def test_entropy_one_column(self, idadf):
if len(idadf.columns) >= 1:
result = entropy(idadf, target = idadf.columns[0])
assert(isinstance(result, float))
def test_entropy_default(self, idadf):
if len(idadf.columns) > 1:
result = entropy(idadf)
assert(isinstance(result, pandas.core.series.Series))
assert(len(result.index) == len(idadf.columns))
def test_entropy_multiple_columns(self, idadf):
if len(idadf.columns) > 1:
result = entropy(idadf, target = [idadf.columns[0],idadf.columns[1]])
assert(isinstance(result, float))
def su(idadf, target=None, features=None, ignore_indexer=True):
"""
Compute the symmetric uncertainty coefficients between a set of features
and a set of target in an IdaDataFrame.
Parameters
----------
idadf : IdaDataFrame
target : str or list of str, optional
A column or list of columns against to be used as target. Per default,
consider all columns
features : str or list of str, optional
A column or list of columns to be used as features. Per default,
consider all columns.
ignore_indexer : bool, default: True
Per default, ignore the column declared as indexer in idadf
Returns
-------
Pandas.DataFrame or Pandas.Series if only one target
Notes
-----
Input columns as target and features should be categorical, otherwise
this measure does not make much sense.
Examples
--------
>>> idadf = IdaDataFrame(idadb, "IRIS")
>>> su(idadf)
"""
# Check input
target, features = _check_input(idadf, target, features, ignore_indexer)
entropy_dict = dict()
length = len(idadf)
corrector = np.log(length) * length
values = OrderedDict()
for t in target:
if t not in values:
values[t] = OrderedDict()
features_notarget = [x for x in features if (x != t)]
for feature in features_notarget:
if feature not in values:
values[feature] = OrderedDict()
if t not in values[feature]:
if t not in entropy_dict:
entropy_dict[t] = entropy(idadf, t, mode="raw")
if feature not in entropy_dict:
entropy_dict[feature] = entropy(idadf, feature, mode="raw")
join_entropy = entropy(idadf, [t] + [feature], mode="raw")
disjoin_entropy = entropy_dict[t] + entropy_dict[feature]
value = (2.0 * (disjoin_entropy - join_entropy + corrector) /
(disjoin_entropy + corrector * 2))
values[t][feature] = value
if feature in target:
values[feature][t] = value
result = pd.DataFrame(values).fillna(np.nan)
result = result.dropna(axis=1, how="all")
if len(result.columns) > 1:
order = [x for x in result.columns if x in features
] + [x for x in features if x not in result.columns]
result = result.reindex(order)
if len(result.columns) == 1:
if len(result) == 1:
result = result.iloc[0, 0]
else:
result = result[result.columns[0]].copy()
result.sort(ascending=True)
else:
result = result.fillna(1)
return result
def su(idadf, target = None, features = None, ignore_indexer=True):
"""
Compute the symmetric uncertainty coefficients between a set of features
and a set of target in an IdaDataFrame.
Parameters
----------
idadf : IdaDataFrame
target : str or list of str, optional
A column or list of columns against to be used as target. Per default,
consider all columns
features : str or list of str, optional
A column or list of columns to be used as features. Per default,
consider all columns.
ignore_indexer : bool, default: True
Per default, ignore the column declared as indexer in idadf
Returns
-------
Pandas.DataFrame or Pandas.Series if only one target
Notes
-----
Input columns as target and features should be categorical, otherwise
this measure does not make much sense.
Examples
--------
>>> idadf = IdaDataFrame(idadb, "IRIS")
>>> su(idadf)
"""
# Check input
target, features = _check_input(idadf, target, features, ignore_indexer)
entropy_dict = dict()
length = len(idadf)
corrector = np.log(length)*length
values = OrderedDict()
for t in target:
if t not in values:
values[t] = OrderedDict()
features_notarget = [x for x in features if (x != t)]
for feature in features_notarget:
if feature not in values:
values[feature] = OrderedDict()
if t not in values[feature]:
if t not in entropy_dict:
entropy_dict[t] = entropy(idadf, t, mode = "raw")
if feature not in entropy_dict:
entropy_dict[feature] = entropy(idadf, feature, mode = "raw")
join_entropy = entropy(idadf, [t] + [feature], mode = "raw")
disjoin_entropy = entropy_dict[t] + entropy_dict[feature]
value = (2.0*(disjoin_entropy - join_entropy + corrector)/(disjoin_entropy + corrector*2))
values[t][feature] = value
if feature in target:
values[feature][t] = value
result = pd.DataFrame(values).fillna(np.nan)
result = result.dropna(axis=1, how="all")
if len(result.columns) > 1:
order = [x for x in result.columns if x in features] + [x for x in features if x not in result.columns]
result = result.reindex(order)
if len(result.columns) == 1:
if len(result) == 1:
result = result.iloc[0,0]
else:
result = result[result.columns[0]].copy()
result.sort(ascending = True)
else:
result = result.fillna(1)
return result
def test_entropy_one_column(self, idadf):
if len(idadf.columns) >= 1:
result = entropy(idadf, target=idadf.columns[0])
assert (isinstance(result, float))
def test_entropy_multiple_columns(self, idadf):
if len(idadf.columns) > 1:
result = entropy(idadf,
target=[idadf.columns[0], idadf.columns[1]])
assert (isinstance(result, float))
def test_entropy_default(self, idadf):
if len(idadf.columns) > 1:
result = entropy(idadf)
assert (isinstance(result, pandas.core.series.Series))
assert (len(result.index) == len(idadf.columns))