tsadmetrics 0.1.12__py3-none-any.whl → 0.1.14__py3-none-any.whl

tsadmetrics/non_binary_metrics.py

@@ -15,8 +15,13 @@ def precision_at_k(y_true : np.array, y_anomaly_scores:  np.array):
     y_true. That is, k = sum(y_true).
 
     Parameters:
-    y_true (np.array): The ground truth binary labels for the time series data.
-    y_anomaly_scores (np.array): The predicted anomaly scores for the time series data.
+        y_true (np.array):
+            The ground truth binary labels for the time series data.
+        y_anomaly_scores (np.array):
+            The predicted anomaly scores for the time series data.
+
+    Returns:
+        float: The precision at k score.
     """
     m = PatK_pw(y_true,y_anomaly_scores)
 
@@ -31,8 +36,10 @@ def auc_roc_pw(y_true : np.array, y_anomaly_scores:  np.array):
     independently when calculating true positives, false positives, and false negatives.
 
     Parameters:
-        y_true (np.array): Ground-truth binary labels for the time series (0 = normal, 1 = anomaly).
-        y_anomaly_scores (np.array): Continuous anomaly scores assigned to each point in the series.
+        y_true (np.array):
+            Ground-truth binary labels for the time series (0 = normal, 1 = anomaly).
+        y_anomaly_scores (np.array):
+            Continuous anomaly scores assigned to each point in the series.
 
     Returns:
         float: AUC-ROC score.
@@ -52,8 +59,10 @@ def auc_pr_pw(y_true : np.array ,y_anomaly_scores:  np.array):
     independently when calculating precision and recall.
 
     Parameters:
-        y_true (np.array): Ground-truth binary labels for the time series (0 = normal, 1 = anomaly).
-        y_anomaly_scores (np.array): Continuous anomaly scores assigned to each point in the series.
+        y_true (np.array):
+            Ground-truth binary labels for the time series (0 = normal, 1 = anomaly).
+        y_anomaly_scores (np.array):
+            Continuous anomaly scores assigned to each point in the series.
 
     Returns:
         float: AUC-PR score.
@@ -76,8 +85,10 @@ def auc_pr_pa(y_true: np.array, y_anomaly_scores: np.array):
     which are used to construct the PR curve.
 
     Parameters:
-        y_true (np.array): Ground-truth binary labels for the time series (0 = normal, 1 = anomaly).
-        y_anomaly_scores (np.array): Continuous anomaly scores assigned to each point in the series.
+        y_true (np.array):
+            Ground-truth binary labels for the time series (0 = normal, 1 = anomaly).
+        y_anomaly_scores (np.array):
+            Continuous anomaly scores assigned to each point in the series.
 
     Returns:
         float: AUC-PR score (with point-adjusted evaluation).
@@ -166,8 +177,10 @@ def auc_pr_sw(y_true: np.array, y_anomaly_scores: np.array):
     to compute precision and recall for constructing the PR curve.
 
     Parameters:
-        y_true (np.array): Ground-truth binary labels for the time series (0 = normal, 1 = anomaly).
-        y_anomaly_scores (np.array): Continuous anomaly scores assigned to each point in the series.
+        y_true (np.array):
+            Ground-truth binary labels for the time series (0 = normal, 1 = anomaly).
+        y_anomaly_scores (np.array):
+            Continuous anomaly scores assigned to each point in the series.
 
     Returns:
         float: AUC-PR score (with segment-wise evaluation).
@@ -271,16 +284,21 @@ def vus_roc(y_true : np.array ,y_anomaly_scores:  np.array, window=4):
     the ROC-AUC over different values of the tolerance parameter, from 0 to `window`, thus producing
     a volume under the ROC surface.
 
+    For more information, see the original paper:
+    https://dl.acm.org/doi/10.14778/3551793.3551830
+
     Parameters:
-        y_true (np.array): Ground-truth binary labels (0 = normal, 1 = anomaly).
-        y_anomaly_scores (np.array): Anomaly scores for each time point.
-        window (int): Maximum temporal tolerance `l` used to smooth the evaluation.
+        y_true (np.array):
+            Ground-truth binary labels (0 = normal, 1 = anomaly).
+        y_anomaly_scores (np.array):
+            Anomaly scores for each time point.
+        window (int):
+            Maximum temporal tolerance `l` used to smooth the evaluation.
 
     Returns:
         float: VUS-ROC score.
 
-    For more information, see the original paper:
-    https://dl.acm.org/doi/10.14778/3551793.3551830
+    
     """
     m = VUS_ROC(y_true,y_anomaly_scores,max_window=window)
 
@@ -296,16 +314,21 @@ def vus_pr(y_true : np.array ,y_anomaly_scores:  np.array,  window=4):
     anomalies that are temporally close to the true events. The final metric integrates the PR-AUC
     over several levels of temporal tolerance (from 0 to `window`), yielding a volume under the PR surface.
 
+    For more information, see the original paper:
+    https://dl.acm.org/doi/10.14778/3551793.3551830
+
     Parameters:
-        y_true (np.array): Ground-truth binary labels (0 = normal, 1 = anomaly).
-        y_anomaly_scores (np.array): Anomaly scores for each time point.
-        window (int): Maximum temporal tolerance `l` used to smooth the evaluation.
+        y_true (np.array):
+            Ground-truth binary labels (0 = normal, 1 = anomaly).
+        y_anomaly_scores (np.array):
+            Anomaly scores for each time point.
+        window (int):
+            Maximum temporal tolerance `l` used to smooth the evaluation.
 
     Returns:
         float: VUS-PR score.
 
-    For more information, see the original paper:
-    https://dl.acm.org/doi/10.14778/3551793.3551830
+    
     """
     m = VUS_PR(y_true,y_anomaly_scores,max_window=window)
 
@@ -331,10 +354,14 @@ def real_pate(y_true: np.array, y_anomaly_scores: np.array, early: int, delay: i
     https://arxiv.org/abs/2405.12096
 
     Parameters:
-        y_true (np.array): Ground truth binary labels (0 = normal, 1 = anomaly).
-        y_anomaly_scores (np.array): Real-valued anomaly scores for each time point.
-        early (int): Length of the early buffer zone before each anomaly interval.
-        delay (int): Length of the delay buffer zone after each anomaly interval.
+        y_true (np.array):
+            Ground truth binary labels (0 = normal, 1 = anomaly).
+        y_anomaly_scores (np.array):
+            Real-valued anomaly scores for each time point.
+        early (int):
+            Length of the early buffer zone before each anomaly interval.
+        delay (int):
+            Length of the delay buffer zone after each anomaly interval.
 
     Returns:
         float: The real-valued PATE score.

tsadmetrics/utils.py

@@ -7,14 +7,20 @@ def compute_metrics(y_true: np.array,y_pred: np.array, metrics: list, metrics_pa
     Computes the specified metrics for the given true and predicted values.
 
     Parameters:
-    - y_true (np.array): True labels.
-    - y_pred (np.array): Predicted labels or scores.
-    - metrics (list): List of metric names to compute.
-    - metrics_params (dict): Dictionary of parameters for each metric.
-    - is_anomaly_score (bool): Flag indicating if y_true and y_pred are anomaly scores. Otherwise, they are treated as binary labels.
-    - verbose (bool): Flag to print additional information.
+        y_true (np.array):
+            True labels.
+        y_pred (np.array):
+            Predicted labels or scores.
+        metrics (list):
+            List of metric names to compute.
+        metrics_params (dict):
+            Dictionary of parameters for each metric.
+        is_anomaly_score (bool):
+            Flag indicating if y_true and y_pred are anomaly scores. Otherwise, they are treated as binary labels.
+        verbose (bool):
+            Flag to print additional information.
     Returns:
-    - metrics_df (DataFrame): DataFrame containing the computed metrics and their values.
+        results (DataFrame): DataFrame containing the computed metrics and their values.
     """
     if not (np.array_equal(np.unique(y_true), [0, 1]) or np.array_equal(np.unique(y_true), [0]) or np.array_equal(np.unique(y_true), [1])):
         raise ValueError("y_true must be binary labels (0 or 1).")  

{tsadmetrics-0.1.12.dist-info → tsadmetrics-0.1.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tsadmetrics
-Version: 0.1.12
+Version: 0.1.14
 Summary: =?unknown-8bit?q?Librer=C3=ADa_para_evaluaci=C3=B3n_de_detecci=C3=B3n_de_anomal=C3=ADas?= en series temporales
 Home-page: https://github.com/pathsko/TSADmetrics
 Author: Pedro Rafael Velasco Priego

{tsadmetrics-0.1.12.dist-info → tsadmetrics-0.1.14.dist-info}/RECORD

@@ -16,11 +16,11 @@ tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/test_binary.py,sha256=dj9BsKBo5rpWw4JGiKKoVkg4rIW4YylTie2VxH2DAGo,29787
 tests/test_non_binary.py,sha256=syANlwm0DKsL6geGeq6nQI6ZVe6T_YXWTyk2-Hmck4s,11308
 tsadmetrics/__init__.py,sha256=MTWOa43fgOdkMNo5NglCReRnB8hoF0ob2PIvDziCNHw,1575
-tsadmetrics/binary_metrics.py,sha256=vpUczjPPv1GhTDnFL2fNsHnCuZSRmmGQVsj5te2c6Ss,60116
+tsadmetrics/binary_metrics.py,sha256=6GxE3HSiAC9OeDOpP6QFgPwbp-Q37-F3cUdyYcpRrxE,62841
 tsadmetrics/metric_utils.py,sha256=fm8v0X37_AlqWpkcUT9r3680QsjLljrHe2YuXkRLAZ4,10873
-tsadmetrics/non_binary_metrics.py,sha256=yo620BWZIq-OkBqQV7t7ynjGhcuX6QWQ6iq_7eJq9gI,13074
+tsadmetrics/non_binary_metrics.py,sha256=O6AqceHrjCVV1kJPBzXQIgtiu6afzoiJz2biNsxf3_4,13389
 tsadmetrics/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tsadmetrics/utils.py,sha256=15X_RkHdCxhu_-OH8fEm3gRVQ4tTMqCkNaQsQoloEYQ,2361
+tsadmetrics/utils.py,sha256=BqsG4DyP3AffuMFQCJ-Qy4YaDu4IkFudZWYCvyTGvvY,2444
 tsadmetrics/_tsadeval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tsadmetrics/_tsadeval/auc_roc_pr_plot.py,sha256=PHqJUXq2qI248XV9o04D8SsUJgowetaKq0Cu5bYrIAE,12689
 tsadmetrics/_tsadeval/discontinuity_graph.py,sha256=Ci65l_DPi6HTtb8NvQJe1najgGrRuEpOMWvSyi2AeR0,4088
@@ -53,7 +53,7 @@ tsadmetrics/_tsadeval/prts/time_series_metrics/fscore.py,sha256=pJz4iuPyVGNvwsaR
 tsadmetrics/_tsadeval/prts/time_series_metrics/precision.py,sha256=jLkcMg7UNl25SHtZUBGkP-RV8HsvaZCtjakryl7PFWU,3204
 tsadmetrics/_tsadeval/prts/time_series_metrics/precision_recall.py,sha256=OhUJSm_I7VZ_gX_SSg8AYUq3_NW9rMIy7lAVsnOFw4Q,417
 tsadmetrics/_tsadeval/prts/time_series_metrics/recall.py,sha256=LL-0pPer3ymovVRlktaHo5XDzpgiDhWOVfdPOzKR6og,3152
-tsadmetrics-0.1.12.dist-info/METADATA,sha256=cVz915nkQa7ViK8Va6rQlW5Z5U6ABoP47rWQmpMnqaY,831
-tsadmetrics-0.1.12.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
-tsadmetrics-0.1.12.dist-info/top_level.txt,sha256=s2VIr_ePl-WZbYt9FsYbsDGM7J-Qc5cgpwEOeQ3FVpM,31
-tsadmetrics-0.1.12.dist-info/RECORD,,
+tsadmetrics-0.1.14.dist-info/METADATA,sha256=TCFL9Dpv6zwwM_5n2HeCxKgFP-KB4AHYrvCe3rMZMOI,831
+tsadmetrics-0.1.14.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
+tsadmetrics-0.1.14.dist-info/top_level.txt,sha256=s2VIr_ePl-WZbYt9FsYbsDGM7J-Qc5cgpwEOeQ3FVpM,31
+tsadmetrics-0.1.14.dist-info/RECORD,,