make release-tag: Merge branch 'master' into stable

Author: sarahmish

HISTORY.md

@@ -1,5 +1,13 @@
 # History
 
+## 0.1.0 – 2025-10-06
+
+New multivariate Prompter pipeline
+
+* Update ``rolling_window_sequences`` primitives name – [Issue #48](https://github.com/sintel-dev/sigllm/issues/48) by @sarahmish
+* Multivariate prompter pipeline – [Issue #47](https://github.com/sintel-dev/sigllm/issues/47) by @sarahmish
+
+
 ## 0.0.4 – 2025-07-31
 
 New benchmarking suite

pyproject.toml

@@ -22,6 +22,7 @@ dependencies = [
     'pandas>=1.0.0,<2',
     'scikit-learn>=0.22.1,<2',
     'orion-ml>=0.6,<0.8',
+    'ml-stars>=0.2.1,<0.4',
     'openai>=1.46.0',
     'tiktoken>=0.7.0',
     'transformers>=4.44.2',
@@ -113,7 +114,7 @@ namespaces = false
 version = {attr = 'sigllm.__version__'}
 
 [tool.bumpversion]
-current_version = "0.0.4"
+current_version = "0.1.0.dev0"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',

sigllm/__init__.py

@@ -4,7 +4,7 @@
 
 __author__ = 'MIT Data To AI Lab'
 __email__ = '[email protected]'
-__version__ = '0.0.4'
+__version__ = '0.1.0.dev0'
 
 import os
 

sigllm/core.py

@@ -16,7 +16,7 @@
 
 INTERVAL_PRIMITIVE = 'mlstars.custom.timeseries_preprocessing.time_segments_aggregate#1'
 DECIMAL_PRIMITIVE = 'sigllm.primitives.transformation.Float2Scalar#1'
-WINDOW_SIZE_PRIMITIVE = 'sigllm.primitives.forecasting.custom.rolling_window_sequences#1'
+WINDOW_SIZE_PRIMITIVE = 'mlstars.custom.timeseries_preprocessing.rolling_window_sequences#1'
 
 
 class SigLLM(Orion):

sigllm/pipelines/detector/gpt_detector.json

@@ -3,7 +3,7 @@
         "mlstars.custom.timeseries_preprocessing.time_segments_aggregate",
         "sklearn.impute.SimpleImputer",
         "sigllm.primitives.transformation.Float2Scalar",
-        "sigllm.primitives.forecasting.custom.rolling_window_sequences",
+        "mlstars.custom.timeseries_preprocessing.rolling_window_sequences",
         "sigllm.primitives.transformation.format_as_string",
         "sigllm.primitives.forecasting.gpt.GPT",
         "sigllm.primitives.transformation.format_as_integer",
@@ -23,7 +23,7 @@
             "decimal": 2,
             "rescale": true
         },
-        "sigllm.primitives.forecasting.custom.rolling_window_sequences#1": {
+        "mlstars.custom.timeseries_preprocessing.rolling_window_sequences#1": {
             "target_column": 0,
             "window_size": 140,
             "target_size": 1

sigllm/pipelines/detector/mistral_detector.json

@@ -3,7 +3,7 @@
         "mlstars.custom.timeseries_preprocessing.time_segments_aggregate",
         "sklearn.impute.SimpleImputer",
         "sigllm.primitives.transformation.Float2Scalar",
-        "sigllm.primitives.forecasting.custom.rolling_window_sequences",
+        "mlstars.custom.timeseries_preprocessing.rolling_window_sequences",
         "sigllm.primitives.transformation.format_as_string",
         "sigllm.primitives.forecasting.huggingface.HF",
         "sigllm.primitives.transformation.format_as_integer",
@@ -23,7 +23,7 @@
             "decimal": 2,
             "rescale": true
         },
-        "sigllm.primitives.forecasting.custom.rolling_window_sequences#1": {
+        "mlstars.custom.timeseries_preprocessing.rolling_window_sequences#1": {
             "target_column": 0,
             "window_size": 140,
             "target_size": 1

sigllm/pipelines/prompter/mistral_prompter_multivariate_0shot.json

@@ -0,0 +1,68 @@
+{
+    "primitives": [
+        "mlstars.custom.timeseries_preprocessing.time_segments_aggregate",
+        "sklearn.impute.SimpleImputer",
+        "sigllm.primitives.transformation.Float2Scalar",
+        "sigllm.primitives.prompting.timeseries_preprocessing.rolling_window_sequences",
+	    "sigllm.primitives.transformation.format_as_string",
+        "sigllm.primitives.prompting.huggingface.HF",
+        "sigllm.primitives.prompting.anomalies.parse_anomaly_response",
+        "sigllm.primitives.prompting.anomalies.find_anomalies_in_windows",
+        "sigllm.primitives.prompting.anomalies.merge_anomalous_sequences",
+        "sigllm.primitives.prompting.anomalies.format_anomalies"
+    ],
+    "init_params": {
+        "mlstars.custom.timeseries_preprocessing.time_segments_aggregate#1": {
+            "time_column": "timestamp",
+            "interval": 21600,
+            "method": "mean"
+        },
+        "sigllm.primitives.transformation.Float2Scalar#1": {
+            "decimal": 2,
+            "rescale": true
+        },
+        "sigllm.primitives.prompting.timeseries_preprocessing.rolling_window_sequences#1": {
+            "window_size": 100,
+            "step_size": 40
+        },
+        "sigllm.primitives.transformation.format_as_string#1": {
+            "space": false
+        },
+        "sigllm.primitives.prompting.huggingface.HF#1": {
+            "name": "mistralai/Mistral-7B-Instruct-v0.2",
+            "samples": 1,
+            "temp": 0.01
+        },
+        "sigllm.primitives.prompting.anomalies.parse_anomaly_response#1": {
+            "interval": true
+        },
+        "sigllm.primitives.prompting.anomalies.find_anomalies_in_windows#1": {
+            "alpha": 0.4
+        },
+        "sigllm.primitives.prompting.anomalies.merge_anomalous_sequences#1": {
+            "beta": 0.5
+        }
+    },
+    "input_names": {
+        "sigllm.primitives.prompting.huggingface.HF#1": {
+            "X": "X_str"
+        },
+        "sigllm.primitives.prompting.anomalies.parse_anomaly_response#1": {
+            "X": "y_hat"
+        }
+    },
+    "output_names": {
+        "mlstars.custom.timeseries_preprocessing.time_segments_aggregate#1": {
+            "index": "timestamp"
+        },
+        "sigllm.primitives.transformation.format_as_string#1": {
+            "X": "X_str"
+        },
+        "sigllm.primitives.prompting.huggingface.HF#1": {
+            "y": "y_hat"
+        },
+        "sigllm.primitives.prompting.anomalies.parse_anomaly_response#1": {
+            "X": "y"
+        }
+    }
+}

sigllm/primitives/forecasting/custom.py

@@ -17,6 +17,11 @@
                 "name": "X",
                 "type": "ndarray"
             },
+            {
+                "name": "dim",
+                "type": "int",
+                "default": 1
+            },
             {
                 "name": "normal",
                 "type": "ndarray",