def tsne_executor(X, y, logger, path_logs):
check_input_type(
['epi'],
"t-SNE experiment work just with epigenetic data, {} found".format(
config['general']['input_type']))
cell_lines = config['general']['cell_lines']
tasks_dict = config['general']['tasks']
results = {}
for t in tasks_dict:
task_name, X_filtered, y_filtered = filter_labels(X, y, t)
logger.debug("TASK: {}".format(task_name))
cpus = multiprocessing.cpu_count(
) // 2 # we use just half of avaible cpus to not overload the machine
logger.debug("Using {} cpus".format(cpus))
for cl, data, labels in zip(cell_lines, X_filtered, y_filtered):
logger.debug("Computing t-SNE for {}".format(cl))
tsne = TSNE(perplexity=config['tsne']['perplexity'],
n_jobs=cpus) # TODO: add parameters
tsne_results = tsne.fit_transform(data)
assert len(tsne_results) == len(labels)
tsne_results = np.c_[
tsne_results,
labels] # to save the labels with the tsne results
results["{}_{}".format(task_name, cl)] = tsne_results
save_tsne(path_logs, "tsne_results", results)
if config['tsne']['save_plots']:
plot_tsne(results, path_logs, "tsne_plot")
def main(feats_path):
with open(feats_path, 'rb') as handle:
unpickler = pickle.Unpickler(handle)
labels = unpickler.load()
labels = {
name: vector
for name, vector in labels.items() if vector is not None
}
features = np.asarray(list(labels.values()))
print('[INFO] Conducting t-SNE on ' + feats_path)
tsne = TSNE(metric='braycurtis',
verbose=1,
n_iter=5000,
random_state=42,
n_jobs=-1)
projection = tsne.fit_transform(features)
# save reduced vectors
base = path.basename(feats_path)
name = path.splitext(base)[0]
output = name + '_tsne.pickle'
print('[INFO] Saving reduced vectors to ' + output)
with open(output, 'wb') as handle:
pickle.dump(projection, handle)
def calcTSNEMulti(data, iterations, perplexity, learning_rate):
tsne = TSNE(n_jobs=4,
perplexity=perplexity,
n_iter=iterations,
learning_rate=learning_rate)
Y = tsne.fit_transform(data)
return data.assign(x=Y[:, 0], y=Y[:, 1])
def set_params(self,
n_components=2,
perplexity=30.0,
early_exaggeration=12,
learning_rate=200,
n_iter=1000,
n_iter_without_progress=30,
min_grad_norm=1e-07,
metric='euclidean',
init='random',
verbose=0,
random_state=None,
method='barnes_hut',
angle=0.5,
n_jobs=1,
cheat_metric=True):
self.tsne = MulticoreTSNE(
n_components=n_components,
perplexity=perplexity,
early_exaggeration=early_exaggeration,
learning_rate=learning_rate,
n_iter=n_iter,
n_iter_without_progress=n_iter_without_progress,
min_grad_norm=min_grad_norm,
metric=metric,
init=init,
verbose=verbose,
random_state=random_state,
method=method,
angle=angle,
n_jobs=n_jobs,
cheat_metric=cheat_metric)
def draw(x, y):
from matplotlib.colors import ListedColormap
from MulticoreTSNE import MulticoreTSNE as TSNE
print("TSNE: fitting start...")
tsne = TSNE(2, n_jobs=4, perplexity=30)
Y = tsne.fit_transform(x)
# matplotlib_axes_logger.setLevel('ERROR')
labels = [
'c1', 'c2', 'c3', 'c4', 'c5', 'c6', 'c7', 'c8', 'c9', 'c10', 'open'
]
id_to_label = {i: label for i, label in enumerate(labels)}
y_true = pd.Series(y)
plt.style.use('ggplot')
n_class = y_true.unique().shape[0]
colors = ('gray', 'lightgreen', 'plum', 'DarkMagenta', 'SkyBlue',
'PaleTurquoise', 'DeepPink', 'Gold', 'Orange', 'Brown',
'DarkKhaki')
fig, ax = plt.subplots(figsize=(9, 6), )
la = [i for i in range(n_class)]
la = sorted(la, reverse=True)
cmap = ListedColormap(colors)
for idx, label in enumerate(la):
ix = y_true[y_true == label].index
x = Y[:, 0][ix]
y = Y[:, 1][ix]
ax.scatter(x, y, c=cmap(idx), label=id_to_label[label], alpha=0.5)
# Shrink current axis by 20%
ax.set_title('proto_loss')
box = ax.get_position()
ax.set_position([box.x0, box.y0, box.width * 0.8, box.height])
ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))
def generate2dftEmb():
global w2id, w, i, word, tsne, post_2d
####
# Loading glove embeddings from pickle file glove_new.pickle and writing into embedding map and a text file which
# can be used to gensim model
####
file = open(finetuned_path, 'rb')
embedding_map = pickle.load(file)
# In[470]:
##########
##Converting glove embeddings to numpy matrix where each row contains embedding of a word.
##Adding words to "word to id" and "id to word" maps
##########
w2id = {}
id2w = {}
w = np.zeros((len(embedding_map.keys()), 300))
for i, word in enumerate(embedding_map.keys()):
w2id[word] = i
id2w[i] = word
w[i] = embedding_map[word]
# In[6]:
######
##Applying t-SNE to reduce the dimension of the embedding from 300D to 2D.
######
tsne = TSNE(n_jobs=12)
post_2d = tsne.fit_transform(w)
# In[486]:
return post_2d, w2id, w
def generate2dpre():
global word, i, pre_w2id, tsne, pre_2d
pre_vocab = []
pre = open(pretrained_path, 'r')
for line in pre:
embeds = line.rstrip().split(" ")
word = embeds[0]
pre_vocab.append(word)
# In[37]:
pre_w = np.zeros((len(pre_vocab), 300))
for i, line in enumerate(pre):
embeds = line.rstrip().split(" ")
word = embeds[0]
pre_w[i, :] = embeds[1:]
# In[ ]:
##########
##Converting pre glove embeddings to numpy matrix where each row contains embedding of a word.
##Adding words to "word to id" and "id to word" maps
##########
pre_w2id = {}
for i in range(len(pre_vocab)):
pre_w2id[pre_vocab[i]] = i
# In[39]:
######
##Applying t-SNE to reduce the dimension of the embedding from 300D to 2D.
######
tsne = TSNE(n_jobs=12)
pre_2d = tsne.fit_transform(pre_w)
return pre_2d, pre_w2id, pre_w
def run_tSNE(natural_embed, n_jobs, perplexity):
'''
The GPU version requires CUDA 9.0 and install the tsnecuda package by running
conda install tsnecuda -c cannylab
The Multicore CPU version can be installed by running
pip install MulticoreTSNE
Apply t-SNE to the input data
INPUT:
natural_embed: 2d numpy array with size [number of points, embedding length]
n_jobs:
perplexity:
OUTPUT:
natural_2d: 2d numpy array with size [number of points, 2]
adversary_2d: 2d numpy array with size [number of points, 2]
'''
X = natural_embed
# CPU Sklearn
# from sklearn.manifold import TSNE
# tsne = TSNE(perplexity=perplexity, n_iter=5000, n_iter_without_progress=800, learning_rate=20, metric='cosine')
# X_embedded = tsne.fit_transform(X)
# CPU
from MulticoreTSNE import MulticoreTSNE as TSNE
tsne = TSNE(n_jobs=n_jobs, perplexity=perplexity, n_iter=5000, n_iter_without_progress=800, learning_rate=20, metric='cosine')
X_embedded = tsne.fit_transform(X)
# GPU
# from tsnecuda import TSNE
# X_embedded = TSNE(n_components=2, perplexity=30, learning_rate=10).fit_transform(X)
return X_embedded
def ex3(wv):
phrases = [
"szkoda",
"strata",
"uszczerbek",
"szkoda majątkowa",
# "uszczerbek na zdrowiu",
"krzywda",
"niesprawiedliwość",
"nieszczęście"
]
tsne = MulticoreTSNE(n_components=2, n_jobs=os.cpu_count())
tsne.fit(wv.vectors)
vectors_embedded = tsne.fit_transform(wv[(sanitize(phrase)
for phrase in phrases)])
fig, ax = plt.subplots()
ax.scatter(vectors_embedded[:, 0], vectors_embedded[:, 1])
for i, phrase in enumerate(phrases):
ax.annotate(phrase, (vectors_embedded[:, 0][i], vectors_embedded[:, 1][i]))
plt.show()
def plot_tsne(experience=None, latent_states=None, rewards=None):
if latent_states is None or rewards is None:
latent_states = np.array([
list(rssm_state.prev_state.stoch)
for rssm_state in experience['agent_infos']
])
rewards = np.array(experience['reward'])
np.random.seed(0)
perm = np.random.permutation(10000)
latent_states = latent_states[perm]
rewards = rewards[perm]
feature_cols = ['axis_' + str(i) for i in range(latent_states.shape[1])]
df = DataFrame(latent_states, columns=feature_cols)
df['y'] = rewards
time_start = time()
tsne = TSNE(n_components=2,
verbose=1,
perplexity=1000,
n_iter=1000,
n_jobs=16)
tsne_results = tsne.fit_transform(df[feature_cols].values)
print('t-SNE done! Time elapsed: {} seconds'.format(time() - time_start))
pickle.dump(tsne_results, open('tsne_results.pkl', 'wb'))
df['tsne-2d-one'] = tsne_results[:, 0]
df['tsne-2d-two'] = tsne_results[:, 1]
sns.scatterplot(x="tsne-2d-one",
y="tsne-2d-two",
hue="y",
palette=sns.color_palette("flare", as_cmap=True),
data=df,
alpha=0.6,
s=5)
plt.show()
def main():
parser = argparse.ArgumentParser(description='main function parser')
parser.add_argument('--path',
type=str,
help='load file path',
required=True)
parser.add_argument('--dump_dir',
type=str,
help='dump directory',
default=None)
parser.add_argument('--size',
type=int,
default=1000,
help='embedding vector size')
args = parser.parse_args()
embeddings, labels = load(args.path, args.size)
output = args.path.split('/')[-1]
# # UMAP
# weights = umap.UMAP().fit_transform(embeddings)
# show(weights, labels, 'umap.svg')
# t-SNE
tsne_model = TSNE(n_components=2)
weights = tsne_model.fit_transform(embeddings)
show(weights, labels, f'graph/{output}.svg')
def plot_distribution(
epoch,
train,
# acc,
path,
data_x,
# true_y,
pred_y,
learning_rate=100,
n_jobs=-1):
print("plotting image on " + path + "...")
if (os.path.exists(path) == False):
os.makedirs(path)
tsne_model = TSNE(n_components=2,
learning_rate=learning_rate,
n_jobs=n_jobs)
# pca_model = PCA(n_components=2)
data_x = np.array(data_x)
if (len(data_x.shape) > 2):
data_temp = []
for data in data_x:
data_temp.append(data.rehsape(-1))
data_x = np.array(data_temp)
transformed = tsne_model.fit_transform(data_x)
# transformed = pca_model.fit_transform(data_x)
xs = transformed[:, 0]
ys = transformed[:, 1]
# draw_plot(xs, ys, train, epoch, true_y, os.path.join(path, "true_label"))
draw_plot(xs, ys, train, epoch, pred_y, path)
def display_closestwords_tsnescatterplot(arg_path_to_model, word):
model = word2vec.Word2Vec.load(arg_path_to_model)
for i in range(len(word)):
arr = np.empty((0, 300), dtype='f')
word_labels = [word[i]]
# get close words
close_words = model.similar_by_word(word[i])
# add the vector for each of the closest words to the array
arr = np.append(arr, np.array([model[word[i]]]), axis=0)
for wrd_score in close_words:
wrd_vector = model[wrd_score[0]]
word_labels.append(wrd_score[0])
arr = np.append(arr, np.array([wrd_vector]), axis=0)
# find tsne coords for 2 dimensions
tsne = TSNE(n_components=2, random_state=0)
np.set_printoptions(suppress=True)
Y = tsne.fit_transform(arr)
x_coords = Y[:, 0]
y_coords = Y[:, 1]
# display scatter plot
plt.scatter(x_coords, y_coords)
for label, x, y in zip(word_labels, x_coords, y_coords):
plt.annotate(label, xy=(x, y), xytext=(0, 0), textcoords='offset points')
# Zmiana mnoznika powoduje zmiane 'przyblizenia' wykresu (mniejszy mnoznik = wieksze przyblizenie)
plt.xlim(x_coords.min()*1, x_coords.max()*1)
plt.ylim(y_coords.min()*1, y_coords.max()*1)
plt.show()
def main():
parser = argparse.ArgumentParser(description='main function parser')
parser.add_argument('--path', type=str, help='load file path', required=True)
parser.add_argument('--dump_dir', type=str, help='dump directory', default=None)
parser.add_argument('--size', type=int, default=1000, help='embedding vector size')
args = parser.parse_args()
embeddings, labels = load(args.path)
embeddings = np.array(embeddings)
output = args.path.split('/')[-1]
# # UMAP
n_neighbors = [15] #, 35, 55, 75]
min_dists = [0.1] #0.001, 0.01, 0.1]
for min_dist in min_dists:
for n_neighbor in n_neighbors:
start = time.time()
weights = umap.UMAP(n_neighbors=n_neighbor, min_dist=min_dist).fit_transform(embeddings)
finish = time.time()
print(f'time: {finish-start} s', flush=True)
os.makedirs(f'graph/umap/{output}', exist_ok=True)
show(weights, labels, f'graph/umap/{output}/min_dist:{min_dist}_neighbor:{n_neighbor}.svg')
# t-SNE
perplexities = [30] #10, 20, 30, 40, 50]
for perplexity in perplexities:
start = time.time()
tsne_model = TSNE(n_components=2, perplexity=perplexity, n_jobs=10)
weights = tsne_model.fit_transform(embeddings)
finish = time.time()
print(f'time: {finish-start} s', flush=True)
os.makedirs(f'graph/tsne/{output}', exist_ok=True)
show(weights, labels, f'graph/tsne/{output}/perplexity:{perplexity}.svg')
def __async_tsne_embedding(x):
# learn manifold
tsne = MulticoreTSNE(n_jobs=32, n_components=2)
x = x.astype(np.float64)
x_fitted = tsne.fit_transform(x)
return x_fitted
def tsne_vis(netZ, rn, img_size, real_imgs):
import matplotlib.pyplot as plt
from MulticoreTSNE import MulticoreTSNE as TSNE
Zs_real = netZ.emb.weight.data.detach().cpu().numpy()
if not os.path.isdir("runs"):
os.mkdir("runs")
if not os.path.isdir("runs/ims_%s" % rn):
os.mkdir("runs/ims_%s" % rn)
tsne = TSNE(n_components=2, perplexity=30, n_jobs=20)
n_samples = len(real_imgs)
targets = np.asarray([netZ.idx2label[x] for x in range(n_samples)])
filtered_indices = targets[targets < 11]
targets = targets[filtered_indices]
Z_filter = Zs_real[filtered_indices]
print(len(Z_filter))
reduced_data = tsne.fit_transform(np.asarray(Z_filter, dtype='float64'))
plot_by_latent(reduced_data,
real_imgs,
indices=filtered_indices,
img_size=img_size,
rn=rn,
title="G2")
# print(indices)
# y_for_plot = np.concatenate([a, moves_,y_labels])
# N = len(y_lables)
# Y=Y[indices]
# Y = bh_sne(np.asarray(s_t[0:N], dtype='float64'))
# normalize
min_1 = reduced_data[:, 0].min()
max_1 = reduced_data[:, 0].max()
min_2 = reduced_data[:, 1].min()
max_2 = reduced_data[:, 1].max()
Yn = reduced_data[:]
Yn[:, 0] = (reduced_data[:, 0] - min_1) / (max_1 - min_1)
Yn[:, 1] = (reduced_data[:, 1] - min_2) / (max_2 - min_2)
## plot distribution
unique_classes = len(np.unique(targets))
y_labels_colors = targets
plt.scatter(Yn[:, 1],
-Yn[:, 0],
c=y_labels_colors,
cmap=plt.cm.get_cmap("tab20", unique_classes),
s=10,
edgecolors='k')
mn = int(np.floor(y_labels_colors.min())) # colorbar min value
mx = int(np.ceil(y_labels_colors.max())) # colorbar max value
md = (mx - mn) // 2
cbar = plt.colorbar()
cbar.set_ticks([mn, md, mx])
cbar.set_ticklabels([mn, md, mx])
# plt.scatter(Yn[Zs_real, 1], -Yn[Zs_real, 0], c="black", s=100, edgecolors='k', marker="x")
# plt.scatter(Yn[indices[0], 1], -Yn[indices[0], 0], c="darkorange", s=100, edgecolors='k', marker="P", label="start")
# plt.scatter(Yn[indices[1], 1], -Yn[indices[1], 0], c="yellow", s=100, edgecolors='k', marker="p", label="target")
# plot_path(moves_knn, start_point_plt, targ_point_plt, title="RNN miniImagenet", more="")
plt.savefig(f"runs/ims_{rn}/tsne_{rn}.jpg")
def compute_tsne(X, y, n_class=2,
savepath=None,
xlim=(-50,50), ylim=(-50,50),
cls_lbl=['Benign','Tumor'],
title=' ',PCADIM=50):
tsne = TSNE(n_jobs=4, random_state=1337)
#X = PCA(n_components=PCADIM).fit_transform(X)
embs = tsne.fit_transform(X)
plt.figure(figsize=(10,10))
for i in range(n_class):
inds = np.where(y == i)[0]
plt.scatter(embs[inds, 0], embs[inds, 1], color=colors[i], marker='*', s=30)
if xlim:
plt.xlim(xlim[0], xlim[1])
if ylim:
plt.ylim(ylim[0], ylim[1])
plt.legend(cls_lbl)
plt.grid(b=None)
plt.title(title)
if savepath:
plt.savefig(savepath, dpi=300, bbox_inches='tight')
plt.savefig(savepath.replace('.png','.pdf'), dpi=300, bbox_inches='tight')
else:
plt.show()
plt.clf()
def tsne_image(
features, images, img_res=64, res=4000, background_color=255, max_feature_size=-1, labels=None, point_radius=20, n_threads=0
):
"""
Embeds images via tsne into a scatter plot.
Parameters
---------
features: numpy array
Features to visualize
images: list or numpy array
Corresponding images to features.
img_res: int
Resolution to embed images at
res: int
Size of embedding image in pixels
background_color: float or numpy array
Background color value
max_feature_size: int
If input_feature_size > max_feature_size> 0, features are first
reduced using PCA to the desired size.
point_radius: int
Size of the circle for the label image.
n_threads: int
Number of threads to use for t-SNE
labels: List or numpy array if provided
Label for each image for drawing circle image.
"""
features = np.asarray(features, dtype=np.float32)
assert len(features.shape) == 2
print("Starting TSNE")
s_time = time.time()
if 0 < max_feature_size < features.shape[-1]:
pca = PCA(n_components=max_feature_size)
features = pca.fit_transform(features)
if n_threads <= 0:
n_threads = multiprocessing.cpu_count()
model = TSNE(n_components=2, verbose=1, random_state=0, n_jobs=n_threads)
f2d = model.fit_transform(features)
print("TSNE done.", (time.time() - s_time))
print("Starting drawing.")
x_coords = f2d[:, 0]
y_coords = f2d[:, 1]
return image_util.draw_images_at_locations(images, x_coords, y_coords, img_res, res, background_color, labels, point_radius)
def calc_tsne(
X,
n_jobs,
n_components,
perplexity,
early_exaggeration,
learning_rate,
random_state,
init="random",
n_iter=1000,
n_iter_early_exag=250,
):
"""
TODO: Typing
"""
tsne = TSNE(
n_jobs=n_jobs,
n_components=n_components,
perplexity=perplexity,
early_exaggeration=early_exaggeration,
learning_rate=learning_rate,
random_state=random_state,
verbose=1,
init=init,
n_iter=n_iter,
n_iter_early_exag=n_iter_early_exag,
)
X_tsne = tsne.fit_transform(X)
logger.info("Final error = {}".format(tsne.kl_divergence_))
return X_tsne
def tsne_reduction(samples,
perplexity,
data=None,
n_components=2,
l_r=200,
dim=2,
ex=12,
iterations=5000,
verbosity=0):
if (samples is None) and (data is not None):
samples = data[:, :-1]
targets = data[:, -1]
# tsne = manifold.TSNE(n_components = dim, init='pca', learning_rate = l_r,
# perplexity=perplexity, early_exaggeration = ex,
# n_iter = iterations, random_state=data_handling.RANDOM_SEED,
# verbose = verbosity)
tsne = TSNE(n_components=dim,
n_jobs=-1,
learning_rate=l_r,
perplexity=perplexity,
early_exaggeration=ex,
n_iter=iterations,
random_state=data_handling.RANDOM_SEED,
verbose=verbosity)
reduced_samples = tsne.fit_transform(samples)
return reduced_samples, tsne
def get_data(n_cmd, n_spk, only_missed=False):
if only_missed:
# most popular MIS-CLASSIFIED command based on utterances count
top_cmd = itemfreq(y_command[y_missed.astype('int32')])
top_spk = itemfreq(y_speaker[y_missed.astype('int32')])
else:
top_spk = itemfreq(y_speaker)
top_cmd = itemfreq(y_command)
top_cmd = top_cmd[np.argsort(top_cmd[:, 1])][::-1]
top_cmd = top_cmd[:, 0]
# most speaker command based on utterances count
top_spk = top_spk[np.argsort(top_spk[:, 1].astype('int32'))][::-1]
top_spk = top_spk[:, 0]
spk = top_spk[:n_spk]
cmd = top_cmd[:n_cmd]
ids = get_indices(speaker_set=spk, command_set=cmd)
if only_missed:
ids = np.array([i for i in ids if i in y_missed], dtype='int32')
y_cmd = y_command[ids]
y_spk = y_speaker[ids]
z_org = Z_original[ids]
z_max = Z_maximize[ids]
tsne = TSNE(random_state=SEED)
t = tsne.fit_transform(np.concatenate((z_org, z_max), axis=0))
t_org = t[:z_org.shape[0]]
t_max = t[z_org.shape[0]:]
return t_org, t_max, y_cmd, y_spk
def __init__(self,
container,
perplexity=30.0,
learning_rate=120.0,
n_componenets=2,
n_jobs=4,
n_iter=1000,
verbose=1000):
"""
Args:
container: EmbeddingContainer
"""
self._container = container
self._engine = MulticoreTSNE(
perplexity=perplexity,
learning_rate=learning_rate,
n_components=n_componenets,
n_jobs=n_jobs,
n_iter=n_iter,
verbose=verbose)
self._results = None
self._ids = None
self._label_ids = None
self._label_names = None
def plot_conti_code_tsne():
data = pickle.load(
open(
"/home/patrick/repositories/hyperspectral_phenotyping_gan/experiments_{}/generated_code_noise{}_disc{}_conti{}_epoch{}.p"
.format(opt.dataset, opt.n_noise, opt.n_dis, opt.n_conti,
opt.epoch), "rb"))
labels = np.array(data["y"]).squeeze()
labels_unique = np.unique(labels)
code = np.array(data["z"]).copy()
z = np.array(data["z"]).copy()
# print(code[0])
# code = code[:, -5:-2]
code = code[:, -2:]
# print(code[0])
# 1 / 0
signatures = np.array(data["x"])
tsne = TSNE(n_jobs=26, n_components=2, learning_rate=100)
Y = tsne.fit_transform(code)
colors = ["red", "green", "blue"]
for idx, label in enumerate(labels_unique):
data_tsne = Y[labels == label]
plt.scatter(data_tsne[:, 0],
data_tsne[:, 1],
c=colors[idx],
alpha=0.3,
label=str(label))
plt.legend()
plt.show()
def run(self, word_embedding):
"""
Runs t-SNE model with specified parameters and data. Returns result.
:param word_embedding: Word embedding; expected to be only as long as self.num_words.
:return:
"""
self.word_embedding = word_embedding
word_vector_data = numpy.stack(word_embedding['values'].values, axis=0)
# Initialize t-SNE instance.
tsne = MulticoreTSNE(n_components=self.num_dimensions,
perplexity=self.perplexity,
early_exaggeration=self.early_exaggeration,
learning_rate=self.learning_rate,
n_iter=self.num_iterations,
min_grad_norm=self.min_grad_norm,
random_state=self.random_state,
angle=self.angle,
metric=self.metric,
init=self.init_method,
n_jobs=2)
# Train TSNE on gensim's model.
# Note: Since MulticoreTSNE doesn't support metrics other than Euclidean, we normalize our vectors to an unit
# norm so that the Euclidean distance yields results/ordering more similar to the cosine similarity.
self.tsne_results = tsne.fit_transform(
sklearn.preprocessing.normalize(word_vector_data,
axis=1,
norm='l2'))
return self.tsne_results
def train(self, parameters):
tsne = TSNE(**parameters)
tsne_outputs = tsne.fit_transform(self.x_train)
utils.save_data_to_pkl(tsne_outputs,
tsne_outputs_path + 'tsne_outputs.p')
def run_tSNE(data, n_pc, n_dim, p, verbose = 3, random_state = 0, n_jobs = 20): pca = PCA(n_components = n_pc) rateb_reduce = pca.fit_transform(data) ndim = n_dim tsne = MulticoreTSNE(perplexity = p, verbose = verbose, random_state = random_state, n_jobs = n_jobs) y = tsne.fit_transform(rateb_reduce[:, :n_dim]) return y
def visualize(self, indices = [], center_num = 0,
ref_labels = [], use_colors = True):
# If indices are not given
if len(indices) ==0:
indices = np.arange(len(self.embeddings_))
# If center number is not given
if center_num == 0:
center_num = self.opt_speaker_num_
# If reference labels are used
if len(ref_labels) != 0:
speaker_labels = ref_labels
# Allow visualization of different center number configurations
else:
# Get speaker labels
spkmeans = SphericalKMeans(n_clusters=len(self.centers_[center_num]),
init = self.centers_[center_num],
max_iter=1, n_init=1, n_jobs=1).fit(self.embeddings_[indices])
speaker_labels = spkmeans.labels_+1
if len(self.speaker_labels_) == 0:
raise RuntimeError("Clustering not performed.")
# Compute TSNE only once
if len(self.emb_2d_) == 0:
print("Computing TSNE transform...")
tsne = TSNE(n_jobs=4)
self.emb_2d_ = tsne.fit_transform(self.embeddings_)
# Visualize
emb_2d = self.emb_2d_[indices]
speaker_labels = speaker_labels.astype(np.int)
speakers = np.unique(speaker_labels)
colors=cm.rainbow(np.linspace(0,1,len(speakers)))
plt.figure(figsize=(7,7))
for speaker in speakers:
speak_ind = np.where(speaker_labels == speaker)[0]
x, y = np.transpose(emb_2d[speak_ind])
if use_colors == True:
plt.scatter(x, y, c="k", edgecolors=colors[speaker-1], s=2, label=speaker)
else:
plt.scatter(x, y, c="k", edgecolors="k", s=2, label=speaker)
plt.legend(title = "Speakers", prop={'size': 10})
if len(ref_labels) == 0:
plt.title("Predicted speaker clusters")
else:
plt.title("Reference speaker clusters")
plt.show()
def get_2D_vector(vectors):
"""
Sử dụng giải thuật TSNE để ánh xạ vectors nhiều chiều về 2 chiều
http://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html
https://distill.pub/2016/misread-tsne/
"""
tsne = TSNE(perplexity=25, n_components=2, init='random', n_iter=1000, n_jobs=-1)
return tsne.fit_transform(vectors)
def run_tsne(path):
ids, X = load_matrix(path)
tsne = TSNE(n_jobs=8)
# tsne = TSNE(metric='cosine')
Y = tsne.fit_transform(X)
for i, row in enumerate(Y):
print(' '.join([ids[i], str(row[0]), str(row[1])]))
def generate_tsne(path, data, label):
print '\nGenerating t-SNE...'
tsne = TSNE(n_jobs=-1)
Y = tsne.fit_transform(data)
plt.figure(figsize=(20, 20))
plt.scatter(Y[:, 0], Y[:, 1], c=label, s=100, cmap='Set1', alpha=0.2)
plt.colorbar()
plt.savefig(path)
