def test_construct(self):
t = XArray([1, 2, 3, 4, 5])
ss = t.sketch_summary()
self.assertAlmostEqual(3, ss.quantile(0.5), places=1)
self.assertAlmostEqual(4, ss.quantile(0.8), places=1)
self.assertAlmostEqual(5, ss.quantile(0.9), places=1)
self.assertAlmostEqual(5, ss.quantile(0.99), places=1)
def __repr__(self):
"""
Emits a brief summary of all the statistics as a string.
"""
return "<sketch>" # TODO remove
fields = [
['size', 'Length' , 'Yes'],
['min', 'Min' , 'Yes'],
['max', 'Max' , 'Yes'],
['mean', 'Mean' , 'Yes'],
['sum', 'Sum' , 'Yes'],
['var', 'Variance' , 'Yes'],
['std', 'Standard Deviation' , 'Yes'],
['num_undefined', '# Missing Values' , 'Yes',],
['num_unique', '# unique values', 'No' ]
]
s = '\n'
result = []
for field in fields:
try:
method_to_call = getattr(self, field[0])
result.append([field[1], str(method_to_call()), field[2]])
except:
pass
sf = XArray(result).unpack(column_name_prefix = "")
sf.rename({'0': 'item', '1':'value', '2': 'is exact'})
s += sf.__str__(footer=False)
s += "\n"
s += "\nMost frequent items:\n"
frequent = self.frequent_items()
sorted_freq = sorted(frequent.iteritems(), key=operator.itemgetter(1), reverse=True)
if len(sorted_freq) == 0:
s += " -- All elements appear with less than 0.01% frequency -- \n"
else:
sorted_freq = sorted_freq[:10]
sf = XFrame()
sf.add_column(XArray(['count']), 'value')
for elem in sorted_freq:
sf.add_column(XArray([elem[1]]), str(elem[0]))
s += sf.__str__(footer=False) + "\n"
s += "\n"
try:
# print quantiles
t = self.quantile(0)
s += "Quantiles: \n"
sf = XFrame()
for q in [0.0,0.01,0.05,0.25,0.5,0.75,0.95,0.99,1.00]:
sf.add_column(XArray([self.quantile(q)]), str(int(q * 100)) + '%')
s += sf.__str__(footer=False) + "\n"
except:
pass
try:
t_k = self.dict_key_summary()
t_v = self.dict_value_summary()
s += "\n******** Dictionary Element Key Summary ********\n"
s += t_k.__repr__()
s += "\n******** Dictionary Element Value Summary ********\n"
s += t_v.__repr__() + '\n'
except:
pass
try:
t_k = self.element_summary()
s += "\n******** Element Summary ********\n"
s += t_k.__repr__() + '\n'
except:
pass
return s.expandtabs(8)
