Mab2Rec:
Multi-Armed Bandit Recommenders

# An example that shows how to use the UCB1 learning policy
# to choose between two arms based on their expected rewards.

# Import MABWiser Library
from mabwiser.mab import MAB, LearningPolicy, NeighborhoodPolicy

# Data
arms = ['Arm1', 'Arm2']
decisions = ['Arm1', 'Arm1', 'Arm2', 'Arm1']
rewards = [20, 17, 25, 9]

# Model
mab = MAB(arms, LearningPolicy.UCB1(alpha=1.25))

# Train
mab.fit(decisions, rewards)

# Test
mab.predict()

# Conceptually, TextWiser is composed of an Embedding, potentially with a pretrained model,
# that can be chained into zero or more Transformations
from textwiser import TextWiser, Embedding, Transformation, WordOptions, PoolOptions

# Data
documents = ["Some document", "More documents. Including multi-sentence documents."]

# Model: TFIDF `min_df` parameter gets passed to sklearn automatically
emb = TextWiser(Embedding.TfIdf(min_df=1))

# Model: TFIDF followed with an NMF + SVD
emb = TextWiser(Embedding.TfIdf(min_df=1), [Transformation.NMF(n_components=30), Transformation.SVD(n_components=10)])

# Model: Word2Vec with no pretraining that learns from the input data
emb = TextWiser(Embedding.Word(word_option=WordOptions.word2vec, pretrained=None), Transformation.Pool(pool_option=PoolOptions.min))

# Model: BERT with the pretrained bert-base-uncased embedding
emb = TextWiser(Embedding.Word(word_option=WordOptions.bert), Transformation.Pool(pool_option=PoolOptions.first))

# Features
vecs = emb.fit_transform(documents)

# Import Selective and SelectionMethod
from sklearn.datasets import fetch_california_housing
from feature.utils import get_data_label
from feature.selector import Selective, SelectionMethod

# Data
data, label = get_data_label(fetch_california_housing())

# Feature selectors from simple to more complex
selector = Selective(SelectionMethod.Variance(threshold=0.0))
selector = Selective(SelectionMethod.Correlation(threshold=0.5, method="pearson"))
selector = Selective(SelectionMethod.Statistical(num_features=3, method="anova"))
selector = Selective(SelectionMethod.Linear(num_features=3, regularization="none"))
selector = Selective(SelectionMethod.TreeBased(num_features=3))

# Feature reduction
subset = selector.fit_transform(data, label)
print("Reduction:", list(subset.columns))
print("Scores:", list(selector.get_absolute_scores()))

# Example to show how to find frequent sequential patterns
# from a given sequence database subject to constraints
from sequential.seq2pat import Seq2Pat, Attribute

# Seq2Pat over 3 sequences
seq2pat = Seq2Pat(sequences=[["A", "A", "B", "A", "D"],
                             ["C", "B", "A"],
                             ["C", "A", "C", "D"]])

# Price attribute corresponding to each item
price = Attribute(values=[[5, 5, 3, 8, 2],
                          [1, 3, 3],
                          [4, 5, 2, 1]])

# Average price constraint
seq2pat.add_constraint(3 <= price.average() <= 4)

# Patterns that occur at least twice (A-D)
patterns = seq2pat.get_patterns(min_frequency=2)

# Import binary and multi-class fairness metrics
from jurity.fairness import BinaryFairnessMetrics, MultiClassFairnessMetrics

# Data
binary_predictions = [1, 1, 0, 1, 0, 0]
multi_class_predictions = ["a", "b", "c", "b", "a", "a"]
multi_class_multi_label_predictions = [["a", "b"], ["b", "c"], ["b"], ["a", "b"], ["c", "a"], ["c"]]
memberships = [0, 0, 0, 1, 1, 1]
classes = ["a", "b", "c"]

# Metrics (see also other available metrics)
metric = BinaryFairnessMetrics.StatisticalParity()
multi_metric = MultiClassFairnessMetrics.StatisticalParity(classes)

# Scores
print("Metric:", metric.description)
print("Lower Bound: ", metric.lower_bound)
print("Upper Bound: ", metric.upper_bound)
print("Ideal Value: ", metric.ideal_value)
print("Binary Fairness score: ", metric.get_score(binary_predictions, memberships))
print("Multi-class Fairness scores: ", multi_metric.get_scores(multi_class_predictions, memberships))
print("Multi-class multi-label Fairness scores: ", multi_metric.get_scores(multi_class_multi_label_predictions, memberships))

import numpy as np
from sklearn.metrics import balanced_accuracy_score

from boolxai import BoolXAI, Operator

# Create random toy data for binary classification. X and y must be binary!
rng = np.random.default_rng(seed=42)
X = rng.choice([0, 1], size=(100, 10))
y = rng.choice([0, 1], size=100)

# Rule classifier with maximum depth, complexity, possible operators
rule_classifier = BoolXAI.RuleClassifier(max_depth=3,
                                         max_complexity=6,
                                         operators=[Operator.And, Operator.Or, Operator.Choose, Operator.AtMost, Operator.AtLeast],
                                         random_state=42)

# Learn the best rule
rule_classifier.fit(X, y)

# Best rule and best score
best_rule = rule_classifier.best_rule_
best_score = rule_classifier.best_score_
print(f"{best_rule=} {best_score=:.2f}")

# The depth of a rule is the number of edges in the longest path from the root to any leaf/literal.
# The complexity of a rule is the total number of operators and literals.
print(f"depth={best_rule.depth()} complexity={best_rule.complexity()}")

# Predict and score
y_pred = rule_classifier.predict(X)
score = balanced_accuracy_score(y, y_pred)
print(f"{score=:.2f}")

# It is also possible to plot the best rule --requires installing plot dependencies
best_rule.plot()

# or get a networkx.DiGraph representation of the rule --requires installing plot dependencies
G = best_rule.to_graph()
print(G)