def wiki_sizes_chart(path, prefixes, upperlimit = None ):
prefixes, sizes = zip(*sorted( [(pr, dumpSize(pr)) for pr in prefixes]
, key = operator.itemgetter(1)
)
)
blockSize = 5
ind = p.arange(0, blockSize*len(prefixes), blockSize) # y location for groups
height = 4 # bar height
#colors = ['g','r','c','m','y']
colors = html_colors
thresholds = [5000, 2000,1000,500,200,100,50,20,10]
#colors = [str(float(i+1) / (len(thresholds)+1)) for i in xrange(len(thresholds))]
#colors.reverse()
overall = p.barh( ind
, sizes
, height
, color = 'b'
, linewidth = 0
, align='center'
)
subbars = []
for i, thresh in enumerate(thresholds) :
subbars.append( p.barh( ind
, [ docs_under_thresh(pr, thresh) for pr in prefixes]
, height
, color = colors[ i % len(colors) ]
, linewidth = 0
, align='center'
)
)
p.ylim(-height, len(prefixes) * blockSize)
if upperlimit:
p.xlim(0, upperlimit)
yfontprop = FontProperties(size=4)
xfontprop = FontProperties(size=4)
p.xlabel('Documents')
p.ylabel('Language Code')
p.title('Number of Documents Under Threshold')
p.yticks(ind, prefixes, fontproperties = yfontprop)
xmin, xmax = p.xlim()
xtick_interval = rounded_interval(xmin, xmax, 20, 2)
p.xticks( p.arange(xmin,xmax,xtick_interval),fontproperties = xfontprop)
p.gca().xaxis.grid(linestyle = '-', linewidth=0.15)
p.gca().yaxis.tick_left()
p.legend( [ b[0] for b in subbars]
, map(str,thresholds)
, prop = xfontprop
, loc = 'lower right'
)
p.savefig(path, dpi=300)
p.close()
p.clf()
def wiki_proportions_chart(path, prefixes):
prefixes, sizes = zip(*sorted([(pr, dumpSize(pr)) for pr in prefixes],
key=operator.itemgetter(1)))
blockSize = 5
ind = p.arange(0, blockSize * len(prefixes),
blockSize) # y location for groups
height = 4 # bar height
#colors = ['g','r','c','m','y']
thresholds = [5000, 2000, 1000, 500, 200, 100, 50, 20, 10]
colors = [
str(float(i + 1) / (len(thresholds) + 1))
for i in xrange(len(thresholds))
]
colors.reverse()
p.clf()
"""
overall = p.barh( ind
, [1.0] * len(ind)
, height
, color = 'b'
, linewidth = 0
, align='center'
)
"""
subbars = []
for i, thresh in enumerate(thresholds):
subbars.append(
p.barh(ind, [
float(docs_under_thresh(pr, thresh)) / dumpSize(pr)
for pr in prefixes
],
height,
color=colors[i % len(colors)],
linewidth=0,
align='center'))
p.ylim(-height, len(prefixes) * blockSize)
p.xlim(0, 1)
yfontprop = FontProperties(size=4)
xfontprop = FontProperties(size=4)
p.xlabel('Proportion')
p.ylabel('Language Code')
p.title('Proportion of Documents Under Threshold')
p.yticks(ind, prefixes, fontproperties=yfontprop)
xmin, xmax = p.xlim()
xtick_interval = 0.1
p.xticks(p.arange(xmin, xmax, xtick_interval), fontproperties=xfontprop)
p.gca().xaxis.grid(linestyle='-', linewidth=0.15)
p.gca().yaxis.tick_left()
p.savefig(path, dpi=300)
p.close()
p.clf()
def wiki_sizes_chart(path, prefixes, upperlimit=None):
prefixes, sizes = zip(*sorted([(pr, dumpSize(pr)) for pr in prefixes],
key=operator.itemgetter(1)))
blockSize = 5
ind = p.arange(0, blockSize * len(prefixes),
blockSize) # y location for groups
height = 4 # bar height
#colors = ['g','r','c','m','y']
colors = html_colors
thresholds = [5000, 2000, 1000, 500, 200, 100, 50, 20, 10]
#colors = [str(float(i+1) / (len(thresholds)+1)) for i in xrange(len(thresholds))]
#colors.reverse()
overall = p.barh(ind,
sizes,
height,
color='b',
linewidth=0,
align='center')
subbars = []
for i, thresh in enumerate(thresholds):
subbars.append(
p.barh(ind, [docs_under_thresh(pr, thresh) for pr in prefixes],
height,
color=colors[i % len(colors)],
linewidth=0,
align='center'))
p.ylim(-height, len(prefixes) * blockSize)
if upperlimit:
p.xlim(0, upperlimit)
yfontprop = FontProperties(size=4)
xfontprop = FontProperties(size=4)
p.xlabel('Documents')
p.ylabel('Language Code')
p.title('Number of Documents Under Threshold')
p.yticks(ind, prefixes, fontproperties=yfontprop)
xmin, xmax = p.xlim()
xtick_interval = rounded_interval(xmin, xmax, 20, 2)
p.xticks(p.arange(xmin, xmax, xtick_interval), fontproperties=xfontprop)
p.gca().xaxis.grid(linestyle='-', linewidth=0.15)
p.gca().yaxis.tick_left()
p.legend([b[0] for b in subbars],
map(str, thresholds),
prop=xfontprop,
loc='lower right')
p.savefig(path, dpi=300)
p.close()
p.clf()
def wiki_proportions_chart(path, prefixes):
prefixes, sizes = zip(*sorted( [(pr, dumpSize(pr)) for pr in prefixes]
, key = operator.itemgetter(1)
)
)
blockSize = 5
ind = p.arange(0, blockSize*len(prefixes), blockSize) # y location for groups
height = 4 # bar height
#colors = ['g','r','c','m','y']
thresholds = [5000, 2000,1000,500,200,100,50,20,10]
colors = [str(float(i+1) / (len(thresholds)+1)) for i in xrange(len(thresholds))]
colors.reverse()
p.clf()
"""
overall = p.barh( ind
, [1.0] * len(ind)
, height
, color = 'b'
, linewidth = 0
, align='center'
)
"""
subbars = []
for i, thresh in enumerate(thresholds) :
subbars.append( p.barh( ind
, [ float(docs_under_thresh(pr, thresh)) / dumpSize(pr) for pr in prefixes]
, height
, color = colors[ i % len(colors) ]
, linewidth = 0
, align='center'
)
)
p.ylim(-height, len(prefixes) * blockSize)
p.xlim(0, 1)
yfontprop = FontProperties(size=4)
xfontprop = FontProperties(size=4)
p.xlabel('Proportion')
p.ylabel('Language Code')
p.title('Proportion of Documents Under Threshold')
p.yticks(ind, prefixes, fontproperties = yfontprop)
xmin, xmax = p.xlim()
xtick_interval = 0.1
p.xticks( p.arange(xmin,xmax,xtick_interval),fontproperties = xfontprop)
p.gca().xaxis.grid(linestyle = '-', linewidth=0.15)
p.gca().yaxis.tick_left()
p.savefig(path, dpi=300)
p.close()
p.clf()
