def support_vector_machine(input_data,
kernel='linear',
C=1,
feature_names=None,
validate=True):
"""
Fits, trains, and tests/makes predictions with a support vector machine.
Args:
input_data (tuple): x_train, y_train, x_test
kernel (str): The kernel to be used by the SVM
C (int or float): The regularization parameter for the SVM
feature_names (list): The names of every feature in input_data, if
given, a sorted [high to low] list of the most
important features used to make predictions is
also returned.
validate (bool): If True a model accuracy is returned, if False
a list of predicted classifications for x_test
is returned.
Returns:
list: Predicted classifications for each x_test
or
float: Model accuracy
or
tuple: accuracy/predictions, features ranked by importance
"""
x_train = input_data[0]
y_train = input_data[1]
x_test = input_data[2]
y_test = input_data[3]
if len(x_train.shape) == 3:
x_train = flatten(x_train)
x_test = flatten(x_test)
model = svm.SVC(kernel=kernel, C=C)
model.fit(x_train, y_train)
if validate:
output_data = model.score(x_test, y_test)
else:
output_data = model.predict(x_test)
if feature_names is not None:
coefs = model.coef_
if coefs.ndim > 1:
coefs = coefs.sum(axis=0)
coefs = coefs.ravel()
absolute_coefs = np.absolute(coefs)
absolute_coefs = [float(x) for x in absolute_coefs]
feature_names = [convert_well_index(x) for x in feature_names]
features_coefs = dict(list(zip(feature_names, absolute_coefs)))
output = (output_data, features_coefs)
else:
output = (output_data, None)
return output
def recursive_feature_elimination(input_data,
feature_names,
estimator=SVC(kernel='linear'),
n_features_to_select=None,
step=0.1):
"""
Recursively eliminates features from x_train and x_test using
scikit-learn's RFE, see documentation:
http://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.RFE.html
If feature_names is given it is also returned with any features from
x_train and x_test also removed from feature_names.
Args:
input_data (tuple): x_train, y_train, x_test, y_test
feature_names (list): The names of all features before
feature selection or None.
estimator (object): Passed to RFE, see documentation
n_features_to_select (int or None): Passed to RFE, see documentation
step (int or float): Passed to RFE, see documentation
Returns:
tuple: (x_train, y_train, x_test, y_test), feature_names, input_Args
"""
x_train = input_data[0]
y_train = input_data[1]
x_test = input_data[2]
y_test = input_data[3]
dims = len(x_train.shape)
if dims == 3:
x_train = flatten(x_train)
x_test = flatten(x_test)
feature_selector = RFE(estimator, n_features_to_select, step)
x_train = feature_selector.fit_transform(x_train, y_train)
x_test = feature_selector.transform(x_test)
if dims == 3:
x_train = make3D(x_train)
x_test = make3D(x_test)
output_data = (x_train, y_train, x_test, y_test)
if feature_names is not None:
mask = feature_selector.get_support()
feature_names = feature_names[mask]
args = {
'estimator': estimator,
'n_features_to_select': n_features_to_select,
'step': step
}
return output_data, feature_names, args
def select_percentile(input_data,
feature_names,
score_func=chi2,
percentile=5):
"""
Selects the percentile best features in x_train, removes the rest of the
features from x_train and x_test. Selects the best features by using the
score function score_func and scikit-learn's SelectPercentile. If
feature_names is given it is also returned with any features removed from
x_train and x_test also removed from feature_names.
Args:
input_data (tuple): x_train, y_train, x_test, y_test
feature_names (list): The names of all features before selection or
None.
score_func (function): The score function to be passed to SelectKBest
percentile (int): Percentile of features to keep.
Returns:
tuple: (x_train, y_train, x_test, y_test), feature_names, input_args
"""
if score_func == f_classif:
input_data, feature_names, _ = remove_constant(input_data,
feature_names)
x_train = input_data[0]
y_train = input_data[1]
x_test = input_data[2]
y_test = input_data[3]
dims = len(x_train.shape)
if dims == 3:
x_train = flatten(x_train)
x_test = flatten(x_test)
feature_selector = SelectPercentile(score_func=score_func,
percentile=percentile)
x_train = feature_selector.fit_transform(x_train, y_train)
x_test = feature_selector.transform(x_test)
if dims == 3:
x_train = make3D(x_train)
x_test = make3D(x_test)
output_data = (x_train, y_train, x_test, y_test)
if feature_names is not None:
mask = feature_selector.get_support()
feature_names = feature_names[mask]
return output_data, feature_names, {
'score_func': score_func,
'percentile': percentile
}
def select_fdr(input_data,
feature_names=None,
score_func=f_classif,
alpha=0.05):
if score_func == f_classif:
input_data, feature_names, _ = remove_constant(input_data,
feature_names)
x_train = input_data[0]
y_train = input_data[1]
x_test = input_data[2]
y_test = input_data[3]
dims = len(x_train.shape)
if dims == 3:
x_train = flatten(x_train)
x_test = flatten(x_test)
done = False
increment = alpha
while not done:
feature_selector = SelectFdr(score_func=score_func, alpha=alpha)
temp_x_train = feature_selector.fit_transform(x_train, y_train)
temp_x_test = feature_selector.transform(x_test)
if temp_x_train.shape[1] > 1 and temp_x_test.shape[1] > 1:
done = True
x_train = temp_x_train
x_test = temp_x_test
else:
msg = 'Feature selection was too aggresive, '
msg += 'increasing alpha from {} to {}'.format(
alpha, alpha + increment)
alpha += increment
logging.warning(msg)
if dims == 3:
x_train = make3D(x_train)
x_test = make3D(x_test)
output_data = (x_train, y_train, x_test, y_test)
if feature_names is not None:
mask = feature_selector.get_support()
feature_names = feature_names[mask]
logging.info('Selected {} features'.format(x_train.shape[1]))
final_args = {'score_func': score_func, 'alpha': alpha}
return output_data, feature_names, final_args
def recursive_feature_elimination_cv(input_data,
feature_names,
step=0.1,
cv=3,
estimator=SVC(kernel='linear')):
"""
Recursively elinates features from x_train and x_test with cross
validation, uses scikit-learn's RFECV see documentation:
http://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.RFECV.html
If feature_names is given it is also returned with any features from
x_train and x_test also removed from feature_names.
Args:
input_data (tuple): x_train, y_train, x_test, y_test
feature_names: The names of all features before feature
selection or None.
estimator (object): Passed to RFECV, see documentation
step (int or float): Passed to RFECV, see documentation
cv (int): Passed to RFECV, see documentation
Returns:
tuple: (x_train, y_train, x_test, y_test), feature_names, input_args
"""
x_train = input_data[0]
y_train = input_data[1]
x_test = input_data[2]
y_test = input_data[3]
dims = len(x_train.shape)
if dims == 3:
x_train = flatten(x_train)
x_test = flatten(x_test)
feature_selector = RFECV(estimator, step, cv)
x_train = feature_selector.fit_transform(x_train, y_train)
x_test = feature_selector.transform(x_test)
if dims == 3:
x_train = make3D(x_train)
x_test = make3D(x_test)
output_data = (x_train, y_train, x_test, y_test)
if feature_names is not None:
mask = feature_selector.get_support()
feature_names = feature_names[mask]
args = {'step': step, 'cv': cv, 'estimator': estimator}
return output_data, feature_names, args
def f_test_threshold(input_data,
feature_names=None,
threshold=0.01,
increment=0.01,
min_keep=100):
input_data, feature_names, _ = remove_constant(input_data, feature_names)
x_train = input_data[0]
y_train = input_data[1]
x_test = input_data[2]
y_test = input_data[3]
dims = len(x_train.shape)
if dims == 3:
x_train = flatten(x_train)
x_test = flatten(x_test)
F, pval = f_classif(x_train, y_train)
while True:
keep = np.where(pval <= threshold, True, False)
new_x_train = x_train[:, keep]
new_x_test = x_test[:, keep]
if new_x_train.shape[1] >= min_keep:
break
else:
threshold += increment
logging.info('Selected {} features'.format(new_x_train.shape[1]))
logging.info('Final p-value threshold: {}'.format(threshold))
output_data = (new_x_train, y_train, new_x_test, y_test)
if feature_names is not None:
feature_names = feature_names[keep]
args = {
'threshold': threshold,
'increment': increment,
'min_keep': min_keep
}
return output_data, feature_names, args
def variance_threshold(input_data, feature_names, threshold=0.16):
"""
Removes all features from x_train and x_test whose variances in x_train is
less than threshold. Uses scikit-learn's VarianceThreshold If feature_names
is given it is also returned with any features removed from x_train and
x_test also removed from feature_names.
Args:
input_data (tuple): x_train, y_train, x_test, y_test
feature_names (list): The names of all features before selection or
None.
threshold (float): Lower limit of variance for a feature to be kept
Returns:
tuple: (x_train, y_train, x_test, y_test), feature_names, input_args
"""
x_train = input_data[0]
y_train = input_data[1]
x_test = input_data[2]
y_test = input_data[3]
dims = len(x_train.shape)
if dims == 3:
x_train = flatten(x_train)
x_test = flatten(x_test)
feature_selector = VarianceThreshold(threshold=threshold)
x_train = feature_selector.fit_transform(x_train)
x_test = feature_selector.transform(x_test)
if dims == 3:
x_train = make3D(x_train)
x_test = make3D(x_test)
output_data = (x_train, y_train, x_test, y_test)
if feature_names is not None:
mask = feature_selector.get_support()
feature_names = feature_names[mask]
return output_data, feature_names, {'threshold': threshold}
def random_forest(input_data,
n_estimators=50,
feature_names=None,
validate=True):
"""
Fits, trains, and tests/makes predictions with s a random forest
classifier.
Args:
input_data (tuple): x_train, y_train, x_test, y_test
n_estimators (int): How many trees to use in the forest.
feature_names (list): The names of every feature in input_data, if
given, a sorted [high to low] list of the most
important features used to make predictions is
also returned.
validate (bool): If True a model accuracy is returned, if False
a list of predicted classifications for x_test
is returned.
Returns:
list: Predicted classifications for each x_test
or
float: Model accuracy
or
tuple: accuracy/predictions, features ranked by importance
"""
x_train = input_data[0]
y_train = input_data[1]
x_test = input_data[2]
y_test = input_data[3]
if len(x_train.shape) == 3:
x_train = flatten(x_train)
x_test = flatten(x_test)
kwargs = {
'n_estimators': n_estimators,
'criterion': 'entropy',
'max_features': 'log2',
'max_depth': 100,
'min_samples_split': 2,
'min_samples_leaf': 1,
'min_weight_fraction_leaf': 0.01,
'max_leaf_nodes': 25,
'min_impurity_decrease': 0.001,
'bootstrap': False,
'n_jobs': -1
}
model = RandomForestClassifier(**kwargs)
model.fit(x_train, y_train)
if validate:
output_data = model.score(x_test, y_test)
else:
output_data = model.predict(x_test)
if feature_names is not None:
importances = model.feature_importances_.ravel()
importances = [float(x) for x in importances]
feature_names = [convert_well_index(x) for x in feature_names]
features_importances = dict(list(zip(feature_names, importances)))
output = (output_data, features_importances)
else:
output = (output_data, None)
return output
def setUp(self):
self.input = np.array([[[1], [2], [3]], [[4], [5], [6]], [[7], [8],
[9]]])
self.output = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
self.flat = flatten(self.input)
self.threeD = make3D(self.output)
