def test_custom_ordinal_time_comparison(X=None, iterations=10, verbose=1):
if not X:
X = np.array([
["P", "+"],
["P2", "-"],
["P3", "-"],
])
custom_encoder = CustomOrdinalFeatureEncoder()
ordinal_encoder = OrdinalEncoder()
ordinal_encoder_time = []
custom_encoder_time = []
for i in range(iterations):
ts = time()
custom_encoder.fit(X)
transformed = custom_encoder.transform(X)
custom_encoder.inverse_transform(transformed)
custom_encoder_time.append(time() - ts)
ts = time()
ordinal_encoder.fit(X)
transformed = ordinal_encoder.transform(X)
ordinal_encoder.inverse_transform(transformed)
ordinal_encoder_time.append(time() - ts)
custom_encoder_time = np.mean(custom_encoder_time)
ordinal_encoder_time = np.mean(ordinal_encoder_time)
if verbose:
print(f"CustomEncoder -> Time: {custom_encoder_time}")
print(f"OrdinalEncoder -> Time: {ordinal_encoder_time}")
return custom_encoder_time, ordinal_encoder_time
def acfs_score_comparison(datasets,
seed,
base_path,
params,
n_splits=3,
n_repeats=5,
n_intervals=5,
metric="accuracy",
send_email=False,
email_data=dict(),
verbose=True):
# List to store results and column names for the csv
result = []
columns = [
"Database", "Number of attributes", "NBScore", "NBScore STD",
"ACFCS Score", "ACFCS Score STD", "Configuration", "Nodes",
"Contruction Matrix", "Selection Matrix", "Selected_attributes",
"Original"
]
dataset_tqdm = tqdm(datasets)
# Instantiate the classifier
acfcs = ACFCS(verbose=0, metric=metric)
nb = NaiveBayes(encode_data=False, n_intervals=n_intervals, metric=metric)
# Execute algorithm on datasets
for database in dataset_tqdm:
name, label = database
if not os.path.exists(base_path + name):
print(f"{name} doesnt' exist")
continue
# Assume UCI REPO like data
test = f"{name}.test.csv"
data = f"{name}.data.csv"
X, y = get_X_y_from_database(base_path, name, data, test, label)
# Update progressbar
dataset_tqdm.set_postfix({"DATABASE": name})
# Set up data structures to store results
nb_score = np.zeros(shape=(len(params), n_splits * n_repeats))
acfcs_score = np.zeros(shape=(len(params), n_splits * n_repeats))
acfcs_selection_matrix = np.zeros(shape=(len(params),
n_splits * n_repeats))
acfcs_construction_matrix = np.zeros(shape=(len(params),
n_splits * n_repeats))
acfcs_nodes = np.zeros(shape=(len(params), n_splits * n_repeats))
acfcs_dummy = np.zeros(shape=(len(params), n_splits * n_repeats))
acfcs_selected = np.zeros(shape=(len(params), n_splits * n_repeats))
# Create splits for the experiments
rskf = RepeatedStratifiedKFold(n_splits=n_splits,
n_repeats=n_repeats,
random_state=seed)
seed_tqdm = tqdm(rskf.split(X, y),
leave=False,
total=n_splits * n_repeats,
bar_format='{l_bar}{bar:20}{r_bar}{bar:-10b}'
) if verbose else rskf.split(X, y)
# Execute experiments
for i, data in enumerate(seed_tqdm):
train_index, test_index = data
X_train, X_test = X.iloc[train_index], X.iloc[test_index]
y_train, y_test = y.iloc[train_index], y.iloc[test_index]
# Encode the data
c = CustomOrdinalFeatureEncoder(n_intervals=n_intervals)
X_train = c.fit_transform(X_train)
X_test = c.transform(X_test)
l = CustomLabelEncoder()
y_train = l.fit_transform(y_train)
y_test = l.transform(y_test)
# Assess the classifiers reusing info to speed up evaluation
nb.fit(X_train, y_train)
naive_bayes_score = nb.score(X_test, y_test)
acfcs.reset_cache()
for conf_index, conf in enumerate(params):
acfcs.set_params(**conf)
acfcs.fit(X_train, y_train, init_graph=conf_index == 0)
# score
acfcs_score_conf = acfcs.score(X_test, y_test)
if verbose:
seed_tqdm.set_postfix({
"config": conf_index,
"nb_score": naive_bayes_score,
"ant_score": acfcs_score_conf
})
# Get data
n_original_features = len(
list(
filter(
lambda x: isinstance(x, DummyFeatureConstructor),
acfcs.best_features)))
n_selected = len(acfcs.best_features)
selection_matrix = len(acfcs.afg.pheromone_selection)
construction_matrix = len(acfcs.afg.pheromone_construction)
nodes = len(acfcs.afg.nodes)
# Update
nb_score[conf_index, i] = naive_bayes_score
acfcs_score[conf_index, i] = acfcs_score_conf
acfcs_selection_matrix[conf_index, i] = selection_matrix
acfcs_construction_matrix[conf_index, i] = construction_matrix
acfcs_nodes[conf_index, i] = nodes
acfcs_dummy[conf_index, i] = n_original_features
acfcs_selected[conf_index, i] = n_selected
# Insert the final result - averaged metrics for this database.
for conf_index, conf in enumerate(params):
row = [
name, X.shape[1],
np.mean(nb_score[conf_index]),
np.std(nb_score[conf_index]),
np.mean(acfcs_score[conf_index]),
np.std(acfcs_score[conf_index]), conf,
np.mean(acfcs_nodes[conf_index]),
np.mean(acfcs_construction_matrix[conf_index]),
np.mean(acfcs_selection_matrix[conf_index]),
np.mean(acfcs_selected[conf_index]),
np.mean(acfcs_dummy[conf_index])
]
result.append(row)
result = pd.DataFrame(result, columns=columns)
if send_email:
from tfg.utils import send_results
send_results("ACFCS", email_data, result)
return result
class RankerLogicalFeatureConstructor(TransformerMixin, ClassifierMixin,
BaseEstimator):
"""First proposal: Hybrid-Ranker Wrapper.
Build a ranking based on Symmetrical Uncertainty (SU) of every possible logical feature of depth 1
(1 operator, 2 operands), using XOR, AND and OR operator. The steps are:
- Find out combinations of values in database of every pair of features Xi, Xj:
- Example:
- Xi = [1,2,3,2]
- Xj = ['a','b','c','a']
Possible combinations:
[(1,'a'),(2,'b'),(3,'c'),(2,'a')]
- Apply operator to every combination:
- Example:
- Xi = [1,2,3,2]
- Xj = ['a','b','c','a']
Possible combinations:
[(1,'a','AND'),(2,'b','AND'),(3,'c','AND'),(2,'a','AND'),
(1,'a','OR'),(2,'b','OR'),(3,'c','OR'),(2,'a','OR'),
(1,'a','XOR'),(2,'b','XOR'),(3,'c','XOR'),(2,'a','XOR')]
- Add original variables to the list
- Evaluate SU for every value in the list, and rank them
- Go over the list following one of the two strategies proposed and evaluate
the subset based on a leave-one-out cross-validation with the NaiveBayes classifier.
Parameters
----------
strategy : str {eager,skip}
After the ranking is built if the eager strategy is chosen we stop considering attributes
when there is no improvement from one iteration to the next
block_size : int, default=1
Number of features that are added in each iteration
encode_data : boolean
Whether or not to encode the received data. If set to false the classifier
expects data to be encoded with an ordinal encoder.
verbose : {boolean,int}
If set to true it displays information of the remaining time
and inside variables.
operators : array-like, deafult = ("XOR","AND","OR")
Operators used for the constructed features.
max_features : int, deafult = inf
Maximum number of features to include in the selected subset
max_iterations : int, deafult = inf
Maximum number of iterations in the wrapper step.
use_graph : bool, default = False
Generate Ranking from features obtained from the pruned-graph of the ACO algorithm.
(Experimentation not carried out)
use_initials: bool, default = False
Force the set of initial features in the final solution. The set if trimmed with a backward elimination before-hand.
Attributes
----------
feature_encoder_ : CustomOrdinalFeatureEncoder or None
Encodes data in ordinal way with unseen values handling if encode_data is set to True.
class_encoder_ : LabelEncoder or None
Encodes Data in ordinal way for the class if encode_data is set to True.
all_feature_constructors: array-like
List of FeatureConstructor objects with all the possible logical
features
symmetrical_uncertainty_rank: array-like
SU for every feature in all_feature_constructors
rank : array-like
Array of indexes corresponding to the sorted SU rank (in descending order).
final_feature_constructors:
Selected feature subset (list of constructors)
classifier: NaiveBayes
Classifier used in the wrapper and to perform predictions after fitting.
"""
def __init__(self,
strategy="eager",
block_size=10,
encode_data=True,
n_intervals=5,
verbose=0,
operators=("AND", "OR", "XOR"),
max_features=float("inf"),
max_iterations=float("inf"),
metric="accuracy",
use_initials=False,
max_err=0,
prune=None,
use_graph=False):
self.strategy = strategy
self.block_size = max(block_size, 1)
self.encode_data = encode_data
self.verbose = verbose
self.operators = operators
self.max_features = max_features
self.max_iterations = max_iterations
self.n_intervals = n_intervals
self.metric = metric
self.max_err = max_err
self.use_initials = use_initials
self.prune = prune
self.use_graph = use_graph
allowed_strategies = ("eager", "skip")
if self.strategy not in allowed_strategies:
raise ValueError("Unknown operator type: %s, expected one of %s." %
(self.strategy, allowed_strategies))
def fit(self, X, y):
# Parse input
if isinstance(y, pd.DataFrame):
y = y.to_numpy()
if self.encode_data:
self.feature_encoder_ = CustomOrdinalFeatureEncoder(
n_intervals=self.n_intervals)
self.class_encoder_ = CustomLabelEncoder()
X = self.feature_encoder_.fit_transform(X)
y = self.class_encoder_.fit_transform(y)
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
check_X_y(X, y)
# Reset the stored results for new fit
self.reset_evaluation()
# Generate rank
if self.use_graph:
# Construct the minimum graph and create rank
graph = AntFeatureGraphMI(seed=None, connections=1).compute_graph(
X, y, ("AND", "OR", "XOR"))
self.all_feature_constructors = graph.get_rank()
elif self.prune is not None:
# Construct the rank with pruning by selecting pais that maximise SU(X_iX_j,Y)
feature_combinations = list(
combinations(list(range(X.shape[1])),
2)) + [(i, i) for i in range(X.shape[1])]
rank_pairs = [
symmetrical_uncertainty_two_variables(X[:, i], X[:, j], y)
for i, j in feature_combinations
]
rank_pairs_index = np.argsort(rank_pairs)[::-1]
# Create the unsorted list
self.all_feature_constructors = []
for index in rank_pairs_index[:self.prune]:
i, j = feature_combinations[index]
if i == j:
from tfg.feature_construction import create_feature
self.all_feature_constructors.extend([
create_feature("OR", [(i, n), (i, m)])
for n, m in combinations(np.unique(X[:, i]), 2)
])
else:
self.all_feature_constructors.extend(
construct_features(X[:, [i, j]],
operators=self.operators,
same_feature=False))
else:
# Create the unsorted list of all features
self.all_feature_constructors = construct_features(
X, operators=self.operators)
if self.verbose:
print(
f"Total number of constructed features: {len(self.all_feature_constructors)}"
)
self.all_feature_constructors.extend(
[DummyFeatureConstructor(j) for j in range(X.shape[1])])
self.symmetrical_uncertainty_rank = []
# Sort the ranking
for feature_constructor in self.all_feature_constructors:
feature = feature_constructor.transform(X)
su = symmetrical_uncertainty(f1=feature.flatten(), f2=y)
self.symmetrical_uncertainty_rank.append(su)
# Store the descending order index
self.rank = np.argsort(self.symmetrical_uncertainty_rank)[::-1]
# If the initial variables are
if self.use_initials:
classifier = NaiveBayes(encode_data=False,
n_intervals=self.n_intervals,
metric=self.metric)
classifier.fit(X, y)
current_features = [
DummyFeatureConstructor(j) for j in range(X.shape[1])
]
# Store the backward result to reuse it for other executions
self.initial_backward_features = backward_search(
X, y, current_features, classifier)
# Feature Subset Selection (FSS) from the rank
self.filter_features(X, y)
return self
def predict(self, X):
X, _ = self.transform(X)
if self.encode_data:
return self.class_encoder_.inverse_transform(
self.classifier.predict(X))
return self.classifier.predict(X)
def reset_evaluation(self):
# Reset the memoize evaluations
self.evaluate_leave_one_out_cross_val = memoize(evaluate_leave_one_out)
def predict_proba(self, X):
X, _ = self.transform(X)
return self.classifier.predict_proba(X)
def score(self, X, y):
X, y = self.transform(X, y)
return self.classifier.score(X, y)
def filter_features(self, X, y):
'''After the rank is built this perform the greedy wrapper search'''
check_is_fitted(self)
self.classifier = NaiveBayes(encode_data=False,
n_intervals=self.n_intervals,
metric=self.metric)
current_score = np.NINF
first_iteration = True
current_features = []
current_data = None
if self.use_initials:
# Original Features have already been taken into account
rank_iter = filter(
lambda x: not isinstance(self.all_feature_constructors[x],
DummyFeatureConstructor),
iter(self.rank))
# Deep copy to avoid issues when modifying the list
current_features = deepcopy(self.initial_backward_features)
current_data = np.concatenate(
[f.transform(X) for f in current_features], axis=1)
# Get initial LOO score
current_score = self.evaluate_leave_one_out_cross_val(
self.classifier, current_features, current_data, y, fit=True)
else:
# Iterator over the sorted list of indexes
rank_iter = iter(self.rank)
if self.verbose:
progress_bar = tqdm(total=len(self.rank),
bar_format='{l_bar}{bar:20}{r_bar}{bar:-10b}')
iteration = 0
iterations_without_improvements = 0
# Loop for including {block size} elements at a time
# Rank is an iterator, so the for loop is not sequential!
for feature_constructor_index in rank_iter:
iteration += 1
if self.verbose:
progress_bar.set_postfix({
"n_features": len(current_features),
"score": current_score
})
progress_bar.update(1)
progress_bar.refresh()
# Add block size features
new_X = [
self.all_feature_constructors[feature_constructor_index].
transform(X)
]
selected_features = [
self.all_feature_constructors[feature_constructor_index]
]
for _ in range(self.block_size - 1):
try:
index = next(rank_iter)
selected_features.append(
self.all_feature_constructors[index])
new_X.append(
self.all_feature_constructors[index].transform(X))
if self.verbose:
progress_bar.update(1)
progress_bar.refresh()
except:
# Block size does not divide the number of elements in the rank. The search is halted
break
# Evaluate features
new_X = np.concatenate(new_X, axis=1)
if iteration == 1 and not self.use_initials:
current_data = new_X
current_score = self.evaluate_leave_one_out_cross_val(
self.classifier,
selected_features,
current_data,
y,
fit=True)
current_features = selected_features
first_iteration = False
if self.max_iterations <= iteration or (
len(current_features) +
self.block_size) > self.max_features:
break
continue
data = np.concatenate([current_data, new_X], axis=1)
self.classifier.add_features(new_X, y)
# LOO evaluation
score = self.evaluate_leave_one_out_cross_val(self.classifier,
current_features +
selected_features,
data,
y,
fit=False)
if score > current_score:
current_score = score
current_data = data
current_features.extend(selected_features)
iterations_without_improvements = 0
else:
iterations_without_improvements += 1
# Remove last added block
for feature_index_to_remove in range(
data.shape[1], data.shape[1] - new_X.shape[1], -1):
self.classifier.remove_feature(feature_index_to_remove - 1)
if self.strategy == "eager" and self.max_err < iterations_without_improvements:
# Stops as soon as no impovement
break
if self.max_iterations <= iteration or (
len(current_features) +
self.block_size) > self.max_features:
break
if self.verbose:
progress_bar.close()
print(
f"\nFinal number of included features: {len(current_features)} - Final Score: {current_score}"
)
self.final_feature_constructors = current_features
return self
def transform(self, X, y=None):
check_is_fitted(self)
if isinstance(y, pd.DataFrame):
y = y.to_numpy()
if self.encode_data:
X = self.feature_encoder_.transform(X)
if y is not None:
y = self.class_encoder_.transform(y)
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
new_X = []
for feature_constructor in self.final_feature_constructors:
new_X.append(feature_constructor.transform(X))
return np.concatenate(new_X, axis=1), y
def ranker_score_comparison(datasets,
seed,
base_path,
params,
n_splits=3,
n_repeats=5,
n_intervals=5,
metric="accuracy",
send_email=False,
email_data=dict(),
share_rank=True):
result = []
columns = ["Database",
"Number of attributes",
"NBScore",
"NBScore STD",
"Ranker Score",
"Ranker Score STD",
"Configuration",
"Combinations",
"Selected_attributes",
"Original"]
dataset_tqdm = tqdm(datasets)
# Instantiate the classifier
r = RankerLogicalFeatureConstructor(n_intervals=n_intervals, metric=metric)
nb = NaiveBayes(encode_data=False, n_intervals=n_intervals, metric=metric)
# Execute algorithm on datasets
for database in dataset_tqdm:
name, label = database
if not os.path.exists(base_path + name):
print(f"{name} doesnt' exist")
continue
# Assume UCI REPO like data
test = f"{name}.test.csv"
data = f"{name}.data.csv"
X, y = get_X_y_from_database(base_path, name, data, test, label)
dataset_tqdm.set_postfix({"DATABASE": name})
# Set up data structures to store results
nb_score = np.zeros(shape=(len(params), n_splits*n_repeats))
r_score = np.zeros(shape=(len(params), n_splits*n_repeats))
r_combinations = np.zeros(shape=(len(params), n_splits*n_repeats))
r_selected = np.zeros(shape=(len(params), n_splits*n_repeats))
r_dummy = np.zeros(shape=(len(params), n_splits*n_repeats))
r_total_constructed = np.zeros(shape=(len(params), n_splits*n_repeats))
r_total_selected = np.zeros(shape=(len(params), n_splits*n_repeats))
r_original_selected = np.zeros(shape=(len(params), n_splits*n_repeats))
rskf = RepeatedStratifiedKFold(n_splits=n_splits, n_repeats=n_repeats, random_state=seed)
seed_tqdm = tqdm(rskf.split(X, y),
leave=False,
total=n_splits*n_repeats,
bar_format='{l_bar}{bar:20}{r_bar}{bar:-10b}')
for i, data in enumerate(seed_tqdm):
train_index, test_index = data
X_train, X_test = X.iloc[train_index], X.iloc[test_index]
y_train, y_test = y.iloc[train_index], y.iloc[test_index]
c = CustomOrdinalFeatureEncoder(n_intervals=n_intervals)
X_train = c.fit_transform(X_train)
X_test = c.transform(X_test)
l = CustomLabelEncoder()
y_train = l.fit_transform(y_train)
y_test = l.transform(y_test)
# Assess the classifiers
nb.fit(X=X_train, y=y_train)
naive_bayes_score = nb.score(X_test, y_test)
for conf_index, conf in enumerate(params):
seed_tqdm.set_postfix({"config": conf_index})
r.set_params(**conf)
# Fit
if conf_index == 0 or not share_rank:
# The rank is computed from scratch
r.fit(X_train, y_train)
else:
r.filter_features(r.feature_encoder_.transform(
X_train), r.class_encoder_.transform(y_train))
# score
ranker_score = r.score(X_test, y_test)
# Get data
n_original_features = len(list(filter(lambda x: isinstance(
x, DummyFeatureConstructor), r.final_feature_constructors)))
n_combinations = len(r.all_feature_constructors)
n_selected = len(r.final_feature_constructors)
# Update
nb_score[conf_index, i] = naive_bayes_score
r_score[conf_index, i] = ranker_score
r_combinations[conf_index, i] = n_combinations
r_selected[conf_index, i] = n_selected
r_dummy[conf_index, i] = n_original_features
# Insert to final result averaged metrics for this dataset
for conf_index, conf in enumerate(params):
row = [name,
X.shape[1],
np.mean(nb_score[conf_index]),
np.std(nb_score[conf_index]),
np.mean(r_score[conf_index]),
np.std(r_score[conf_index]),
conf,
np.mean(r_combinations[conf_index]),
np.mean(r_selected[conf_index]),
np.mean(r_dummy[conf_index])]
result.append(row)
result = pd.DataFrame(result, columns=columns)
if send_email:
from tfg.utils import send_results
send_results("RANKER", email_data, result)
return result
def genetic_score_comparison(datasets,
seed,
base_path,
params,
n_splits=3,
n_repeats=5,
n_intervals=5,
metric="accuracy",
send_email=False,
email_data=dict(),
verbose=True,
version=1):
result = []
columns = [
"Database", "Number of attributes", "NBScore", "NBScore STD",
"Genetic Score", "Genetic Score STD", "Configuration",
"Selected_attributes", "Original"
]
dataset_tqdm = tqdm(datasets)
# Instantiate the classifier
if version == 1:
# First Version - No flexibility in the number of attributes (bad performance)
# clf = GeneticProgramming(seed=seed, metric=metric)
clf = GeneticProgrammingFlexibleLogic(seed=seed, metric=metric)
elif version == 2:
# Version with flexibility
clf = GeneticProgrammingFlexibleLogic(seed=seed, metric=metric)
else:
# Guided mutation based on SU
clf = GeneticProgrammingRankMutation(seed=seed, metric=metric)
nb = NaiveBayes(encode_data=False, n_intervals=n_intervals, metric=metric)
# Execute algorithm on datasets
for database in dataset_tqdm:
name, label = database
if not os.path.exists(base_path + name):
print(f"{name} doesnt' exist")
continue
# Assume UCI REPO like data
test = f"{name}.test.csv"
data = f"{name}.data.csv"
X, y = get_X_y_from_database(base_path, name, data, test, label)
dataset_tqdm.set_postfix({"DATABASE": name})
# Set up data structures to store results
nb_score = np.zeros(shape=(len(params), n_splits * n_repeats))
clf_score = np.zeros(shape=(len(params), n_splits * n_repeats))
clf_selected = np.zeros(shape=(len(params), n_splits * n_repeats))
clf_dummy = np.zeros(shape=(len(params), n_splits * n_repeats))
# Create splits for the experiments
rskf = RepeatedStratifiedKFold(n_splits=n_splits,
n_repeats=n_repeats,
random_state=seed)
seed_tqdm = tqdm(rskf.split(X, y),
leave=False,
total=n_splits * n_repeats,
bar_format='{l_bar}{bar:20}{r_bar}{bar:-10b}'
) if verbose else rskf.split(X, y)
# Execute experiments
for i, data in enumerate(seed_tqdm):
train_index, test_index = data
X_train, X_test = X.iloc[train_index], X.iloc[test_index]
y_train, y_test = y.iloc[train_index], y.iloc[test_index]
# Encode the data
c = CustomOrdinalFeatureEncoder(n_intervals=n_intervals)
X_train = c.fit_transform(X_train)
X_test = c.transform(X_test)
l = CustomLabelEncoder()
y_train = l.fit_transform(y_train)
y_test = l.transform(y_test)
# Assess the classifiers reusing info to speed up evaluation
nb.fit(X_train, y_train)
naive_bayes_score = nb.score(X_test, y_test)
# Reset evaluation-cache for new split
clf.reset_evaluation()
for conf_index, conf in enumerate(params):
if verbose:
seed_tqdm.set_postfix({"config": conf_index})
clf.set_params(**conf)
clf.fit(X_train, y_train)
# score
genetic_score = clf.score(X_test, y_test)
# Get data
n_original_features = len(
list(
filter(
lambda x: isinstance(x, DummyFeatureConstructor),
clf.best_features)))
n_selected = len(clf.best_features)
# Update
nb_score[conf_index, i] = naive_bayes_score
clf_score[conf_index, i] = genetic_score
clf_selected[conf_index, i] = n_selected
clf_dummy[conf_index, i] = n_original_features
# Insert to final result averaged metrics for this database
for conf_index, conf in enumerate(params):
row = [
name, X.shape[1],
np.mean(nb_score[conf_index]),
np.std(nb_score[conf_index]),
np.mean(clf_score[conf_index]),
np.std(clf_score[conf_index]), conf,
np.mean(clf_selected[conf_index]),
np.mean(clf_dummy[conf_index])
]
result.append(row)
result = pd.DataFrame(result, columns=columns)
if send_email:
from tfg.utils import send_results
send_results(f"GENETIC_{version}", email_data, result)
return result
class NaiveBayes(ClassifierMixin, BaseEstimator):
"""A Naive Bayes classifier.
Simple NaiveBayes classifier accepting non-encoded input, enhanced with numba using MAP
to predict most likely class.
Parameters
----------
alpha : {float, array-like}, default=1.0
Additive (Laplace/Lidstone) smoothing parameter
(0 for no smoothing). If it is an array it is
expected to have the same size as number of attributes
encode_data : bool, default=True
Encode data when data is not encoded by default with an OrdinalEncoder
discretize : bool, default=True
Discretize numerical data
n_intervals : int or None, default=5
Discretize numerical data using the specified number of intervals
Attributes
----------
feature_encoder_ : CustomOrdinalFeatureEncoder or None
Encodes data in ordinal way with unseen values handling if encode_data is set to True.
class_encoder_ : LabelEncoder or None
Encodes Data in ordinal way for the class if encode_data is set to True.
n_samples_ : int
Number of samples
n_features_ : int
Number of features
n_classes_ : int
Number of classes
class_values_ : array-like of shape (n_classes_,)
Array containing the values of the classes, as ordinal encoding is assumed it will be an array
ranging from 0 to largest value for the class
class_count_ : array-like of shape (n_classes_,)
Array where `class_count_[i]` contains the count of the ith class value.
class_log_count_ : array-like of shape (n_classes_,)
Array where `class_count_[i]` contains the log count of the ith class value.
feature_values_count_per_element_ : array-like of shape (column_count,~)
Array where `feature_values_count_per_element_[i]` is an array where `feature_values_count_per_element_[i][j]`
contains the count of the jth value for the ith feature. Assuming ordinal encoding, some values might be equal to 0
feature_values_count_ : array-like of shape (column_count,)
Array where `feature_values_count_per_element_[i]` is an integer with the number of possible values for the ith feature.
feature_unique_values_count_ : array-like of shape (column_count,)
Array where `feature_unique_values_count_[i]` is an integer with the number of unique seen values for the ith feature at
fitting time. This is needed to compute the smoothing.
total_probability_ : array-like of shape (n_classes,)
Smoothing factor to be applied to the prediction. Array where `total_probability_[i]` if equal to
class_count_[i] + alpha*feature_unique_values_count_
self.indepent_term_ : array-like of shape (n_classes,)
Independent term computed at fitting time. It includes the smoothing factor to be applied to the prediction and
the apriori probability.
probabilities_ : array-like of shape (column_count,~)
Array where `feature_values_count_per_element_[i]` is an array of shape (where `feature_values_count_per_element_[i][j]`
contains the count of the jth value for the ith feature. Assuming ordinal encoding, some values might be equal to 0
"""
def __init__(self,
alpha=1.0,
encode_data=True,
n_intervals=5,
discretize=True,
metric="accuracy"):
self.alpha = alpha
self.encode_data = encode_data
self.n_intervals = n_intervals
self.discretize = discretize
self.metric = metric
self._get_scorer()
super().__init__()
def _get_scorer(self):
self.scorer = get_scorer(self.metric)
if self.metric == "f1_score": # Unseen values for target class may cause errors
self.scorer = lambda y_true, y_pred: get_scorer(self.metric)(
y_true=y_true, y_pred=y_pred, average="macro", zero_division=0)
def set_params(self, **params):
super().set_params(**params)
self._get_scorer()
def _compute_independent_terms(self):
"""Computes the terms that are indepent of the prediction"""
self.total_probability_ = compute_total_probability_(
self.class_count_, self.feature_unique_values_count_, self.alpha)
# self.total_probability_ = compute_total_probability_(self.class_count_,self.feature_values_count_,self.alpha) #-->scikit uses this
self.indepent_term_ = self.class_log_count_smoothed_ - self.total_probability_
def _compute_class_counts(self, X: np.ndarray, y: np.ndarray):
"""Computes the counts for the priors"""
self.n_classes_ = 1 + np.max(y)
self.class_count_ = np.bincount(y)
self.class_log_count_ = np.log(self.class_count_)
self.class_count_smoothed_ = (self.class_count_ + self.alpha)
self.class_log_count_smoothed_ = np.log(self.class_count_smoothed_)
def _compute_feature_counts(self, X: np.ndarray, y: np.ndarray):
"""Computes the conditional smoothed counts for each feature"""
tables = _get_tables(X, y, self.n_classes_, self.alpha)
self.smoothed_counts_ = tables[0]
self.smoothed_log_counts_ = tables[1]
self.feature_values_count_ = tables[2]
self.feature_values_count_per_element_ = tables[3]
self.feature_unique_values_count_ = tables[4]
def fit(self, X: np.ndarray, y: np.ndarray):
""" Fits the classifier with trainning data.
Parameters
----------
X : array-like of shape (n_samples, n_features_)
Training array that must be encoded unless
encode_data is set to True
y : array-like of shape (n_samples,)
Label of the class associated to each sample.
Returns
-------
self : object
"""
if isinstance(y, pd.DataFrame):
y = y.to_numpy()
if self.encode_data:
self.feature_encoder_ = CustomOrdinalFeatureEncoder(
n_intervals=self.n_intervals, discretize=self.discretize)
self.class_encoder_ = CustomLabelEncoder()
X = self.feature_encoder_.fit_transform(X)
y = self.class_encoder_.fit_transform(y)
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
check_X_y(X, y)
if X.dtype != int:
X = X.astype(int)
if y.dtype != int:
y = y.astype(int)
self.n_samples_, self.n_features_ = X.shape
self._compute_class_counts(X, y)
self._compute_feature_counts(X, y)
self._compute_independent_terms()
return self
def predict(self, X: np.ndarray):
""" Predicts the label of the samples based on the MAP.
Parameters
----------
X : array-like of shape (n_samples, n_features_)
Training array that must be encoded unless
encode_data is set to True
Returns
-------
y : array-like of shape (n_samples)
Predicted label for each sample.
"""
check_is_fitted(self)
if self.encode_data:
X = self.feature_encoder_.transform(X)
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
if X.dtype != int:
X = X.astype(int)
check_array(X)
log_probabilities = _predict(X, self.smoothed_log_counts_,
self.feature_values_count_, self.alpha)
log_probabilities += self.indepent_term_
output = np.argmax(log_probabilities, axis=1)
if self.encode_data:
output = self.class_encoder_.inverse_transform(output)
return output
def predict_proba(self, X: np.ndarray):
""" Predicts the probability for each label of the samples based on the MAP.
Parameters
----------
X : array-like of shape (n_samples, n_features_)
Training array that must be encoded unless
encode_data is set to True
Returns
-------
y : array-like of shape (n_classes,n_samples)
Array where `y[i][j]` contains the MAP of the jth class for ith
sample
"""
check_is_fitted(self)
if X.dtype != int:
X = X.astype(int)
if self.encode_data:
X = self.feature_encoder_.transform(X)
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
log_probabilities = _predict(X, self.smoothed_log_counts_,
self.feature_values_count_, self.alpha)
log_probabilities += self.indepent_term_
log_prob_x = logsumexp(log_probabilities, axis=1)
return np.exp(log_probabilities - np.atleast_2d(log_prob_x).T)
def leave_one_out_cross_val(self, X, y, fit=True):
"""Efficient LOO computation"""
if fit:
self.fit(X, y)
if self.encode_data:
X = self.feature_encoder_.transform(X)
y = self.class_encoder_.transform(y)
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
if X.dtype != int:
X = X.astype(int)
if y.dtype != int:
X = X.astype(int)
log_alpha = np.log(self.alpha)
log_proba = np.zeros((X.shape[0], self.n_classes_))
for i in range(X.shape[0]):
example, label = X[i], y[i]
class_count_ = self.class_count_.copy()
class_count_[label] -= 1
log_proba[i] = np.log(class_count_ + self.alpha)
for j in range(X.shape[1]):
p = self.smoothed_log_counts_[j][example[j]].copy()
p[label] = np.log(
np.max([
self.smoothed_counts_[j][example[j]][label] - 1,
self.alpha
]))
log_proba[i] += p
if self.feature_values_count_per_element_[j][example[j]] == 1:
update_value = np.log(class_count_ + (
self.feature_unique_values_count_[j] - 1) * self.alpha)
else:
update_value = np.log(
class_count_ +
(self.feature_unique_values_count_[j]) * self.alpha)
log_proba[i] -= np.where(update_value == np.NINF, 0,
update_value)
y_pred = np.argmax(log_proba, axis=1)
return self.scorer(y, y_pred)
def add_features(self, X, y, index=None):
"""Updates classifier with new features
Parameters
----------
X : array-like of shape (n_samples, n_features_)
Training array that must be encoded unless
encode_data is set to True
y : array-like of shape (n_samples,)
Label of the class associated to each sample.
index: {None,array-like of shape (X.shape[1])}
Indicates where to insert each new feature, if it is None
they are all appended at the very end.
Returns
-------
self : object
"""
check_is_fitted(self)
if isinstance(y, pd.DataFrame):
y = y.to_numpy()
if self.encode_data:
# y should be the same than the one that was first fitted for now ----> FUTURE IMPLEMENTATION
y = self.class_encoder_.transform(y)
X = self.feature_encoder_.add_features(X,
transform=True,
index=index)
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
check_X_y(X, y)
if X.dtype != int:
X = X.astype(int)
if y.dtype != int:
X = X.astype(int)
self.n_features_ += X.shape[1]
tables = _get_tables(X, y, self.n_classes_, self.alpha)
new_smoothed_counts = tables[0]
new_smoothed_log_counts = tables[1]
new_feature_value_counts = tables[2]
new_feature_value_counts_per_element = tables[3]
new_feature_unique_values_count_ = tables[4]
new_feature_contribution = compute_total_probability_(
self.class_count_, new_feature_unique_values_count_, self.alpha)
if index:
sort_index = np.argsort(index)
index_with_column = list(enumerate(index))
for i in sort_index:
column, list_insert_index = index_with_column[i]
self.feature_values_count_per_element_.insert(
list_insert_index,
new_feature_value_counts_per_element[column])
self.feature_values_count_ = np.insert(
self.feature_values_count_, list_insert_index,
new_feature_value_counts[column])
self.smoothed_counts_.insert(list_insert_index,
new_smoothed_counts[column])
self.smoothed_log_counts_.insert(
list_insert_index, new_smoothed_log_counts[column])
self.feature_unique_values_count_ = np.insert(
self.feature_unique_values_count_, list_insert_index,
new_feature_unique_values_count_[column])
else:
self.feature_values_count_per_element_.extend(
new_feature_value_counts_per_element)
self.feature_values_count_ = np.concatenate(
[self.feature_values_count_, new_feature_value_counts])
self.smoothed_counts_.extend(new_smoothed_counts)
self.smoothed_log_counts_.extend(new_smoothed_log_counts)
self.feature_unique_values_count_ = np.concatenate([
self.feature_unique_values_count_,
new_feature_unique_values_count_
])
self.total_probability_ += new_feature_contribution
self.indepent_term_ -= new_feature_contribution
return self
def remove_feature(self, index):
"""Updates classifierby removing one feature (index)"""
check_is_fitted(self)
if self.n_features_ <= 1:
raise Exception("Cannot remove only feature from classifier")
if not 0 <= index < self.n_features_:
raise Exception(
f"Feature index not valid, expected index between 0 and {self.n_features_}"
)
self.n_features_ -= 1
feature_contribution = self.class_count_ + self.alpha * self.feature_unique_values_count_[
index]
feature_contribution = np.log(feature_contribution)
self.total_probability_ -= feature_contribution
self.indepent_term_ += feature_contribution
self.feature_unique_values_count_ = np.delete(
self.feature_unique_values_count_, index)
self.feature_values_count_ = np.delete(self.feature_values_count_,
index)
del self.feature_values_count_per_element_[index]
del self.smoothed_counts_[index]
del self.smoothed_log_counts_[index]
if self.encode_data:
self.feature_encoder_.remove_feature(index)
return self
def score(self, X: np.ndarray, y: np.ndarray):
"""Computes the accuracy
Parameters
----------
X : array-like of shape (n_samples, n_features_)
Training array that must be encoded unless
encode_data is set to True
y : array-like of shape (n_samples,)
Label of the class associated to each sample.
Returns
-------
score : float
Percentage of correctly classified instances
"""
y_pred = self.predict(X)
return self.scorer(y, y_pred)