def run_clustering(dY, aY, rdir, pdir):
"""Re-run clustering experiments on datasets after dimensionality
reduction.
Args:
dY (Numpy.Array): Labels for digits.
aY (Numpy.Array): Labels for abalone.
rdir (str): Input file directory.
pdir (str): Output directory.
"""
digitspath = get_abspath('digits_projected.csv', rdir)
abalonepath = get_abspath('abalone_projected.csv', rdir)
dX = np.loadtxt(digitspath, delimiter=',')
aX = np.loadtxt(abalonepath, delimiter=',')
rdir = rdir + '/clustering'
pdir = pdir + '/clustering'
# re-run clustering experiments after applying PCA
clusters = [2, 3, 5, 10, 15, 20, 25, 30, 35, 40, 50]
clustering_experiment(dX, dY, 'digits', clusters, rdir=rdir)
clustering_experiment(aX, aY, 'abalone', clusters, rdir=rdir)
# generate 2D data for cluster visualization
get_cluster_data(dX, dY, 'digits', km_k=10, gmm_k=10, rdir=rdir)
get_cluster_data(aX, aY, 'abalone', km_k=10, gmm_k=5, rdir=rdir)
# generate component plots (metrics to choose size of k)
generate_component_plots(name='digits', rdir=rdir, pdir=pdir)
generate_component_plots(name='abalone', rdir=rdir, pdir=pdir)
# generate validation plots (relative performance of clustering)
generate_validation_plots(name='digits', rdir=rdir, pdir=pdir)
generate_validation_plots(name='abalone', rdir=rdir, pdir=pdir)
# generate validation plots (relative performance of clustering)
df_digits = pd.read_csv(get_abspath('digits_2D.csv', rdir))
df_abalone = pd.read_csv(get_abspath('abalone_2D.csv', rdir))
generate_cluster_plots(df_digits, name='digits', pdir=pdir)
generate_cluster_plots(df_abalone, name='abalone', pdir=pdir)
def run_clustering(wY, sY, rdir, pdir):
"""Re-run clustering experiments on datasets after dimensionality
reduction.
Args:
wY (Numpy.Array): Labels for winequality.
sY (Numpy.Array): Labels for seismic-bumps.
rdir (str): Input file directory.
pdir (str): Output directory.
"""
winepath = get_abspath('winequality_projected.csv', rdir)
seismicpath = get_abspath('seismic-bumps_projected.csv', rdir)
wX = np.loadtxt(winepath, delimiter=',')
sX = np.loadtxt(seismicpath, delimiter=',')
rdir = rdir + '/clustering'
pdir = pdir + '/clustering'
# re-run clustering experiments after applying PCA
clusters = [2, 3, 4, 5, 6, 7, 8, 10, 12, 15, 18, 20, 25, 30, 45, 80, 120]
clustering_experiment(wX, wY, 'winequality', clusters, rdir=rdir)
clustering_experiment(sX, sY, 'seismic-bumps', clusters, rdir=rdir)
# generate 2D data for cluster visualization
get_cluster_data(wX, wY, 'winequality', km_k=15, gmm_k=15, rdir=rdir)
get_cluster_data(sX, sY, 'seismic-bumps', km_k=20, gmm_k=15, rdir=rdir)
# generate component plots (metrics to choose size of k)
generate_component_plots(name='winequality', rdir=rdir, pdir=pdir)
generate_component_plots(name='seismic-bumps', rdir=rdir, pdir=pdir)
# # generate validation plots (relative performance of clustering)
generate_validation_plots(name='winequality', rdir=rdir, pdir=pdir)
generate_validation_plots(name='seismic-bumps', rdir=rdir, pdir=pdir)
# generate validation plots (relative performance of clustering)
df_wine = pd.read_csv(get_abspath('winequality_2D.csv', rdir))
df_seismic = pd.read_csv(get_abspath('seismic-bumps_2D.csv', rdir))
generate_cluster_plots(df_wine, name='winequality', pdir=pdir)
generate_cluster_plots(df_seismic, name='seismic-bumps', pdir=pdir)
def run_clustering(digits_y, abalone_y, rdir, pdir, experiment=False):
"""Re-run clustering experiments on datasets after dimensionality
reduction.
Args:
digits_y (Numpy.Array): Labels for digits.
abalone_y(Numpy.Array): Labels for abalones.
rdir (str): Input file directory.
pdir (str): Output directory.
"""
start_time = timeit.default_timer()
abalone_X = np.loadtxt(
get_abspath('abalone_projected.csv', rdir),
delimiter=','
)
digits_X = np.loadtxt(
get_abspath('digits_projected.csv', rdir),
delimiter=','
)
rdir = rdir + '/clustering'
pdir = pdir + '/clustering'
if experiment:
# re-run clustering experiments after applying PCA
clusters = range(2, 51)
clustering_experiment(abalone_X, abalone_y,
'abalone', clusters, rdir=rdir)
clustering_experiment(digits_X, digits_y, 'digits',
clusters, rdir=rdir)
# generate component plots (metrics to choose size of k)
generate_component_plots(name='abalone', rdir=rdir, pdir=pdir)
generate_component_plots(name='digits', rdir=rdir, pdir=pdir)
# # generate validation plots (relative performance of clustering)
generate_validation_plots(name='abalone', rdir=rdir, pdir=pdir)
generate_validation_plots(name='digits', rdir=rdir, pdir=pdir)
return
# generate 2D data for cluster visualization
get_cluster_data(
abalone_X, abalone_y, 'abalone',
km_k=9, gmm_k=12, rdir=rdir, pdir=pdir,
)
get_cluster_data(
digits_X, digits_y, 'digits',
km_k=20, gmm_k=12, rdir=rdir, pdir=pdir,
)
# generate validation plots (relative performance of clustering)
generate_cluster_plots(
pd.read_csv(get_abspath('abalone_2D.csv', rdir)),
name='abalone',
pdir=pdir
)
generate_cluster_plots(
pd.read_csv(get_abspath('digits_2D.csv', rdir)),
name='digits',
pdir=pdir
)
def run_clustering(digits_y, abalone_y, rdir, pdir, experiment=False):
"""Re-run clustering experiments on datasets after dimensionality
reduction.
Args:
digits_y (Numpy.Array): Labels for digits.
abalone_y(Numpy.Array): Labels for abalones.
rdir (str): Input file directory.
pdir (str): Output directory.
"""
print('Running base clustering experiments RP')
start_time = timeit.default_timer()
digits_path = get_abspath('digits_projected.csv', rdir)
abalone_path = get_abspath('abalone_projected.csv', rdir)
digits_X = np.loadtxt(digits_path, delimiter=',')
abalone_X = np.loadtxt(abalone_path, delimiter=',')
rdir = rdir + '/clustering'
pdir = pdir + '/clustering'
# re-run clustering experiments after applying PCA
if experiment:
clusters = range(2, 51)
clustering_experiment(digits_X,
digits_y,
'digits',
clusters,
rdir=rdir)
clustering_experiment(abalone_X,
abalone_y,
'abalone',
clusters,
rdir=rdir)
# generate component plots (metrics to choose size of k)
generate_component_plots(name='digits', rdir=rdir, pdir=pdir)
generate_component_plots(name='abalone', rdir=rdir, pdir=pdir)
# # generate validation plots (relative performance of clustering)
generate_validation_plots(name='digits', rdir=rdir, pdir=pdir)
generate_validation_plots(name='abalone', rdir=rdir, pdir=pdir)
return
# # generate 2D data for cluster visualization
get_cluster_data(
digits_X,
digits_y,
'digits',
km_k=3,
gmm_k=9,
rdir=rdir,
pdir=pdir,
)
get_cluster_data(abalone_X,
abalone_y,
'abalone',
km_k=5,
gmm_k=10,
rdir=rdir,
pdir=pdir)
# generate validation plots (relative performance of clustering)
df_digits_2D = pd.read_csv(get_abspath('digits_2D.csv', rdir))
generate_cluster_plots(df_digits_2D, name='digits', pdir=pdir)
df_abalone_2D = pd.read_csv(get_abspath('abalone_2D.csv', rdir))
generate_cluster_plots(df_abalone_2D, name='abalone', pdir=pdir)
end_time = timeit.default_timer()
elapsed = end_time - start_time
print("Completed clustering experiments in {} seconds".format(elapsed))
