multivariate pipeline

Author: sarahmish

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/prompting/anomalies.py

@@ -206,6 +206,7 @@ def format_anomalies(y, timestamp, padding_size=50):
     if len(y) == 0:
         return []
 
+    print(y)
     y = y[y < len(timestamp)].astype(int)
     y = timestamp[y]  # Convert list of indices into list of timestamps
     start, end = timestamp[0], timestamp[-1]

sigllm/primitives/prompting/huggingface_messages.json

@@ -2,6 +2,6 @@
     "system_message": "You are an expert in time series analysis. Your task is to detect anomalies in time series data.",
     "user_message": "Below is a [SEQUENCE], please return the anomalies in that sequence in [RESPONSE]. Only return the numbers. [SEQUENCE]",
     "user_message_unrestricted": "Below is a [SEQUENCE], analyze the following time series and identify any anomalies. If you find anomalies, provide their values in the format [first_anomaly, ..., last_anomaly]. If no anomalies are found, respond with 'no anomalies'. Be concise, do not write code, do not perform any calculations, just give your answers as told.: [SEQUENCE]",
-    "user_message_multivariate": "Below is a multivariate time series of {} dimensions with the following format \"{}\".\nYour job is to detect ranges of anomalies in this time series, in terms of the x-axis coordinates. List one by one in a list.\nFor example, if ranges (incluing two endpoints) [5, 12], [71, 74], and [105, 131], are anomalies, then output \"[[5,12], [71, 74], [105, 131]]\".\nIf no anomalies are found, respond with 'no anomalies'. Be concise, do not write code, do not perform any calculations, just give your answers as told.\n[SEQUENCE]\n",
+    "user_message_multivariate": "Below is a multivariate time series of {} dimensions with the following format \"{}\".\nYour job is to detect ranges of anomalies in this time series, in terms of the x-axis coordinates. List one by one in a list.\nFor example, if ranges (including two endpoints) [5, 12], [71, 74], and [105, 131], are anomalies, then output \"[[5,12], [71, 74], [105, 131]]\".\nIf no anomalies are found, respond with 'no anomalies'. Be concise, do not write code, do not perform any calculations, just give your answers as told.\n[SEQUENCE]\n",
     "one_shot_prefix": "Here is a normal reference of the time series: [NORMAL]"
 }