def ICA():
global range_n_clusters
range_n_clusters = [i for i in range(5, 62, 8)]
_r, _c = get_data('{}/ICA'.format(OUTPUT), '37-')
c_X, _ = _c
main(c_X)
_r, _c = get_data('{}/ICA'.format(OUTPUT), '45-')
r_X, _ = _r
main(r_X)
def comparePCA(p, ds):
global BASE
bests = []
params = p
BASE = '{}/PCA'.format(OUTPUT)
for param in params:
_r, _c = get_data(BASE, param)
r, _ = _r
find_best(r, bests)
bests = np.array(bests)
plot_gmms(bests, ds)
def compare(dim_red_alg, p1, p2):
global BASE
r_bests = []
c_bests = []
params = p1
BASE = '{}/{}'.format(OUTPUT, dim_red_alg)
for param in params:
_r, _c = get_data(BASE, param)
c, _ = _c
find_best(c, c_bests)
params = p2
BASE = '{}/{}'.format(OUTPUT, dim_red_alg)
for param in params:
_r, _c = get_data(BASE, param)
r, _ = _r
find_best(r, r_bests)
r_bests = np.array(r_bests)
c_bests = np.array(c_bests)
print(r_bests)
plot_gmms(r_bests, "Reviews")
plot_gmms(c_bests, "Cancer")
import numpy as np
np.random.seed(0)
dir_path = dirname(realpath(__file__))
sys.path.insert(0, '{}/..'.format(dir_path))
from helpers.dim_reduction import run_dim_alg, get_data
from helpers.constants import ICA_DIMS
r_dims = c_dims = ICA_DIMS
OUT = '{}/../../OUTPUT/ICA'.format(dir_path)
BASE = '{}/../../OUTPUT/BASE'.format(dir_path)
r, c = get_data(BASE)
r_X, r_y = r
c_X, c_y = c
ica = FastICA(random_state=5)
kurt = {}
for dim in r_dims:
ica.set_params(n_components=dim)
tmp = ica.fit_transform(r_X)
tmp = pd.DataFrame(tmp)
tmp = tmp.kurt(axis=0)
kurt[dim] = tmp.abs().mean()
kurt = pd.Series(kurt)
kurt.to_csv('{}/reviews kurtosis.csv'.format(OUT))
sys.path.insert(0, '{}/..'.format(dir_path))
from helpers.dim_reduction import get_data
from helpers.scoring import metrics
from helpers.constants import ICA_DIMS, SVD_DIMS_R as SVD_DIMS, RP_DIMS, PCA_DIMS
from helpers.figures import bar_plot
from helpers.clustering import r_clusters
PCA = '{}/../OUTPUT/PCA/{}'.format(dir_path, 'datasets-w-cluster')
ICA = '{}/../OUTPUT/ICA/{}'.format(dir_path, 'datasets-w-cluster')
RP = '{}/../OUTPUT/RP/{}'.format(dir_path, 'datasets-w-cluster')
SVD = '{}/../OUTPUT/SVD/{}'.format(dir_path, 'datasets-w-cluster')
BASE = '{}/../OUTPUT/BASE'.format(dir_path)
OUT = '{}/../OUTPUT/NN'.format(dir_path)
data_BASE = get_data(BASE, prefix='', ds='r')
data_ICA = []#[get_data(ICA, ds='r', suffix='%s-%s-datasets.km.hdf') for d, c in product(ICA_DIMS, r_clusters)]
data_RP = []#[get_data(RP, ds='r', suffix='%s-%s-datasets.km.hdf') for d, c in product(RP_DIMS, r_clusters)]
data_SVD = []#[get_data(SVD, ds='r', suffix='%s-%s-datasets.km.hdf') for d, c in product(SVD_DIMS, r_clusters)]
data_PCA_KM = [(get_data(PCA, ds='r', suffix='%s-%s-datasets.km.hdf' % (c, d)), '%s-%s-km' % (c, d)) for d, c in product(PCA_DIMS, r_clusters)]
data_PCA_GMM = [(get_data(PCA, ds='r', suffix='%s-%s-datasets.gmm.hdf' % (c, d)), '%s-%s-gmm' % (c, d)) for d, c in product(PCA_DIMS, r_clusters)]
data_ICA_KM = [(get_data(ICA, ds='r', suffix='%s-%s-datasets.km.hdf' % (c, d)), '%s-%s-km' % (c, d)) for d, c in product(ICA_DIMS, r_clusters)]
data_ICA_GMM = [(get_data(ICA, ds='r', suffix='%s-%s-datasets.gmm.hdf' % (c, d)), '%s-%s-gmm' % (c, d)) for d, c in product(ICA_DIMS, r_clusters)]
data_SVD_KM = [(get_data(SVD, ds='r', suffix='%s-%s-datasets.km.hdf' % (c, d)), '%s-%s-km' % (c, d)) for d, c in product(SVD_DIMS, r_clusters)]
data_SVD_GMM = [(get_data(SVD, ds='r', suffix='%s-%s-datasets.gmm.hdf' % (c, d)), '%s-%s-gmm' % (c, d)) for d, c in product(SVD_DIMS, r_clusters)]
data_RP_KM = [(get_data(RP, ds='r', suffix='%s-%s-datasets.km.hdf' % (c, d)), '%s-%s-km' % (c, d)) for d, c in product(RP_DIMS, r_clusters)]
data_RP_GMM = [(get_data(RP, ds='r', suffix='%s-%s-datasets.gmm.hdf' % (c, d)), '%s-%s-gmm' % (c, d)) for d, c in product(RP_DIMS, r_clusters)]
dir_path = dirname(realpath(__file__))
sys.path.insert(0, '{}/..'.format(dir_path))
from helpers.dim_reduction import get_data
from helpers.scoring import metrics
from helpers.constants import ICA_DIMS, SVD_DIMS_R as SVD_DIMS, RP_DIMS, PCA_DIMS
from helpers.figures import bar_plot
PCA = '{}/../OUTPUT/PCA'.format(dir_path)
ICA = '{}/../OUTPUT/ICA'.format(dir_path)
RP = '{}/../OUTPUT/RP'.format(dir_path)
SVD = '{}/../OUTPUT/SVD'.format(dir_path)
BASE = '{}/../OUTPUT/BASE'.format(dir_path)
OUT = '{}/../OUTPUT/NN'.format(dir_path)
data_BASE = get_data(BASE, '', 'r')
data_ICA = [get_data(ICA, '%d-' % i, 'r') for i in ICA_DIMS]
data_RP = [get_data(RP, '%d-' % i, 'r') for i in RP_DIMS]
data_SVD = [get_data(SVD, '%d-' % i, 'r') for i in SVD_DIMS]
data_PCA = [get_data(PCA, '%s-' % i, 'r') for i in PCA_DIMS]
np.random.seed(0)
def get_schwifty(X, y, dataset, dims, classifier):
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
start = clock()
classifier.fit(X_train, y_train)
pred = classifier.predict(X_test)
elapsed = clock() - start
print('%ss for %s at %s dimensions' % (elapsed, dataset, dims))
def runitr(p):
r_X, _ = get_data('{}/SVD'.format(OUTPUT), '%d-' % p, 'r')
print('Reviews at %s dimensions' % p)
main(r_X, 'Reviews', ' (%s dims)' % p)
def runitc(p):
c_X, _ = get_data('{}/SVD'.format(OUTPUT), '%s-' % p, 'c')
print('Cancer at %s dimensions' % p)
main(c_X, 'Cancer', ' (%s dims)' % p)
def runit(p):
_r, _c = get_data('{}/PCA'.format(OUTPUT), '%s-' % p)
r_X, _ = _r
c_X, _ = _c
main(r_X)
main(c_X)
def runitr(p):
_r, _c = get_data('{}/RP'.format(OUTPUT), '%s-' % p)
r_X, _ = _r
print('Reviews at %s dimensions' % p)
main(r_X, 'Reviews', ' (%s dims)' % p)
def runitc(p):
_r, _c = get_data('{}/RP'.format(OUTPUT), '%s-' % p)
c_X, _ = _c
print('Cancer at %s dimensions' % p)
main(c_X, 'Cancer', ' (%s dims)' % p)
from sklearn import mixture
from helpers.dim_reduction import get_data
print(__doc__)
dir_path = dirname(realpath(__file__))
output_dir = sys.argv[1] if len(sys.argv) >= 2 else 'BASE'
OUTPUT = '{}/../OUTPUT'.format(dir_path)
OUT = '{}/{}'.format(OUTPUT, output_dir)
BASE = '{}/BASE'.format(OUTPUT)
# Generating the sample data from make_blobs
# This particular setting has one distinct cluster and 3 clusters placed close
# together.
_r, _c = get_data(BASE)
r_X, r_y = _r
c_X, c_y = _c
r_components = [8, 13, 21, 34, 55, 89, 104, 119, 134, 159]
c_components = [8, 10, 14, 18, 25, 35, 45, 55, 65, 75]
n_components_range = None
def find_best(X, bic): #pylint: disable
cv_types = ['spherical', 'tied', 'diag', 'full']
lowest_bic = np.infty
for cv_type in cv_types:
for n_components in n_components_range:
# Fit a Gaussian mixture with EM
gmm = mixture.GaussianMixture(n_components=n_components,
covariance_type=cv_type)
gmm.fit(X)
