def aplicar_gap(predicao, gabarito):
import gap
resultados = {}
for lexelt in predicao:
ranklist = predicao[lexelt]
gold_ranklist = [palavra for palavra, peso in gabarito[lexelt]]
gold_weights = [peso for palavra, peso in gabarito[lexelt]]
resultados[lexelt] = gap.gap(ranklist, gold_ranklist, gold_weights)
return resultados, Util.media(resultados.values())
def plot_gap(self, *args, **kwargs):
if self.clusters != 1:
raise RuntimeError("GAP only defined for 1 cluster")
f = self.layer_outputs()
embedded, _ = self.predict(f)
embedded2 = np.apply_along_axis(lambda x: x[0], 1, embedded)
x = list(range(1, 21))
g = gap.gap(embedded2, ks=x)
fig, ax = plt.subplots()
ax.plot(x, g)
ax.set_title("GAP Statistic on un-clustered dataset")
ax.set_xlabel("Clusters (k)")
ax.set_ylabel("GAP statistic")
ax.set_xticks(x)
fig.savefig(os.path.join(self.img_dir, "gap.png"), dpi=300)
plt.close(fig)
def estimate_k_clusters(self, X, max_num_clusters):
from gap import gap
num_clusters = gap(X, max_num_clusters=max_num_clusters)
# silhouette_score is between [-1,1],
# so set score of 0 cluster as -1.0
# so set score of 1 cluster as 0.0
score = np.zeros(max_num_clusters + 1)
score[0] = -1.0
for k in range(2, max_num_clusters + 1):
labels = KMeans(n_clusters=k).fit_predict(X)
score[k] = silhouette_score(X, labels)
print('silhouette :', np.argmax(score))
return num_clusters
def main():
global loopCount, scoreCount, touch
while True:
gapSize = random.randint(5, 25)
if loopCount % 90 == 0:
topPos = random.randint(0, height / 2) - 400
pipes.add(pipe((width + 100, topPos + gapSize + 800)))
score.add(gap((width + 100, topPos + gapSize + 800)))
pipes.add(pipe((width + 100, topPos), True))
for event in pygame.event.get():
if event.type == QUIT:
sys.exit()
if event.type == pygame.KEYDOWN:
if event.key == pygame.K_SPACE:
player.speed[1] = -10
player.update()
pipes.update()
score.update()
gets_hit = pygame.sprite.spritecollide(player, pipes, False) \
or player.rect.center[1] > height
point_get = pygame.sprite.spritecollide(player, score, True)
screen.blit(background, [0, 0])
pipes.draw(screen)
score.draw(screen)
screen.blit(player.image, player.rect)
pygame.display.flip()
loopCount += 1
if gets_hit:
lose()
#print("Touch = "+str(touch)+" Point Get? = "+str(point_get))
if point_get and touch == False:
scoreCount += 1
print("Score: " + str(scoreCount))
touch = True
else:
touch = False
def main():
parser = argparse.ArgumentParser(prog='invocaGap.py',
description='Testing gap staticstics',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--sourceFolder',
help='Source folder',
type=str, required=True)
parser.add_argument('--outputFolder',
help='Output folder',
type=str, required=True)
args = parser.parse_args()
#Source folder of the files with the timestamps
sourceFolder = rfe.fixPath(args.sourceFolder)
if not os.path.exists(sourceFolder):
print ''
print 'Source folder does not exists ' + sourceFolder
print ''
sys.exit()
#Output folder for the graphics and files
outputFolder = rfe.fixPath(args.outputFolder)
if not os.path.exists(outputFolder):
try:
os.makedirs(outputFolder)
except:
print ''
print 'Unable to create folder ' + outputFolder
print ''
sys.exit()
#dataCluster stores the data to be used for the clustering process
#the size is equal to the number of frames, aka, the time component
#plus 5 as we are incorporating the 2 dimensions of the ellipse,
#x position, y position and angle
dataCluster = zeros((1,27))
units = []
dato = empty((1,1))
for unitFile in os.listdir(sourceFolder):
if os.path.isdir(sourceFolder+unitFile):
dato = empty((1,1))
unitName = unitFile.rsplit('_', 1)[0]
#print unitName
dataUnit, coordinates = rfe.loadSTACurve(sourceFolder,unitFile,unitName)
xSize = dataUnit.shape[0]
ySize = dataUnit.shape[1]
fitResult = rfe.loadFitMatrix(sourceFolder,unitFile)
#Time data from STA with gauss fit
#dataUnitTemporal = scipy.ndimage.gaussian_filter(dataUnit[coordinates[0][0],[coordinates[1][0]],:],2)
#Time data from STA without gauss fit
dataUnitTemporal = dataUnit[coordinates[0][0],[coordinates[1][0]],:]
#Time data from FITResult
#dataUnitTemporal = rfe.loadVectorAmp(sourceFolder,unitFile).T
#A radius of the RF ellipse
aRadius = fitResult[0][2]
dato[0] = aRadius
dataUnitCompleta = concatenate((dataUnitTemporal,dato),1)
#B radius of the RF ellipse
bRadius = fitResult[0][3]
dato[0] = bRadius
dataUnitCompleta = concatenate((dataUnitCompleta,dato),1)
#angle of the RF ellipse
angle = fitResult[0][1]
dato[0] = angle
dataUnitCompleta = concatenate((dataUnitCompleta,dato),1)
#X coordinate of the RF ellipse
xCoordinate = fitResult[0][4]
#print 'xCoordinate',xCoordinate
dato[0] = xCoordinate
dataUnitCompleta = concatenate((dataUnitCompleta,dato),1)
#Y coordinate of the RF ellipse
yCoordinate = fitResult[0][5]
#print 'yCoordinate',yCoordinate
dato[0] = yCoordinate
dataUnitCompleta = concatenate((dataUnitCompleta,dato),1)
#Area of the RF ellipse
area = aRadius*bRadius*pi
dato[0] = area
dataUnitCompleta = concatenate((dataUnitCompleta,dato),1)
#UnitName
dato=empty(1, dtype='|S16')
dato[0]=unitName
dataUnitCompleta = concatenate((dataUnitCompleta,dato.reshape(1, 1)),1)
dataCluster = append(dataCluster,dataUnitCompleta, axis=0)
units.append(unitName)
# remove the first row of zeroes
dataCluster = dataCluster[1:,:]
data = dataCluster[:,0:19]
data = data.astype(float64, copy=False)
gaps = gap.gap(data, refs=None, nrefs=len(data), ks=range(1,10))
dgap = zeros(len(gaps))
for i in range(len(gaps)-1):
dgap[i] = gaps[i]-gaps[i+1]
plt.plot(gaps)
plt.show()
plt.plot(dgap)
plt.show()
return 0
from gap import gap
import os
pwd = os.getcwd()
files = os.listdir(pwd + "/bands")
fo = open("phase3d.dat", "w")
for f in files:
os.system("cp bands/" + f + " BANDS.OUT")
l = f.split("_")
mu = l[2]
zee = l[4]
g = gap()
fo.write(str(mu) + " " + str(zee) + " " + str(g) + "\n")
fo.close()
from gap import gap
import os
pwd = os.getcwd()
files = os.listdir(pwd+"/bands")
for f in files:
os.system("cp bands/"+f+" BANDS.OUT")
l = f.split("_")
mu = l[2]
zee = l[4]
g = gap()
os.system("tb90-bands -noshow")
os.system("cp BANDS.png images/"+f+".png")
print mu,zee,g
import io import sys import gap # my_ranklist is the output of any paraphrase-ranking algorithm (let's say it gives top 5 words) my_ranklist = ['clever', 'intelligent', 'luminous', 'hopeful', 'intelligent']; # gold_ranklist is the actual gold data that was ranked by people (assume 5 people were asked, and this is what they chose) gold_ranklist = ['clever', 'intelligent', 'smart']; # the i-th element in gold_weights gives the weight associated with corresponding element in gold_ranklist. # for example, 3 people told 'clever', and 1 each told 'intelligent' and 'smart'. gold_weights = [3, 1, 1]; print >>sys.stderr, my_ranklist; print >>sys.stderr, gold_ranklist; print >>sys.stderr, gold_weights; print 'average precision = ' + str(gap.average_precision(my_ranklist, gold_ranklist)); print 'GAP = ' + str(gap.gap(my_ranklist, gold_ranklist, gold_weights)); my_ranklist = ['luminous', 'hopeful', 'intelligent', 'clever', 'intelligent']; gold_ranklist = ['clever', 'intelligent', 'smart']; gold_weights = [3, 1, 1]; print >>sys.stderr, my_ranklist; print >>sys.stderr, gold_ranklist; print 'average precision = ' + str(gap.average_precision(my_ranklist, gold_ranklist)); print 'GAP = ' + str(gap.gap(my_ranklist, gold_ranklist, gold_weights));