def info_gain(idadf, target = None, features = None, ignore_indexer=True):
"""
Compute the information gain / mutual information 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")
>>> info_gain(idadf)
"""
# Check input
target, features = _check_input(idadf, target, features, ignore_indexer)
entropy_dict = OrderedDict()
length = len(idadf)
loglength = log(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")
value = ((entropy_dict[t] + entropy_dict[feature] - join_entropy)/length + loglength)/log(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 = False)
return result
def info_gain(idadf, target=None, features=None, ignore_indexer=True):
"""
Compute the information gain / mutual information 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")
>>> info_gain(idadf)
"""
# Check input
target, features = _check_input(idadf, target, features, ignore_indexer)
entropy_dict = OrderedDict()
length = len(idadf)
loglength = log(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")
value = (
(entropy_dict[t] + entropy_dict[feature] - join_entropy) /
length + loglength) / log(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_values(inplace=True, ascending=False)
return result
def gain_ratio(idadf,
target=None,
features=None,
symmetry=True,
ignore_indexer=True):
"""
Compute the gain ratio 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.
symmetry : bool, default: True
If True, compute the symmetric gain ratio as defined by
[Lopez de Mantaras 1991]. Otherwise, the asymmetric gain ratio.
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")
>>> gain_ratio(idadf)
"""
# Check input
target, features = _check_input(idadf, target, features, ignore_indexer)
entropy_dict = dict()
length = len(idadf)
values = OrderedDict()
corrector = length * np.log(length)
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]: # i.e. it was not already computed
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]
info_gain = (disjoin_entropy - join_entropy)
if symmetry:
gain_ratio = (info_gain + corrector) / (
disjoin_entropy + 2 * corrector
) # 2* because symmetric
values[t][feature] = gain_ratio
if feature in target:
values[feature][t] = gain_ratio
else:
gain_ratio_1 = (info_gain + corrector) / (entropy_dict[t] +
corrector)
values[t][feature] = gain_ratio_1
if feature in target:
gain_ratio_2 = (info_gain + corrector) / (
entropy_dict[feature] + corrector)
values[feature][t] = gain_ratio_2
### Fill the matrix
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 gain_ratio(idadf, target=None, features=None, symmetry=True, ignore_indexer=True):
"""
Compute the gain ratio 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.
symmetry : bool, default: True
If True, compute the symmetric gain ratio as defined by
[Lopez de Mantaras 1991]. Otherwise, the asymmetric gain ratio.
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")
>>> gain_ratio(idadf)
"""
# Check input
target, features = _check_input(idadf, target, features, ignore_indexer)
entropy_dict = dict()
length = len(idadf)
values = OrderedDict()
corrector = length * np.log(length)
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]: # i.e. it was not already computed
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]
info_gain = disjoin_entropy - join_entropy
if symmetry:
gain_ratio = (info_gain + corrector) / (disjoin_entropy + 2 * corrector) # 2* because symmetric
values[t][feature] = gain_ratio
if feature in target:
values[feature][t] = gain_ratio
else:
gain_ratio_1 = (info_gain + corrector) / (entropy_dict[t] + corrector)
values[t][feature] = gain_ratio_1
if feature in target:
gain_ratio_2 = (info_gain + corrector) / (entropy_dict[feature] + corrector)
values[feature][t] = gain_ratio_2
### Fill the matrix
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
