard linear PCA will fail to accurately represent data in 1D space.
#Use PCA for dimensionality reduction
#specify number of components in PCA
pca = PCA(n_components=2)
#Transform X in accordance with 2-component PCA
X_pca = pca.fit(X).transform(X)
# Red half moon
plt.scatter(X_pca[y==0, 0], X_pca[y==0, 1], # Start and peak/troughof each 'moon'.
color ='red', marker='o', alpha=0.5)
#Blue half moon
plt.scatter(X_pca[y==1, 0], X_pca[y==1, 1], # Start and peak/troughof each 'moon'.
color='blue', marker='^', alpha=0.5)
plt.xlabel('PC1')
plt.ylabel('PC2')
#plt.show()
def test_variance_explained_ratio():
pca = PCA()
pca.fit(X_std)
assert_almost_equal(np.sum(pca.e_vals_normalized_), 1.)
assert np.sum(pca.e_vals_normalized_ < 0.) == 0
def test_eigen_vs_svd():
pca = PCA(n_components=2, solver='eigen')
eigen_res = pca.fit(X).transform(X)
pca = PCA(n_components=2, solver='svd')
svd_res = pca.fit(X).transform(X)
assert_allclose(np.absolute(eigen_res), np.absolute(svd_res), atol=0.0001)
from mlxtend.feature_extraction import PrincipalComponentAnalysis as PCA
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from mlxtend.classifier import StackingClassifier
X = np.genfromtxt('../../contest_data/xtrain_linear_imputed.csv',
delimiter=',')
print 'loaded X'
y = np.genfromtxt('../../contest_data/train.csv', delimiter=',')[1:, -1]
print 'loaded y'
pca = PCA(n_components=300)
X_pca = pca.fit(X).transform(X)
et = ExtraTreesClassifier(n_estimators=1000,
max_depth=None,
random_state=0,
verbose=0)
svc = SVC(C=1, gamma='auto', verbose=0)
#dt = DecisionTreeClassifier(min_samples_leaf=5,random_state=0)
rf = RandomForestClassifier(n_estimators=1000,
max_depth=None,
random_state=0,
verbose=0)
lr = LogisticRegression()
sclf = StackingClassifier(classifiers=[et, svc, rf],
use_probas=True,
def test_fail_array_dimension():
pca = PCA(n_components=2)
assert_raises(ValueError, 'X must be a 2D array. Try X[:, numpy.newaxis]',
pca.transform, X[1])
def test_default_components():
pca = PCA(n_components=0)
pca.fit(X)
res = pca.fit(X).transform(X)
