From 850082334322b14f6c5d98975aa3d93fb95a860c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Judith=20S=C3=A1inz-Pardo=20D=C3=ADaz?=
 <sainzpardo@ifca.unican.es>
Date: Tue, 7 May 2024 12:15:50 +0200
Subject: [PATCH] feat: generate interval-based hierarchies

---
 anjana/anonymity/utils/__init__.py |  2 ++
 anjana/anonymity/utils/utils.py    | 38 ++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/anjana/anonymity/utils/__init__.py b/anjana/anonymity/utils/__init__.py
index 491758a..7318105 100644
--- a/anjana/anonymity/utils/__init__.py
+++ b/anjana/anonymity/utils/__init__.py
@@ -20,6 +20,7 @@
     apply_hierarchy,
     check_gen_level,
     get_transformation,
+    generate_intervals,
 )
 
 __all__ = [
@@ -27,4 +28,5 @@
     "apply_hierarchy",
     "check_gen_level",
     "get_transformation",
+    "generate_intervals",
 ]
diff --git a/anjana/anonymity/utils/utils.py b/anjana/anonymity/utils/utils.py
index 7f61747..08f0eee 100644
--- a/anjana/anonymity/utils/utils.py
+++ b/anjana/anonymity/utils/utils.py
@@ -149,3 +149,41 @@ def get_transformation(
             transformation.append(0)
 
     return transformation
+
+
+@beartype()
+def generate_intervals(
+    quasi_ident: typing.Union[typing.List, np.ndarray],
+    inf: typing.Union[int, float],
+    sup: typing.Union[int, float],
+    step: int,
+) -> list:
+    """Given a quasi-identifier of numeric type, creates a list containing an
+    interval-based generalization (hierarchy) of the values of the quasi-identifier.
+    The intervals will have the length entered in the parameter step.
+
+    :param quasi_ident: values of the quasi-identifier on which the interval-based
+        generalization is to be obtained
+    :type quasi_ident: list or numpy array
+
+    :param inf: lower value of the set of intervals
+    :type inf: int or float
+
+    :param sup: bigger value of the set of intervals
+    :type sup: int or float
+
+    :param step: spacing between values of the intervals
+    :type step: int
+
+    :return: list with the intervals associated with the given values
+    :rtype: list
+    """
+    values = np.arange(inf, sup + 1, step)
+    interval = []
+    for num in quasi_ident:
+        lower = np.searchsorted(values, num)
+        if lower == 0:
+            lower = 1
+        interval.append(f"[{values[lower - 1]}, {values[lower]})")
+
+    return interval