tsadmetrics 0.1.15__py3-none-any.whl → 0.1.17__py3-none-any.whl

tsadmetrics/utils.py

@@ -1,7 +1,8 @@
 import numpy as np
 import pandas as pd
 import time
-
+import sys
+import tsadmetrics
 def compute_metrics(y_true: np.array,y_pred: np.array, metrics: list, metrics_params: dict, is_anomaly_score = False, verbose = False):
     """
     Computes the specified metrics for the given true and predicted values.
@@ -52,4 +53,72 @@ def compute_metrics(y_true: np.array,y_pred: np.array, metrics: list, metrics_pa
     metrics_df['metric_name'] = results.keys()
     metrics_df['metric_value'] = results.values()
     
-    return metrics_df
+    return metrics_df
+
+
+def compute_metrics_from_file(results_file: str, conf_file: str, output_dir: str = '.'):
+    """
+    Computes metrics based on prediction results from a CSV file and configuration from a JSON file.
+
+    Parameters:
+        results_file (str):
+            Path to CSV file containing y_true and y_pred columns.
+        conf_file (str):
+            Path to JSON configuration file with metrics and parameters.
+
+    Returns:
+        pd.DataFrame: DataFrame with computed metrics.
+    """
+    # Read results data
+    res = pd.read_csv(results_file)
+    y_true = res['y_true'].values
+    y_pred = res['y_pred'].values
+    
+    # Determine if predictions are binary or scores
+    is_anomaly_score = False
+    unique_values = np.unique(y_pred)
+    if not (np.array_equal(unique_values, [0, 1]) or 
+            np.array_equal(unique_values, [0]) or 
+            np.array_equal(unique_values, [1])):
+        is_anomaly_score = True
+        if not np.all((y_pred >= 0) & (y_pred <= 1)):
+            raise ValueError("y_pred must be either binary (0/1) or anomaly scores in range [0, 1]")
+
+    # Read configuration from JSON using pandas
+    try:
+        config_df = pd.read_json(conf_file, orient='records')
+    except ValueError as e:
+        raise ValueError(f"Invalid JSON format in configuration file: {str(e)}")
+
+    # Convert pandas DataFrame to format expected by compute_metrics
+    metrics = []
+    metrics_params = {}
+    
+    for _, row in config_df.iterrows():
+        metric_name = row['name']
+        try:
+            metric_func = getattr(tsadmetrics, metric_name)
+        except AttributeError:
+            raise ValueError(f"Metric function '{metric_name}' not found in tsadmetrics module")
+        
+        metrics.append((metric_name, metric_func))
+        
+        # Handle params (convert from pandas Series to dict if needed)
+        params = row.get('params', {})
+        if pd.notna(params) and params:  # Check for non-empty params
+            if isinstance(params, pd.Series):
+                metrics_params[metric_name] = params.to_dict()
+            else:
+                metrics_params[metric_name] = params
+
+    # Compute metrics
+    metrics_df = compute_metrics(
+        y_true=y_true,
+        y_pred=y_pred,
+        metrics=metrics,
+        metrics_params=metrics_params,
+        is_anomaly_score=is_anomaly_score,
+        verbose=False
+    )
+    metrics_df.to_csv(output_dir+'/computed_metrics.csv', index=False)
+

tsadmetrics/validation.py

@@ -0,0 +1,35 @@
+import numpy as np
+
+def check_gt_binary_array(arr):
+    if len(arr.shape) != 1:
+        raise ValueError("Ground truth input must be a 1D binary array.")
+    if not np.all(np.isin(arr, [0, 1])):
+        raise ValueError("Ground truth input array must contain only binary values (0 or 1).")
+    return True
+
+def check_pred_binary_array(arr):
+    if len(arr.shape) != 1:
+        raise ValueError("Prediction input must be a 1D binary array.")
+    if not np.all(np.isin(arr, [0, 1])):
+        raise ValueError("Prediction input array must contain only binary values (0 or 1).")
+    return True
+def check_same_length(arr1, arr2):
+    if len(arr1) != len(arr2):
+        raise ValueError("Ground truth and prediction arrays must have the same length.")
+    return True
+
+def check_pred_continuous_array(arr):
+    if len(arr.shape) != 1:
+        raise ValueError("Prediction input must be a 1D continuous array.")
+    if not np.all((arr >= 0) & (arr <= 1)):
+        raise ValueError("All values in the array must be in the range [0, 1].")
+    return True
+
+def validate_binary_inputs(y_true, y_pred):
+    check_gt_binary_array(y_true)
+    check_pred_binary_array(y_pred)
+    check_same_length(y_true, y_pred)
+
+def validate_non_binary_inputs(y_true, y_anomaly_scores):
+    check_gt_binary_array(y_true)
+    check_same_length(y_true, y_anomaly_scores)

tsadmetrics-0.1.17.dist-info/METADATA

@@ -0,0 +1,54 @@
+Metadata-Version: 2.1
+Name: tsadmetrics
+Version: 0.1.17
+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
+Author-email: Pedro Rafael Velasco Priego <i12veprp@uco.es>
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: joblib (==1.4.2)
+Requires-Dist: numpy (==1.24.4)
+Requires-Dist: pandas (==2.0.3)
+Requires-Dist: PATE (==0.1.1)
+Requires-Dist: patsy (==0.5.6)
+Requires-Dist: python-dateutil (==2.9.0.post0)
+Requires-Dist: pytz (==2024.1)
+Requires-Dist: scikit-learn (==1.3.2)
+Requires-Dist: scipy (==1.10.1)
+Requires-Dist: six (==1.16.0)
+Requires-Dist: statsmodels (==0.14.1)
+Requires-Dist: threadpoolctl (==3.5.0)
+Requires-Dist: tzdata (==2024.1)
+
+# TSADmetrics - Time Series Anomaly Detection Metrics
+
+**TSADmetrics** is a Python library for evaluating anomaly detection algorithms in time series data. It provides a comprehensive set of binary and non-binary metrics designed specifically for the challenges of anomaly detection in temporal contexts.
+
+## Features
+
+- **Binary Metrics**: Evaluate discrete anomaly predictions (0/1 labels)
+
+- **Non-Binary Metrics**: Assess continuous anomaly scores
+
+- **Efficient Computation**: Compute multiple metrics at once
+
+- **CLI Tool**: Evaluate metrics directly from CSV/JSON files
+
+## Installation
+
+Install TSADmetrics via pip:
+
+```bash
+pip install tsadmetrics
+```
+
+## Documentation
+
+The complete documentation for TSADmetrics is available at:  
+���� [https://tsadmetrics.readthedocs.io/](https://tsadmetrics.readthedocs.io/)
+
+## Acknowledgements
+
+This library is based on the concepts and implementations from:  
+S��rb��, S., & Ruocco, M. (2023). *Navigating the metric maze: a taxonomy of evaluation metrics for anomaly detection in time series*. https://doi.org/10.1007/s10618-023-00988-8

{tsadmetrics-0.1.15.dist-info → tsadmetrics-0.1.17.dist-info}/RECORD

@@ -1,4 +1,6 @@
 docs/conf.py,sha256=UvAyr0jPk75vQyREMEG3TIs96Pk-hslOgLQUpySp2tw,1645
+docs_api/conf.py,sha256=Ba8bUV-53VLgJ93hOesXr1xzLMpXlATnyZYlmyoM85g,2333
+docs_manual/conf.py,sha256=uUY57MH63QsFLhn_W7LIbwMMQO3rcdUxhCAdzx_d0Z0,2331
 entorno/bin/activate_this.py,sha256=45dnJsdtOWIt5LtVSBmBfB8E7AlKcnhnZe9e3WGclak,1199
 entorno/bin/rst2html.py,sha256=h4RydG-iAectsUra0lNFGwB4_1mngxrtPPgQrxUWQ3A,643
 entorno/bin/rst2html4.py,sha256=Xiv3Zb1gk4jT7DYFVlf5w4LJtI5ZI3pW3b1KLxyPS5A,765
@@ -13,14 +15,16 @@ entorno/bin/rst2xetex.py,sha256=spisB81JgqAmMAkjdTaP8awFQS_Zuob9HIcbMi1kOS8,922
 entorno/bin/rst2xml.py,sha256=uoIfpn3prnir2tzqdycsAjOg-OWw663XOK47IeHCZdY,651
 entorno/bin/rstpep2html.py,sha256=sthYQHEgYfj4JqwG45URwVbRAs-HYuwKget7SUwp9fc,719
 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=XK1HSkCwg7lIYN0KHrSNDWSFBxlWfubp6U-2fgdCIrU,63587
-tsadmetrics/metric_utils.py,sha256=fm8v0X37_AlqWpkcUT9r3680QsjLljrHe2YuXkRLAZ4,10873
-tsadmetrics/non_binary_metrics.py,sha256=O6AqceHrjCVV1kJPBzXQIgtiu6afzoiJz2biNsxf3_4,13389
+tests/test_binary.py,sha256=Qt14fP-F-TW6KlPz6X-2DhtFpaHNrODiMA2DI39JrBI,39311
+tests/test_non_binary.py,sha256=jBn3GfBpbK7ktIS9FNIeYi0ob8jkkbMCyCX7-_8LI-k,15755
+tests/test_utils.py,sha256=8Favmlyix1YaAm03XuzMfEjLnq_Ud0YV_6aFwsIMpl8,2192
+tsadmetrics/__init__.py,sha256=BxSqvH0NselzEIZhw4rpnUh6UkzRh0eDpkNvChqWv_8,1604
+tsadmetrics/binary_metrics.py,sha256=PiecIZ2z2B3-uCx1H3KXfLXdSIu8vxY5sUsIb2vmobk,69729
+tsadmetrics/metric_utils.py,sha256=1nuHQp5fc7whPMfJTfWmKb6XmSngoe6p7fdsoP0Vz-I,2876
+tsadmetrics/non_binary_metrics.py,sha256=FsXRMeZIvQsEP5BLT02nW7_yjDnF9wD-h8h-B6eTRVs,14238
 tsadmetrics/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tsadmetrics/utils.py,sha256=BqsG4DyP3AffuMFQCJ-Qy4YaDu4IkFudZWYCvyTGvvY,2444
+tsadmetrics/utils.py,sha256=mu49QEftRI4HEXvjfiE_CnsujgiNd62U9DRWCEvtO9M,4913
+tsadmetrics/validation.py,sha256=fseGfpGhN-3zAMo2WZLxahcOAsOOyBb2RAFRDKB1KI8,1340
 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 +57,10 @@ 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-0.1.15.dist-info/METADATA,sha256=Ks2Kq9EAPqiV8kPwnYUY4Ytzgq4_ig7TwvpcC94Zmjg,831
-tsadmetrics-0.1.15.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
-tsadmetrics-0.1.15.dist-info/top_level.txt,sha256=s2VIr_ePl-WZbYt9FsYbsDGM7J-Qc5cgpwEOeQ3FVpM,31
-tsadmetrics-0.1.15.dist-info/RECORD,,
+tsadmetrics/scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tsadmetrics/scripts/compute_metrics.py,sha256=PwtH6XmpKEWwdY62pMfZGrgIBTIms0z3qVpw5LjnuwE,991
+tsadmetrics-0.1.17.dist-info/METADATA,sha256=Lcjim8NZYuZ-WRBosqpYy_CISaVXF2SOZ7dI-RjoiVI,1936
+tsadmetrics-0.1.17.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
+tsadmetrics-0.1.17.dist-info/entry_points.txt,sha256=fnsO232FxrQC6pmeZnyZ4UaiXyvN1rKxksLKQO9n7q8,81
+tsadmetrics-0.1.17.dist-info/top_level.txt,sha256=jFJiGEaMZwBStgmkeS19H9fyWDDcPDgmNjinjVrh0jk,52
+tsadmetrics-0.1.17.dist-info/RECORD,,

tsadmetrics-0.1.17.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+tsadmetrics-compute = tsadmetrics.scripts.compute_metrics:main

{tsadmetrics-0.1.15.dist-info → tsadmetrics-0.1.17.dist-info}/top_level.txt

@@ -1,4 +1,6 @@
 docs
+docs_api
+docs_manual
 entorno
 tests
 tsadmetrics

tsadmetrics-0.1.15.dist-info/METADATA

@@ -1,23 +0,0 @@
-Metadata-Version: 2.1
-Name: tsadmetrics
-Version: 0.1.15
-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
-Author-email: Pedro Rafael Velasco Priego <i12veprp@uco.es>
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-Requires-Dist: joblib (==1.4.2)
-Requires-Dist: numpy (==1.24.4)
-Requires-Dist: pandas (==2.0.3)
-Requires-Dist: PATE (==0.1.1)
-Requires-Dist: patsy (==0.5.6)
-Requires-Dist: python-dateutil (==2.9.0.post0)
-Requires-Dist: pytz (==2024.1)
-Requires-Dist: scikit-learn (==1.3.2)
-Requires-Dist: scipy (==1.10.1)
-Requires-Dist: six (==1.16.0)
-Requires-Dist: statsmodels (==0.14.1)
-Requires-Dist: threadpoolctl (==3.5.0)
-Requires-Dist: tzdata (==2024.1)
-