Jurity is a research library that provides fairness metrics, recommender system evaluations, classification metrics and bias mitigation techniques. The library adheres to PEP-8 standards and is tested heavily.
Jurity is developed by the Artificial Intelligence Center of Excellence at Fidelity Investments. Documentation is available at fidelity.github.io/jurity.
- Average Odds
- Disparate Impact
- Equal Opportunity
- False Negative Rate (FNR) Difference
- Generalized Entropy Index
- Predictive Equality
- Statistical Parity
- Theil Index
- AUC: Area Under the Curve
- CTR: Click-through rate
- DR: Doubly robust estimation
- IPS: Inverse propensity scoring
- MAP@K: Mean Average Precision
- NDCG: Normalized discounted cumulative gain
- Precision@K
- Recall@K
- Inter-List Diversity@K
- Intra-List Diversity@K
# 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"]]
is_member = [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, is_member))
print("Multi-class Fairness scores: ", multi_metric.get_scores(multi_class_predictions, is_member))
print("Multi-class multi-label Fairness scores: ", multi_metric.get_scores(multi_class_multi_label_predictions, is_member))# Import binary fairness and binary bias mitigation
from jurity.mitigation import BinaryMitigation
from jurity.fairness import BinaryFairnessMetrics
# Data
labels = [1, 1, 0, 1, 0, 0, 1, 0]
predictions = [0, 0, 0, 1, 1, 1, 1, 0]
likelihoods = [0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.1]
is_member = [0, 0, 0, 0, 1, 1, 1, 1]
# Bias Mitigation
mitigation = BinaryMitigation.EqualizedOdds()
# Training: Learn mixing rates from the labeled data
mitigation.fit(labels, predictions, likelihoods, is_member)
# Testing: Mitigate bias in predictions
fair_predictions, fair_likelihoods = mitigation.transform(predictions, likelihoods, is_member)
# Scores: Fairness before and after
print("Fairness Metrics Before:", BinaryFairnessMetrics().get_all_scores(labels, predictions, is_member), '\n'+30*'-')
print("Fairness Metrics After:", BinaryFairnessMetrics().get_all_scores(labels, fair_predictions, is_member))# Import recommenders metrics
from jurity.recommenders import BinaryRecoMetrics, RankingRecoMetrics, DiversityRecoMetrics
import pandas as pd
# Data
actual = pd.DataFrame({"user_id": [1, 2, 3, 4], "item_id": [1, 2, 0, 3], "clicks": [0, 1, 0, 0]})
predicted = pd.DataFrame({"user_id": [1, 2, 3, 4], "item_id": [1, 2, 2, 3], "clicks": [0.8, 0.7, 0.8, 0.7]})
item_features = pd.DataFrame({"item_id": [0, 1, 2, 3], "feature1": [1, 2, 2, 1], "feature2": [0.8, 0.7, 0.8, 0.7]})
# Metrics
auc = BinaryRecoMetrics.AUC(click_column="clicks")
ctr = BinaryRecoMetrics.CTR(click_column="clicks")
dr = BinaryRecoMetrics.CTR(click_column="clicks", estimation='dr')
ips = BinaryRecoMetrics.CTR(click_column="clicks", estimation='ips')
map_k = RankingRecoMetrics.MAP(click_column="clicks", k=2)
ncdg_k = RankingRecoMetrics.NDCG(click_column="clicks", k=3)
precision_k = RankingRecoMetrics.Precision(click_column="clicks", k=2)
recall_k = RankingRecoMetrics.Recall(click_column="clicks", k=2)
interlist_diversity_k = DiversityRecoMetrics.InterListDiversity(click_column="clicks", k=2)
intralist_diversity_k = DiversityRecoMetrics.IntraListDiversity(item_features, click_column="clicks", k=2)
# Scores
print("AUC:", auc.get_score(actual, predicted))
print("CTR:", ctr.get_score(actual, predicted))
print("Doubly Robust:", dr.get_score(actual, predicted))
print("IPS:", ips.get_score(actual, predicted))
print("MAP@K:", map_k.get_score(actual, predicted))
print("NCDG:", ncdg_k.get_score(actual, predicted))
print("Precision@K:", precision_k.get_score(actual, predicted))
print("Recall@K:", recall_k.get_score(actual, predicted))
print("Inter-List Diversity@K:", interlist_diversity_k.get_score(actual, predicted))
print("Intra-List Diversity@K:", intralist_diversity_k.get_score(actual, predicted))# Import classification metrics
from jurity.classification import BinaryClassificationMetrics
# Data
labels = [1, 1, 0, 1, 0, 0, 1, 0]
predictions = [0, 0, 0, 1, 1, 1, 1, 0]
# Available: Accuracy, F1, Precision, Recall, and AUC
f1_score = BinaryClassificationMetrics.F1()
print('F1 score is', f1_score.get_score(predictions, labels))Jurity requires Python 3.6+ and can be installed from PyPI using pip install jurity or by building from source as shown in installation instructions.
Please submit bug reports and feature requests as Issues.
Jurity is licensed under the Apache License 2.0.