def _cluster_data(self, ps: int,
data: List[List],
ground_truth: List,
desired_k: int):
clu_lss = Clusterer(dtm=data,
true_labels=ground_truth,
max_nbr_clusters=len(data)-1,
min_nbr_clusters=1,
min_cluster_size=2,
metric="cosine",
desired_n_clusters=desired_k)
# Run SPKMeans 10 times to get mean performance
# This is also what supplied the estimated k for the Clusterer
# TODO: decouple k estimations from the evaluation
norm_spk_pred, norm_spk_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_spherical_k_means,
param_init="k-means++")
cop_kmeans_pred, cop_kmeans_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_cop_kmeans,
param_constraints_size=constraints_fraction,
param_copkmeans_init="random")
if include_older_algorithms:
norm_hdbscan_pred, norm_hdbscan_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_h_dbscan)
norm_ms_pred, norm_ms_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_mean_shift)
# norm_xm_pred, norm_xm_evals = clu_lss.evaluate(
# alg_option=Clusterer.alg_x_means)
nhac_complete_pred, nhac_complete_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_hac,
param_linkage="complete")
nhac_s_pred, nhac_s_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_hac,
param_linkage="single")
nhac_a_pred, nhac_a_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_hac,
param_linkage="average")
n_optics_pred, n_optics_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_optics)
# Baselines
bl_rand_pred, bl_rand_evals = clu_lss.evaluate(
alg_option=Clusterer.bl_random)
bl_singleton_pred, bl_singleton_evals = clu_lss.evaluate(
alg_option=Clusterer.bl_singleton)
nhdp_pred, nhdp_evals = clu_lss.eval_cluster_hdp()
ntrue_pred, ntrue_evals = clu_lss.eval_true_clustering()
# SOTA - Gomez et. al. HAC and Log-Entropy with 20k features
# Not Applicable for Training data
if not train_phase:
sota_pred_path_le = (r"D:\College\DKEM\Thesis\AuthorshipClustering"
r"\Code\clusterPAN2017-master\output_LogEnt"
f"\\problem{ps:03d}\\clustering.json")
sota_predicted_le = Tools.load_true_clusters_into_vector(
sota_pred_path_le)
sota_pred_le, sota_evals_le = clu_lss.eval_sota(
sota_predicted=sota_predicted_le)
sota_pred_path_tf = (r"D:\College\DKEM\Thesis\AuthorshipClustering"
r"\Code\clusterPAN2017-master\output_Tf"
f"\\problem{ps:03d}\\clustering.json")
sota_predicted_tf = Tools.load_true_clusters_into_vector(
sota_pred_path_tf)
sota_pred_tf, sota_evals_tf = clu_lss.eval_sota(
sota_predicted=sota_predicted_tf)
sota_pred_path_tfidf = (
r"D:\College\DKEM\Thesis\AuthorshipClustering"
r"\Code\clusterPAN2017-master\output_TfIdf"
f"\\problem{ps:03d}\\clustering.json")
sota_predicted_tfidf = Tools.load_true_clusters_into_vector(
sota_pred_path_tfidf)
sota_pred_tfidf, sota_evals_tfidf = clu_lss.eval_sota(
sota_predicted=sota_predicted_tfidf)
else:
# Build some placeholders only as SOTA isn't required to train
# sota_pred_le = [0] * len(data)
# sota_pred_tf = [0] * len(data)
# sota_pred_tfidf = [0] * len(data)
placebo_ret = {}
placebo_ret.update({"nmi": None,
"ami": None,
"ari": None,
"fms": None,
"v_measure": None,
"bcubed_precision": None,
"bcubed_recall": None,
"bcubed_fscore": None,
"Silhouette": None,
"Calinski_harabasz": None,
"Davies_Bouldin": None
# Here goes the unsupervised indices
})
sota_evals_le = placebo_ret
sota_evals_tf = placebo_ret
sota_evals_tfidf = placebo_ret
# Control whether k is estimated or it is the true k replicated:
if desired_k != 0:
k_trend = clu_lss.cand_k
k_trend.append(1 + max(clu_lss.true_labels))
else:
k_trend = [1 + max(clu_lss.true_labels)
] * (nbr_competing_methods + 1)
result = Tools.form_problemset_result_dictionary(
dictionaries=[
# ispk_evals, norm_spk_evals, norm_hdbscan_evals,
norm_spk_evals, norm_hdbscan_evals,
norm_ms_evals, # norm_xm_evals,
nhac_complete_evals, nhac_s_evals, nhac_a_evals,
n_optics_evals, cop_kmeans_evals,
bl_rand_evals, bl_singleton_evals,
nhdp_evals,
sota_evals_tf, sota_evals_tfidf, sota_evals_le,
ntrue_evals
],
identifiers=[ # "iSpKmeans",
"E_SPKMeans", "E_HDBSCAN",
"E_Mean_Shift", # "XMeans",
"E_HAC_C", "E_HAC_Single", "E_HAC_Average",
"E_OPTICS", "E_COP_KMeans",
"BL_r", "BL_s", "S_HDP",
"BL_SOTA_tf", "BL_SOTA_tfidf", "BL_SOTA_le",
"Labels"],
problem_set=ps)
return result, k_trend
def problem_set_run(problem_set_id: int,
n_clusters: int,
seed: int,
configuration: str,
drop_uncommon: bool,
verbose: bool,
infer_lss: bool = False):
problem_nbr = f"{problem_set_id:03d}"
# Define an LSS modeller to represent documents in LSS non-sparse space
# HDP with Gibbs sampler is being used as is from:
# https://github.com/blei-lab/hdp
# Adjust the parameters according to the preference
if configuration == config_sparse:
eta = 0.3
gamma = 0.1
alpha = 0.1
elif configuration == config_dense:
eta = 0.8
gamma = 1.5
alpha = 1.5
else:
eta = 0.5
gamma = 1.0
alpha = 1.0
Modeller = LssHdpModeller(
hdp_path=r"..\hdps\hdp",
input_docs_path=r"..\..\Datasets\pan17_train\problem{}".format(
problem_nbr),
ldac_filename=r"ldac_corpus",
hdp_output_dir=r"hdp_lss",
hdp_iters=10000,
hdp_seed=seed,
hdp_sample_hyper=False,
hdp_eta=eta,
hdp_gamma_s=gamma,
hdp_alpha_s=alpha,
word_grams=1,
drop_uncommon=drop_uncommon,
freq_threshold=1,
verbose=verbose)
# Infer the BoW and LSS representations of the documents
try:
# Load, project and visualise the data
plain_docs, bow_rep_docs, lss_rep_docs = Modeller.get_corpus_lss(
infer_lss,
bim=False)
# Begin Clustering Attempts
true_labels_path = (r"..\..\Datasets\pan17_train\truth"
r"\problem{}\clustering.json"
).format(problem_nbr)
ground_truth = Tools.load_true_clusters_into_vector(true_labels_path)
# Normalise the data if not BIM is used!
clu_lss = Clusterer(dtm=Tools.normalise_data(data=lss_rep_docs),
true_labels=ground_truth,
max_nbr_clusters=len(lss_rep_docs)-1,
min_nbr_clusters=1,
min_cluster_size=2,
metric="cosine",
desired_n_clusters=n_clusters)
norm_spk_pred, norm_spk_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_spherical_k_means,
param_init="k-means++")
# ispk_pred, ispk_evals = clu_lss.evaluate(
# alg_option=Clusterer.alg_iterative_spherical_k_means,
# param_init="k-means++")
norm_hdbscan_pred, norm_hdbscan_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_h_dbscan)
norm_ms_pred, norm_ms_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_mean_shift)
# norm_xm_pred, norm_xm_evals = clu_lss.evaluate(
# alg_option=Clusterer.alg_x_means)
nhac_complete_pred, nhac_complete_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_hac,
param_linkage="complete")
nhac_s_pred, nhac_s_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_hac,
param_linkage="single")
nhac_a_pred, nhac_a_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_hac,
param_linkage="average")
n_optics_pred, n_optics_evals = clu_lss.evaluate(
alg_option=Clusterer.alg_optics)
# Baselines
bl_rand_pred, bl_rand_evals = clu_lss.evaluate(
alg_option=Clusterer.bl_random)
bl_singleton_pred, bl_singleton_evals = clu_lss.evaluate(
alg_option=Clusterer.bl_singleton)
nhdp_pred, nhdp_evals = clu_lss.eval_cluster_hdp()
ntrue_pred, ntrue_evals = clu_lss.eval_true_clustering()
# SOTA - Gomez et. al. HAC and Log-Entropy with 20k features
sota_pred_path = (r"D:\College\DKEM\Thesis\AuthorshipClustering\Code"
r"\clusterPAN2017-master\train_out_LogEnt"
f"\\problem{problem_nbr}\\clustering.json")
sota_predicted = Tools.load_true_clusters_into_vector(sota_pred_path)
sota_pred, sota_evals = clu_lss.eval_sota(
sota_predicted=sota_predicted)
# Return the results:
return (Tools.form_problemset_result_dictionary(
dictionaries=[
# ispk_evals, norm_spk_evals, norm_hdbscan_evals,
norm_spk_evals, norm_hdbscan_evals,
norm_ms_evals, # norm_xm_evals,
nhac_complete_evals, nhac_s_evals, nhac_a_evals,
n_optics_evals, bl_rand_evals, bl_singleton_evals,
nhdp_evals, sota_evals, ntrue_evals
],
identifiers=[ # "iSpKmeans",
"E_SPKMeans", "E_HDBSCAN",
"E_Mean_Shift", # "XMeans",
"E_HAC_C", "E_HAC_Single", "E_HAC_Average",
"E_OPTICS", "BL_r", "BL_s",
"S_HDP", "BL_SOTA", "Labels"],
problem_set=problem_set_id),
ground_truth,
lss_rep_docs,
plain_docs,
clu_lss)
except FileNotFoundError:
print("Please run HDP on these data first.")
