def mine_c45(table, result):
""" An entry point for C45 algorithm.
_table_ - a dict representing data table in the following format:
{
"<column name>': [<column values>],
"<column name>': [<column values>],
...
}
_result_: a string representing a name of column indicating a result.
"""
col = max([(k, gain(table, k, result))
for k in table.keys() if k != result],
key=lambda x: x[1])[0]
tree = []
for subt in get_subtables(table, col):
v = subt[col][0]
if is_mono(subt[result]):
tree.append(
['%s=%s' % (col, v),
'%s=%s' % (result, subt[result][0])])
else:
del subt[col]
tree.append(['%s=%s' % (col, v)] + mine_c45(subt, result))
return tree
def mine_c45(table, result):
col = max([(k, gain(table, k, result)) for k in table.keys() if k != result],
key=lambda x: x[1])[0]
tree = []
for subt in get_subtables(table, col):
v = subt[col][0]
if is_mono(subt[result]):
tree.append(['%s=%s' % (col, v),
'%s=%s' % (result, subt[result][0])])
else:
del subt[col]
tree.append(['%s=%s' % (col, v)] + mine_c45(subt, result))
return tree
def mine_c45(table, result):
col = max([(k, gain(table, k, result))
for k in table.keys() if k != result],
key=lambda x: x[1])[0]
tree = []
for subt in get_subtables(table, col):
v = subt[col][0]
if is_mono(subt[result]):
tree.append(
['%s=%s' % (col, v),
'%s=%s' % (result, subt[result][0])])
else:
del subt[col]
tree.append(['%s=%s' % (col, v)] + mine_c45(subt, result))
return tree
def mine_c45(table, result):
""" An entry point for C45 algorithm.
_table_ - a dict representing data table in the following format:
{
"<column name>': [<column values>],
"<column name>': [<column values>],
...
}
_result_: a string representing a name of column indicating a result.
"""
tree = []
# Special case when there is a mixed strategy
if len(table.keys()) == 1:
key_distr = get_distribution(table[result])
for k in key_distr[1].keys():
tree.append([
'probability=%f' % (key_distr[1][k] / key_distr[0]),
'%s=%s' % (result, k)
])
return tree
# All other cases
col = max([(k, gain(table, k, result))
for k in table.keys() if k != result],
key=lambda x: x[1])[0]
for subt in get_subtables(table, col):
v = subt[col][0]
if is_mono(subt[result]):
tree.append(
['%s=%s' % (col, v),
'%s=%s' % (result, subt[result][0])])
else:
del subt[col]
tree.append(['%s=%s' % (col, v)] + mine_c45(subt, result))
return tree
def mine_c45(table, result):
""" An entry point for C45 algorithm.
_table_ - a dict representing data table in the following format:
{
"<column name>': [<column values>],
"<column name>': [<column values>],
...
}
_result_: a string representing a name of column indicating a result.
"""
col = max([(k, gain(table, k, result)) for k in table.keys() if k != result],
key=lambda x: x[1])[0]
tree = []
for subt in get_subtables(table, col):
v = subt[col][0]
if is_mono(subt[result]):
tree.append(['%s=%s' % (col, v),
'%s=%s' % (result, subt[result][0])])
else:
del subt[col]
tree.append(['%s=%s' % (col, v)] + mine_c45(subt, result))
return tree
def mine_c45(table, result):
""" An entry point for C45 algorithm.
_table_ - a dict representing data table in the following format:
{
"<column name>': [<column values>],
"<column name>': [<column values>],
...
}
_result_: a string representing a name of column indicating a result.
"""
tree = []
# Special case when there is a mixed strategy
if len(table.keys()) == 1:
key_distr = get_distribution(table[result])
for k in key_distr[1].keys():
tree.append(['probability=%f' % (key_distr[1][k] / key_distr[0]),
'%s=%s' % (result, k)])
return tree
# All other cases
col = max([(k, gain(table, k, result)) for k in table.keys() if k != result],
key=lambda x: x[1])[0]
for subt in get_subtables(table, col):
v = subt[col][0]
if is_mono(subt[result]):
tree.append(['%s=%s' % (col, v),
'%s=%s' % (result, subt[result][0])])
else:
del subt[col]
tree.append(['%s=%s' % (col, v)] + mine_c45(subt, result))
return tree
def test_gain(self):
self.assertEqual(gain(self.table, 'arg1', 'result'), 0)
def test_gain(self):
self.assertEqual(gain(self.table, 'arg1', 'result'), 0)