def clustering_states(args,
texts1,
texts2,
ex_name,
ex_instance,
size,
input_scaling,
leak_rate,
spectral_radius,
input_sparsity,
w_sparsity,
logging,
save_graph=False,
pca_model=None,
flow=None):
# >> 1. Convert the text to symbolic or continuous representations
if args.converter == "pos":
converter = RCNLPPosConverter(resize=args.in_components,
pca_model=pca_model)
elif args.converter == "tag":
converter = RCNLPTagConverter(resize=args.in_components,
pca_model=pca_model)
elif args.converter == "fw":
converter = RCNLPFuncWordConverter(resize=args.in_components,
pca_model=pca_model)
else:
converter = RCNLPWordVectorConverter(resize=args.in_components,
pca_model=pca_model)
# end if
# >> 2. Create an echo state network
if flow is None:
flow = create_reservoir(converter.get_n_inputs(), size, input_scaling,
leak_rate, spectral_radius, input_sparsity,
w_sparsity)
# end if
# >> 3. Generate Temporal Representations
# Generate "temporal representations" for first author
a1_states, a1_index, a1_n_samples = generate_documents_states(
converter, flow, texts1, args)
if save_graph:
generate_plot(logging,
ex_name,
ex_instance,
"Temporal representations for Author 1",
"Time",
"Neurons",
a1_states[:args.show_states],
transpose=True,
cmap='Greys')
# end if
# Generate "temporal representations" for second author
a2_states, a2_index, a2_n_samples = generate_documents_states(
converter, flow, texts2, args)
if save_graph:
generate_plot(logging,
ex_name,
ex_instance,
"Temporal representations for Author 2",
"Time",
"Neurons",
a2_states[:args.show_states],
transpose=True,
cmap='Greys')
# end if
# >> 4. Complete states.
complete_states = np.vstack((a1_states, a2_states))
if save_graph:
generate_plot(logging,
ex_name,
ex_instance,
"Complete joined Reservoir states",
"Time",
"Neurons",
complete_states,
transpose=True,
cmap='Greys')
# end if
# Get average and std dev
logging.save_results("Average neural activations",
np.average(complete_states))
logging.save_results("Std dev of neural activations",
np.std(complete_states))
# Same size for each authors in needed
if args.homogene:
if a1_states.shape[0] > a2_states.shape[0]:
a1_states = a1_states[:a2_states.shape[0]]
elif a2_states.shape[0] > a1_states.shape[0]:
a2_states = a2_states[:a1_states.shape[0]]
# end if
# end if
# >> 5. Join states.
join_states = np.vstack((a1_states, a2_states))
if save_graph:
generate_plot(logging,
ex_name,
ex_instance,
"Joined Reservoir states",
"Time",
"Neurons",
join_states,
transpose=True,
cmap='Greys')
# end if
# >> 6. Clustering
if args.out_components != -1:
# PCA
pca = PCA(n_components=args.out_components)
pca.fit(join_states)
# Generate PCA image of principal components
if args.pca_images and save_graph:
# Generate PCA
a1_states_pca = pca.transform(a1_states)
a2_states_pca = pca.transform(a2_states)
for c in np.arange(0, 8):
save_pca_image(logging, a1_states_pca, a2_states_pca, c, c + 1)
# end for
# end if
# Reduce whole states
join_states_reduced = pca.transform(join_states)
# Get centroids for the whole components
centroids, _ = kmeans(join_states_reduced, 2)
# Assign each sample to a cluster
idx, _ = vq(pca.transform(complete_states), centroids)
a1_idx = idx[:a1_n_samples]
a2_idx = idx[a1_n_samples:]
else:
# Get centroids for the whole components
centroids, _ = kmeans(join_states, 2)
# Assign each sample to a cluster
idx, _ = vq(complete_states, centroids)
a1_idx = idx[:a1_n_samples]
a2_idx = idx[a1_n_samples:]
# end if
# Compute average precision
return get_v_measure_score(a1_idx, a2_idx, a1_index, a2_index)
pca_model=pca_model)
elif args.converter == "fw":
converter = RCNLPFuncWordConverter(resize=args.in_components,
pca_model=pca_model)
else:
converter = RCNLPWordVectorConverter(resize=args.in_components,
pca_model=pca_model)
# end if
# Whathever
max_score = 0.0
# Iterate over reservoirs
for r in range(args.nreservoir):
# Create a reservoir
flow = cf.create_reservoir(converter.get_n_inputs(), rc_size,
rc_input_scaling, rc_leak_rate,
rc_spectral_radius, rc_input_sparsity,
rc_w_sparsity)
# Iterate
for i in np.arange(0, args.samples):
authors_id = np.random.choice(49, 2, replace=False) + 1
texts1 = os.path.join(args.texts, str(authors_id[0]))
texts2 = os.path.join(args.texts, str(authors_id[1]))
print("Round %d with author %s and %s" % (i, texts1, texts2))
state_score, doc_score = cf.clustering_states(
args=args,
texts1=texts1,
texts2=texts2,
ex_name=ex_name,