def getTokenColorMapMultiRun(saveDir, topWords, topName):
numTops = len(topWords)
tokenMaps = []
fnames = ["%scolorByIndex.json" % (saveDir)]
for file in utils.listFiles("%sextra_runs/" % saveDir):
fnames.append("%sextra_runs/%s" % (saveDir, file))
for fname in fnames:
colors = utils.getContent(fname, True)
tokenMap = []
for c in colors:
tokenMap.append((c[0], c[1], c[2]))
tokenMaps.append(tokenMap)
text_end = 0
rect_width = 12
rect_margin_h = 5
rect_height = 5
rect_top = 1
rect_bottom = 4
width = text_end + len(tokenMaps) * (rect_margin_h +
rect_width) + rect_margin_h
height = rect_height * numTops + 5
im = Image.new("RGB", (width, height), "#FFFFFF")
# get drawing context
d = ImageDraw.Draw(im)
# get a font
fnt = ImageFont.truetype('fonts/DejaVuSans.ttf', int(0.8 * rect_height))
includedColors = {}
colorList = []
# draw text labels
for i in range(numTops):
baseY = rect_height * i
# text = topWords[i]
# text_width, _ = d.textsize(text, font=fnt)
#
# d.text((text_end - text_width,baseY+rect_top), text, font=fnt, fill=(0, 0, 0))
rect_right = text_end
# draw groupings for this word
for tm in tokenMaps:
rgb = tm[i]
rect_left = rect_right + rect_margin_h
rect_right = rect_left + rect_width
d.rectangle(((rect_left, baseY + rect_top),
(rect_right, baseY + rect_bottom)),
fill=rgb)
fname = saveDir + "images/groupingCompare.png"
utils.check_and_create_path(fname)
im.save(fname)
def getTokenColorMap(saveDir, topWords, topName):
numTops = len(topWords)
tokenMap = []
usePrecomputed = True
if (usePrecomputed):
fname = "%scolorByIndex.json" % (saveDir)
colors = utils.getContent(fname, True)
for c in colors:
tokenMap.append((c[0], c[1], c[2]))
else:
fname = "%s../wordCountData/wordPrincipalComponents_%d.json" % (
saveDir, topName)
components = np.array(utils.getContent(fname, True))
skipFirst = 4
minVals = np.min(wordPCAFitTransform(components), axis=0)
valRange = np.max(wordPCAFitTransform(components), axis=0) - minVals
normalizedComponents = np.round(255 * np.clip(
(components - minVals) / valRange, 0, 1))
for i in range(numTops):
comps = normalizedComponents[i]
rgb = (int(comps[0]), int(comps[1]), int(comps[2]))
tokenMap.append(rgb)
width = 400
height = 20 * numTops
im = Image.new("RGB", (width, height), "#FFFFFF")
# get drawing context
d = ImageDraw.Draw(im)
# get a font
fnt = ImageFont.truetype('fonts/DejaVuSans.ttf', 16)
includedColors = {}
colorList = []
for i in range(numTops):
rgb = tokenMap[i]
baseY = 20 * i
colorValuesText = "(%03d,%03d,%03d) " % rgb
# keep track of each new color
if not (colorValuesText in includedColors):
includedColors[colorValuesText] = True
colorList.append(rgb)
text = colorValuesText + topWords[i]
d.text((50, baseY + 2), text, font=fnt, fill=(0, 0, 0))
d.rectangle(((10, baseY + 2), (40, baseY + 18)), fill=rgb)
fname = saveDir + "images/key.png"
utils.check_and_create_path(fname)
im.save(fname)
return tokenMap, colorList
def build_caching_dir(self):
# build safer perturbation set path
if self.safer_perturbation_set is not None:
self.safer_perturbation_set = os.path.join(
self.caching_dir,
os.path.join(self.dataset_name, self.safer_perturbation_set))
self.caching_dir = os.path.join(
self.caching_dir, "{}_{}".format(self.dataset_name,
self.model_type))
check_and_create_path(self.caching_dir)
def imageFromRGBArray(arr, fname):
width = 300
height = int(np.ceil(len(arr) / width))
# default to transparent
im = Image.new("RGBA", (width, height), "#00000000")
pixels = im.load()
for i, rgb in enumerate(arr):
x = i % width
y = int(np.floor(i / width))
pixels[x, y] = rgb
utils.check_and_create_path(fname)
im.save(fname)
def imageFromRGBArrays(arrs, fname):
gapWidth = 8
width = 100
height = 1
for arr in arrs:
height += int(np.ceil((len(arr) + gapWidth) / width))
# default to transparent
im = Image.new("RGBA", (width, height), "#00000000")
pixels = im.load()
trueIndex = 0
for arr in arrs:
for i, rgb in enumerate(arr):
x = trueIndex % width
y = int(np.floor(trueIndex / width))
pixels[x, y] = rgb
trueIndex += 1
trueIndex += gapWidth
utils.check_and_create_path(fname)
im.save(fname)
for j in range(len(row)):
cell = row[j]
spec = getAlpha[j] + str(i + 1)
sheet[spec] = cell
wb.remove(wb["Sheet"])
wb.save(filename)
# Check for db
if (not (utils.fileExists(DB_LOCATION))):
raise Exception("Please add a database at '" + DB_LOCATION + "'")
# Create input folder and subfolders
utils.check_and_create_path("input/articles")
utils.check_and_create_path("input/illustrations")
utils.safeWrite(
"input/articles/README.md",
"Place articles here. Articles should be included in a text file and the filename should be [lemma].txt, where [lemma] is the lemma the article is about. For example, the article for ἄβουλος should be in ἄβουλος.txt"
)
utils.safeWrite(
"input/illustrations/README.md",
"Place illustrations here. Illustrations should be a .jpg, .gif, or .png with the name of the lemma they are an illustraiton for. For example, the image for ἄβουλος should be in ἄβουλος.png (or ἄβουλος.gif or ἄβουλος.jpg)"
)
# Create lemmata xlsx
lemma_info = []
lemma_info.append([
"Matched", "Lemma", "Short Definition", "Compounds", "Roots", "Sphere",
def build_logging_dir(self):
self.logging_dir = os.path.join(
self.logging_dir, "{}_{}".format(self.dataset_name,
self.model_type))
check_and_create_path(self.logging_dir)