def get_cv_cpv(x: str, percent: float) -> float:
global model_goal
# Get dataset number
dataset_num = get_dataset_num(x)
# Get number of pcs for CPV > 0.8 and CPV > 0.99
if percent == 0.99:
pcs_cpv = df_selection.loc[dataset_num, "Cum. Perc. Var. (0.99)"]
else:
pcs_cpv = df_selection.loc[dataset_num, "Cum. Perc. Var. (0.8)"]
# Get df_results
df = pd.read_csv(x)
idx = df.features_kept == pcs_cpv
try:
return df.loc[idx].cv.values[0]
except:
inputs = Inputs(paths)
inputs.random_seed = 1969
inputs.get_df_split(dataset_num)
pca_model = get_pca_model(inputs)
cluster_model = Clustering(inputs.num_cluster, 100, inputs.random_seed)
cluster_model.fit(pca_model.pcs_train.loc[:, :pcs_cpv - 1])
cluster_prediction = cluster_model.predict(
pca_model.pcs_test.loc[:, :pcs_cpv - 1])
cluster_performances = cluster_model.get_cluster_performances(
inputs.df_test.copy(),
cluster_prediction,
pcs_cpv,
inputs.num_cluster,
model_goal=model_goal)
return variation(cluster_performances)
def cluster(self, shapelets):
"""
Uses a clustering algorithm to reduce the number of shapelets.
:param shapelets: list of shapelet candidates
:type shapelets: np.array, shape = (len(shapelets), len(s), len(dim(s)))
:return: list of remaining shapelet candidates
:rtype np.array, shape = (|remaining candidates|, len(s), len(dim(s)))
"""
clustering = Clustering(self.d_max)
clustering.fit(shapelets)
return clustering.nn_centers()
def perform_clustering(
term_ids_to_embs: Dict[int, List[float]]) -> Dict[int, Set[int]]:
"""Cluster the given terms into 5 clusters.
Args:
term_ids_to_embs: A dictionary mapping term-ids to their
embeddings.
Return:
A dictionary of mapping each cluster label to its cluster.
Each cluster is a set of term-ids.
"""
# Case less than 5 terms to cluster.
num_terms = len(term_ids_to_embs)
if num_terms < 5:
clusters = {}
for i, tid in enumerate(term_ids_to_embs):
clusters[i] = {tid}
return clusters
# Case more than 5 terms to cluster.
c = Clustering()
term_ids_embs_items = [(k, v) for k, v in term_ids_to_embs.items()]
results = c.fit([it[1] for it in term_ids_embs_items])
labels = results['labels']
print(' Density:', results['density'])
clusters = defaultdict(set)
for i in range(len(term_ids_embs_items)):
term_id = term_ids_embs_items[i][0]
label = labels[i]
clusters[label].add(term_id)
return clusters
def clustering(x, df, n_clusters=10, distance='angular', method='K-medians'):
"""
Do the clustering, based on the 91 features.
Args:
x: array of features
df: dataframe of features
n_clusters: number of clusters
distance: could be 'angular' or 'euclidean';
method: could be 'K-medians', 'K-means', 'Hierarchical'
Output:
new_df: the labeled dataframe, according to the clustering algorithm
relevant_features_cs: a list with the relevant features (angles of the consecutive limbs) of the centroids
cs: dictionary with the centroid features
"""
relevant_features_id = [
0, 3, 5, 13, 15, 17, 25, 46, 47, 56, 64, 65, 76, 77, 83, 85, 90
]
keys_dict = [
'0-1', '0-4', '0-6', '1-2', '1-4', '1-6', '2-3', '4-5', '4-6', '5-7',
'6-8', '6-9', '8-9', '8-10', '9-12', '10-11', '12-13'
]
clustering_ = Clustering(k=n_clusters, distance=distance, method=method)
cs, cls = clustering_.fit(x)
assert len(list(cls.keys())) == n_clusters
d = pd.DataFrame()
l = []
for i in range(n_clusters):
df1 = pd.DataFrame(cls[i])
d = pd.concat([d, df1], sort=False)
l += [i] * len(cls[i])
d.columns = df.columns
d.insert(91, 'label', l)
new_df = df.reset_index().merge(d).set_index('index')
relevant_features_cs = []
if method == 'Hierarchical':
pass
else:
for i in range(len(cs)):
d = {}
cs_rf = cs[i][relevant_features_id]
for k in range(len(keys_dict)):
d[keys_dict[k]] = cs_rf[k]
relevant_features_cs.append(d)
return new_df, relevant_features_cs, cs
def clustering(x, n_clusters):
"""
Do the clustering, based on the 91 features.
We compute the reconstructed poses only with the following default parameters:
method: 'K-Medians'
distance: 'angular'
Args:
x: array of features
n_clusters: number of clusters
Output:
new_df: the labeled dataframe, according to the clustering algorithm
relevant_features_cs: a list with the relevant features (angles of the consecutive limbs) of the centroids
cs: dictionary with the centroid features
"""
clustering_ = Clustering(k=n_clusters)
cs, cls = clustering_.fit(x)
d = pd.DataFrame()
l = []
for i in range(len(cs)):
df1 = pd.DataFrame(cls[i])
d = pd.concat([d, df1], sort=False)
l += [i] * len(cls[i])
d.columns = df.columns
d.insert(91, 'label', l)
new_df = df.reset_index().merge(d).set_index('index')
assert len(cs) == n_clusters
relevant_features_cs = []
for i in range(len(cs)):
d = {}
cs_rf = cs[i][relevant_features_id]
for k in range(len(keys_dict)):
d[keys_dict[k]] = cs_rf[k]
relevant_features_cs.append(d)
return new_df, relevant_features_cs, cs
from clustering import Clustering
# from embeddings import *
words = [
'computer', 'algorithm', 'program', 'bear', 'cat', 'snake', 'fish', 'tree',
'flower', 'gras', 'tea', 'water', 'milk'
]
# embedder = FastTextE()
# embedder.load_model()
emb_dict = {}
with open('fasttext-wiki-news-300d-1M.vec', 'r', encoding='utf8') as f:
for line in f:
sp_line = line.split(' ')
token, vector = sp_line[0], sp_line[1:]
emb_dict[token] = vector
word_embeddings = [emb_dict[word] for word in words]
clus = Clustering()
print(clus)
print(clus.clus_type)
print(clus.affinity)
print(clus.fit(word_embeddings))
