From 6ec568ab0c557ecbdc69739e68a502806453bc53 Mon Sep 17 00:00:00 2001
From: Tyler Martin <tyler.martin@nist.gov>
Date: Tue, 4 Mar 2025 19:45:01 -0500
Subject: [PATCH 1/8] [feat] adds reading/writing Pipelines to json

- New _stored_args hidden attribute gathers the passed arguments at runtime
- Modifications to this argument dictionary are transparent to the user and happen automatically
- _stored_args used to create json reprsentations of PipelineOps and json serialization trivially created by iterating Pipeline
- print_code also updated to use _stored_args
---
 AFL/double_agent/Pipeline.py   |  78 +++++++++++++++++------
 AFL/double_agent/PipelineOp.py | 110 ++++++++++++++++++++++++++++++---
 2 files changed, 161 insertions(+), 27 deletions(-)

diff --git a/AFL/double_agent/Pipeline.py b/AFL/double_agent/Pipeline.py
index 2ee273e..7d5eaaf 100644
--- a/AFL/double_agent/Pipeline.py
+++ b/AFL/double_agent/Pipeline.py
@@ -18,6 +18,9 @@
 import re
 from typing import Generator, Optional, List
 import warnings
+import datetime
+import json
+import pathlib
 
 import matplotlib.pyplot as plt
 import networkx as nx
@@ -29,7 +32,6 @@
 from AFL.double_agent.PipelineContext import PipelineContext
 from AFL.double_agent.PipelineOp import PipelineOp
 from AFL.double_agent.util import listify
-from AFL.double_agent.util import extract_parameters
 
 
 class Pipeline(PipelineContext):
@@ -120,29 +122,18 @@ def print(self) -> None:
     def print_code(self) -> None:
         """String representation of approximate code to generate this pipeline
 
-        Run this method to produce a string of Python code that should **approximate**
-        this Pipeline. If all constructor parameters are not stored as class attributes,
-        this method will fail and the code result will need to be edited.
-
-        Warning
-        --------
-        This method is approximate. The code generated by this method may not produce
-        an identical Pipeline to this method. Use with caution.
+        Run this method to produce a string of Python code that should
+        recreate this Pipeline. 
 
         """
 
-        warnings.warn(
-            """Pipeline.emit_code() cannot perfectly infer pipeline code and is not"""
-            """ guaranteed to reproduce the same pipeline. Use with caution.""",
-            stacklevel=2,
-        )
 
         output_string = f"with Pipeline(name = \"{self.name}\") as p:\n"
 
         for op in self:
-            params = extract_parameters(op)
+            args = op._stored_args
             output_string += f"    {type(op).__name__}(\n"
-            for k, v in params.items():
+            for k, v in args.items():
                 if isinstance(v, str):
                     output_string += f'        {k}="{v}",\n'
                 else:
@@ -168,10 +159,57 @@ def clear_outputs(self):
 
     def copy(self) -> Self:
         return copy.deepcopy(self)
+    
+    def write_json(self,filename:str,overwrite=False): 
+        """Write pipeline to disk as a JSON
+
+        Parameters
+        ----------
+        filename: str
+            Filename or filepath to be written
+        """
+
+        if not overwrite and pathlib.Path(filename).exists():
+            raise FileExistsError()
+
+        pipeline_dict = {
+            'name':self.name,
+            'date': datetime.datetime.now().strftime('%m/%d/%y %H:%M:%S-%f'),
+            'ops':[op.to_json() for op in self]
+        }
+
+        with open(filename,'w') as f:
+            json.dump(pipeline_dict,f,indent=1)
+
+    @staticmethod
+    def read_json(filename: str):
+        """Read pipeline from json file on disk
 
-    def write(self, filename: str):
+        Usage
+        -----
+        ```python
+        from AFL.double_agent.Pipeline import Pipeline
+        pipeline1 = Pipeline.read_json('pickled_pipeline.pkl')
+        ````
+        """
+        with open(filename, "r") as f:
+            pipeline_dict = json.load(f)
+
+        pipeline = Pipeline(
+            name=pipeline_dict['name'],
+            ops=[PipelineOp.from_json(op) for op in pipeline_dict['ops']]
+        )
+
+        return pipeline
+
+
+    def write_pkl(self, filename: str):
         """Write pipeline to disk as a pkl
 
+        .. warning::
+            Please use the read_json and write_json methods. The pickle methods
+            are insecure and prone to errors.
+
         Parameters
         ----------
         filename: str
@@ -184,9 +222,13 @@ def write(self, filename: str):
             pickle.dump(pipeline, f)
 
     @staticmethod
-    def read(filename: str):
+    def read_pkl(filename: str):
         """Read pipeline from pickle file on disk
 
+        .. warning::
+            Please use the  `read_json`  and `write_json` methods. The pickle methods
+            are insecure and prone to errors.
+
         Usage
         -----
         ```python
diff --git a/AFL/double_agent/PipelineOp.py b/AFL/double_agent/PipelineOp.py
index 4a2fbe5..d63f9df 100644
--- a/AFL/double_agent/PipelineOp.py
+++ b/AFL/double_agent/PipelineOp.py
@@ -2,6 +2,9 @@
 import warnings
 from abc import ABC, abstractmethod
 from typing import Optional, Dict, List
+import inspect
+import json
+import importlib
 
 import matplotlib.pyplot as plt
 import xarray as xr
@@ -39,19 +42,18 @@ def __init__(self,
                 'No input/output information set for PipelineOp...this is likely an error',
                 stacklevel=2
             )
-
-        if name is None:
-            self.name = 'PipelineOp'
-        else:
-            self.name = name
-
+        
+        self.name = name or 'PipelineOp'
         self.input_variable = input_variable
         self.output_variable = output_variable
         self.input_prefix = input_prefix
         self.output_prefix = output_prefix
-
         self.output: Dict[str, xr.DataArray] = {}
 
+        # variables to exclude when constructing attrs dict for xarray
+        self._banned_from_attrs = ['output', '_banned_from_attrs']
+
+        ## PipelineContext
         try:
             # try to add this object to current pipeline on context stack
             PipelineContext.get_context().append(self)
@@ -59,8 +61,98 @@ def __init__(self,
             # silently continue for those working outside a context manager
             pass
 
-        # variables to exclude when constructing attrs dict for xarray
-        self._banned_from_attrs = ['output', '_banned_from_attrs']
+        ## Gathering Arguments of Most-derived Child Class
+
+        # Retrieve the full stack.
+        stack = inspect.stack()
+        valid_frames = []
+        # Iterate through all frames in the stack.
+        for frame_info in stack:
+            # Look for __init__ functions where 'self' is our instance.
+            if frame_info.function == '__init__' and frame_info.frame.f_locals.get('self') is self:
+                valid_frames.append(frame_info)
+        if valid_frames:
+            # Choose the last __init__ call in the inheritance chain.
+            final_frame = valid_frames[-1].frame
+            args_info = inspect.getargvalues(final_frame)
+        else:
+            # Fallback: use the immediate caller if nothing was found.
+            final_frame = inspect.currentframe().f_back
+            args_info = inspect.getargvalues(final_frame)
+        
+        # Build _stored_args by checking JSON serializability of each constructor argument.
+        stored_args = {}
+        for arg in args_info.args:
+            if arg != "self":
+                value = args_info.locals[arg]
+                try:
+                    json.dumps(value)
+                except (TypeError, OverflowError) as e:
+                    raise TypeError(
+                        f"Constructor argument '{arg}' with value {value!r} of type {type(value).__name__} "
+                        f"is not JSON serializable: {e}"
+                    )
+                stored_args[arg] = value
+        self._stored_args = stored_args
+     
+    def __getattribute__(self, name):
+        # Avoid recursion when accessing _stored_args.
+        if name == '_stored_args':
+            return object.__getattribute__(self, name)
+        
+        stored_args = object.__getattribute__(self, "_stored_args")
+        if name in stored_args:
+            return stored_args[name]
+        return object.__getattribute__(self, name)
+    
+    def __setattr__(self, name, value):
+        if name == "_stored_args":
+            return object.__setattr__(self, name, value)
+        
+        try:
+            stored_args = object.__getattribute__(self, "_stored_args")
+        except AttributeError:
+            stored_args = None
+        
+        if stored_args is not None and name in stored_args:
+            try:
+                json.dumps(value)
+            except (TypeError, OverflowError) as e:
+                raise TypeError(
+                    f"New value for attribute '{name}' with value {value!r} of type {type(value).__name__} "
+                    f"is not JSON serializable: {e}"
+                )
+            stored_args[name] = value
+        else:
+            object.__setattr__(self, name, value)
+    
+    def to_json(self):
+        """
+        Serializes the fully qualified class name and the constructor arguments
+        stored in _stored_args into a JSON string.
+        """
+        cls = self.__class__
+        module = cls.__module__
+        qualname = cls.__qualname__
+        data = {
+            "class": f"{module}.{qualname}",
+            "args": self._stored_args
+        }
+        return data
+
+    @classmethod
+    def from_json(cls, json_data):
+        """
+        Deserializes the JSON string back to an object.
+        Dynamically imports the module, gets the class, and instantiates it
+        using the stored constructor arguments.
+        """
+        fqcn = json_data["class"]  # e.g. "module.ClassName"
+        args = json_data["args"]
+        mod_name, class_name = fqcn.rsplit(".", 1)
+        module = importlib.import_module(mod_name)
+        klass = getattr(module, class_name)
+        return klass(**args)
 
     @abstractmethod
     def calculate(self, dataset: xr.Dataset) -> Self:

From 8bf2d362f0c23a29779245b2e547a7ec39b569d2 Mon Sep 17 00:00:00 2001
From: Tyler Martin <tyler.martin@nist.gov>
Date: Tue, 4 Mar 2025 20:10:17 -0500
Subject: [PATCH 2/8] [feat] adds pipeline reading/writing documentation

---
 AFL/double_agent/Pipeline.py              |   2 +
 docs/source/how-to/index.rst              |   1 +
 docs/source/how-to/saving_pipelines.ipynb | 261 ++++++++++++++++++++++
 3 files changed, 264 insertions(+)
 create mode 100644 docs/source/how-to/saving_pipelines.ipynb

diff --git a/AFL/double_agent/Pipeline.py b/AFL/double_agent/Pipeline.py
index 7d5eaaf..fd5b727 100644
--- a/AFL/double_agent/Pipeline.py
+++ b/AFL/double_agent/Pipeline.py
@@ -181,6 +181,8 @@ def write_json(self,filename:str,overwrite=False):
         with open(filename,'w') as f:
             json.dump(pipeline_dict,f,indent=1)
 
+        print(f'Pipeline successfully written to {filename}.')
+
     @staticmethod
     def read_json(filename: str):
         """Read pipeline from json file on disk
diff --git a/docs/source/how-to/index.rst b/docs/source/how-to/index.rst
index 0248c59..ce264d9 100644
--- a/docs/source/how-to/index.rst
+++ b/docs/source/how-to/index.rst
@@ -9,3 +9,4 @@ Guides for specific tasks
    building_xarray_datasets
    create_pipelineop
    appending
+   saving_pipelines
diff --git a/docs/source/how-to/saving_pipelines.ipynb b/docs/source/how-to/saving_pipelines.ipynb
new file mode 100644
index 0000000..59426f3
--- /dev/null
+++ b/docs/source/how-to/saving_pipelines.ipynb
@@ -0,0 +1,261 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/usnistgov/AFL-agent/blob/main/docs/source/how-to/saving_pipelines.ipynb)\n",
+    "\n",
+    "# Reading and Writing Pipelines \n",
+    "\n",
+    "Its"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Google Colab Setup\n",
+    "\n",
+    "Only uncomment and run the next cell if you are running this notebook in Google Colab or if don't already have the AFL-agent package installed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install git+https://github.com/usnistgov/AFL-agent.git"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Writing A Pipeline\n",
+    "\n",
+    "To begin, let's load the necessary libraries and define a short pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "PipelineOp                               input_variable ---> output_variable\n",
+      "----------                               -----------------------------------\n",
+      "0  ) <SavgolFilter>                      measurement ---> derivative\n",
+      "1  ) <SimilarityMetric>                  derivative ---> similarity\n",
+      "2  ) <SpectralClustering>                similarity ---> labels\n",
+      "\n",
+      "Input Variables\n",
+      "---------------\n",
+      "0) measurement\n",
+      "\n",
+      "Output Variables\n",
+      "----------------\n",
+      "0) labels\n"
+     ]
+    }
+   ],
+   "source": [
+    "from AFL.double_agent import *\n",
+    "\n",
+    "with Pipeline('MyPipeline') as my_important_pipeline:\n",
+    "\n",
+    "        SavgolFilter(\n",
+    "            input_variable='measurement', \n",
+    "            output_variable='derivative', \n",
+    "            dim='x', \n",
+    "            derivative=1\n",
+    "            )\n",
+    "\n",
+    "        Similarity(\n",
+    "            input_variable='derivative', \n",
+    "            output_variable='similarity', \n",
+    "            sample_dim='sample',\n",
+    "            params={'metric': 'laplacian','gamma':1e-4}\n",
+    "            )\n",
+    "    \n",
+    "        SpectralClustering(\n",
+    "            input_variable='similarity',\n",
+    "            output_variable='labels',\n",
+    "            dim='sample',\n",
+    "            params={'n_phases': 2}\n",
+    "            )\n",
+    "\n",
+    "my_important_pipeline.print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now, we can write the pipeline by simply calling the `.write_json()` method"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pipeline successfully written to pipeline.json.\n"
+     ]
+    }
+   ],
+   "source": [
+    "my_important_pipeline.write_json('pipeline.json')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Excellent! Let's take a look at the json file that was written. We can inspect it using the json module"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'MyPipeline',\n",
+       " 'date': '03/04/25 19:59:19-576491',\n",
+       " 'ops': [{'class': 'AFL.double_agent.Preprocessor.SavgolFilter',\n",
+       "   'args': {'input_variable': 'measurement',\n",
+       "    'output_variable': 'derivative',\n",
+       "    'dim': 'x',\n",
+       "    'xlo': None,\n",
+       "    'xhi': None,\n",
+       "    'xlo_isel': None,\n",
+       "    'xhi_isel': None,\n",
+       "    'pedestal': None,\n",
+       "    'npts': 250,\n",
+       "    'derivative': 1,\n",
+       "    'window_length': 31,\n",
+       "    'polyorder': 2,\n",
+       "    'apply_log_scale': True,\n",
+       "    'name': 'SavgolFilter'}},\n",
+       "  {'class': 'AFL.double_agent.PairMetric.Similarity',\n",
+       "   'args': {'input_variable': 'derivative',\n",
+       "    'output_variable': 'similarity',\n",
+       "    'sample_dim': 'sample',\n",
+       "    'params': {'metric': 'laplacian', 'gamma': 0.0001},\n",
+       "    'constrain_same': [],\n",
+       "    'constrain_different': [],\n",
+       "    'name': 'SimilarityMetric'}},\n",
+       "  {'class': 'AFL.double_agent.Labeler.SpectralClustering',\n",
+       "   'args': {'input_variable': 'similarity',\n",
+       "    'output_variable': 'labels',\n",
+       "    'dim': 'sample',\n",
+       "    'params': {'n_phases': 2},\n",
+       "    'name': 'SpectralClustering',\n",
+       "    'use_silhouette': False}}]}"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import json\n",
+    "\n",
+    "with open('pipeline.json','r') as f:\n",
+    "    display(json.load(f))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "With this, we can see that all of the `PipelineOps` are stored in the `ops` keyword with the keyword arguments we specified above. Also included are any default arguments that we didn't explicitly specify. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Reading a Pipeline\n",
+    "\n",
+    "So the next and final step is to load the pipeline from disk."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "PipelineOp                               input_variable ---> output_variable\n",
+      "----------                               -----------------------------------\n",
+      "0  ) <SavgolFilter>                      measurement ---> derivative\n",
+      "1  ) <SimilarityMetric>                  derivative ---> similarity\n",
+      "2  ) <SpectralClustering>                similarity ---> labels\n",
+      "\n",
+      "Input Variables\n",
+      "---------------\n",
+      "0) measurement\n",
+      "\n",
+      "Output Variables\n",
+      "----------------\n",
+      "0) labels\n"
+     ]
+    }
+   ],
+   "source": [
+    "loaded_pipeline = Pipeline.read_json('pipeline.json')\n",
+    "loaded_pipeline.print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Success!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Conclusion"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

From 09baa6c02b26bc3195733f489bb33e0cd28827ff Mon Sep 17 00:00:00 2001
From: Tyler Martin <tyler.martin@nist.gov>
Date: Thu, 6 Mar 2025 00:02:33 -0500
Subject: [PATCH 3/8] [feat] adds prefabricated pipeline utilities

---
 .gitignore                          |   3 +-
 AFL/double_agent/Pipeline.py        |  31 ++--
 AFL/double_agent/prefab/__init__.py | 258 ++++++++++++++++++++++++++++
 3 files changed, 276 insertions(+), 16 deletions(-)
 create mode 100644 AFL/double_agent/prefab/__init__.py

diff --git a/.gitignore b/.gitignore
index cbe0cf5..dedd1c1 100644
--- a/.gitignore
+++ b/.gitignore
@@ -18,4 +18,5 @@ docs/source/reference/_autosummary/
 objects.inv
 _build/
 .doctrees/
-*.mo
\ No newline at end of file
+*.mo
+AFL-agent.code-workspace
diff --git a/AFL/double_agent/Pipeline.py b/AFL/double_agent/Pipeline.py
index fd5b727..5ea7fb1 100644
--- a/AFL/double_agent/Pipeline.py
+++ b/AFL/double_agent/Pipeline.py
@@ -62,17 +62,12 @@ class Pipeline(PipelineContext):
         Edge labels for the pipeline graph visualization
     """
 
-    def __init__(self, name: Optional[str] = None, ops: Optional[List] = None) -> None:
+    def __init__(self, name: Optional[str] = None, ops: Optional[List] = None, description: Optional[str] = None) -> None:
         self.result = None
-        if ops is None:
-            self.ops = []
-        else:
-            self.ops = ops
+        self.ops = ops or []
+        self.description = str(description)
+        self.name = name or "Pipeline"
 
-        if name is None:
-            self.name = "Pipeline"
-        else:
-            self.name = name
 
         # placeholder for networkx graph
         self.graph = None
@@ -160,26 +155,31 @@ def clear_outputs(self):
     def copy(self) -> Self:
         return copy.deepcopy(self)
     
-    def write_json(self,filename:str,overwrite=False): 
+    def write_json(self, filename: str, overwrite=False, description: Optional[str] = None): 
         """Write pipeline to disk as a JSON
 
         Parameters
         ----------
         filename: str
             Filename or filepath to be written
+        overwrite: bool, default=False
+            Whether to overwrite an existing file
+        description: str, optional
+            A descriptive text about the pipeline's purpose and functionality
         """
 
         if not overwrite and pathlib.Path(filename).exists():
             raise FileExistsError()
 
         pipeline_dict = {
-            'name':self.name,
+            'name': self.name,
             'date': datetime.datetime.now().strftime('%m/%d/%y %H:%M:%S-%f'),
-            'ops':[op.to_json() for op in self]
+            'description': str(description) if description is not None else self.description,
+            'ops': [op.to_json() for op in self]
         }
 
-        with open(filename,'w') as f:
-            json.dump(pipeline_dict,f,indent=1)
+        with open(filename, 'w') as f:
+            json.dump(pipeline_dict, f, indent=1)
 
         print(f'Pipeline successfully written to {filename}.')
 
@@ -199,7 +199,8 @@ def read_json(filename: str):
 
         pipeline = Pipeline(
             name=pipeline_dict['name'],
-            ops=[PipelineOp.from_json(op) for op in pipeline_dict['ops']]
+            ops=[PipelineOp.from_json(op) for op in pipeline_dict['ops']],
+            description=pipeline_dict['description']
         )
 
         return pipeline
diff --git a/AFL/double_agent/prefab/__init__.py b/AFL/double_agent/prefab/__init__.py
new file mode 100644
index 0000000..b8d36b3
--- /dev/null
+++ b/AFL/double_agent/prefab/__init__.py
@@ -0,0 +1,258 @@
+"""
+Prefabricated Pipelines module for AFL.double_agent.
+
+This module provides access to prefabricated pipelines that can be used with AFL.double_agent.
+It allows loading, listing, and combining multiple pipelines into a single pipeline.
+"""
+
+import os
+import pathlib
+import warnings
+import json
+from typing import List, Dict, Optional, Union
+
+import xarray as xr
+
+from AFL.double_agent.Pipeline import Pipeline
+
+# Get the path to the prefab directory
+def get_prefab_dir():
+    """
+    Get the path to the prefabricated pipelines directory.
+    
+    Returns
+    -------
+    pathlib.Path
+        Path to the prefab directory.
+    """
+    # The prefab directory is located in AFL/double_agent/prefab
+    module_dir = pathlib.Path(__file__).parent
+    prefab_dir = module_dir
+    
+    if not prefab_dir.exists():
+        warnings.warn(f"Prefab directory not found at {prefab_dir}")
+    
+    return prefab_dir
+
+def list_prefabs(display_table: bool = True):
+    """
+    List all available prefabricated pipelines.
+    
+    Parameters
+    ----------
+    display_table : bool, default=True
+        Whether to display the results in a formatted table with descriptions.
+        If False, returns just the list of prefab names.
+    
+    Returns
+    -------
+    list or None
+        If display_table is False, returns a list of available prefabricated pipeline names.
+        If display_table is True, prints a formatted table and returns None.
+    """
+    prefab_dir = get_prefab_dir()
+    if not prefab_dir.exists():
+        warnings.warn(f"Prefab directory not found at {prefab_dir}")
+        return []
+    
+    prefab_files = list(prefab_dir.glob("*.json"))
+    
+    if not display_table:
+        return [f.stem for f in prefab_files]
+    
+    if not prefab_files:
+        print("No prefabricated pipelines found.")
+        return None
+    
+    # Get descriptions from each prefab file
+    prefabs_info = []
+    max_name_len = 4  # Minimum width for "Name" column
+    max_desc_len = 11  # Minimum width for "Description" column
+    
+    for file_path in prefab_files:
+        try:
+            with open(file_path, 'r') as f:
+                prefab_data = json.load(f)
+            
+            name = file_path.stem
+            description = prefab_data.get('description', 'No description available')
+            
+            # Track maximum lengths for formatting
+            max_name_len = max(max_name_len, len(name))
+            max_desc_len = max(max_desc_len, len(description))
+            
+            prefabs_info.append((name, description))
+        except Exception as e:
+            warnings.warn(f"Error reading prefab {file_path.name}: {str(e)}")
+    
+    # Print formatted table
+    header = f"| {'Name':<{max_name_len}} | {'Description':<{max_desc_len}} |"
+    separator = f"|-{'-'*max_name_len}-|-{'-'*max_desc_len}-|"
+    
+    print("\nAvailable Prefabricated Pipelines:")
+    print(separator)
+    print(header)
+    print(separator)
+    
+    for name, description in sorted(prefabs_info):
+        print(f"| {name:<{max_name_len}} | {description:<{max_desc_len}} |")
+    
+    print(separator)
+    print(f"Total: {len(prefabs_info)} prefabricated pipeline(s)")
+    
+    return None
+
+def load_prefab(name: str) -> Pipeline:
+    """
+    Load a prefabricated pipeline by name.
+    
+    Parameters
+    ----------
+    name : str
+        Name of the prefabricated pipeline to load.
+        
+    Returns
+    -------
+    Pipeline
+        The loaded pipeline.
+        
+    Raises
+    ------
+    FileNotFoundError
+        If the prefabricated pipeline does not exist.
+    """
+    prefab_dir = get_prefab_dir()
+    file_path = prefab_dir / f"{name}.json"
+    
+    if not file_path.exists():
+        raise FileNotFoundError(
+            f"Prefabricated pipeline '{name}' not found at {file_path}. "
+            f"Prefab directory: {prefab_dir}. "
+            f"Available prefabs: {list_prefabs()}"
+        )
+    
+    return Pipeline.read_json(str(file_path))
+
+def combine_prefabs(prefab_names: List[str], new_name: Optional[str] = None) -> Pipeline:
+    """
+    Combine multiple prefabricated pipelines into a single pipeline.
+    
+    Parameters
+    ----------
+    prefab_names : List[str]
+        List of prefabricated pipeline names to combine.
+    new_name : Optional[str], default=None
+        Name for the combined pipeline. If None, a name will be generated from the component pipelines.
+        
+    Returns
+    -------
+    Pipeline
+        The combined pipeline.
+        
+    Raises
+    ------
+    FileNotFoundError
+        If any of the prefabricated pipelines do not exist.
+    ValueError
+        If no prefabricated pipelines are provided.
+    """
+    if not prefab_names:
+        raise ValueError("No prefabricated pipelines provided for combination.")
+    
+    if len(prefab_names) == 1:
+        return load_prefab(prefab_names[0])
+    
+    # Generate a combined name if not provided
+    if new_name is None:
+        new_name = f"Combined_{'_'.join(prefab_names)}"
+    
+    # Load all pipelines
+    pipelines = [load_prefab(name) for name in prefab_names]
+    
+    # Create a new pipeline with the first pipeline's ops
+    combined_pipeline = pipelines[0].copy()
+    combined_pipeline.name = new_name
+    
+    # Add all operations from subsequent pipelines
+    for pipeline in pipelines[1:]:
+        combined_pipeline.extend(pipeline.ops)
+    
+    return combined_pipeline
+
+def save_prefab(pipeline: Pipeline, name: Optional[str] = None, overwrite: bool = False, description: Optional[str] = None) -> str:
+    """
+    Save a pipeline as a prefabricated pipeline.
+    
+    Parameters
+    ----------
+    pipeline : Pipeline
+        The pipeline to save.
+    name : Optional[str], default=None
+        Name to save the pipeline as. If None, uses the pipeline's name.
+    overwrite : bool, default=False
+        Whether to overwrite an existing prefabricated pipeline with the same name.
+    description : Optional[str], default=None
+        A descriptive text about the pipeline's purpose and functionality.
+        If None and pipeline has a description attribute, that will be used.
+        
+    Returns
+    -------
+    str
+        The path to the saved prefabricated pipeline file.
+        
+    Raises
+    ------
+    FileExistsError
+        If a prefabricated pipeline with the given name already exists and overwrite=False.
+    """
+    prefab_dir = get_prefab_dir()
+    
+    # Use the pipeline's name if no name is provided
+    if name is None:
+        name = pipeline.name
+    
+    # Use the pipeline's description if available and none provided
+    if description is None and hasattr(pipeline, 'description'):
+        description = pipeline.description
+    
+    # Ensure valid filename
+    name = name.replace(" ", "_")
+    file_path = prefab_dir / f"{name}.json"
+    
+    # Check if file exists and overwrite is not allowed
+    if file_path.exists() and not overwrite:
+        raise FileExistsError(
+            f"Prefabricated pipeline '{name}' already exists at {file_path}. "
+            f"Use overwrite=True to overwrite."
+        )
+    
+    # Save the pipeline with description
+    pipeline.write_json(str(file_path), overwrite=True, description=description)
+    
+    return str(file_path)
+
+# Define any example prefabs that should be available by default
+def example_prefab1():
+    """
+    Load an example prefabricated pipeline.
+    
+    Returns
+    -------
+    Pipeline
+        An example prefabricated pipeline.
+    """
+    try:
+        return load_prefab("example_prefab")
+    except FileNotFoundError:
+        warnings.warn("Example prefab not found. You may need to create example prefabs.")
+        return Pipeline(name="empty_example")
+
+# Export public functions
+__all__ = [
+    "get_prefab_dir", 
+    "list_prefabs", 
+    "load_prefab", 
+    "combine_prefabs", 
+    "save_prefab", 
+    "example_prefab1"
+] 
\ No newline at end of file

From 2a0479f20db5779f3f0a9403fb526235ff35bb5e Mon Sep 17 00:00:00 2001
From: Tyler Martin <tyler.martin@nist.gov>
Date: Thu, 6 Mar 2025 19:55:42 -0500
Subject: [PATCH 4/8] [refactor] converts transforms to strings in constructor

---
 AFL/double_agent/Preprocessor.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/AFL/double_agent/Preprocessor.py b/AFL/double_agent/Preprocessor.py
index 894c1d7..810b9a7 100644
--- a/AFL/double_agent/Preprocessor.py
+++ b/AFL/double_agent/Preprocessor.py
@@ -742,6 +742,9 @@ def __init__(
         name: str = "SympyTransform",
     ) -> None:
 
+        # must convert to strings for JSON serialization
+        transforms = {k:str(v) for k,v in transforms.items()}
+
         super().__init__(
             name=name, input_variable=input_variable, output_variable=output_variable
         )
@@ -765,6 +768,7 @@ def calculate(self, dataset: xr.Dataset) -> Self:
         # apply transform
         new_comps = xr.Dataset()
         for name, transform in self.transforms.items():
+            transform = sympy.sympify(transform)
             symbols = list(transform.free_symbols)
             lam = sympy.lambdify(symbols, transform)
             new_comps[name] = (

From 630ed07ca69709303782ece90685317ca63c9a26 Mon Sep 17 00:00:00 2001
From: Tyler Martin <tyler.martin@nist.gov>
Date: Thu, 6 Mar 2025 20:57:32 -0500
Subject: [PATCH 5/8] [refactor] changes kernel handling for extrapolators for
 JSON serializability

---
 AFL/double_agent/Extrapolator.py | 64 ++++++++++++++------------------
 1 file changed, 28 insertions(+), 36 deletions(-)

diff --git a/AFL/double_agent/Extrapolator.py b/AFL/double_agent/Extrapolator.py
index 186f386..3e7af4f 100644
--- a/AFL/double_agent/Extrapolator.py
+++ b/AFL/double_agent/Extrapolator.py
@@ -13,7 +13,7 @@
 - Support for different sample and grid dimensions
 """
 
-from typing import List, Optional
+from typing import List
 
 import numpy as np
 import sklearn.gaussian_process  # type: ignore
@@ -260,9 +260,12 @@ class predictions and uncertainty estimates through entropy.
         The `xarray` dimension over the discrete 'samples' in the `feature_input_variable`. This is typically
         a variant of `sample` e.g., `saxs_sample`.
 
-    kernel: Optional[object]
-        A optional sklearn.gaussian_process.kernel to use the classifier. If not provided, will default to
+    kernel: str
+        The name of the sklearn.gaussian_process.kernel to use the classifier. If not provided, will default to
         `Matern`.
+    
+    kernel_kwargs: dict
+        Additional keyword arguments to pass to the sklearn.gaussian_process.kernel
 
     optimizer: str
         The name of the optimizer to use in optimizer the gaussian process parameters
@@ -279,7 +282,8 @@ def __init__(
         grid_variable: str,
         grid_dim: str,
         sample_dim: str,
-        kernel: Optional[object] = None,
+        kernel: str = 'Matern',
+        kernel_kwargs: dict = {'length_scale':1.0, 'nu':1.5},
         optimizer: str = "fmin_l_bfgs_b",
         name: str = "GaussianProcessClassifier",
     ) -> None:
@@ -294,19 +298,11 @@ def __init__(
             grid_dim=grid_dim,
             sample_dim=sample_dim,
         )
-
-        if kernel is None:
-            self.kernel = sklearn.gaussian_process.kernels.Matern(
-                length_scale=1.0, nu=1.5
-            )
-        else:
-            self.kernel = kernel
-
+        self.kernel = kernel
+        self.kernel_kwargs = kernel_kwargs
         self.output_prefix = output_prefix
-        if optimizer is not None:
-            self.optimizer = optimizer
-        else:
-            self.optimizer = None
+        self.optimizer = optimizer 
+
 
     def calculate(self, dataset: xr.Dataset) -> Self:
         """Apply this GP classifier to the supplied dataset.
@@ -341,8 +337,10 @@ def calculate(self, dataset: xr.Dataset) -> Self:
             )
 
         else:
+            kernel  = getattr(sklearn.gaussian_process.kernels, self.kernel)(**self.kernel_kwargs)
+
             clf = sklearn.gaussian_process.GaussianProcessClassifier(
-                kernel=self.kernel, optimizer=self.optimizer
+                kernel=kernel, optimizer=self.optimizer
             ).fit(X.values, y.values)
 
             # entropy approach to classification probabilities
@@ -395,14 +393,14 @@ class GaussianProcessRegressor(Extrapolator):
         The `xarray` dimension over the discrete 'samples' in the `feature_input_variable`. This is typically
         a variant of `sample` e.g., `saxs_sample`.
 
-    predictor_uncertainty_variable: Optional[str]
+    predictor_uncertainty_variable: str | None
         Variable containing uncertainty estimates for the predictor values
 
     optimizer: str
         The name of the optimizer to use in optimizer the gaussian process parameters
 
-    kernel: Optional[object]
-        A optional sklearn.gaussian_process.kernel to use the regressor. If not provided, will default to
+    kernel: str | None
+        The name of the sklearn.gaussian_process.kernel to use the regressor. If not provided, will default to
         `Matern`.
 
     name: str
@@ -422,7 +420,8 @@ def __init__(
         sample_dim,
         predictor_uncertainty_variable=None,
         optimizer="fmin_l_bfgs_b",
-        kernel=None,
+        kernel: str = 'Matern',
+        kernel_kwargs: dict = {'length_scale':1.0, 'nu':1.5},
         name="GaussianProcessRegressor",
         fix_nans=True,
     ) -> None:
@@ -440,19 +439,10 @@ def __init__(
         self.predictor_uncertainty_variable = predictor_uncertainty_variable
         if predictor_uncertainty_variable is not None:
             self.input_variable.append(predictor_uncertainty_variable)
-
-        if kernel is None:
-            self.kernel = sklearn.gaussian_process.kernels.Matern(
-                #length_scale=[0.1], length_scale_bounds=(1e-3, 1e0), nu=1.5
-                length_scale = [0.1], length_scale_bounds = (0.2, 1e0), nu = 1.5
-            )
-        else:
-            self.kernel = kernel
-
-        if optimizer is not None:
-            self.optimizer = optimizer
-        else:
-            self.optimizer = "fmin_l_bfgs_b"
+        
+        self.kernel = kernel
+        self.kernel_kwargs = kernel_kwargs
+        self.optimizer = optimizer 
 
         self.predictor_uncertainty_variable = predictor_uncertainty_variable
         self._banned_from_attrs.append("predictor_uncertainty_variable")
@@ -491,15 +481,17 @@ def calculate(self, dataset: xr.Dataset) -> Self:
             dy = dataset[self.predictor_uncertainty_variable].transpose(
                 self.sample_dim, ...
             )
+            kernel  = getattr(sklearn.gaussian_process.kernels, self.kernel)(**self.kernel_kwargs)
             reg = sklearn.gaussian_process.GaussianProcessRegressor(
-                kernel=self.kernel, alpha=dy.values, optimizer=self.optimizer
+                kernel=kernel, alpha=dy.values, optimizer=self.optimizer
             ).fit(X.values, y.values)
 
             reg_type = "heteroscedastic"
 
         else:
+            kernel  = getattr(sklearn.gaussian_process.kernels, self.kernel)(**self.kernel_kwargs)
             reg = sklearn.gaussian_process.GaussianProcessRegressor(
-                kernel=self.kernel, optimizer=self.optimizer
+                kernel=kernel, optimizer=self.optimizer
             ).fit(X.values, y.values)
             reg_type = "homoscedastic"
 

From d795555bbb6f3c95b1c1dfdaee35d38c89c7b821 Mon Sep 17 00:00:00 2001
From: Tyler Martin <tyler.martin@nist.gov>
Date: Thu, 6 Mar 2025 20:58:14 -0500
Subject: [PATCH 6/8] [feat] adds first prefab pipelines

---
 AFL/double_agent/Preprocessor.py              |  32 ++---
 AFL/double_agent/TensorFlowExtrapolator.py    |  25 ++--
 AFL/double_agent/__init__.py                  |   2 +
 AFL/double_agent/data/__init__.py             |  11 +-
 AFL/double_agent/prefab/__init__.py           |  12 +-
 AFL/double_agent/prefab/find_boundaries.json  | 129 ++++++++++++++++++
 AFL/double_agent/prefab/preprocess.json       | 123 +++++++++++++++++
 .../prefab/similarity_clustering.json         |  35 +++++
 8 files changed, 328 insertions(+), 41 deletions(-)
 create mode 100644 AFL/double_agent/prefab/find_boundaries.json
 create mode 100644 AFL/double_agent/prefab/preprocess.json
 create mode 100644 AFL/double_agent/prefab/similarity_clustering.json

diff --git a/AFL/double_agent/Preprocessor.py b/AFL/double_agent/Preprocessor.py
index 810b9a7..513a54a 100644
--- a/AFL/double_agent/Preprocessor.py
+++ b/AFL/double_agent/Preprocessor.py
@@ -324,14 +324,14 @@ class Standardize(Preprocessor):
         The name of the variable to be inserted into the `xarray.Dataset` by this `PipelineOp`
     dim : str
         The dimension used for calculating the data minimum
-    component_dim : Optional[str], default="component"
+    component_dim : str | None, default="component"
         The dimension for component-wise operations
-    scale_variable : Optional[str], default=None
+    scale_variable : str | None, default=None
         If specified, the min/max of this data variable in the supplied `xarray.Dataset` will be used to scale the
         data rather than min/max of the `input_variable` or the supplied `min_val` or `max_val`
-    min_val : Optional[Number], default=None
+    min_val : Number | None, default=None
         Value used to scale the data minimum
-    max_val : Optional[Number], default=None
+    max_val : Number | None, default=None
         Value used to scale the data maximum
     name : str, default="Standardize"
         The name to use when added to a Pipeline
@@ -342,10 +342,10 @@ def __init__(
         input_variable: str,
         output_variable: str,
         dim: str,
-        component_dim: Optional[str] = "component",
-        scale_variable: Optional[str] = None,
-        min_val: Optional[Number] = None,
-        max_val: Optional[Number] = None,
+        component_dim: str | None = "component",
+        scale_variable: str | None = None,
+        min_val: Number | None = None,
+        max_val: Number | None = None,
         name: str = "Standardize",
     ) -> None:
         super().__init__(
@@ -401,14 +401,14 @@ class Destandardize(Preprocessor):
         The name of the variable to be inserted into the `xarray.Dataset` by this `PipelineOp`
     dim : str
         The dimension used for calculating the data minimum
-    component_dim : Optional[str], default="component"
+    component_dim : str | None, default="component"
         The dimension for component-wise operations
-    scale_variable : Optional[str], default=None
+    scale_variable : str | None, default=None
         If specified, the min/max of this data variable in the supplied `xarray.Dataset` will be used to scale the
         data rather than min/max of the `input_variable` or the supplied `min_val` or `max_val`
-    min_val : Optional[Number], default=None
+    min_val : Number | None, default=None
         Value used to scale the data minimum
-    max_val : Optional[Number], default=None
+    max_val : Number | None, default=None
         Value used to scale the data maximum
     name : str, default="Destandardize"
         The name to use when added to a Pipeline
@@ -419,10 +419,10 @@ def __init__(
         input_variable: str,
         output_variable: str,
         dim: str,
-        component_dim: Optional[str] = "component",
-        scale_variable: Optional[str] = None,
-        min_val: Optional[Number] = None,
-        max_val: Optional[Number] = None,
+        component_dim: str | None = "component",
+        scale_variable: str | None = None,
+        min_val: Number | None = None,
+        max_val: Number | None = None,
         name: str = "Destandardize",
     ) -> None:
 
diff --git a/AFL/double_agent/TensorFlowExtrapolator.py b/AFL/double_agent/TensorFlowExtrapolator.py
index 3dc8e63..185142c 100644
--- a/AFL/double_agent/TensorFlowExtrapolator.py
+++ b/AFL/double_agent/TensorFlowExtrapolator.py
@@ -4,7 +4,7 @@
 This file segments all extapolators that require tensorflow.
 """
 
-from typing import List, Optional
+from typing import List
 from typing_extensions import Self
 
 import numpy as np
@@ -114,7 +114,8 @@ def __init__(
         grid_dim: str,
         sample_dim: str,
         optimize: bool = True,
-        kernel: Optional[gpflow.kernels.Kernel] = None,
+        kernel: str = 'Matern32',
+        kernel_kwargs: dict = {'lengthscales':0.1, 'variance':0.1},
         name: str = "TFGaussianProcessClassifier",
     ) -> None:
         """
@@ -141,9 +142,12 @@ def __init__(
             The `xarray` dimension over the discrete 'samples' in the `feature_input_variable`. This is typically
             a variant of `sample` e.g., `saxs_sample`.
 
-        kernel: Optional[object]
-            A optional sklearn.gaussian_process.kernel to use the classifier. If not provided, will default to
-            `Matern`.
+        kernel: str | None
+            The name of the sklearn.gaussian_process.kernel to use the classifier. If not provided, will default to
+            `Matern32`.
+        
+        kernel_kwargs: dict | None
+            Additional keyword arguments to pass to the sklearn.gaussian_process.kernel
 
         name: str
             The name to use when added to a Pipeline. This name is used when calling Pipeline.search()
@@ -161,12 +165,8 @@ def __init__(
             optimize=optimize,
         )
 
-        if kernel is None:
-            self.kernel: gpflow.kernels.Kernel = gpflow.kernels.Matern32(
-                variance=0.1, lengthscales=0.1
-            )
-        else:
-            self.kernel = kernel
+        self.kernel = kernel
+        self.kernel_kwargs = kernel_kwargs
 
         self.output_prefix = output_prefix
 
@@ -191,9 +191,10 @@ def calculate(self, dataset: xr.Dataset) -> Self:
 
             invlink = gpflow.likelihoods.RobustMax(n_classes)
             likelihood = gpflow.likelihoods.MultiClass(n_classes, invlink=invlink)
+            kernel = getattr(gpflow.kernels, self.kernel)(**self.kernel_kwargs)
             model = gpflow.models.VGP(
                 data=data,
-                kernel=self.kernel,
+                kernel=kernel,
                 likelihood=likelihood,
                 num_latent_gps=n_classes,
             )
diff --git a/AFL/double_agent/__init__.py b/AFL/double_agent/__init__.py
index c360f76..829f01a 100644
--- a/AFL/double_agent/__init__.py
+++ b/AFL/double_agent/__init__.py
@@ -7,6 +7,8 @@
 from .Generator import *
 from .plotting import *
 from .Boundary import *
+from .prefab import *
+from .data import *
 
 import os
 import subprocess
diff --git a/AFL/double_agent/data/__init__.py b/AFL/double_agent/data/__init__.py
index 0984dc9..79fae98 100644
--- a/AFL/double_agent/data/__init__.py
+++ b/AFL/double_agent/data/__init__.py
@@ -6,13 +6,12 @@
 
 import os
 import pathlib
-import importlib.resources
 import warnings
 
 import xarray as xr
 
 # Get the path to the data directory
-def get_data_dir():
+def get_data_dir() -> pathlib.Path:
     """
     Get the path to the data directory.
     
@@ -23,14 +22,14 @@ def get_data_dir():
     """
     # The data directory is now located in AFL/double_agent/data
     module_dir = pathlib.Path(__file__).parent
-    data_dir = module_dir#.parent / "data"
+    data_dir = module_dir
     
     if not data_dir.exists():
         warnings.warn(f"Data directory not found at {data_dir}")
     
     return data_dir
 
-def list_datasets():
+def list_datasets() -> list[str]:
     """
     List all available datasets.
     
@@ -46,7 +45,7 @@ def list_datasets():
     
     return [f.stem for f in data_dir.glob("*.nc")]
 
-def load_dataset(name):
+def load_dataset(name: str) -> xr.Dataset:
     """
     Load a dataset by name.
     
@@ -78,7 +77,7 @@ def load_dataset(name):
     return xr.open_dataset(file_path)
 
 # Define specific dataset loaders
-def example_dataset1():
+def example_dataset1() -> xr.Dataset:
     """
     Load the example dataset.
     
diff --git a/AFL/double_agent/prefab/__init__.py b/AFL/double_agent/prefab/__init__.py
index b8d36b3..0830e13 100644
--- a/AFL/double_agent/prefab/__init__.py
+++ b/AFL/double_agent/prefab/__init__.py
@@ -11,8 +11,6 @@
 import json
 from typing import List, Dict, Optional, Union
 
-import xarray as xr
-
 from AFL.double_agent.Pipeline import Pipeline
 
 # Get the path to the prefab directory
@@ -133,7 +131,7 @@ def load_prefab(name: str) -> Pipeline:
     
     return Pipeline.read_json(str(file_path))
 
-def combine_prefabs(prefab_names: List[str], new_name: Optional[str] = None) -> Pipeline:
+def combine_prefabs(prefab_names: List[str], new_name: str | None = None) -> Pipeline:
     """
     Combine multiple prefabricated pipelines into a single pipeline.
     
@@ -141,7 +139,7 @@ def combine_prefabs(prefab_names: List[str], new_name: Optional[str] = None) ->
     ----------
     prefab_names : List[str]
         List of prefabricated pipeline names to combine.
-    new_name : Optional[str], default=None
+    new_name : str | None, default=None
         Name for the combined pipeline. If None, a name will be generated from the component pipelines.
         
     Returns
@@ -179,7 +177,7 @@ def combine_prefabs(prefab_names: List[str], new_name: Optional[str] = None) ->
     
     return combined_pipeline
 
-def save_prefab(pipeline: Pipeline, name: Optional[str] = None, overwrite: bool = False, description: Optional[str] = None) -> str:
+def save_prefab(pipeline: Pipeline, name: str | None = None, overwrite: bool = False, description: str | None = None) -> str:
     """
     Save a pipeline as a prefabricated pipeline.
     
@@ -187,11 +185,11 @@ def save_prefab(pipeline: Pipeline, name: Optional[str] = None, overwrite: bool
     ----------
     pipeline : Pipeline
         The pipeline to save.
-    name : Optional[str], default=None
+    name : str | None, default=None
         Name to save the pipeline as. If None, uses the pipeline's name.
     overwrite : bool, default=False
         Whether to overwrite an existing prefabricated pipeline with the same name.
-    description : Optional[str], default=None
+    description : str | None, default=None
         A descriptive text about the pipeline's purpose and functionality.
         If None and pipeline has a description attribute, that will be used.
         
diff --git a/AFL/double_agent/prefab/find_boundaries.json b/AFL/double_agent/prefab/find_boundaries.json
new file mode 100644
index 0000000..f81b37b
--- /dev/null
+++ b/AFL/double_agent/prefab/find_boundaries.json
@@ -0,0 +1,129 @@
+{
+ "name": "find_boundaries",
+ "date": "03/06/25 20:30:14-992001",
+ "description": "A simlarity-clustering-classification pipeline for finding boundaries in measurement data",
+ "ops": [
+  {
+   "class": "AFL.double_agent.Preprocessor.Standardize",
+   "args": {
+    "input_variable": "composition",
+    "output_variable": "normalized_composition",
+    "dim": "sample",
+    "component_dim": "component",
+    "scale_variable": null,
+    "min_val": {
+     "A": 0.0,
+     "B": 0.0
+    },
+    "max_val": {
+     "A": 10.0,
+     "B": 25.0
+    },
+    "name": "Standardize"
+   }
+  },
+  {
+   "class": "AFL.double_agent.Preprocessor.Standardize",
+   "args": {
+    "input_variable": "composition_grid",
+    "output_variable": "normalized_composition_grid",
+    "dim": "grid",
+    "component_dim": "component",
+    "scale_variable": null,
+    "min_val": {
+     "A": 0.0,
+     "B": 0.0
+    },
+    "max_val": {
+     "A": 10.0,
+     "B": 25.0
+    },
+    "name": "Standardize"
+   }
+  },
+  {
+   "class": "AFL.double_agent.Preprocessor.SavgolFilter",
+   "args": {
+    "input_variable": "measurement",
+    "output_variable": "derivative",
+    "dim": "x",
+    "xlo": null,
+    "xhi": null,
+    "xlo_isel": null,
+    "xhi_isel": null,
+    "pedestal": null,
+    "npts": 250,
+    "derivative": 1,
+    "window_length": 31,
+    "polyorder": 2,
+    "apply_log_scale": true,
+    "name": "SavgolFilter"
+   }
+  },
+  {
+   "class": "AFL.double_agent.PairMetric.Similarity",
+   "args": {
+    "input_variable": "derivative",
+    "output_variable": "similarity",
+    "sample_dim": "sample",
+    "params": {
+     "metric": "laplacian",
+     "gamma": 0.0001
+    },
+    "constrain_same": [],
+    "constrain_different": [],
+    "name": "SimilarityMetric"
+   }
+  },
+  {
+   "class": "AFL.double_agent.Labeler.SpectralClustering",
+   "args": {
+    "input_variable": "similarity",
+    "output_variable": "labels",
+    "dim": "sample",
+    "params": {
+     "n_phases": 2
+    },
+    "name": "SpectralClustering",
+    "use_silhouette": false
+   }
+  },
+  {
+   "class": "AFL.double_agent.Extrapolator.GaussianProcessClassifier",
+   "args": {
+    "feature_input_variable": "normalized_composition",
+    "predictor_input_variable": "labels",
+    "output_prefix": "extrap",
+    "grid_variable": "normalized_composition_grid",
+    "grid_dim": "grid",
+    "sample_dim": "sample",
+    "kernel": "Matern",
+    "kernel_kwargs": {
+     "length_scale": 1.0,
+     "nu": 1.5
+    },
+    "optimizer": "fmin_l_bfgs_b",
+    "name": "GaussianProcessClassifier"
+   }
+  },
+  {
+   "class": "AFL.double_agent.AcquisitionFunction.MaxValueAF",
+   "args": {
+    "input_variables": [
+     "extrap_entropy"
+    ],
+    "grid_variable": "composition_grid",
+    "grid_dim": "grid",
+    "combine_coeffs": null,
+    "output_prefix": null,
+    "output_variable": "next_sample",
+    "decision_rtol": 0.05,
+    "excluded_comps_variables": null,
+    "excluded_comps_dim": null,
+    "exclusion_radius": 0.001,
+    "count": 1,
+    "name": "MaxValueAF"
+   }
+  }
+ ]
+}
\ No newline at end of file
diff --git a/AFL/double_agent/prefab/preprocess.json b/AFL/double_agent/prefab/preprocess.json
new file mode 100644
index 0000000..a1c422f
--- /dev/null
+++ b/AFL/double_agent/prefab/preprocess.json
@@ -0,0 +1,123 @@
+{
+ "name": "preprocess",
+ "date": "03/06/25 20:55:30-351053",
+ "description": "A pipeline that generates a Cartesian grid, normalizes data, and calculates derivatives using Savgol filter",
+ "ops": [
+  {
+   "class": "AFL.double_agent.Generator.CartesianGrid",
+   "args": {
+    "output_variable": "composition_grid",
+    "grid_spec": {
+     "A": {
+      "min": 0.0,
+      "max": 10.0,
+      "steps": 50
+     },
+     "B": {
+      "min": 0.0,
+      "max": 25.0,
+      "steps": 50
+     }
+    },
+    "sample_dim": "grid",
+    "component_dim": "component",
+    "name": "CartesianGridGenerator"
+   }
+  },
+  {
+   "class": "AFL.double_agent.Preprocessor.Standardize",
+   "args": {
+    "input_variable": "composition_grid",
+    "output_variable": "normalized_composition_grid",
+    "dim": "grid",
+    "component_dim": "component",
+    "scale_variable": null,
+    "min_val": {
+     "A": 0.0,
+     "B": 0.0
+    },
+    "max_val": {
+     "A": 10.0,
+     "B": 25.0
+    },
+    "name": "Standardize"
+   }
+  },
+  {
+   "class": "AFL.double_agent.Preprocessor.Standardize",
+   "args": {
+    "input_variable": "composition",
+    "output_variable": "normalized_composition",
+    "dim": "sample",
+    "component_dim": "component",
+    "scale_variable": null,
+    "min_val": {
+     "A": 0.0,
+     "B": 0.0
+    },
+    "max_val": {
+     "A": 10.0,
+     "B": 25.0
+    },
+    "name": "Standardize"
+   }
+  },
+  {
+   "class": "AFL.double_agent.Preprocessor.SavgolFilter",
+   "args": {
+    "input_variable": "measurement",
+    "output_variable": "measurement_derivative0",
+    "dim": "q",
+    "xlo": null,
+    "xhi": null,
+    "xlo_isel": null,
+    "xhi_isel": null,
+    "pedestal": null,
+    "npts": 250,
+    "derivative": 0,
+    "window_length": 31,
+    "polyorder": 2,
+    "apply_log_scale": true,
+    "name": "SavgolFilter"
+   }
+  },
+  {
+   "class": "AFL.double_agent.Preprocessor.SavgolFilter",
+   "args": {
+    "input_variable": "measurement",
+    "output_variable": "measurement_derivative1",
+    "dim": "q",
+    "xlo": null,
+    "xhi": null,
+    "xlo_isel": null,
+    "xhi_isel": null,
+    "pedestal": null,
+    "npts": 250,
+    "derivative": 1,
+    "window_length": 31,
+    "polyorder": 2,
+    "apply_log_scale": true,
+    "name": "SavgolFilter"
+   }
+  },
+  {
+   "class": "AFL.double_agent.Preprocessor.SavgolFilter",
+   "args": {
+    "input_variable": "measurement",
+    "output_variable": "measurement_derivative2",
+    "dim": "q",
+    "xlo": null,
+    "xhi": null,
+    "xlo_isel": null,
+    "xhi_isel": null,
+    "pedestal": null,
+    "npts": 250,
+    "derivative": 2,
+    "window_length": 31,
+    "polyorder": 2,
+    "apply_log_scale": true,
+    "name": "SavgolFilter"
+   }
+  }
+ ]
+}
\ No newline at end of file
diff --git a/AFL/double_agent/prefab/similarity_clustering.json b/AFL/double_agent/prefab/similarity_clustering.json
new file mode 100644
index 0000000..56153d4
--- /dev/null
+++ b/AFL/double_agent/prefab/similarity_clustering.json
@@ -0,0 +1,35 @@
+{
+ "name": "similarity_clustering",
+ "date": "03/06/25 20:38:57-760847",
+ "description": "A simlarity-clustering pipeline for clustering measurements into groups",
+ "ops": [
+  {
+   "class": "AFL.double_agent.PairMetric.Similarity",
+   "args": {
+    "input_variable": "measurement",
+    "output_variable": "similarity",
+    "sample_dim": "sample",
+    "params": {
+     "metric": "laplacian",
+     "gamma": 0.0001
+    },
+    "constrain_same": [],
+    "constrain_different": [],
+    "name": "SimilarityMetric"
+   }
+  },
+  {
+   "class": "AFL.double_agent.Labeler.SpectralClustering",
+   "args": {
+    "input_variable": "similarity",
+    "output_variable": "labels",
+    "dim": "sample",
+    "params": {
+     "n_phases": 2
+    },
+    "name": "SpectralClustering",
+    "use_silhouette": false
+   }
+  }
+ ]
+}
\ No newline at end of file

From f33816534b4233314c7537448b3146c4f94a85fc Mon Sep 17 00:00:00 2001
From: Tyler Martin <tyler.martin@nist.gov>
Date: Fri, 7 Mar 2025 23:44:54 -0500
Subject: [PATCH 7/8] [feat] print_code() not prints into a Jupyter Notebook
 cell

---
 AFL/double_agent/Pipeline.py | 65 ++++++++++++++++++++++++------------
 1 file changed, 44 insertions(+), 21 deletions(-)

diff --git a/AFL/double_agent/Pipeline.py b/AFL/double_agent/Pipeline.py
index 5ea7fb1..8549076 100644
--- a/AFL/double_agent/Pipeline.py
+++ b/AFL/double_agent/Pipeline.py
@@ -37,19 +37,19 @@
 class Pipeline(PipelineContext):
     """
     Container class for defining and executing computational workflows.
-    
+
     The Pipeline class serves as a framework for organizing and running sequences of
     operations (PipelineOps) on data. Each operation in the pipeline takes input data,
     performs a specific transformation, and produces output data that can be used by
     subsequent operations.
-    
+
     Parameters
     ----------
     name : Optional[str], default=None
         Name of the pipeline. If None, defaults to "Pipeline".
     ops : Optional[List], default=None
         List of PipelineOp objects to initialize the pipeline with.
-        
+
     Attributes
     ----------
     result : Any
@@ -62,13 +62,17 @@ class Pipeline(PipelineContext):
         Edge labels for the pipeline graph visualization
     """
 
-    def __init__(self, name: Optional[str] = None, ops: Optional[List] = None, description: Optional[str] = None) -> None:
+    def __init__(
+        self,
+        name: Optional[str] = None,
+        ops: Optional[List] = None,
+        description: Optional[str] = None,
+    ) -> None:
         self.result = None
         self.ops = ops or []
         self.description = str(description)
         self.name = name or "Pipeline"
 
-
         # placeholder for networkx graph
         self.graph = None
         self.graph_edge_labels = None
@@ -118,12 +122,11 @@ def print_code(self) -> None:
         """String representation of approximate code to generate this pipeline
 
         Run this method to produce a string of Python code that should
-        recreate this Pipeline. 
+        recreate this Pipeline.
 
         """
 
-
-        output_string = f"with Pipeline(name = \"{self.name}\") as p:\n"
+        output_string = f'with Pipeline(name = "{self.name}") as p:\n'
 
         for op in self:
             args = op._stored_args
@@ -135,7 +138,24 @@ def print_code(self) -> None:
                     output_string += f"        {k}={v},\n"
             output_string += f"    )\n\n"
 
-        print(output_string)
+        try:
+            shell = get_ipython().__class__.__name__
+            if shell == "ZMQInteractiveShell":
+                # Create IPython magic for creating executable code
+                ip = get_ipython()
+
+                # First display the code with syntax highlighting for visibility
+                from IPython.display import display, Code
+
+                # display(Code(output_string, language="python"))
+
+                # Define a temporary magic to create a new cell with the code
+                ip.set_next_input(output_string)
+                print("Pipeline code has been prepared in a new cell below.")
+            else:
+                print(output_string)
+        except NameError:
+            print(output_string)
 
     def append(self, op: PipelineOp) -> Self:
         """Mirrors the behavior of python lists"""
@@ -154,8 +174,10 @@ def clear_outputs(self):
 
     def copy(self) -> Self:
         return copy.deepcopy(self)
-    
-    def write_json(self, filename: str, overwrite=False, description: Optional[str] = None): 
+
+    def write_json(
+        self, filename: str, overwrite=False, description: Optional[str] = None
+    ):
         """Write pipeline to disk as a JSON
 
         Parameters
@@ -172,16 +194,18 @@ def write_json(self, filename: str, overwrite=False, description: Optional[str]
             raise FileExistsError()
 
         pipeline_dict = {
-            'name': self.name,
-            'date': datetime.datetime.now().strftime('%m/%d/%y %H:%M:%S-%f'),
-            'description': str(description) if description is not None else self.description,
-            'ops': [op.to_json() for op in self]
+            "name": self.name,
+            "date": datetime.datetime.now().strftime("%m/%d/%y %H:%M:%S-%f"),
+            "description": (
+                str(description) if description is not None else self.description
+            ),
+            "ops": [op.to_json() for op in self],
         }
 
-        with open(filename, 'w') as f:
+        with open(filename, "w") as f:
             json.dump(pipeline_dict, f, indent=1)
 
-        print(f'Pipeline successfully written to {filename}.')
+        print(f"Pipeline successfully written to {filename}.")
 
     @staticmethod
     def read_json(filename: str):
@@ -198,14 +222,13 @@ def read_json(filename: str):
             pipeline_dict = json.load(f)
 
         pipeline = Pipeline(
-            name=pipeline_dict['name'],
-            ops=[PipelineOp.from_json(op) for op in pipeline_dict['ops']],
-            description=pipeline_dict['description']
+            name=pipeline_dict["name"],
+            ops=[PipelineOp.from_json(op) for op in pipeline_dict["ops"]],
+            description=pipeline_dict["description"],
         )
 
         return pipeline
 
-
     def write_pkl(self, filename: str):
         """Write pipeline to disk as a pkl
 

From e49747a37d07f04eea8ce30e9e6565900485502f Mon Sep 17 00:00:00 2001
From: Tyler Martin <tyler.martin@nist.gov>
Date: Sat, 8 Mar 2025 00:03:47 -0500
Subject: [PATCH 8/8] [docs] adds tutorial for using prefab pipelines

---
 AFL/double_agent/PipelineOp.py           |  117 +-
 AFL/double_agent/data/__init__.py        |   29 +-
 docs/source/tutorials/index.rst          |    3 +-
 docs/source/tutorials/using_prefab.ipynb | 1502 ++++++++++++++++++++++
 4 files changed, 1587 insertions(+), 64 deletions(-)
 create mode 100644 docs/source/tutorials/using_prefab.ipynb

diff --git a/AFL/double_agent/PipelineOp.py b/AFL/double_agent/PipelineOp.py
index d63f9df..a5a52e3 100644
--- a/AFL/double_agent/PipelineOp.py
+++ b/AFL/double_agent/PipelineOp.py
@@ -30,20 +30,25 @@ class PipelineOp(ABC):
         Prefix for output variables when using pattern matching
     """
 
-    def __init__(self,
-                 name: Optional[str] | List[str] = None,
-                 input_variable: Optional[str] | List[str] = None,
-                 output_variable: Optional[str] | List[str] = None,
-                 input_prefix: Optional[str] | List[str] = None,
-                 output_prefix: Optional[str] | List[str] = None):
-
-        if all(x is None for x in [input_variable, output_variable, input_prefix, output_prefix]):
+    def __init__(
+        self,
+        name: Optional[str] | List[str] = None,
+        input_variable: Optional[str] | List[str] = None,
+        output_variable: Optional[str] | List[str] = None,
+        input_prefix: Optional[str] | List[str] = None,
+        output_prefix: Optional[str] | List[str] = None,
+    ):
+
+        if all(
+            x is None
+            for x in [input_variable, output_variable, input_prefix, output_prefix]
+        ):
             warnings.warn(
-                'No input/output information set for PipelineOp...this is likely an error',
-                stacklevel=2
+                "No input/output information set for PipelineOp...this is likely an error",
+                stacklevel=2,
             )
-        
-        self.name = name or 'PipelineOp'
+
+        self.name = name or "PipelineOp"
         self.input_variable = input_variable
         self.output_variable = output_variable
         self.input_prefix = input_prefix
@@ -51,7 +56,7 @@ def __init__(self,
         self.output: Dict[str, xr.DataArray] = {}
 
         # variables to exclude when constructing attrs dict for xarray
-        self._banned_from_attrs = ['output', '_banned_from_attrs']
+        self._banned_from_attrs = ["output", "_banned_from_attrs"]
 
         ## PipelineContext
         try:
@@ -69,7 +74,10 @@ def __init__(self,
         # Iterate through all frames in the stack.
         for frame_info in stack:
             # Look for __init__ functions where 'self' is our instance.
-            if frame_info.function == '__init__' and frame_info.frame.f_locals.get('self') is self:
+            if (
+                frame_info.function == "__init__"
+                and frame_info.frame.f_locals.get("self") is self
+            ):
                 valid_frames.append(frame_info)
         if valid_frames:
             # Choose the last __init__ call in the inheritance chain.
@@ -79,7 +87,7 @@ def __init__(self,
             # Fallback: use the immediate caller if nothing was found.
             final_frame = inspect.currentframe().f_back
             args_info = inspect.getargvalues(final_frame)
-        
+
         # Build _stored_args by checking JSON serializability of each constructor argument.
         stored_args = {}
         for arg in args_info.args:
@@ -94,26 +102,30 @@ def __init__(self,
                     )
                 stored_args[arg] = value
         self._stored_args = stored_args
-     
+
     def __getattribute__(self, name):
-        # Avoid recursion when accessing _stored_args.
-        if name == '_stored_args':
+        if name == "_stored_args":
+            try:
+                return object.__getattribute__(self, name)
+            except AttributeError:
+                return {}
+        try:
+            stored_args = object.__getattribute__(self, "_stored_args")
+        except AttributeError:
             return object.__getattribute__(self, name)
-        
-        stored_args = object.__getattribute__(self, "_stored_args")
         if name in stored_args:
             return stored_args[name]
         return object.__getattribute__(self, name)
-    
+
     def __setattr__(self, name, value):
         if name == "_stored_args":
             return object.__setattr__(self, name, value)
-        
+
         try:
             stored_args = object.__getattribute__(self, "_stored_args")
         except AttributeError:
             stored_args = None
-        
+
         if stored_args is not None and name in stored_args:
             try:
                 json.dumps(value)
@@ -125,7 +137,7 @@ def __setattr__(self, name, value):
             stored_args[name] = value
         else:
             object.__setattr__(self, name, value)
-    
+
     def to_json(self):
         """
         Serializes the fully qualified class name and the constructor arguments
@@ -134,10 +146,7 @@ def to_json(self):
         cls = self.__class__
         module = cls.__module__
         qualname = cls.__qualname__
-        data = {
-            "class": f"{module}.{qualname}",
-            "args": self._stored_args
-        }
+        data = {"class": f"{module}.{qualname}", "args": self._stored_args}
         return data
 
     @classmethod
@@ -159,7 +168,7 @@ def calculate(self, dataset: xr.Dataset) -> Self:
         pass
 
     def __repr__(self) -> str:
-        return f'<PipelineOp:{self.name}>'
+        return f"<PipelineOp:{self.name}>"
 
     def copy(self) -> Self:
         return copy.deepcopy(self)
@@ -167,7 +176,7 @@ def copy(self) -> Self:
     def _prefix_output(self, variable_name: str) -> str:
         prefixed_variable = copy.deepcopy(variable_name)
         if self.output_prefix is not None:
-            prefixed_variable = f'{self.output_prefix}_{prefixed_variable}'
+            prefixed_variable = f"{self.output_prefix}_{prefixed_variable}"
         return prefixed_variable
 
     def _get_attrs(self) -> Dict:
@@ -178,7 +187,7 @@ def _get_attrs(self) -> Dict:
             except KeyError:
                 pass
 
-        #sanitize
+        # sanitize
         for key in output_dict.keys():
             output_dict[key] = str(output_dict[key])
             # if output_dict[key] is None:
@@ -190,16 +199,20 @@ def _get_attrs(self) -> Dict:
 
     def _get_variable(self, dataset: xr.Dataset) -> xr.DataArray:
         if self.input_variable is None and self.input_prefix is None:
-            raise ValueError((
-                """Can't get variable for {self.name} without input_variable """
-                """or input_prefix specified in constructor """
-            ))
+            raise ValueError(
+                (
+                    """Can't get variable for {self.name} without input_variable """
+                    """or input_prefix specified in constructor """
+                )
+            )
 
         if self.input_variable is not None and self.input_prefix is not None:
-            raise ValueError((
-                """Both input_variable and input_prefix were specified in constructor. """
-                """Only one should be specified to avoid ambiguous operation"""
-            ))
+            raise ValueError(
+                (
+                    """Both input_variable and input_prefix were specified in constructor. """
+                    """Only one should be specified to avoid ambiguous operation"""
+                )
+            )
 
         if self.input_variable is not None:
             output = dataset[self.input_variable].copy()
@@ -229,10 +242,12 @@ def add_to_dataset(self, dataset, copy_dataset=True):
                 value.attrs.update(self._get_attrs())
                 dataset1[name] = value
             else:
-                raise ValueError((
-                    f"""Items in output dictionary of PipelineOp {self.name} must be xr.Dataset or xr.DataArray """
-                    f"""Found variable named {name} of type {type(value)}."""
-                ))
+                raise ValueError(
+                    (
+                        f"""Items in output dictionary of PipelineOp {self.name} must be xr.Dataset or xr.DataArray """
+                        f"""Found variable named {name} of type {type(value)}."""
+                    )
+                )
         return dataset1
 
     def add_to_tiled(self, tiled_data):
@@ -242,20 +257,20 @@ def add_to_tiled(self, tiled_data):
         # for name, dataarray in self.output.items():
         #     tiled_data.add_array(name, value.values)
 
-    def plot(self,**mpl_kwargs) -> plt.Figure:
+    def plot(self, **mpl_kwargs) -> plt.Figure:
         n = len(self.output)
-        if n>0:
-            fig, axes = plt.subplots(n,1,figsize=(8,n*4))
-            if n>1:
+        if n > 0:
+            fig, axes = plt.subplots(n, 1, figsize=(8, n * 4))
+            if n > 1:
                 axes = list(axes.flatten())
             else:
                 axes = [axes]
 
-            for i,(name,data) in enumerate(self.output.items()):
-                if 'sample' in data.dims:
-                    data = data.plot(hue='sample',ax=axes[i],**mpl_kwargs)
+            for i, (name, data) in enumerate(self.output.items()):
+                if "sample" in data.dims:
+                    data = data.plot(hue="sample", ax=axes[i], **mpl_kwargs)
                 else:
-                    data.plot(ax=axes[i],**mpl_kwargs)
+                    data.plot(ax=axes[i], **mpl_kwargs)
                 axes[i].set(title=name)
             return fig
         else:
diff --git a/AFL/double_agent/data/__init__.py b/AFL/double_agent/data/__init__.py
index 79fae98..e4853e8 100644
--- a/AFL/double_agent/data/__init__.py
+++ b/AFL/double_agent/data/__init__.py
@@ -10,11 +10,12 @@
 
 import xarray as xr
 
+
 # Get the path to the data directory
 def get_data_dir() -> pathlib.Path:
     """
     Get the path to the data directory.
-    
+
     Returns
     -------
     pathlib.Path
@@ -23,16 +24,17 @@ def get_data_dir() -> pathlib.Path:
     # The data directory is now located in AFL/double_agent/data
     module_dir = pathlib.Path(__file__).parent
     data_dir = module_dir
-    
+
     if not data_dir.exists():
         warnings.warn(f"Data directory not found at {data_dir}")
-    
+
     return data_dir
 
+
 def list_datasets() -> list[str]:
     """
     List all available datasets.
-    
+
     Returns
     -------
     list
@@ -42,23 +44,24 @@ def list_datasets() -> list[str]:
     if not data_dir.exists():
         warnings.warn(f"Data directory not found at {data_dir}")
         return []
-    
+
     return [f.stem for f in data_dir.glob("*.nc")]
 
+
 def load_dataset(name: str) -> xr.Dataset:
     """
     Load a dataset by name.
-    
+
     Parameters
     ----------
     name : str
         Name of the dataset to load.
-        
+
     Returns
     -------
     xarray.Dataset
         The loaded dataset.
-        
+
     Raises
     ------
     FileNotFoundError
@@ -66,21 +69,22 @@ def load_dataset(name: str) -> xr.Dataset:
     """
     data_dir = get_data_dir()
     file_path = data_dir / f"{name}.nc"
-    
+
     if not file_path.exists():
         raise FileNotFoundError(
             f"Dataset '{name}' not found at {file_path}. "
             f"Data directory: {data_dir}. "
             f"Available datasets: {list_datasets()}"
         )
-    
+
     return xr.open_dataset(file_path)
 
+
 # Define specific dataset loaders
 def example_dataset1() -> xr.Dataset:
     """
     Load the example dataset.
-    
+
     Returns
     -------
     xarray.Dataset
@@ -88,5 +92,6 @@ def example_dataset1() -> xr.Dataset:
     """
     return load_dataset("example_dataset")
 
+
 # Add all datasets as module-level variables
-__all__ = ["load_dataset", "list_datasets", "example_dataset1"] 
\ No newline at end of file
+__all__ = ["load_dataset", "list_datasets", "example_dataset1"]
diff --git a/docs/source/tutorials/index.rst b/docs/source/tutorials/index.rst
index a19c97d..bce27da 100644
--- a/docs/source/tutorials/index.rst
+++ b/docs/source/tutorials/index.rst
@@ -9,5 +9,6 @@ Step-by-step guides for beginners to use AFL-agent
    installation
    quickstart
    building_pipelines
+   interactive
    using_datasets
-   interactive
\ No newline at end of file
+   using_prefab
\ No newline at end of file
diff --git a/docs/source/tutorials/using_prefab.ipynb b/docs/source/tutorials/using_prefab.ipynb
new file mode 100644
index 0000000..ad7d184
--- /dev/null
+++ b/docs/source/tutorials/using_prefab.ipynb
@@ -0,0 +1,1502 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "341bc47b",
+   "metadata": {},
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/usnistgov/AFL-agent/blob/main/docs/source/tutorials/using_prefab.ipynb)\n",
+    "\n",
+    "# Using Prefabricated Pipelines\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "94aae7f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "df5b7fd4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import required libraries\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "from AFL.double_agent import *\n",
+    "from AFL.double_agent.data import example_dataset1\n",
+    "from AFL.double_agent.prefab import load_prefab, list_prefabs, combine_prefabs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "573d1b1d",
+   "metadata": {},
+   "source": [
+    "Introduction\n",
+    "-----------\n",
+    "\n",
+    "Prefabricated pipelines (prefabs) are pre-configured pipelines that can be easily loaded and used in your projects. \n",
+    "This tutorial will guide you through the process of loading and using prefabricated pipelines from the ``AFL.double_agent.prefab`` module.\n",
+    "\n",
+    "Prefabricated pipelines are particularly useful when:\n",
+    "\n",
+    "* You have common processing steps that you use frequently\n",
+    "* You want to share pipeline configurations with colleagues\n",
+    "* You want to create building blocks that can be combined into more complex pipelines\n",
+    "\n",
+    "In this tutorial, we'll:\n",
+    "\n",
+    "1. Load an example dataset\n",
+    "2. Load a prefabricated pipeline \n",
+    "3. Inspect the pipeline\n",
+    "4. Customize the pipeline to work with our dataset\n",
+    "5. Execute the pipeline and analyze the results\n",
+    "\n",
+    "Let's get started!\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3b97422d",
+   "metadata": {},
+   "source": [
+    "## Google Colab Setup\n",
+    "\n",
+    "Only uncomment and run the next cell if you are running this notebook in Google Colab or if don't already have the AFL-agent package installed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "26dfcff9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install git+https://github.com/usnistgov/AFL-agent.git"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "34e6a733",
+   "metadata": {},
+   "source": [
+    "\n",
+    "## Loading an Example Dataset\n",
+    "\n",
+    "First, let's load an example dataset from the ``AFL.double_agent.data`` module:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "76b65e22",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div><svg style=\"position: absolute; width: 0; height: 0; overflow: hidden\">\n",
+       "<defs>\n",
+       "<symbol id=\"icon-database\" viewBox=\"0 0 32 32\">\n",
+       "<path d=\"M16 0c-8.837 0-16 2.239-16 5v4c0 2.761 7.163 5 16 5s16-2.239 16-5v-4c0-2.761-7.163-5-16-5z\"></path>\n",
+       "<path d=\"M16 17c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
+       "<path d=\"M16 26c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
+       "</symbol>\n",
+       "<symbol id=\"icon-file-text2\" viewBox=\"0 0 32 32\">\n",
+       "<path d=\"M28.681 7.159c-0.694-0.947-1.662-2.053-2.724-3.116s-2.169-2.030-3.116-2.724c-1.612-1.182-2.393-1.319-2.841-1.319h-15.5c-1.378 0-2.5 1.121-2.5 2.5v27c0 1.378 1.122 2.5 2.5 2.5h23c1.378 0 2.5-1.122 2.5-2.5v-19.5c0-0.448-0.137-1.23-1.319-2.841zM24.543 5.457c0.959 0.959 1.712 1.825 2.268 2.543h-4.811v-4.811c0.718 0.556 1.584 1.309 2.543 2.268zM28 29.5c0 0.271-0.229 0.5-0.5 0.5h-23c-0.271 0-0.5-0.229-0.5-0.5v-27c0-0.271 0.229-0.5 0.5-0.5 0 0 15.499-0 15.5 0v7c0 0.552 0.448 1 1 1h7v19.5z\"></path>\n",
+       "<path d=\"M23 26h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "<path d=\"M23 22h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "<path d=\"M23 18h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "</symbol>\n",
+       "</defs>\n",
+       "</svg>\n",
+       "<style>/* CSS stylesheet for displaying xarray objects in jupyterlab.\n",
+       " *\n",
+       " */\n",
+       "\n",
+       ":root {\n",
+       "  --xr-font-color0: var(--jp-content-font-color0, rgba(0, 0, 0, 1));\n",
+       "  --xr-font-color2: var(--jp-content-font-color2, rgba(0, 0, 0, 0.54));\n",
+       "  --xr-font-color3: var(--jp-content-font-color3, rgba(0, 0, 0, 0.38));\n",
+       "  --xr-border-color: var(--jp-border-color2, #e0e0e0);\n",
+       "  --xr-disabled-color: var(--jp-layout-color3, #bdbdbd);\n",
+       "  --xr-background-color: var(--jp-layout-color0, white);\n",
+       "  --xr-background-color-row-even: var(--jp-layout-color1, white);\n",
+       "  --xr-background-color-row-odd: var(--jp-layout-color2, #eeeeee);\n",
+       "}\n",
+       "\n",
+       "html[theme=\"dark\"],\n",
+       "html[data-theme=\"dark\"],\n",
+       "body[data-theme=\"dark\"],\n",
+       "body.vscode-dark {\n",
+       "  --xr-font-color0: rgba(255, 255, 255, 1);\n",
+       "  --xr-font-color2: rgba(255, 255, 255, 0.54);\n",
+       "  --xr-font-color3: rgba(255, 255, 255, 0.38);\n",
+       "  --xr-border-color: #1f1f1f;\n",
+       "  --xr-disabled-color: #515151;\n",
+       "  --xr-background-color: #111111;\n",
+       "  --xr-background-color-row-even: #111111;\n",
+       "  --xr-background-color-row-odd: #313131;\n",
+       "}\n",
+       "\n",
+       ".xr-wrap {\n",
+       "  display: block !important;\n",
+       "  min-width: 300px;\n",
+       "  max-width: 700px;\n",
+       "}\n",
+       "\n",
+       ".xr-text-repr-fallback {\n",
+       "  /* fallback to plain text repr when CSS is not injected (untrusted notebook) */\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-header {\n",
+       "  padding-top: 6px;\n",
+       "  padding-bottom: 6px;\n",
+       "  margin-bottom: 4px;\n",
+       "  border-bottom: solid 1px var(--xr-border-color);\n",
+       "}\n",
+       "\n",
+       ".xr-header > div,\n",
+       ".xr-header > ul {\n",
+       "  display: inline;\n",
+       "  margin-top: 0;\n",
+       "  margin-bottom: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-obj-type,\n",
+       ".xr-array-name {\n",
+       "  margin-left: 2px;\n",
+       "  margin-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-obj-type {\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-sections {\n",
+       "  padding-left: 0 !important;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 150px auto auto 1fr 0 20px 0 20px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input {\n",
+       "  display: inline-block;\n",
+       "  opacity: 0;\n",
+       "  height: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input + label {\n",
+       "  color: var(--xr-disabled-color);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input:enabled + label {\n",
+       "  cursor: pointer;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input:focus + label {\n",
+       "  border: 2px solid var(--xr-font-color0);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input:enabled + label:hover {\n",
+       "  color: var(--xr-font-color0);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary {\n",
+       "  grid-column: 1;\n",
+       "  color: var(--xr-font-color2);\n",
+       "  font-weight: 500;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary > span {\n",
+       "  display: inline-block;\n",
+       "  padding-left: 0.5em;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:disabled + label {\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in + label:before {\n",
+       "  display: inline-block;\n",
+       "  content: \"►\";\n",
+       "  font-size: 11px;\n",
+       "  width: 15px;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:disabled + label:before {\n",
+       "  color: var(--xr-disabled-color);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked + label:before {\n",
+       "  content: \"▼\";\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked + label > span {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary,\n",
+       ".xr-section-inline-details {\n",
+       "  padding-top: 4px;\n",
+       "  padding-bottom: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-inline-details {\n",
+       "  grid-column: 2 / -1;\n",
+       "}\n",
+       "\n",
+       ".xr-section-details {\n",
+       "  display: none;\n",
+       "  grid-column: 1 / -1;\n",
+       "  margin-bottom: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked ~ .xr-section-details {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-array-wrap {\n",
+       "  grid-column: 1 / -1;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 20px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-array-wrap > label {\n",
+       "  grid-column: 1;\n",
+       "  vertical-align: top;\n",
+       "}\n",
+       "\n",
+       ".xr-preview {\n",
+       "  color: var(--xr-font-color3);\n",
+       "}\n",
+       "\n",
+       ".xr-array-preview,\n",
+       ".xr-array-data {\n",
+       "  padding: 0 5px !important;\n",
+       "  grid-column: 2;\n",
+       "}\n",
+       "\n",
+       ".xr-array-data,\n",
+       ".xr-array-in:checked ~ .xr-array-preview {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-array-in:checked ~ .xr-array-data,\n",
+       ".xr-array-preview {\n",
+       "  display: inline-block;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list {\n",
+       "  display: inline-block !important;\n",
+       "  list-style: none;\n",
+       "  padding: 0 !important;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list li {\n",
+       "  display: inline-block;\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list:before {\n",
+       "  content: \"(\";\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list:after {\n",
+       "  content: \")\";\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list li:not(:last-child):after {\n",
+       "  content: \",\";\n",
+       "  padding-right: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-has-index {\n",
+       "  font-weight: bold;\n",
+       "}\n",
+       "\n",
+       ".xr-var-list,\n",
+       ".xr-var-item {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-var-item > div,\n",
+       ".xr-var-item label,\n",
+       ".xr-var-item > .xr-var-name span {\n",
+       "  background-color: var(--xr-background-color-row-even);\n",
+       "  margin-bottom: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-var-item > .xr-var-name:hover span {\n",
+       "  padding-right: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-list > li:nth-child(odd) > div,\n",
+       ".xr-var-list > li:nth-child(odd) > label,\n",
+       ".xr-var-list > li:nth-child(odd) > .xr-var-name span {\n",
+       "  background-color: var(--xr-background-color-row-odd);\n",
+       "}\n",
+       "\n",
+       ".xr-var-name {\n",
+       "  grid-column: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-var-dims {\n",
+       "  grid-column: 2;\n",
+       "}\n",
+       "\n",
+       ".xr-var-dtype {\n",
+       "  grid-column: 3;\n",
+       "  text-align: right;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-var-preview {\n",
+       "  grid-column: 4;\n",
+       "}\n",
+       "\n",
+       ".xr-index-preview {\n",
+       "  grid-column: 2 / 5;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-var-name,\n",
+       ".xr-var-dims,\n",
+       ".xr-var-dtype,\n",
+       ".xr-preview,\n",
+       ".xr-attrs dt {\n",
+       "  white-space: nowrap;\n",
+       "  overflow: hidden;\n",
+       "  text-overflow: ellipsis;\n",
+       "  padding-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-name:hover,\n",
+       ".xr-var-dims:hover,\n",
+       ".xr-var-dtype:hover,\n",
+       ".xr-attrs dt:hover {\n",
+       "  overflow: visible;\n",
+       "  width: auto;\n",
+       "  z-index: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs,\n",
+       ".xr-var-data,\n",
+       ".xr-index-data {\n",
+       "  display: none;\n",
+       "  background-color: var(--xr-background-color) !important;\n",
+       "  padding-bottom: 5px !important;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs-in:checked ~ .xr-var-attrs,\n",
+       ".xr-var-data-in:checked ~ .xr-var-data,\n",
+       ".xr-index-data-in:checked ~ .xr-index-data {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       ".xr-var-data > table {\n",
+       "  float: right;\n",
+       "}\n",
+       "\n",
+       ".xr-var-name span,\n",
+       ".xr-var-data,\n",
+       ".xr-index-name div,\n",
+       ".xr-index-data,\n",
+       ".xr-attrs {\n",
+       "  padding-left: 25px !important;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs,\n",
+       ".xr-var-attrs,\n",
+       ".xr-var-data,\n",
+       ".xr-index-data {\n",
+       "  grid-column: 1 / -1;\n",
+       "}\n",
+       "\n",
+       "dl.xr-attrs {\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 125px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt,\n",
+       ".xr-attrs dd {\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "  float: left;\n",
+       "  padding-right: 10px;\n",
+       "  width: auto;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt {\n",
+       "  font-weight: normal;\n",
+       "  grid-column: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt:hover span {\n",
+       "  display: inline-block;\n",
+       "  background: var(--xr-background-color);\n",
+       "  padding-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dd {\n",
+       "  grid-column: 2;\n",
+       "  white-space: pre-wrap;\n",
+       "  word-break: break-all;\n",
+       "}\n",
+       "\n",
+       ".xr-icon-database,\n",
+       ".xr-icon-file-text2,\n",
+       ".xr-no-icon {\n",
+       "  display: inline-block;\n",
+       "  vertical-align: middle;\n",
+       "  width: 1em;\n",
+       "  height: 1.5em !important;\n",
+       "  stroke-width: 0;\n",
+       "  stroke: currentColor;\n",
+       "  fill: currentColor;\n",
+       "}\n",
+       "</style><pre class='xr-text-repr-fallback'>&lt;xarray.Dataset&gt; Size: 164kB\n",
+       "Dimensions:              (sample: 100, component: 2, x: 150, grid: 2500)\n",
+       "Coordinates:\n",
+       "  * component            (component) &lt;U1 8B &#x27;A&#x27; &#x27;B&#x27;\n",
+       "  * x                    (x) float64 1kB 0.001 0.001047 0.001097 ... 0.9547 1.0\n",
+       "Dimensions without coordinates: sample, grid\n",
+       "Data variables:\n",
+       "    composition          (sample, component) float64 2kB ...\n",
+       "    ground_truth_labels  (sample) int64 800B ...\n",
+       "    measurement          (sample, x) float64 120kB ...\n",
+       "    composition_grid     (grid, component) float64 40kB ...</pre><div class='xr-wrap' style='display:none'><div class='xr-header'><div class='xr-obj-type'>xarray.Dataset</div></div><ul class='xr-sections'><li class='xr-section-item'><input id='section-ed317fc3-f51a-443d-8c7b-c72023f4160e' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-ed317fc3-f51a-443d-8c7b-c72023f4160e' class='xr-section-summary'  title='Expand/collapse section'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span>sample</span>: 100</li><li><span class='xr-has-index'>component</span>: 2</li><li><span class='xr-has-index'>x</span>: 150</li><li><span>grid</span>: 2500</li></ul></div><div class='xr-section-details'></div></li><li class='xr-section-item'><input id='section-2a4b3a5a-aa8f-4aac-abc4-77319289d74d' class='xr-section-summary-in' type='checkbox'  checked><label for='section-2a4b3a5a-aa8f-4aac-abc4-77319289d74d' class='xr-section-summary' >Coordinates: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>component</span></div><div class='xr-var-dims'>(component)</div><div class='xr-var-dtype'>&lt;U1</div><div class='xr-var-preview xr-preview'>&#x27;A&#x27; &#x27;B&#x27;</div><input id='attrs-00746974-2bd2-4867-b879-9f93e16b5cef' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-00746974-2bd2-4867-b879-9f93e16b5cef' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4ef005af-523c-41f5-b045-5c1718fe48f1' class='xr-var-data-in' type='checkbox'><label for='data-4ef005af-523c-41f5-b045-5c1718fe48f1' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;A&#x27;, &#x27;B&#x27;], dtype=&#x27;&lt;U1&#x27;)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>x</span></div><div class='xr-var-dims'>(x)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>0.001 0.001047 ... 0.9547 1.0</div><input id='attrs-6a0650e5-3259-4a64-ad54-c9d53a166950' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-6a0650e5-3259-4a64-ad54-c9d53a166950' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-b990d1b1-07eb-4847-a7d9-c3dc975c4155' class='xr-var-data-in' type='checkbox'><label for='data-b990d1b1-07eb-4847-a7d9-c3dc975c4155' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0.001   , 0.001047, 0.001097, 0.001149, 0.001204, 0.001261, 0.001321,\n",
+       "       0.001383, 0.001449, 0.001518, 0.00159 , 0.001665, 0.001744, 0.001827,\n",
+       "       0.001914, 0.002005, 0.0021  , 0.002199, 0.002304, 0.002413, 0.002527,\n",
+       "       0.002647, 0.002773, 0.002905, 0.003042, 0.003187, 0.003338, 0.003496,\n",
+       "       0.003662, 0.003836, 0.004018, 0.004209, 0.004409, 0.004618, 0.004837,\n",
+       "       0.005066, 0.005307, 0.005559, 0.005822, 0.006099, 0.006388, 0.006691,\n",
+       "       0.007009, 0.007341, 0.00769 , 0.008055, 0.008437, 0.008837, 0.009256,\n",
+       "       0.009696, 0.010156, 0.010638, 0.011142, 0.011671, 0.012225, 0.012805,\n",
+       "       0.013413, 0.014049, 0.014716, 0.015414, 0.016146, 0.016912, 0.017714,\n",
+       "       0.018555, 0.019435, 0.020358, 0.021324, 0.022335, 0.023395, 0.024505,\n",
+       "       0.025668, 0.026886, 0.028162, 0.029498, 0.030898, 0.032364, 0.0339  ,\n",
+       "       0.035509, 0.037194, 0.038959, 0.040807, 0.042744, 0.044772, 0.046897,\n",
+       "       0.049122, 0.051453, 0.053894, 0.056452, 0.059131, 0.061936, 0.064875,\n",
+       "       0.067954, 0.071179, 0.074556, 0.078094, 0.0818  , 0.085681, 0.089747,\n",
+       "       0.094006, 0.098467, 0.103139, 0.108033, 0.11316 , 0.118529, 0.124154,\n",
+       "       0.130045, 0.136216, 0.14268 , 0.14945 , 0.156542, 0.16397 , 0.171751,\n",
+       "       0.179901, 0.188438, 0.197379, 0.206746, 0.216556, 0.226832, 0.237596,\n",
+       "       0.24887 , 0.26068 , 0.27305 , 0.286006, 0.299578, 0.313794, 0.328684,\n",
+       "       0.344281, 0.360618, 0.37773 , 0.395654, 0.414429, 0.434094, 0.454693,\n",
+       "       0.476269, 0.498869, 0.522542, 0.547337, 0.57331 , 0.600514, 0.62901 ,\n",
+       "       0.658858, 0.690122, 0.72287 , 0.757172, 0.793102, 0.830736, 0.870156,\n",
+       "       0.911447, 0.954697, 1.      ])</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-4a8192df-c233-4e85-a3f1-df487205003e' class='xr-section-summary-in' type='checkbox'  checked><label for='section-4a8192df-c233-4e85-a3f1-df487205003e' class='xr-section-summary' >Data variables: <span>(4)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>composition</span></div><div class='xr-var-dims'>(sample, component)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-cb0e0e9e-6386-497b-8ec5-15dcd3548a46' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-cb0e0e9e-6386-497b-8ec5-15dcd3548a46' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-894f0b65-3185-4e16-b78b-50e6d86b1dcd' class='xr-var-data-in' type='checkbox'><label for='data-894f0b65-3185-4e16-b78b-50e6d86b1dcd' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>[200 values with dtype=float64]</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>ground_truth_labels</span></div><div class='xr-var-dims'>(sample)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-c69ded51-2a1a-4d22-988d-9a0e67ddc448' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-c69ded51-2a1a-4d22-988d-9a0e67ddc448' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-09d7e5d4-e794-4b0a-9c46-d2203b444644' class='xr-var-data-in' type='checkbox'><label for='data-09d7e5d4-e794-4b0a-9c46-d2203b444644' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>[100 values with dtype=int64]</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>measurement</span></div><div class='xr-var-dims'>(sample, x)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-e6801502-3dc4-4bc6-a147-128199e5f469' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-e6801502-3dc4-4bc6-a147-128199e5f469' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-0442785a-c278-4513-a510-545bba706793' class='xr-var-data-in' type='checkbox'><label for='data-0442785a-c278-4513-a510-545bba706793' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>[15000 values with dtype=float64]</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>composition_grid</span></div><div class='xr-var-dims'>(grid, component)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-e193bb06-4be6-4520-a7e4-ceaaac5b75eb' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-e193bb06-4be6-4520-a7e4-ceaaac5b75eb' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-3a05cfbb-e659-482c-b9dc-0e26444f5a7f' class='xr-var-data-in' type='checkbox'><label for='data-3a05cfbb-e659-482c-b9dc-0e26444f5a7f' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>[5000 values with dtype=float64]</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-5a082f3c-368b-43dc-ac58-c86781fc6a26' class='xr-section-summary-in' type='checkbox'  ><label for='section-5a082f3c-368b-43dc-ac58-c86781fc6a26' class='xr-section-summary' >Indexes: <span>(2)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-index-name'><div>component</div></div><div class='xr-index-preview'>PandasIndex</div><input type='checkbox' disabled/><label></label><input id='index-984b7d98-e41e-4180-a292-ef05c5d5ca68' class='xr-index-data-in' type='checkbox'/><label for='index-984b7d98-e41e-4180-a292-ef05c5d5ca68' title='Show/Hide index repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-index-data'><pre>PandasIndex(Index([&#x27;A&#x27;, &#x27;B&#x27;], dtype=&#x27;object&#x27;, name=&#x27;component&#x27;))</pre></div></li><li class='xr-var-item'><div class='xr-index-name'><div>x</div></div><div class='xr-index-preview'>PandasIndex</div><input type='checkbox' disabled/><label></label><input id='index-f0833801-582a-4291-9fdd-bb72e01385a7' class='xr-index-data-in' type='checkbox'/><label for='index-f0833801-582a-4291-9fdd-bb72e01385a7' title='Show/Hide index repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-index-data'><pre>PandasIndex(Index([                0.001, 0.0010474522360006332, 0.0010971561867027272,\n",
+       "       0.0011492187010036998, 0.0012037516980200685, 0.0012608724076806808,\n",
+       "        0.001320703622736631, 0.0013833739627296209,  0.001449018150486198,\n",
+       "       0.0015177773017322714,\n",
+       "       ...\n",
+       "          0.6588581861506815,    0.6901224802908528,    0.7228703350949566,\n",
+       "            0.75717214883374,    0.7931016603333051,    0.8307361074919352,\n",
+       "          0.8701563933188907,    0.9114472598521185,    0.9546974703287516,\n",
+       "                         1.0],\n",
+       "      dtype=&#x27;float64&#x27;, name=&#x27;x&#x27;, length=150))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-1c597ec0-607b-45dc-b0e9-834db46d289c' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-1c597ec0-607b-45dc-b0e9-834db46d289c' class='xr-section-summary'  title='Expand/collapse section'>Attributes: <span>(0)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'></dl></div></li></ul></div></div>"
+      ],
+      "text/plain": [
+       "<xarray.Dataset> Size: 164kB\n",
+       "Dimensions:              (sample: 100, component: 2, x: 150, grid: 2500)\n",
+       "Coordinates:\n",
+       "  * component            (component) <U1 8B 'A' 'B'\n",
+       "  * x                    (x) float64 1kB 0.001 0.001047 0.001097 ... 0.9547 1.0\n",
+       "Dimensions without coordinates: sample, grid\n",
+       "Data variables:\n",
+       "    composition          (sample, component) float64 2kB ...\n",
+       "    ground_truth_labels  (sample) int64 800B ...\n",
+       "    measurement          (sample, x) float64 120kB ...\n",
+       "    composition_grid     (grid, component) float64 40kB ..."
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Load the example dataset\n",
+    "dataset = example_dataset1()\n",
+    "\n",
+    "dataset"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "123cdc16",
+   "metadata": {},
+   "source": [
+    "## Listing Available Prefabs\n",
+    "\n",
+    "Next, let's check what prefabricated pipelines are available:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f0b0bdde",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Available Prefabricated Pipelines:\n",
+      "|-----------------------|-------------------------------------------------------------------------------------------------------------|\n",
+      "| Name                  | Description                                                                                                 |\n",
+      "|-----------------------|-------------------------------------------------------------------------------------------------------------|\n",
+      "| find_boundaries       | A simlarity-clustering-classification pipeline for finding boundaries in measurement data                   |\n",
+      "| preprocess            | A pipeline that generates a Cartesian grid, normalizes data, and calculates derivatives using Savgol filter |\n",
+      "| similarity_clustering | A simlarity-clustering pipeline for clustering measurements into groups                                     |\n",
+      "|-----------------------|-------------------------------------------------------------------------------------------------------------|\n",
+      "Total: 3 prefabricated pipeline(s)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# List all available prefabricated pipelines with descriptions\n",
+    "list_prefabs()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9b4cecb",
+   "metadata": {},
+   "source": [
+    "## Loading a Prefabricated Pipeline\n",
+    "\n",
+    "Let's load a prefabricated pipeline called \"preprocess\":"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "ae682619",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "PipelineOp                               input_variable ---> output_variable\n",
+      "----------                               -----------------------------------\n",
+      "0  ) <CartesianGridGenerator>            CartesianGridGenerator ---> composition_grid\n",
+      "1  ) <Standardize>                       composition_grid ---> normalized_composition_grid\n",
+      "2  ) <Standardize>                       composition ---> normalized_composition\n",
+      "3  ) <SavgolFilter>                      measurement ---> measurement_derivative0\n",
+      "4  ) <SavgolFilter>                      measurement ---> measurement_derivative1\n",
+      "5  ) <SavgolFilter>                      measurement ---> measurement_derivative2\n",
+      "\n",
+      "Input Variables\n",
+      "---------------\n",
+      "0) CartesianGridGenerator\n",
+      "1) composition\n",
+      "2) measurement\n",
+      "\n",
+      "Output Variables\n",
+      "----------------\n",
+      "0) normalized_composition_grid\n",
+      "1) normalized_composition\n",
+      "2) measurement_derivative0\n",
+      "3) measurement_derivative1\n",
+      "4) measurement_derivative2\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load the \"preprocess\" prefabricated pipeline\n",
+    "pipeline = load_prefab(\"preprocess\")\n",
+    "pipeline.print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0cc4a9dd",
+   "metadata": {},
+   "source": [
+    "## Inspecting the Pipeline Structure\n",
+    "\n",
+    "To better understand the pipeline we've loaded, we can visualize it using the ``.draw()`` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a548e17f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x800 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Visualize the pipeline structure\n",
+    "pipeline.draw();"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a2a9c229",
+   "metadata": {},
+   "source": [
+    "## Generating Code for the Pipeline\n",
+    "\n",
+    "The ``print_code()`` method allows us to extract Python code that recreates the pipeline. This is particularly useful when we want to:\n",
+    "\n",
+    "1. Understand how the pipeline was built\n",
+    "2. Modify the pipeline to suit our needs\n",
+    "3. Create a new pipeline based on the existing one\n",
+    "\n",
+    "Now, let's reproduce the code from the Pipeline and modify it to work with our example dataset. You'll need to make the following changes:\n",
+    "\n",
+    "- Change the `dim` argument for the Savgol filters from \"q\" to \"x\" to match the example_dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "9f144895",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pipeline code has been prepared in a new cell below.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Generate code for the pipeline\n",
+    "pipeline.print_code()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "44e2dd7b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with Pipeline(name = \"preprocess\") as p:\n",
+    "    CartesianGrid(\n",
+    "        output_variable=\"composition_grid\",\n",
+    "        grid_spec={'A': {'min': 0.0, 'max': 10.0, 'steps': 50}, 'B': {'min': 0.0, 'max': 25.0, 'steps': 50}},\n",
+    "        sample_dim=\"grid\",\n",
+    "        component_dim=\"component\",\n",
+    "        name=\"CartesianGridGenerator\",\n",
+    "    )\n",
+    "\n",
+    "    Standardize(\n",
+    "        input_variable=\"composition_grid\",\n",
+    "        output_variable=\"normalized_composition_grid\",\n",
+    "        dim=\"grid\",\n",
+    "        component_dim=\"component\",\n",
+    "        scale_variable=None,\n",
+    "        min_val={'A': 0.0, 'B': 0.0},\n",
+    "        max_val={'A': 10.0, 'B': 25.0},\n",
+    "        name=\"Standardize\",\n",
+    "    )\n",
+    "\n",
+    "    Standardize(\n",
+    "        input_variable=\"composition\",\n",
+    "        output_variable=\"normalized_composition\",\n",
+    "        dim=\"sample\",\n",
+    "        component_dim=\"component\",\n",
+    "        scale_variable=None,\n",
+    "        min_val={'A': 0.0, 'B': 0.0},\n",
+    "        max_val={'A': 10.0, 'B': 25.0},\n",
+    "        name=\"Standardize\",\n",
+    "    )\n",
+    "\n",
+    "    SavgolFilter(\n",
+    "        input_variable=\"measurement\",\n",
+    "        output_variable=\"measurement_derivative0\",\n",
+    "        dim=\"x\",\n",
+    "        xlo=None,\n",
+    "        xhi=None,\n",
+    "        xlo_isel=None,\n",
+    "        xhi_isel=None,\n",
+    "        pedestal=None,\n",
+    "        npts=250,\n",
+    "        derivative=0,\n",
+    "        window_length=31,\n",
+    "        polyorder=2,\n",
+    "        apply_log_scale=True,\n",
+    "        name=\"SavgolFilter\",\n",
+    "    )\n",
+    "\n",
+    "    SavgolFilter(\n",
+    "        input_variable=\"measurement\",\n",
+    "        output_variable=\"measurement_derivative1\",\n",
+    "        dim=\"x\",\n",
+    "        xlo=None,\n",
+    "        xhi=None,\n",
+    "        xlo_isel=None,\n",
+    "        xhi_isel=None,\n",
+    "        pedestal=None,\n",
+    "        npts=250,\n",
+    "        derivative=1,\n",
+    "        window_length=31,\n",
+    "        polyorder=2,\n",
+    "        apply_log_scale=True,\n",
+    "        name=\"SavgolFilter\",\n",
+    "    )\n",
+    "\n",
+    "    SavgolFilter(\n",
+    "        input_variable=\"measurement\",\n",
+    "        output_variable=\"measurement_derivative2\",\n",
+    "        dim=\"x\",\n",
+    "        xlo=None,\n",
+    "        xhi=None,\n",
+    "        xlo_isel=None,\n",
+    "        xhi_isel=None,\n",
+    "        pedestal=None,\n",
+    "        npts=250,\n",
+    "        derivative=2,\n",
+    "        window_length=31,\n",
+    "        polyorder=2,\n",
+    "        apply_log_scale=True,\n",
+    "        name=\"SavgolFilter\",\n",
+    "    )\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ee1dff21",
+   "metadata": {},
+   "source": [
+    "## Running the Pipeline\n",
+    "\n",
+    "Now let's run our customized pipeline on the example dataset:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "56f7039b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5702d4c0a57f497c96d12042889f7689",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/6 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><svg style=\"position: absolute; width: 0; height: 0; overflow: hidden\">\n",
+       "<defs>\n",
+       "<symbol id=\"icon-database\" viewBox=\"0 0 32 32\">\n",
+       "<path d=\"M16 0c-8.837 0-16 2.239-16 5v4c0 2.761 7.163 5 16 5s16-2.239 16-5v-4c0-2.761-7.163-5-16-5z\"></path>\n",
+       "<path d=\"M16 17c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
+       "<path d=\"M16 26c-8.837 0-16-2.239-16-5v6c0 2.761 7.163 5 16 5s16-2.239 16-5v-6c0 2.761-7.163 5-16 5z\"></path>\n",
+       "</symbol>\n",
+       "<symbol id=\"icon-file-text2\" viewBox=\"0 0 32 32\">\n",
+       "<path d=\"M28.681 7.159c-0.694-0.947-1.662-2.053-2.724-3.116s-2.169-2.030-3.116-2.724c-1.612-1.182-2.393-1.319-2.841-1.319h-15.5c-1.378 0-2.5 1.121-2.5 2.5v27c0 1.378 1.122 2.5 2.5 2.5h23c1.378 0 2.5-1.122 2.5-2.5v-19.5c0-0.448-0.137-1.23-1.319-2.841zM24.543 5.457c0.959 0.959 1.712 1.825 2.268 2.543h-4.811v-4.811c0.718 0.556 1.584 1.309 2.543 2.268zM28 29.5c0 0.271-0.229 0.5-0.5 0.5h-23c-0.271 0-0.5-0.229-0.5-0.5v-27c0-0.271 0.229-0.5 0.5-0.5 0 0 15.499-0 15.5 0v7c0 0.552 0.448 1 1 1h7v19.5z\"></path>\n",
+       "<path d=\"M23 26h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "<path d=\"M23 22h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "<path d=\"M23 18h-14c-0.552 0-1-0.448-1-1s0.448-1 1-1h14c0.552 0 1 0.448 1 1s-0.448 1-1 1z\"></path>\n",
+       "</symbol>\n",
+       "</defs>\n",
+       "</svg>\n",
+       "<style>/* CSS stylesheet for displaying xarray objects in jupyterlab.\n",
+       " *\n",
+       " */\n",
+       "\n",
+       ":root {\n",
+       "  --xr-font-color0: var(--jp-content-font-color0, rgba(0, 0, 0, 1));\n",
+       "  --xr-font-color2: var(--jp-content-font-color2, rgba(0, 0, 0, 0.54));\n",
+       "  --xr-font-color3: var(--jp-content-font-color3, rgba(0, 0, 0, 0.38));\n",
+       "  --xr-border-color: var(--jp-border-color2, #e0e0e0);\n",
+       "  --xr-disabled-color: var(--jp-layout-color3, #bdbdbd);\n",
+       "  --xr-background-color: var(--jp-layout-color0, white);\n",
+       "  --xr-background-color-row-even: var(--jp-layout-color1, white);\n",
+       "  --xr-background-color-row-odd: var(--jp-layout-color2, #eeeeee);\n",
+       "}\n",
+       "\n",
+       "html[theme=\"dark\"],\n",
+       "html[data-theme=\"dark\"],\n",
+       "body[data-theme=\"dark\"],\n",
+       "body.vscode-dark {\n",
+       "  --xr-font-color0: rgba(255, 255, 255, 1);\n",
+       "  --xr-font-color2: rgba(255, 255, 255, 0.54);\n",
+       "  --xr-font-color3: rgba(255, 255, 255, 0.38);\n",
+       "  --xr-border-color: #1f1f1f;\n",
+       "  --xr-disabled-color: #515151;\n",
+       "  --xr-background-color: #111111;\n",
+       "  --xr-background-color-row-even: #111111;\n",
+       "  --xr-background-color-row-odd: #313131;\n",
+       "}\n",
+       "\n",
+       ".xr-wrap {\n",
+       "  display: block !important;\n",
+       "  min-width: 300px;\n",
+       "  max-width: 700px;\n",
+       "}\n",
+       "\n",
+       ".xr-text-repr-fallback {\n",
+       "  /* fallback to plain text repr when CSS is not injected (untrusted notebook) */\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-header {\n",
+       "  padding-top: 6px;\n",
+       "  padding-bottom: 6px;\n",
+       "  margin-bottom: 4px;\n",
+       "  border-bottom: solid 1px var(--xr-border-color);\n",
+       "}\n",
+       "\n",
+       ".xr-header > div,\n",
+       ".xr-header > ul {\n",
+       "  display: inline;\n",
+       "  margin-top: 0;\n",
+       "  margin-bottom: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-obj-type,\n",
+       ".xr-array-name {\n",
+       "  margin-left: 2px;\n",
+       "  margin-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-obj-type {\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-sections {\n",
+       "  padding-left: 0 !important;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 150px auto auto 1fr 0 20px 0 20px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input {\n",
+       "  display: inline-block;\n",
+       "  opacity: 0;\n",
+       "  height: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input + label {\n",
+       "  color: var(--xr-disabled-color);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input:enabled + label {\n",
+       "  cursor: pointer;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input:focus + label {\n",
+       "  border: 2px solid var(--xr-font-color0);\n",
+       "}\n",
+       "\n",
+       ".xr-section-item input:enabled + label:hover {\n",
+       "  color: var(--xr-font-color0);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary {\n",
+       "  grid-column: 1;\n",
+       "  color: var(--xr-font-color2);\n",
+       "  font-weight: 500;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary > span {\n",
+       "  display: inline-block;\n",
+       "  padding-left: 0.5em;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:disabled + label {\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in + label:before {\n",
+       "  display: inline-block;\n",
+       "  content: \"►\";\n",
+       "  font-size: 11px;\n",
+       "  width: 15px;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:disabled + label:before {\n",
+       "  color: var(--xr-disabled-color);\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked + label:before {\n",
+       "  content: \"▼\";\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked + label > span {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary,\n",
+       ".xr-section-inline-details {\n",
+       "  padding-top: 4px;\n",
+       "  padding-bottom: 4px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-inline-details {\n",
+       "  grid-column: 2 / -1;\n",
+       "}\n",
+       "\n",
+       ".xr-section-details {\n",
+       "  display: none;\n",
+       "  grid-column: 1 / -1;\n",
+       "  margin-bottom: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-section-summary-in:checked ~ .xr-section-details {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-array-wrap {\n",
+       "  grid-column: 1 / -1;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 20px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-array-wrap > label {\n",
+       "  grid-column: 1;\n",
+       "  vertical-align: top;\n",
+       "}\n",
+       "\n",
+       ".xr-preview {\n",
+       "  color: var(--xr-font-color3);\n",
+       "}\n",
+       "\n",
+       ".xr-array-preview,\n",
+       ".xr-array-data {\n",
+       "  padding: 0 5px !important;\n",
+       "  grid-column: 2;\n",
+       "}\n",
+       "\n",
+       ".xr-array-data,\n",
+       ".xr-array-in:checked ~ .xr-array-preview {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       ".xr-array-in:checked ~ .xr-array-data,\n",
+       ".xr-array-preview {\n",
+       "  display: inline-block;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list {\n",
+       "  display: inline-block !important;\n",
+       "  list-style: none;\n",
+       "  padding: 0 !important;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list li {\n",
+       "  display: inline-block;\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list:before {\n",
+       "  content: \"(\";\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list:after {\n",
+       "  content: \")\";\n",
+       "}\n",
+       "\n",
+       ".xr-dim-list li:not(:last-child):after {\n",
+       "  content: \",\";\n",
+       "  padding-right: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-has-index {\n",
+       "  font-weight: bold;\n",
+       "}\n",
+       "\n",
+       ".xr-var-list,\n",
+       ".xr-var-item {\n",
+       "  display: contents;\n",
+       "}\n",
+       "\n",
+       ".xr-var-item > div,\n",
+       ".xr-var-item label,\n",
+       ".xr-var-item > .xr-var-name span {\n",
+       "  background-color: var(--xr-background-color-row-even);\n",
+       "  margin-bottom: 0;\n",
+       "}\n",
+       "\n",
+       ".xr-var-item > .xr-var-name:hover span {\n",
+       "  padding-right: 5px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-list > li:nth-child(odd) > div,\n",
+       ".xr-var-list > li:nth-child(odd) > label,\n",
+       ".xr-var-list > li:nth-child(odd) > .xr-var-name span {\n",
+       "  background-color: var(--xr-background-color-row-odd);\n",
+       "}\n",
+       "\n",
+       ".xr-var-name {\n",
+       "  grid-column: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-var-dims {\n",
+       "  grid-column: 2;\n",
+       "}\n",
+       "\n",
+       ".xr-var-dtype {\n",
+       "  grid-column: 3;\n",
+       "  text-align: right;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-var-preview {\n",
+       "  grid-column: 4;\n",
+       "}\n",
+       "\n",
+       ".xr-index-preview {\n",
+       "  grid-column: 2 / 5;\n",
+       "  color: var(--xr-font-color2);\n",
+       "}\n",
+       "\n",
+       ".xr-var-name,\n",
+       ".xr-var-dims,\n",
+       ".xr-var-dtype,\n",
+       ".xr-preview,\n",
+       ".xr-attrs dt {\n",
+       "  white-space: nowrap;\n",
+       "  overflow: hidden;\n",
+       "  text-overflow: ellipsis;\n",
+       "  padding-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-var-name:hover,\n",
+       ".xr-var-dims:hover,\n",
+       ".xr-var-dtype:hover,\n",
+       ".xr-attrs dt:hover {\n",
+       "  overflow: visible;\n",
+       "  width: auto;\n",
+       "  z-index: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs,\n",
+       ".xr-var-data,\n",
+       ".xr-index-data {\n",
+       "  display: none;\n",
+       "  background-color: var(--xr-background-color) !important;\n",
+       "  padding-bottom: 5px !important;\n",
+       "}\n",
+       "\n",
+       ".xr-var-attrs-in:checked ~ .xr-var-attrs,\n",
+       ".xr-var-data-in:checked ~ .xr-var-data,\n",
+       ".xr-index-data-in:checked ~ .xr-index-data {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       ".xr-var-data > table {\n",
+       "  float: right;\n",
+       "}\n",
+       "\n",
+       ".xr-var-name span,\n",
+       ".xr-var-data,\n",
+       ".xr-index-name div,\n",
+       ".xr-index-data,\n",
+       ".xr-attrs {\n",
+       "  padding-left: 25px !important;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs,\n",
+       ".xr-var-attrs,\n",
+       ".xr-var-data,\n",
+       ".xr-index-data {\n",
+       "  grid-column: 1 / -1;\n",
+       "}\n",
+       "\n",
+       "dl.xr-attrs {\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "  display: grid;\n",
+       "  grid-template-columns: 125px auto;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt,\n",
+       ".xr-attrs dd {\n",
+       "  padding: 0;\n",
+       "  margin: 0;\n",
+       "  float: left;\n",
+       "  padding-right: 10px;\n",
+       "  width: auto;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt {\n",
+       "  font-weight: normal;\n",
+       "  grid-column: 1;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dt:hover span {\n",
+       "  display: inline-block;\n",
+       "  background: var(--xr-background-color);\n",
+       "  padding-right: 10px;\n",
+       "}\n",
+       "\n",
+       ".xr-attrs dd {\n",
+       "  grid-column: 2;\n",
+       "  white-space: pre-wrap;\n",
+       "  word-break: break-all;\n",
+       "}\n",
+       "\n",
+       ".xr-icon-database,\n",
+       ".xr-icon-file-text2,\n",
+       ".xr-no-icon {\n",
+       "  display: inline-block;\n",
+       "  vertical-align: middle;\n",
+       "  width: 1em;\n",
+       "  height: 1.5em !important;\n",
+       "  stroke-width: 0;\n",
+       "  stroke: currentColor;\n",
+       "  fill: currentColor;\n",
+       "}\n",
+       "</style><pre class='xr-text-repr-fallback'>&lt;xarray.Dataset&gt; Size: 807kB\n",
+       "Dimensions:                      (sample: 100, component: 2, x: 150,\n",
+       "                                  grid: 2500, log_x: 250)\n",
+       "Coordinates:\n",
+       "  * component                    (component) &lt;U1 8B &#x27;A&#x27; &#x27;B&#x27;\n",
+       "  * x                            (x) float64 1kB 0.001 0.001047 ... 0.9547 1.0\n",
+       "  * log_x                        (log_x) float64 2kB -3.0 -2.988 ... 0.0\n",
+       "Dimensions without coordinates: sample, grid\n",
+       "Data variables:\n",
+       "    composition                  (sample, component) float64 2kB ...\n",
+       "    ground_truth_labels          (sample) int64 800B ...\n",
+       "    measurement                  (sample, x) float64 120kB ...\n",
+       "    composition_grid             (grid, component) float64 40kB 0.0 0.0 ... 25.0\n",
+       "    normalized_composition_grid  (grid, component) float64 40kB 0.0 0.0 ... 1.0\n",
+       "    normalized_composition       (sample, component) float64 2kB 0.1935 ... 0...\n",
+       "    measurement_derivative0      (sample, log_x) float64 200kB 6.306 ... 0.3073\n",
+       "    measurement_derivative1      (sample, log_x) float64 200kB -3.828 ... -0....\n",
+       "    measurement_derivative2      (sample, log_x) float64 200kB -1.838 ... -0....</pre><div class='xr-wrap' style='display:none'><div class='xr-header'><div class='xr-obj-type'>xarray.Dataset</div></div><ul class='xr-sections'><li class='xr-section-item'><input id='section-d40af47a-a6af-4cef-ad9e-2847fa3738b9' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-d40af47a-a6af-4cef-ad9e-2847fa3738b9' class='xr-section-summary'  title='Expand/collapse section'>Dimensions:</label><div class='xr-section-inline-details'><ul class='xr-dim-list'><li><span>sample</span>: 100</li><li><span class='xr-has-index'>component</span>: 2</li><li><span class='xr-has-index'>x</span>: 150</li><li><span>grid</span>: 2500</li><li><span class='xr-has-index'>log_x</span>: 250</li></ul></div><div class='xr-section-details'></div></li><li class='xr-section-item'><input id='section-a9d9e8e7-42a2-4f58-b54f-73f70a3761ac' class='xr-section-summary-in' type='checkbox'  checked><label for='section-a9d9e8e7-42a2-4f58-b54f-73f70a3761ac' class='xr-section-summary' >Coordinates: <span>(3)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>component</span></div><div class='xr-var-dims'>(component)</div><div class='xr-var-dtype'>&lt;U1</div><div class='xr-var-preview xr-preview'>&#x27;A&#x27; &#x27;B&#x27;</div><input id='attrs-94243f79-75cd-47b8-b0f0-a762f2e3a173' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-94243f79-75cd-47b8-b0f0-a762f2e3a173' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-83322cf0-0afd-4922-add5-30f543de0d60' class='xr-var-data-in' type='checkbox'><label for='data-83322cf0-0afd-4922-add5-30f543de0d60' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([&#x27;A&#x27;, &#x27;B&#x27;], dtype=&#x27;&lt;U1&#x27;)</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>x</span></div><div class='xr-var-dims'>(x)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>0.001 0.001047 ... 0.9547 1.0</div><input id='attrs-ea6cc962-af3d-49af-9623-705eb7a0f961' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-ea6cc962-af3d-49af-9623-705eb7a0f961' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-4de8ce3b-9ea6-4134-9f91-758c03546258' class='xr-var-data-in' type='checkbox'><label for='data-4de8ce3b-9ea6-4134-9f91-758c03546258' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([0.001   , 0.001047, 0.001097, 0.001149, 0.001204, 0.001261, 0.001321,\n",
+       "       0.001383, 0.001449, 0.001518, 0.00159 , 0.001665, 0.001744, 0.001827,\n",
+       "       0.001914, 0.002005, 0.0021  , 0.002199, 0.002304, 0.002413, 0.002527,\n",
+       "       0.002647, 0.002773, 0.002905, 0.003042, 0.003187, 0.003338, 0.003496,\n",
+       "       0.003662, 0.003836, 0.004018, 0.004209, 0.004409, 0.004618, 0.004837,\n",
+       "       0.005066, 0.005307, 0.005559, 0.005822, 0.006099, 0.006388, 0.006691,\n",
+       "       0.007009, 0.007341, 0.00769 , 0.008055, 0.008437, 0.008837, 0.009256,\n",
+       "       0.009696, 0.010156, 0.010638, 0.011142, 0.011671, 0.012225, 0.012805,\n",
+       "       0.013413, 0.014049, 0.014716, 0.015414, 0.016146, 0.016912, 0.017714,\n",
+       "       0.018555, 0.019435, 0.020358, 0.021324, 0.022335, 0.023395, 0.024505,\n",
+       "       0.025668, 0.026886, 0.028162, 0.029498, 0.030898, 0.032364, 0.0339  ,\n",
+       "       0.035509, 0.037194, 0.038959, 0.040807, 0.042744, 0.044772, 0.046897,\n",
+       "       0.049122, 0.051453, 0.053894, 0.056452, 0.059131, 0.061936, 0.064875,\n",
+       "       0.067954, 0.071179, 0.074556, 0.078094, 0.0818  , 0.085681, 0.089747,\n",
+       "       0.094006, 0.098467, 0.103139, 0.108033, 0.11316 , 0.118529, 0.124154,\n",
+       "       0.130045, 0.136216, 0.14268 , 0.14945 , 0.156542, 0.16397 , 0.171751,\n",
+       "       0.179901, 0.188438, 0.197379, 0.206746, 0.216556, 0.226832, 0.237596,\n",
+       "       0.24887 , 0.26068 , 0.27305 , 0.286006, 0.299578, 0.313794, 0.328684,\n",
+       "       0.344281, 0.360618, 0.37773 , 0.395654, 0.414429, 0.434094, 0.454693,\n",
+       "       0.476269, 0.498869, 0.522542, 0.547337, 0.57331 , 0.600514, 0.62901 ,\n",
+       "       0.658858, 0.690122, 0.72287 , 0.757172, 0.793102, 0.830736, 0.870156,\n",
+       "       0.911447, 0.954697, 1.      ])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span class='xr-has-index'>log_x</span></div><div class='xr-var-dims'>(log_x)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>-3.0 -2.988 -2.976 ... -0.01205 0.0</div><input id='attrs-424e2e3c-d10d-4918-a641-4c7621ae2b28' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-424e2e3c-d10d-4918-a641-4c7621ae2b28' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-8dacd776-2ede-406a-8c80-33175b716c2c' class='xr-var-data-in' type='checkbox'><label for='data-8dacd776-2ede-406a-8c80-33175b716c2c' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>array([-3.      , -2.987952, -2.975904, ..., -0.024096, -0.012048,  0.      ])</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-72ac1221-3902-4ebb-a01e-2926ed75ebb0' class='xr-section-summary-in' type='checkbox'  checked><label for='section-72ac1221-3902-4ebb-a01e-2926ed75ebb0' class='xr-section-summary' >Data variables: <span>(9)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-var-name'><span>composition</span></div><div class='xr-var-dims'>(sample, component)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-8f84906e-4246-46a3-80cf-26ab018b9003' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-8f84906e-4246-46a3-80cf-26ab018b9003' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-bd05b0cb-d14d-4072-a512-bdb9227522c6' class='xr-var-data-in' type='checkbox'><label for='data-bd05b0cb-d14d-4072-a512-bdb9227522c6' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>[200 values with dtype=float64]</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>ground_truth_labels</span></div><div class='xr-var-dims'>(sample)</div><div class='xr-var-dtype'>int64</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-e775ac11-20d3-48d7-9a6b-9ebd35fa8186' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-e775ac11-20d3-48d7-9a6b-9ebd35fa8186' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-bbeba845-250f-4076-b058-5e020224d5f9' class='xr-var-data-in' type='checkbox'><label for='data-bbeba845-250f-4076-b058-5e020224d5f9' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>[100 values with dtype=int64]</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>measurement</span></div><div class='xr-var-dims'>(sample, x)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>...</div><input id='attrs-238f5ff5-9c84-45ed-97a5-48971250567d' class='xr-var-attrs-in' type='checkbox' disabled><label for='attrs-238f5ff5-9c84-45ed-97a5-48971250567d' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-aef84472-cde0-4ff7-8e6a-001c3ff21720' class='xr-var-data-in' type='checkbox'><label for='data-aef84472-cde0-4ff7-8e6a-001c3ff21720' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'></dl></div><div class='xr-var-data'><pre>[15000 values with dtype=float64]</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>composition_grid</span></div><div class='xr-var-dims'>(grid, component)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>0.0 0.0 0.0 ... 24.49 10.0 25.0</div><input id='attrs-9ea4e7f6-d78d-4191-978e-cd6fc738eb38' class='xr-var-attrs-in' type='checkbox' ><label for='attrs-9ea4e7f6-d78d-4191-978e-cd6fc738eb38' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-875f28d8-b326-4356-8a1b-84a0a228ccec' class='xr-var-data-in' type='checkbox'><label for='data-875f28d8-b326-4356-8a1b-84a0a228ccec' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'><dt><span>name :</span></dt><dd>CartesianGridGenerator</dd><dt><span>input_variable :</span></dt><dd>CartesianGridGenerator</dd><dt><span>output_variable :</span></dt><dd>composition_grid</dd><dt><span>input_prefix :</span></dt><dd>None</dd><dt><span>output_prefix :</span></dt><dd>None</dd><dt><span>_stored_args :</span></dt><dd>{&#x27;output_variable&#x27;: &#x27;composition_grid&#x27;, &#x27;grid_spec&#x27;: {&#x27;A&#x27;: {&#x27;min&#x27;: 0.0, &#x27;max&#x27;: 10.0, &#x27;steps&#x27;: 50}, &#x27;B&#x27;: {&#x27;min&#x27;: 0.0, &#x27;max&#x27;: 25.0, &#x27;steps&#x27;: 50}}, &#x27;sample_dim&#x27;: &#x27;grid&#x27;, &#x27;component_dim&#x27;: &#x27;component&#x27;, &#x27;name&#x27;: &#x27;CartesianGridGenerator&#x27;}</dd><dt><span>components :</span></dt><dd>[&#x27;A&#x27;, &#x27;B&#x27;]</dd></dl></div><div class='xr-var-data'><pre>array([[ 0.        ,  0.        ],\n",
+       "       [ 0.        ,  0.51020408],\n",
+       "       [ 0.        ,  1.02040816],\n",
+       "       ...,\n",
+       "       [10.        , 23.97959184],\n",
+       "       [10.        , 24.48979592],\n",
+       "       [10.        , 25.        ]])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>normalized_composition_grid</span></div><div class='xr-var-dims'>(grid, component)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>0.0 0.0 0.0 ... 0.9796 1.0 1.0</div><input id='attrs-de4ab552-b6d3-4484-8ae3-4a9215bb2101' class='xr-var-attrs-in' type='checkbox' ><label for='attrs-de4ab552-b6d3-4484-8ae3-4a9215bb2101' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-7b582c59-5f83-4050-ac95-7d5617388e5c' class='xr-var-data-in' type='checkbox'><label for='data-7b582c59-5f83-4050-ac95-7d5617388e5c' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'><dt><span>description :</span></dt><dd>Data normalized to have range 0 -&gt; 1</dd><dt><span>name :</span></dt><dd>Standardize</dd><dt><span>input_variable :</span></dt><dd>composition_grid</dd><dt><span>output_variable :</span></dt><dd>normalized_composition_grid</dd><dt><span>input_prefix :</span></dt><dd>None</dd><dt><span>output_prefix :</span></dt><dd>None</dd><dt><span>_stored_args :</span></dt><dd>{&#x27;input_variable&#x27;: &#x27;composition_grid&#x27;, &#x27;output_variable&#x27;: &#x27;normalized_composition_grid&#x27;, &#x27;dim&#x27;: &#x27;grid&#x27;, &#x27;component_dim&#x27;: &#x27;component&#x27;, &#x27;scale_variable&#x27;: None, &#x27;min_val&#x27;: {&#x27;A&#x27;: 0.0, &#x27;B&#x27;: 0.0}, &#x27;max_val&#x27;: {&#x27;A&#x27;: 10.0, &#x27;B&#x27;: 25.0}, &#x27;name&#x27;: &#x27;Standardize&#x27;}</dd></dl></div><div class='xr-var-data'><pre>array([[0.        , 0.        ],\n",
+       "       [0.        , 0.02040816],\n",
+       "       [0.        , 0.04081633],\n",
+       "       ...,\n",
+       "       [1.        , 0.95918367],\n",
+       "       [1.        , 0.97959184],\n",
+       "       [1.        , 1.        ]])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>normalized_composition</span></div><div class='xr-var-dims'>(sample, component)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>0.1935 0.1736 0.4 ... 0.7878 0.5732</div><input id='attrs-e1049692-92fc-40de-b3f1-125e54cb4db8' class='xr-var-attrs-in' type='checkbox' ><label for='attrs-e1049692-92fc-40de-b3f1-125e54cb4db8' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-810dc39e-74a0-4257-a63e-4ca0121382bd' class='xr-var-data-in' type='checkbox'><label for='data-810dc39e-74a0-4257-a63e-4ca0121382bd' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'><dt><span>description :</span></dt><dd>Data normalized to have range 0 -&gt; 1</dd><dt><span>name :</span></dt><dd>Standardize</dd><dt><span>input_variable :</span></dt><dd>composition</dd><dt><span>output_variable :</span></dt><dd>normalized_composition</dd><dt><span>input_prefix :</span></dt><dd>None</dd><dt><span>output_prefix :</span></dt><dd>None</dd><dt><span>_stored_args :</span></dt><dd>{&#x27;input_variable&#x27;: &#x27;composition&#x27;, &#x27;output_variable&#x27;: &#x27;normalized_composition&#x27;, &#x27;dim&#x27;: &#x27;sample&#x27;, &#x27;component_dim&#x27;: &#x27;component&#x27;, &#x27;scale_variable&#x27;: None, &#x27;min_val&#x27;: {&#x27;A&#x27;: 0.0, &#x27;B&#x27;: 0.0}, &#x27;max_val&#x27;: {&#x27;A&#x27;: 10.0, &#x27;B&#x27;: 25.0}, &#x27;name&#x27;: &#x27;Standardize&#x27;}</dd></dl></div><div class='xr-var-data'><pre>array([[0.19350696, 0.1735511 ],\n",
+       "       [0.39999323, 0.60479245],\n",
+       "       [0.51440317, 0.06634039],\n",
+       "       [0.45788323, 0.49367328],\n",
+       "       [0.80556753, 0.41894355],\n",
+       "       [0.10416101, 0.91334468],\n",
+       "       [0.5857579 , 0.75250838],\n",
+       "       [0.42955818, 0.67657706],\n",
+       "       [0.31495021, 0.08357898],\n",
+       "       [0.76525175, 0.52200632],\n",
+       "       [0.55883305, 0.30212056],\n",
+       "       [0.87586496, 0.55600188],\n",
+       "       [0.90357984, 0.04164429],\n",
+       "       [0.69470929, 0.88156382],\n",
+       "       [0.63087273, 0.92327146],\n",
+       "       [0.8382142 , 0.97131272],\n",
+       "       [0.60986192, 0.22702417],\n",
+       "       [0.01217766, 0.06010542],\n",
+       "       [0.54271795, 0.96213564],\n",
+       "       [0.33277349, 0.5166934 ],\n",
+       "...\n",
+       "       [0.77637827, 0.87973744],\n",
+       "       [0.7459914 , 0.3244696 ],\n",
+       "       [0.76385434, 0.54161003],\n",
+       "       [0.08173325, 0.37751018],\n",
+       "       [0.72005913, 0.23432469],\n",
+       "       [0.22080477, 0.27088692],\n",
+       "       [0.36547246, 0.17758467],\n",
+       "       [0.82134564, 0.42989405],\n",
+       "       [0.99214733, 0.62218723],\n",
+       "       [0.95266308, 0.2711052 ],\n",
+       "       [0.70137984, 0.88809291],\n",
+       "       [0.02391468, 0.13985559],\n",
+       "       [0.3464569 , 0.51398727],\n",
+       "       [0.02661836, 0.32502296],\n",
+       "       [0.11156883, 0.01817279],\n",
+       "       [0.69141638, 0.8592665 ],\n",
+       "       [0.05962323, 0.30767944],\n",
+       "       [0.20203193, 0.19743203],\n",
+       "       [0.52140263, 0.19370912],\n",
+       "       [0.78782424, 0.57321402]])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>measurement_derivative0</span></div><div class='xr-var-dims'>(sample, log_x)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>6.306 6.259 6.213 ... 0.3078 0.3073</div><input id='attrs-b3ddc467-51f1-485f-a548-2eadba92eeb9' class='xr-var-attrs-in' type='checkbox' ><label for='attrs-b3ddc467-51f1-485f-a548-2eadba92eeb9' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-15d3c579-a2a5-4d45-b740-dc9152768e08' class='xr-var-data-in' type='checkbox'><label for='data-15d3c579-a2a5-4d45-b740-dc9152768e08' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'><dt><span>description :</span></dt><dd>Savitsky-Golay filtered data</dd><dt><span>name :</span></dt><dd>SavgolFilter</dd><dt><span>input_variable :</span></dt><dd>measurement</dd><dt><span>output_variable :</span></dt><dd>measurement_derivative0</dd><dt><span>input_prefix :</span></dt><dd>None</dd><dt><span>output_prefix :</span></dt><dd>None</dd><dt><span>_stored_args :</span></dt><dd>{&#x27;input_variable&#x27;: &#x27;measurement&#x27;, &#x27;output_variable&#x27;: &#x27;measurement_derivative0&#x27;, &#x27;dim&#x27;: &#x27;x&#x27;, &#x27;xlo&#x27;: None, &#x27;xhi&#x27;: None, &#x27;xlo_isel&#x27;: None, &#x27;xhi_isel&#x27;: None, &#x27;pedestal&#x27;: None, &#x27;npts&#x27;: 250, &#x27;derivative&#x27;: 0, &#x27;window_length&#x27;: 31, &#x27;polyorder&#x27;: 2, &#x27;apply_log_scale&#x27;: True, &#x27;name&#x27;: &#x27;SavgolFilter&#x27;}</dd></dl></div><div class='xr-var-data'><pre>array([[6.30563387, 6.25937812, 6.21285551, ..., 0.25091915, 0.24839576,\n",
+       "        0.2459309 ],\n",
+       "       [6.25520769, 6.21474481, 6.17373602, ..., 0.30378809, 0.3073302 ,\n",
+       "        0.31106921],\n",
+       "       [6.29807208, 6.2514212 , 6.20462334, ..., 0.34531082, 0.35438886,\n",
+       "        0.36405585],\n",
+       "       ...,\n",
+       "       [6.28535392, 6.23468884, 6.18433828, ..., 0.30281236, 0.30375312,\n",
+       "        0.30477185],\n",
+       "       [6.27650503, 6.23702423, 6.19691028, ..., 0.27402484, 0.27197968,\n",
+       "        0.26980797],\n",
+       "       [6.2646559 , 6.21209494, 6.16007247, ..., 0.30817193, 0.30775822,\n",
+       "        0.30729468]])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>measurement_derivative1</span></div><div class='xr-var-dims'>(sample, log_x)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>-3.828 -3.85 ... -0.03641 -0.04054</div><input id='attrs-edaf9469-385d-41c8-ac49-3e20084a734f' class='xr-var-attrs-in' type='checkbox' ><label for='attrs-edaf9469-385d-41c8-ac49-3e20084a734f' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-5c4a8ae5-83dc-4913-a40b-5cf1260b1b81' class='xr-var-data-in' type='checkbox'><label for='data-5c4a8ae5-83dc-4913-a40b-5cf1260b1b81' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'><dt><span>description :</span></dt><dd>Savitsky-Golay filtered data</dd><dt><span>name :</span></dt><dd>SavgolFilter</dd><dt><span>input_variable :</span></dt><dd>measurement</dd><dt><span>output_variable :</span></dt><dd>measurement_derivative1</dd><dt><span>input_prefix :</span></dt><dd>None</dd><dt><span>output_prefix :</span></dt><dd>None</dd><dt><span>_stored_args :</span></dt><dd>{&#x27;input_variable&#x27;: &#x27;measurement&#x27;, &#x27;output_variable&#x27;: &#x27;measurement_derivative1&#x27;, &#x27;dim&#x27;: &#x27;x&#x27;, &#x27;xlo&#x27;: None, &#x27;xhi&#x27;: None, &#x27;xlo_isel&#x27;: None, &#x27;xhi_isel&#x27;: None, &#x27;pedestal&#x27;: None, &#x27;npts&#x27;: 250, &#x27;derivative&#x27;: 1, &#x27;window_length&#x27;: 31, &#x27;polyorder&#x27;: 2, &#x27;apply_log_scale&#x27;: True, &#x27;name&#x27;: &#x27;SavgolFilter&#x27;}</dd></dl></div><div class='xr-var-data'><pre>array([[-3.82815189, -3.85030191, -3.87245192, ..., -0.21187028,\n",
+       "        -0.20701209, -0.2021539 ],\n",
+       "       [-3.33576502, -3.38107428, -3.42638353, ...,  0.2858237 ,\n",
+       "         0.3021667 ,  0.31850969],\n",
+       "       [-3.86592377, -3.8781227 , -3.89032162, ...,  0.72903554,\n",
+       "         0.77791869,  0.82680185],\n",
+       "       ...,\n",
+       "       [-4.21825364, -4.19214886, -4.16604407, ...,  0.07484659,\n",
+       "         0.08131892,  0.08779125],\n",
+       "       [-3.25063037, -3.30318201, -3.35573365, ..., -0.16449625,\n",
+       "        -0.17500039, -0.18550452],\n",
+       "       [-4.38490681, -4.3402124 , -4.29551799, ..., -0.03226873,\n",
+       "        -0.03640584, -0.04054294]])</pre></div></li><li class='xr-var-item'><div class='xr-var-name'><span>measurement_derivative2</span></div><div class='xr-var-dims'>(sample, log_x)</div><div class='xr-var-dtype'>float64</div><div class='xr-var-preview xr-preview'>-1.838 -1.838 ... -0.3434 -0.3434</div><input id='attrs-1b0869ed-4f8b-42d4-96e3-8898d51b6ce6' class='xr-var-attrs-in' type='checkbox' ><label for='attrs-1b0869ed-4f8b-42d4-96e3-8898d51b6ce6' title='Show/Hide attributes'><svg class='icon xr-icon-file-text2'><use xlink:href='#icon-file-text2'></use></svg></label><input id='data-184b3e07-6f04-46a1-9b42-fabb912c1fbc' class='xr-var-data-in' type='checkbox'><label for='data-184b3e07-6f04-46a1-9b42-fabb912c1fbc' title='Show/Hide data repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-var-attrs'><dl class='xr-attrs'><dt><span>description :</span></dt><dd>Savitsky-Golay filtered data</dd><dt><span>name :</span></dt><dd>SavgolFilter</dd><dt><span>input_variable :</span></dt><dd>measurement</dd><dt><span>output_variable :</span></dt><dd>measurement_derivative2</dd><dt><span>input_prefix :</span></dt><dd>None</dd><dt><span>output_prefix :</span></dt><dd>None</dd><dt><span>_stored_args :</span></dt><dd>{&#x27;input_variable&#x27;: &#x27;measurement&#x27;, &#x27;output_variable&#x27;: &#x27;measurement_derivative2&#x27;, &#x27;dim&#x27;: &#x27;x&#x27;, &#x27;xlo&#x27;: None, &#x27;xhi&#x27;: None, &#x27;xlo_isel&#x27;: None, &#x27;xhi_isel&#x27;: None, &#x27;pedestal&#x27;: None, &#x27;npts&#x27;: 250, &#x27;derivative&#x27;: 2, &#x27;window_length&#x27;: 31, &#x27;polyorder&#x27;: 2, &#x27;apply_log_scale&#x27;: True, &#x27;name&#x27;: &#x27;SavgolFilter&#x27;}</dd></dl></div><div class='xr-var-data'><pre>array([[-1.83845126, -1.83845126, -1.83845126, ...,  0.40322989,\n",
+       "         0.40322989,  0.40322989],\n",
+       "       [-3.76066781, -3.76066781, -3.76066781, ...,  1.35646895,\n",
+       "         1.35646895,  1.35646895],\n",
+       "       [-1.01251085, -1.01251085, -1.01251085, ...,  4.0573021 ,\n",
+       "         4.0573021 ,  4.0573021 ],\n",
+       "       ...,\n",
+       "       [ 2.16669708,  2.16669708,  2.16669708, ...,  0.53720341,\n",
+       "         0.53720341,  0.53720341],\n",
+       "       [-4.36178593, -4.36178593, -4.36178593, ..., -0.87184319,\n",
+       "        -0.87184319, -0.87184319],\n",
+       "       [ 3.70963591,  3.70963591,  3.70963591, ..., -0.34337959,\n",
+       "        -0.34337959, -0.34337959]])</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-555adfb8-6e9d-4e10-a4b7-6fbd53a5d838' class='xr-section-summary-in' type='checkbox'  ><label for='section-555adfb8-6e9d-4e10-a4b7-6fbd53a5d838' class='xr-section-summary' >Indexes: <span>(3)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><ul class='xr-var-list'><li class='xr-var-item'><div class='xr-index-name'><div>component</div></div><div class='xr-index-preview'>PandasIndex</div><input type='checkbox' disabled/><label></label><input id='index-1df6b5b8-e799-4393-a83e-a75a1a94da66' class='xr-index-data-in' type='checkbox'/><label for='index-1df6b5b8-e799-4393-a83e-a75a1a94da66' title='Show/Hide index repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-index-data'><pre>PandasIndex(Index([&#x27;A&#x27;, &#x27;B&#x27;], dtype=&#x27;object&#x27;, name=&#x27;component&#x27;))</pre></div></li><li class='xr-var-item'><div class='xr-index-name'><div>x</div></div><div class='xr-index-preview'>PandasIndex</div><input type='checkbox' disabled/><label></label><input id='index-86ae318d-1673-4c24-9397-8f23348f5749' class='xr-index-data-in' type='checkbox'/><label for='index-86ae318d-1673-4c24-9397-8f23348f5749' title='Show/Hide index repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-index-data'><pre>PandasIndex(Index([                0.001, 0.0010474522360006332, 0.0010971561867027272,\n",
+       "       0.0011492187010036998, 0.0012037516980200685, 0.0012608724076806808,\n",
+       "        0.001320703622736631, 0.0013833739627296209,  0.001449018150486198,\n",
+       "       0.0015177773017322714,\n",
+       "       ...\n",
+       "          0.6588581861506815,    0.6901224802908528,    0.7228703350949566,\n",
+       "            0.75717214883374,    0.7931016603333051,    0.8307361074919352,\n",
+       "          0.8701563933188907,    0.9114472598521185,    0.9546974703287516,\n",
+       "                         1.0],\n",
+       "      dtype=&#x27;float64&#x27;, name=&#x27;x&#x27;, length=150))</pre></div></li><li class='xr-var-item'><div class='xr-index-name'><div>log_x</div></div><div class='xr-index-preview'>PandasIndex</div><input type='checkbox' disabled/><label></label><input id='index-28e9c27d-d125-4673-9f64-94e591afefb0' class='xr-index-data-in' type='checkbox'/><label for='index-28e9c27d-d125-4673-9f64-94e591afefb0' title='Show/Hide index repr'><svg class='icon xr-icon-database'><use xlink:href='#icon-database'></use></svg></label><div class='xr-index-data'><pre>PandasIndex(Index([                 -3.0,   -2.9879518072289155,   -2.9759036144578315,\n",
+       "          -2.963855421686747,   -2.9518072289156625,   -2.9397590361445785,\n",
+       "          -2.927710843373494,   -2.9156626506024095,   -2.9036144578313254,\n",
+       "          -2.891566265060241,\n",
+       "       ...\n",
+       "        -0.10843373493975905,  -0.09638554216867457,  -0.08433734939759008,\n",
+       "        -0.07228915662650603,  -0.06024096385542155,  -0.04819277108433706,\n",
+       "        -0.03614457831325302,  -0.02409638554216853, -0.012048192771084043,\n",
+       "                         0.0],\n",
+       "      dtype=&#x27;float64&#x27;, name=&#x27;log_x&#x27;, length=250))</pre></div></li></ul></div></li><li class='xr-section-item'><input id='section-660cf59c-fec1-4dbb-8f51-bfb11ae061b8' class='xr-section-summary-in' type='checkbox' disabled ><label for='section-660cf59c-fec1-4dbb-8f51-bfb11ae061b8' class='xr-section-summary'  title='Expand/collapse section'>Attributes: <span>(0)</span></label><div class='xr-section-inline-details'></div><div class='xr-section-details'><dl class='xr-attrs'></dl></div></li></ul></div></div>"
+      ],
+      "text/plain": [
+       "<xarray.Dataset> Size: 807kB\n",
+       "Dimensions:                      (sample: 100, component: 2, x: 150,\n",
+       "                                  grid: 2500, log_x: 250)\n",
+       "Coordinates:\n",
+       "  * component                    (component) <U1 8B 'A' 'B'\n",
+       "  * x                            (x) float64 1kB 0.001 0.001047 ... 0.9547 1.0\n",
+       "  * log_x                        (log_x) float64 2kB -3.0 -2.988 ... 0.0\n",
+       "Dimensions without coordinates: sample, grid\n",
+       "Data variables:\n",
+       "    composition                  (sample, component) float64 2kB ...\n",
+       "    ground_truth_labels          (sample) int64 800B ...\n",
+       "    measurement                  (sample, x) float64 120kB ...\n",
+       "    composition_grid             (grid, component) float64 40kB 0.0 0.0 ... 25.0\n",
+       "    normalized_composition_grid  (grid, component) float64 40kB 0.0 0.0 ... 1.0\n",
+       "    normalized_composition       (sample, component) float64 2kB 0.1935 ... 0...\n",
+       "    measurement_derivative0      (sample, log_x) float64 200kB 6.306 ... 0.3073\n",
+       "    measurement_derivative1      (sample, log_x) float64 200kB -3.828 ... -0....\n",
+       "    measurement_derivative2      (sample, log_x) float64 200kB -1.838 ... -0...."
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Run the pipeline on the dataset\n",
+    "result = p.calculate(dataset)\n",
+    "result\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6147527b",
+   "metadata": {},
+   "source": [
+    "## Visualizing the Results\n",
+    "\n",
+    "Let's visualize the results of our pipeline:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "77199bf1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.collections.PathCollection at 0x3135b9450>"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x300 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig,axes = plt.subplots(1,2,figsize=(8,3))\n",
+    "result.composition.to_dataset('component').plot.scatter(x='A',y='B',ax=axes[0])\n",
+    "result.normalized_composition.to_dataset('component').plot.scatter(x='A',y='B',ax=axes[1])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9f66648d",
+   "metadata": {},
+   "source": [
+    "We can see that the relative positions of the compositions are unchanged, we simply renormalized the bounds of the data. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b004cfe",
+   "metadata": {},
+   "source": [
+    "## Combining Multiple Prefabs\n",
+    "\n",
+    "One of the powerful features of prefabricated pipelines is the ability to combine multiple prefabs into a single pipeline:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "72a70d7a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x800 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Combine multiple prefabs if you have more than one available\n",
+    "combined_pipeline = combine_prefabs([\"preprocess\", \"similarity_clustering\"], new_name=\"CombinedPipeline\")\n",
+    "combined_pipeline.draw();"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f4a9286",
+   "metadata": {},
+   "source": [
+    "Conclusion\n",
+    "---------\n",
+    "\n",
+    "In this tutorial, we learned how to:\n",
+    "\n",
+    "1. Load an example dataset from the ``AFL.double_agent.data`` module\n",
+    "2. List and load prefabricated pipelines from the ``AFL.double_agent.prefab`` module\n",
+    "3. Inspect the structure of a pipeline using ``.draw()`` and ``.print()`` methods\n",
+    "4. Generate and modify code for a pipeline using ``.print_code()``\n",
+    "5. Run a customized pipeline on a dataset and visualize the results\n",
+    "6. Combine multiple prefabricated pipelines\n",
+    "\n",
+    "Prefabricated pipelines provide a convenient way to reuse and share pipeline configurations, making your analysis workflows more efficient and reproducible."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}