def VarianceThreshold_selector(data, th):
#Select Model
selector = VarianceThreshold(
th
) #Defaults to 0.0, e.g. only remove features with the same value in all samples
#Fit the Model
selector.fit(data)
features = selector.get_support(
indices=True
) #returns an array of integers corresponding to nonremoved features
features = [column for column in data[features]
] #Array of all nonremoved features' names
#Format and Return
selector = pd.DataFrame(selector.transform(data))
selector.columns = features
return selector
def VarianceThreshold_selector(data):
#Select Model
selector = VarianceThreshold(threshold=(.8 * (1 - .8)))
#Fit the Model
selector.fit(data)
features = selector.get_support(indices = True) #returns an array of integers corresponding to nonremoved features
#print (features)
Features = list(data)
features = [Features[i] for i in features]
#features = [column for column in data[features]] #Array of all nonremoved features' names
#print (features)
#Format and Return
selector = pd.DataFrame(selector.transform(data))
selector.columns = features
return selector
def variance_threshold(self: pd.DataFrame, cp, fecha, threshold=0.0):
"""
VarianceThreshold is a simple baseline approach to feature selection. It removes all features whose variance
doesn’t meet some threshold. By default, it removes all zero-variance features, i.e.
features that have the same value in all samples.
As an example, suppose that we have a dataset with boolean features,
and we want to remove all features that are either one or zero (on or off) in more than 80% of the samples.
"""
column_names = self.columns.values.tolist()
key_variables = ['id_siniestro', 'id_poliza', 'cod_filiacion'] + cp + fecha
removed_var = []
for i in key_variables:
try:
column_names.remove(i)
removed_var.append(i)
except:
pass
append_names = []
for i in column_names:
self_i = self[[i]]
self_i = self_i.apply(pd.to_numeric, errors='coerce')
self_i = self_i.dropna(how='any', axis=0)
selection = VarianceThreshold(threshold=threshold)
try:
selection.fit(self_i)
features = selection.get_support(indices=True)
features = self_i.columns[features]
features = [column for column in self_i[features]]
selection = pd.DataFrame(selection.transform(self_i), index=self_i.index)
selection.columns = features
append_names.append(selection.columns.values.tolist())
except:
pass
append_names = [item for sublist in append_names for item in sublist]
append_names = list(set(append_names))
self = self[removed_var + append_names]
return self
