def test_scaletime(self):
data_in = self.timeseries
# Test if 0Div error raises on a call with a scalingfactor = 0
self.assertRaises(ZeroDivisionError,
helper.scaletime, data_in, 0)
# test if function changes the input\
self.assertEqual(data_in, self.timeseries)
# Test if a call with a scalingfactor = 1 maintains the series
self.assertEqual(data_in, helper.scaletime(data_in, 1))
# Generate a random sequence to use as scaling factors
randomseq = range(1, 61)
random.shuffle(randomseq)
# count total number of words happening in the set
termcount_in = self.sum_wordcount(data_in)
for scalingfactor in randomseq:
ret = helper.scaletime(data_in, scalingfactor)
# Make sure input and output have the same type (list)
self.assertEqual(type(data_in), list)
self.assertEqual(type(ret), list)
# Make sure number of ticks is equal to original size divided by SF
# ,or one less due to rounding error.
self.assertTrue(
((len(data_in) / scalingfactor) == len(ret)) or
((len(data_in) / scalingfactor) == len(ret) - 1)
)
# Make sure total size is greater or equal to the scaleddown version
self.assertGreaterEqual(
sum([len(t) for t in data_in]),
sum([len(t) for t in ret])
)
termcount_out = self.sum_wordcount(ret)
# checking consistency of total number of words
self.assertEqual(
len(termcount_out),
len(termcount_in)
)
# checking consistency of total number of words
for word in termcount_in:
self.assertEqual(
termcount_out[word],
termcount_in[word]
)
def test_scaletime(self):
data_in = self.timeseries
# Test if 0Div error raises on a call with a scalingfactor = 0
self.assertRaises(ZeroDivisionError, helper.scaletime, data_in, 0)
# test if function changes the input\
self.assertEqual(data_in, self.timeseries)
# Test if a call with a scalingfactor = 1 maintains the series
self.assertEqual(data_in, helper.scaletime(data_in, 1))
# Generate a random sequence to use as scaling factors
randomseq = range(1, 61)
random.shuffle(randomseq)
# count total number of words happening in the set
termcount_in = self.sum_wordcount(data_in)
for scalingfactor in randomseq:
ret = helper.scaletime(data_in, scalingfactor)
# Make sure input and output have the same type (list)
self.assertEqual(type(data_in), list)
self.assertEqual(type(ret), list)
# Make sure number of ticks is equal to original size divided by SF
# ,or one less due to rounding error.
self.assertTrue(
((len(data_in) / scalingfactor) == len(ret))
or ((len(data_in) / scalingfactor) == len(ret) - 1))
# Make sure total size is greater or equal to the scaleddown version
self.assertGreaterEqual(sum([len(t) for t in data_in]),
sum([len(t) for t in ret]))
termcount_out = self.sum_wordcount(ret)
# checking consistency of total number of words
self.assertEqual(len(termcount_out), len(termcount_in))
# checking consistency of total number of words
for word in termcount_in:
self.assertEqual(termcount_out[word], termcount_in[word])
def main():
if len(sys.argv) < 4 or len(sys.argv) > 5:
helper.msg(
"Usage: timeanalysis TimeseriesFile Top ScalingFactor [plotname]\n"
)
exit(0)
filename = sys.argv[1]
top = int(sys.argv[2])
scalingfactor = int(sys.argv[3])
helper.msg("Reading the file...\n")
filedata = json.load(open(filename))
helper.msg("[DONE]\n")
helper.msg("Parsing the file...\n")
startdate_str, freq, timeseries = filedata
startdate = helper.strtodate(startdate_str)
helper.msg("[DONE]\n")
perminute, sorted_perminute = {}, {}
for category in timeseries:
helper.msg("Changing the time scale...\n")
perminute[category] = helper.scaletime(timeseries[category],
scalingfactor)
helper.msg("[DONE]\n")
tickcount = len(perminute[category])
sorted_perminute[category] = [(dict)] * tickcount
helper.msg("Calculating the top topics...\n")
for tick in range(tickcount):
sorted_perminute[category][tick] = dict(
sorted(perminute[category][tick].items(),
key=lambda l: l[1],
reverse=True)[:top])
#print helper.findtops(perminute[category], top)
print json.dumps((startdate_str, scalingfactor * freq, sorted_perminute))
if len(sys.argv) == 5:
plotname = sys.argv[4]
for category in sorted_perminute:
#print sorted_perminute
helper.plot(sorted_perminute[category], startdate,
scalingfactor * freq, plotname + " " + category)
def main():
if len(sys.argv) < 4 or len(sys.argv) > 5:
helper.msg("Usage: timeanalysis TimeseriesFile Top ScalingFactor [plotname]\n")
exit(0)
filename = sys.argv[1]
top = int(sys.argv[2])
scalingfactor = int(sys.argv[3])
helper.msg("Reading the file...\n")
filedata = json.load(open(filename))
helper.msg("[DONE]\n")
helper.msg("Parsing the file...\n")
startdate_str, freq, timeseries = filedata
startdate = helper.strtodate(startdate_str)
helper.msg("[DONE]\n")
perminute, sorted_perminute = {}, {}
for category in timeseries:
helper.msg("Changing the time scale...\n")
perminute[category] = helper.scaletime(
timeseries[category], scalingfactor)
helper.msg("[DONE]\n")
tickcount = len(perminute[category])
sorted_perminute[category] = [(dict)]*tickcount
helper.msg("Calculating the top topics...\n")
for tick in range(tickcount):
sorted_perminute[category][tick] = dict(
sorted(perminute[category][tick].items(),
key=lambda l: l[1], reverse=True) [:top]
)
#print helper.findtops(perminute[category], top)
print json.dumps((startdate_str, scalingfactor * freq, sorted_perminute))
if len(sys.argv) == 5:
plotname = sys.argv[4]
for category in sorted_perminute:
#print sorted_perminute
helper.plot(sorted_perminute[category],
startdate, scalingfactor * freq, plotname + " " + category)
