From f04c7e9d192a58aee32be9f2e3281aa5f866065d Mon Sep 17 00:00:00 2001
From: Emilie Baillo <eebaill@sandia.gov>
Date: Thu, 11 Dec 2025 06:37:23 -0800
Subject: [PATCH] Fix Sphinx docs + GH pages deployment

- Update artifact for github pages deployment workflow, triggers on push/PR to main
- Restore working .ipynb for Genz bcs example
- Update docs makefile
---
 .github/workflows/documentation.yml          |  11 +-
 docs/Makefile                                |   3 +-
 docs/auto_examples/auto_examples_jupyter.zip | Bin 39996 -> 39860 bytes
 docs/auto_examples/auto_examples_python.zip  | Bin 32131 -> 32002 bytes
 docs/auto_examples/ex_genz_bcs.ipynb         |   2 +-
 docs/auto_examples/ex_genz_bcs.py            |   3 -
 docs/auto_examples/ex_genz_bcs.py.md5        |   2 +-
 docs/auto_examples/ex_genz_bcs.rst           |  73 ++-
 docs/auto_examples/ex_genz_bcs.zip           | Bin 53699 -> 53582 bytes
 docs/auto_examples/ex_nn.ipynb               |   4 +-
 docs/auto_examples/ex_nn.py                  |   6 +-
 docs/auto_examples/ex_nn.rst                 |   8 +-
 docs/auto_examples/ex_nn.zip                 | Bin 9478 -> 9330 bytes
 docs/auto_examples/ex_pce.ipynb              |   2 +-
 docs/auto_examples/ex_pce.zip                | Bin 8972 -> 8972 bytes
 docs/auto_examples/sg_execution_times.rst    |   4 +-
 examples/surrogates/ex_genz_bcs.ipynb        | 598 +++++++++++++------
 17 files changed, 474 insertions(+), 242 deletions(-)

diff --git a/.github/workflows/documentation.yml b/.github/workflows/documentation.yml
index 3b870c5..1b6656b 100644
--- a/.github/workflows/documentation.yml
+++ b/.github/workflows/documentation.yml
@@ -1,6 +1,12 @@
 name: Deploy to GitHub Pages
 
-on: [push, pull_request, workflow_dispatch]
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main # Change this to your main branch if different
 
 permissions:
   contents: write
@@ -18,6 +24,7 @@ jobs:
         run: |
           pip install sphinx sphinx_rtd_theme myst_parser sphinx-autoapi ipython sphinx-gallery
           pip install .[dev]
+          pip install .[all]
 
       - name: List files
         run: |
@@ -50,4 +57,4 @@ jobs:
         uses: actions/upload-artifact@v4
         with:
           name: sphinx-html
-          path: docs/_build/html
+          path: docs/_build/html/index.html
diff --git a/docs/Makefile b/docs/Makefile
index c76bca6..3306624 100644
--- a/docs/Makefile
+++ b/docs/Makefile
@@ -36,4 +36,5 @@ clean:
 	rm -rf $(BUILDDIR)/*
 # 	rm -rf auto_examples/
 	rm -rf auto_tutorials/
-	rm -rf api/
\ No newline at end of file
+	rm -rf api/
+	rm sg_execution_times.rst
\ No newline at end of file
diff --git a/docs/auto_examples/auto_examples_jupyter.zip b/docs/auto_examples/auto_examples_jupyter.zip
index 0425fd690dda4b35b32ec841f87ae05296bb6564..e2cfe70ae6b79b65faad58f2eeef733bca873151 100644
GIT binary patch
delta 255
zcmdn9gK5ilCZPatW)=|!5J=VUjxJaK*0NE^N_eu(Y%5V@iHJZkhH7C3hU(3;g+DS)
zo+0KlnOj_7vZ8q9<~8E|{3z<Pfd-YBY>}K=%)l^pbC<dz$K(|(B9m|E3vcE(D9o0H
zSri2{4}^KZ)<cLTljqKsjR2{D+Xz&_jjW=v1t^kQ5ucZ*mswDmmlWX5$RxrH@dJw0
V#S9FBC>k{;3(Zksdov3p2mtEfJv{&b

delta 307
zcmdn8ooUYwCZPatW)=|!5RjhU6urPCdFDnTD`7_C$sg4mc|k%i&u`dqOqhY;*yh>7
zADLK-D~n_DCbx<OOBLtml%*CG>*eLemt`ts<`(1^l_>c6#fN!LJ}oB88swK+qBHrq
zSe1~DLU3kYs-c07LQ+m?UP@|C&gMk%etxJOR)KlZsUeT=T`Fc^xU|_`U6Df|A7};C
zJcxA@#l$A(>Pt=D%A&HlUB57!1LoFAvqh{IG=f~8S`lB6oT`^uP??t$;LXS+!i?}0
p+zUW&aDx;>!Gg*Dvt{H_8~}8LAWRxaFK8^D+%;Q;tz<Sx5CG6{V*3C9

diff --git a/docs/auto_examples/auto_examples_python.zip b/docs/auto_examples/auto_examples_python.zip
index 3f8d24b8e36a994509be01caba24dc4170c442fb..253ef1f083251105705974cddf6d23d8378cd946 100644
GIT binary patch
delta 230
zcmZqv&DivdkvG7bnMH&F1XA_8H}d}D;|0>uK_`QXl?50Wls8N8e`jPZ$uCOInEX*q
zWU{fK{^Slpfywg(%QmYCmGkm}R7X~>s5u+Mz;HHZ^J;lRcA!F?%?|1lLS;dcJWPKd
z-r{3m0AWtBMG#`i<hM0ap(vICE#yE}(a6XTbXG-tUY=e-Wq>y$lL#~1sYsSGFaV8)
RgC&h#lVfTX*_>-YLI51?JI??B

delta 305
zcmZqr#n}9tkvG7bnMH&F1grw{HuC=C;|0>ukzW3ras(I{ayCowe`jPat}LF+E*KzH
zoS##cT2!o;mlt1_sgRjlkY7}y;O7?~<~iA0P=+<gFSSHxa++Ydkd8udW?rhHfsR5_
zPHA3BYEI7PyMpDsd?2%bov&NT8q2`I8oN13-jH1cYD|7H7nB9EZ56Z3<aKI-llL<#
zZ{DvqAygKmlZWZ=!&`g|3?R%2b~A)nFgd42Dip=tK(})st7v58XJAOJh|kN@E2s?c
fW@Hj!hWi@HMGOo;qv2pd<K)S=YZTdz)PRHlZrW7m

diff --git a/docs/auto_examples/ex_genz_bcs.ipynb b/docs/auto_examples/ex_genz_bcs.ipynb
index b50df99..db4e8bd 100644
--- a/docs/auto_examples/ex_genz_bcs.ipynb
+++ b/docs/auto_examples/ex_genz_bcs.ipynb
@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "import os\nimport sys\n\nimport numpy as np\nimport copy\nimport math\nimport pytuq.utils.funcbank as fcb\nfrom matplotlib import pyplot as plt\nfrom sklearn.metrics import root_mean_squared_error\n\nfrom pytuq.surrogates.pce import PCE\nfrom pytuq.utils.maps import scaleDomTo01\nfrom pytuq.func.genz import GenzOscillatory"
+        "import numpy as np\nimport copy\nimport math\nfrom matplotlib import pyplot as plt\nfrom sklearn.metrics import root_mean_squared_error\n\nfrom pytuq.surrogates.pce import PCE\nfrom pytuq.utils.maps import scaleDomTo01\nfrom pytuq.func.genz import GenzOscillatory"
       ]
     },
     {
diff --git a/docs/auto_examples/ex_genz_bcs.py b/docs/auto_examples/ex_genz_bcs.py
index e186469..d523746 100644
--- a/docs/auto_examples/ex_genz_bcs.py
+++ b/docs/auto_examples/ex_genz_bcs.py
@@ -28,13 +28,10 @@
 """
 # %%
 
-import os
-import sys
 
 import numpy as np
 import copy
 import math
-import pytuq.utils.funcbank as fcb
 from matplotlib import pyplot as plt
 from sklearn.metrics import root_mean_squared_error
 
diff --git a/docs/auto_examples/ex_genz_bcs.py.md5 b/docs/auto_examples/ex_genz_bcs.py.md5
index 2aa64b0..40c4fab 100644
--- a/docs/auto_examples/ex_genz_bcs.py.md5
+++ b/docs/auto_examples/ex_genz_bcs.py.md5
@@ -1 +1 @@
-5470448baa785fa7c8ecd0b4922b46bd
\ No newline at end of file
+a25d30a5101f142688b3c516dc28d1f2
\ No newline at end of file
diff --git a/docs/auto_examples/ex_genz_bcs.rst b/docs/auto_examples/ex_genz_bcs.rst
index a747f77..c3d3aa7 100644
--- a/docs/auto_examples/ex_genz_bcs.rst
+++ b/docs/auto_examples/ex_genz_bcs.rst
@@ -45,18 +45,15 @@ with parity plots and Root Mean Square Error (RMSE) values used to compare their
 To follow along with the cross-validation algorithm for selecting the optimal eta, see section "Functions for cross-validation algorithm" in the second half of the notebook. 
 These methods have been implemented under-the-hood in PyTUQ. Refer to example "Polynomial Chaos Expansion Construction" (``ex_pce.py``) for a demonstration of how to use these methods through a direct call to the PCE class.
 
-.. GENERATED FROM PYTHON SOURCE LINES 30-45
+.. GENERATED FROM PYTHON SOURCE LINES 30-42
 
 .. code-block:: Python
 
 
-    import os
-    import sys
 
     import numpy as np
     import copy
     import math
-    import pytuq.utils.funcbank as fcb
     from matplotlib import pyplot as plt
     from sklearn.metrics import root_mean_squared_error
 
@@ -71,7 +68,7 @@ These methods have been implemented under-the-hood in PyTUQ. Refer to example "P
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 46-54
+.. GENERATED FROM PYTHON SOURCE LINES 43-51
 
 Constructing PC surrogate and generating data
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -82,7 +79,7 @@ along with training data and testing data with output noise. This data and the c
 will be used to create the same PC surrogate fitted in all three examples: first with linear regression, 
 next using BCS with a given eta, and third using BCS with the most optimal eta. 
 
-.. GENERATED FROM PYTHON SOURCE LINES 56-61
+.. GENERATED FROM PYTHON SOURCE LINES 53-58
 
 .. code-block:: Python
 
@@ -98,7 +95,7 @@ next using BCS with a given eta, and third using BCS with the most optimal eta.
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 62-87
+.. GENERATED FROM PYTHON SOURCE LINES 59-84
 
 .. code-block:: Python
 
@@ -134,13 +131,13 @@ next using BCS with a given eta, and third using BCS with the most optimal eta.
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 88-91
+.. GENERATED FROM PYTHON SOURCE LINES 85-88
 
 With a stochastic dimensionality of 4 (defined above) and a chosen polynomial order of 4, we construct the PC surrogate that 
 will be used in both builds. By calling the ``printInfo()`` method from the PCRV variable, you can print the PC surrogate's 
 full basis and current coefficients, before BCS selects and retains the most significant PC terms to reduce the basis.
 
-.. GENERATED FROM PYTHON SOURCE LINES 91-104
+.. GENERATED FROM PYTHON SOURCE LINES 88-101
 
 .. code-block:: Python
 
@@ -246,19 +243,19 @@ full basis and current coefficients, before BCS selects and retains the most sig
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 105-108
+.. GENERATED FROM PYTHON SOURCE LINES 102-105
 
 From the input parameters of our PC surrogate, we have 70 basis terms in our PCE. With 70 training points and no noise, having 70 basis terms would mean that we have a fully determined system, as the number of training points is the same as the number of basis terms. However, with the addition of noise in our training data, it becomes harder for the model to accurately fit all basis terms, leading to potential overfitting. This demonstrates the helpful role BCS might play as a choice for our regression build. As a sparse regression approach, BCS uses regularization to select only the most relevant basis terms, making it particularly effective in situations like this, where we do not have enough clear information to fit all basis terms without overfitting.
 
 In the next sections, we will explore the effects of overfitting in more detail.
 
-.. GENERATED FROM PYTHON SOURCE LINES 110-113
+.. GENERATED FROM PYTHON SOURCE LINES 107-110
 
 Least Squares Regression
 ^^^^^^^^^^^^^^^^^^^^^^^^^
 To start, we call the PCE class method of ``build()`` with no arguments to use the default regression option of least squares. Then, through ``evaluate()``, we can generate model predictions for our training and testing data.
 
-.. GENERATED FROM PYTHON SOURCE LINES 115-123
+.. GENERATED FROM PYTHON SOURCE LINES 112-120
 
 .. code-block:: Python
 
@@ -283,7 +280,7 @@ To start, we call the PCE class method of ``build()`` with no arguments to use t
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 124-137
+.. GENERATED FROM PYTHON SOURCE LINES 121-134
 
 .. code-block:: Python
 
@@ -318,7 +315,7 @@ To start, we call the PCE class method of ``build()`` with no arguments to use t
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 138-154
+.. GENERATED FROM PYTHON SOURCE LINES 135-151
 
 .. code-block:: Python
 
@@ -356,7 +353,7 @@ To start, we call the PCE class method of ``build()`` with no arguments to use t
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 155-163
+.. GENERATED FROM PYTHON SOURCE LINES 152-160
 
 .. code-block:: Python
 
@@ -382,19 +379,19 @@ To start, we call the PCE class method of ``build()`` with no arguments to use t
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 164-167
+.. GENERATED FROM PYTHON SOURCE LINES 161-164
 
 The results above show us the limitations of using least squares regression to construct our surrogate. From the parity plots, we can see how the testing predictions from the LSQ regression are more spread out from the parity line, while the training predictions are extremely close to the line. Because LSQ fits all the basis terms to the training data, the model fits too closely to the noisy training dataset, and the true underlying pattern of the function is not effectively captured. Our RMSE values align with this as well: while the training RMSE is extremely low, the testing RMSE is significantly higher, as the model struggles to generalize to the unseen test data. 
 
 To improve our model's generalization, we can build our model with BCS instead. As a sparse regression method, BCS reduces the number of basis terms with which we can fit our data to, reducing the risk of overfitting. 
 
-.. GENERATED FROM PYTHON SOURCE LINES 169-172
+.. GENERATED FROM PYTHON SOURCE LINES 166-169
 
 BCS with default settings (default eta)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 In this section, we use the same PC surrogate, ``pce_surr``, for the second build. With the flag ``regression='bcs'``, we choose the BCS method for the fitting. A user-defined eta of 1e-10 is also passed in.
 
-.. GENERATED FROM PYTHON SOURCE LINES 172-181
+.. GENERATED FROM PYTHON SOURCE LINES 169-178
 
 .. code-block:: Python
 
@@ -441,11 +438,11 @@ In this section, we use the same PC surrogate, ``pce_surr``, for the second buil
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 182-183
+.. GENERATED FROM PYTHON SOURCE LINES 179-180
 
 After fitting, we evaluate the PCE using our training and testing data. To analyze the model's goodness of fit, we first plot the surrogate predictions against the training and testing data respectively.
 
-.. GENERATED FROM PYTHON SOURCE LINES 183-188
+.. GENERATED FROM PYTHON SOURCE LINES 180-185
 
 .. code-block:: Python
 
@@ -461,7 +458,7 @@ After fitting, we evaluate the PCE using our training and testing data. To analy
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 189-202
+.. GENERATED FROM PYTHON SOURCE LINES 186-199
 
 .. code-block:: Python
 
@@ -496,7 +493,7 @@ After fitting, we evaluate the PCE using our training and testing data. To analy
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 203-219
+.. GENERATED FROM PYTHON SOURCE LINES 200-216
 
 .. code-block:: Python
 
@@ -534,7 +531,7 @@ After fitting, we evaluate the PCE using our training and testing data. To analy
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 220-228
+.. GENERATED FROM PYTHON SOURCE LINES 217-225
 
 .. code-block:: Python
 
@@ -560,13 +557,13 @@ After fitting, we evaluate the PCE using our training and testing data. To analy
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 229-232
+.. GENERATED FROM PYTHON SOURCE LINES 226-229
 
 From our parity plots, we can see how BCS already generalizes better to unseen data as compared to LSQ, with reduced error in our testing data predictions. In our RMSE calculations, notice how the training error is smaller than the testing error. Though the difference in value is small, this amount is still significant as we have noise in our training data yet no noise in our testing data. That the testing error is higher than the training error suggests that overfitting is still happening within our model. 
 
 In the next section, we explore how finding the optimal value of eta -- the stopping criterion for the BCS parameter of gamma, determined through a Bayesian evidence maximization approach -- can impact model sparsity and accuracy to avoid overfitting.
 
-.. GENERATED FROM PYTHON SOURCE LINES 235-241
+.. GENERATED FROM PYTHON SOURCE LINES 232-238
 
 BCS with optimal eta (found through cross-validation) 
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -575,7 +572,7 @@ Before we build our PC surrogate again with the most optimal eta, we first expos
 Functions for cross-validation algorithm
 +++++++++++++++++++++++++++++++++++++++++
 
-.. GENERATED FROM PYTHON SOURCE LINES 243-285
+.. GENERATED FROM PYTHON SOURCE LINES 240-282
 
 .. code-block:: Python
 
@@ -628,7 +625,7 @@ Functions for cross-validation algorithm
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 286-330
+.. GENERATED FROM PYTHON SOURCE LINES 283-327
 
 .. code-block:: Python
 
@@ -683,7 +680,7 @@ Functions for cross-validation algorithm
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 331-448
+.. GENERATED FROM PYTHON SOURCE LINES 328-445
 
 .. code-block:: Python
 
@@ -811,7 +808,7 @@ Functions for cross-validation algorithm
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 449-454
+.. GENERATED FROM PYTHON SOURCE LINES 446-451
 
 BCS build with the most optimal eta
 +++++++++++++++++++++++++++++++++++++
@@ -819,7 +816,7 @@ Instead of using a default eta, here we call the cross-validation algorithm, ``o
 
 - With the flag ``plot=True``, the CV algorithm produces a graph of the training and testing (validation) data's RMSE values for each eta. The eta with the smallest RMSE for the validation data is the one chosen as the optimal eta.
 
-.. GENERATED FROM PYTHON SOURCE LINES 454-461
+.. GENERATED FROM PYTHON SOURCE LINES 451-458
 
 .. code-block:: Python
 
@@ -1007,7 +1004,7 @@ Instead of using a default eta, here we call the cross-validation algorithm, ``o
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 462-467
+.. GENERATED FROM PYTHON SOURCE LINES 459-464
 
 From our eta plot above, we can see that our most optimal eta falls at :math:`1 \times 10^{-10}`, where the validation error is the lowest. While this indicates that the model performs well at this eta value, we can still observe a tendency towards overfitting in the model. For larger eta values, the training and validation RMSE lines are close together, suggesting that the model is performing similarly on both seen and unseen datasets, as would be desired. However, as eta decreases, the training RMSE falls while the validation RMSE rises, highlighting a region where overfitting occurs. 
 
@@ -1015,7 +1012,7 @@ This behavior is expected because smaller eta values retain more basis terms, in
 
 Now, with the optimum eta obtained, we can run the fitting again and produce parity plots for our predicted output.
 
-.. GENERATED FROM PYTHON SOURCE LINES 467-476
+.. GENERATED FROM PYTHON SOURCE LINES 464-473
 
 .. code-block:: Python
 
@@ -1052,7 +1049,7 @@ Now, with the optimum eta obtained, we can run the fitting again and produce par
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 477-482
+.. GENERATED FROM PYTHON SOURCE LINES 474-479
 
 .. code-block:: Python
 
@@ -1068,7 +1065,7 @@ Now, with the optimum eta obtained, we can run the fitting again and produce par
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 483-496
+.. GENERATED FROM PYTHON SOURCE LINES 480-493
 
 .. code-block:: Python
 
@@ -1103,7 +1100,7 @@ Now, with the optimum eta obtained, we can run the fitting again and produce par
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 497-510
+.. GENERATED FROM PYTHON SOURCE LINES 494-507
 
 .. code-block:: Python
 
@@ -1138,7 +1135,7 @@ Now, with the optimum eta obtained, we can run the fitting again and produce par
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 511-519
+.. GENERATED FROM PYTHON SOURCE LINES 508-516
 
 .. code-block:: Python
 
@@ -1164,7 +1161,7 @@ Now, with the optimum eta obtained, we can run the fitting again and produce par
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 520-523
+.. GENERATED FROM PYTHON SOURCE LINES 517-520
 
 In these final RMSE calculations, we can see how our training RMSE has decreased from 1.80e-02 to 1.21e-02 by building with the most optimal eta. This indicates that our model has improved in generalization and is performing better on unseen data. Though our training error is still larger than our testing error, this can be attributed to the lack of noise in our testing data, while noise is present in our training data. While the optimal eta reduces overfitting and improves generalization, the noise in our training data still impacts the training error and remains an important consideration during our evaluation of the model performance.
 
@@ -1173,7 +1170,7 @@ While this demonstration calls the cross-validation algorithm as a function outs
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 6.413 seconds)
+   **Total running time of the script:** (0 minutes 10.810 seconds)
 
 
 .. _sphx_glr_download_auto_examples_ex_genz_bcs.py:
diff --git a/docs/auto_examples/ex_genz_bcs.zip b/docs/auto_examples/ex_genz_bcs.zip
index f9021fb84532e603c08c829a8b2b86d8e5aad25d..ff650c2d197124f31d17d90a9bdb0a3df33f5083 100644
GIT binary patch
delta 135
zcmX@SnEBiyW{CiAW)=|!5J=VUj*hHcQFAtif#Gb-MhQdq$#LvDo7b}Uh4N+t<w{Jp
zNKP$gV3@kuBUX`Pa#O1M=Ci4V*?g$_Ci`5}Q$SG;)FKGB075Kj{24QO)<tEuy%#_N
E0Md;sZ~y=R

delta 250
zcmX@Ni23khW{CiAW)=|!5a3QtjsA7MZY66h0|RU9MhQc9k<8qJ{Gt+t{9-OBtGKdw
zvIo1aGL&0TSyEc4S6Y&pQ>>R(nwOlEn3t`PSgeqioWwObB2{JcO!ll$UOu3~sUeT=
zT`Fc^xU^XyR*^#}zc?ljVPs5ROx|RzR6Qla#%>NvEzagcb?W5n7xWZRECE_12=)_%
SSkh=1J6ZLjGMmvwkN^NQF;uw#

diff --git a/docs/auto_examples/ex_nn.ipynb b/docs/auto_examples/ex_nn.ipynb
index e28a1e2..3cef92d 100644
--- a/docs/auto_examples/ex_nn.ipynb
+++ b/docs/auto_examples/ex_nn.ipynb
@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "import sys\nimport torch\nimport numpy as np\n\nfrom pytuq.surrogates.nn import NN\nfrom quinn.solvers.nn_vi import NN_VI\nfrom quinn.nns.rnet import RNet, Poly\nfrom quinn.utils.plotting import myrc\nfrom quinn.utils.maps import scale01ToDom\nfrom quinn.func.funcs import Sine, Sine10, blundell\n\ndef main():\n    \"\"\"Main function.\"\"\"\n    torch.set_default_dtype(torch.double)\n    myrc()\n\n    #################################################################################\n    #################################################################################\n\n    # defaults to cuda:0 if available\n    device_id='cuda:0'\n    device = torch.device(device_id if torch.cuda.is_available() else 'cpu')\n    print(\"Using device\",device)\n\n    nall = 15 # total number of points\n    trn_factor = 0.9 # which fraction of nall goes to training\n    ntst = 13 # separate test set\n    ndim = 1 # input dimensionality\n    datanoise = 0.02 # Noise in the generated data\n    true_model, nout = Sine, 1  # Scalar valued output example\n\n    #################################################################################\n    #################################################################################\n\n    # Domain: defining range of input variable\n    domain = np.tile(np.array([-np.pi, np.pi]), (ndim, 1))\n\n    np.random.seed(111)\n\n    # Generating x-y training, validation, and testing data\n    xall = scale01ToDom(np.random.rand(nall, ndim), domain)\n    if true_model is not None:\n        yall = true_model(xall, datanoise=datanoise)\n\n    if ntst > 0:\n        np.random.seed(100)\n        xtst = scale01ToDom(np.random.rand(ntst, ndim), domain)\n        if true_model is not None:\n            ytst = true_model(xtst, datanoise=datanoise)\n\n    # (1) Initialize neural network with optional parameters for object instantiation\n    net_options = {'wp_function': Poly(0),\n                   'indim': ndim, \n                   'outdim': nout,\n                   'layer_pre': True,\n                   'layer_post': True,\n                   'biasorno': True,\n                   'nonlin': True,\n                   'mlp': False, \n                   'final_layer': None,\n                   'device': device,\n                   }\n\n    # Pass in unpacked net_options dict to constructor through kwargs\n    nnet = NN('RNet', 3, 3, **net_options)\n    \n    # (1.5) Split data into training and validation, assign through member functions\n    ntrn = int(trn_factor * nall)\n    indperm = range(nall) # np.random.permutation(range(nall))\n    indtrn = indperm[:ntrn]\n    indval = indperm[ntrn:]\n    xtrn, xval = xall[indtrn, :], xall[indval, :]\n    ytrn, yval = yall[indtrn, :], yall[indval, :]\n\n    nnet.set_validation_data(xval, yval) # optional\n    nnet.set_training_data(xtrn, ytrn)\n\n    # (2) 1st build: Call build function (defaults to UQ method of variational inference) with optional parameters for fitting\n    nnet.build(datanoise=datanoise, lrate=0.01, batch_size=None, nsam=1, nepochs=5000, verbose=False)\n\n    results = nnet.evaluate(xtst, nsam = 100, msc = 2) # Return samples of predictions with variance + covariance\n    print(\"Y_eval:\", results['Y_eval'], end=\"\\n\\n\") # Printing only samples of predictions\n\n    # (3) 2nd build: Example of throwing an exception when passing in a network option through build()\n    # fit_options = {'datanoise': 0.05,\n    #                'outdim': 3,\n    #                'lrate': 0.01,\n    #                'batch_size': None,\n    #                'nsam': 1,\n    #                'nepochs': 300,\n    #                'verbose': False\n    #                }\n\n    # nnet.build(**fit_options)\n    # results = nnet.evaluate(xtst, nsam = 100, msc = 2)\n    # print(results)\n\n\nif __name__ == '__main__':\n    main()"
+        "import torch\nimport numpy as np\n\nfrom pytuq.surrogates.nn import NN\nfrom quinn.nns.rnet import Poly\nfrom quinn.utils.plotting import myrc\nfrom quinn.utils.maps import scale01ToDom\nfrom quinn.func.funcs import Sine\n\ndef main():\n    \"\"\"Main function.\"\"\"\n    torch.set_default_dtype(torch.double)\n    myrc()\n\n    #################################################################################\n    #################################################################################\n\n    # defaults to cuda:0 if available\n    device_id='cuda:0'\n    device = torch.device(device_id if torch.cuda.is_available() else 'cpu')\n    print(\"Using device\",device)\n\n    nall = 15 # total number of points\n    trn_factor = 0.9 # which fraction of nall goes to training\n    ntst = 13 # separate test set\n    ndim = 1 # input dimensionality\n    datanoise = 0.02 # Noise in the generated data\n    true_model, nout = Sine, 1  # Scalar valued output example\n\n    #################################################################################\n    #################################################################################\n\n    # Domain: defining range of input variable\n    domain = np.tile(np.array([-np.pi, np.pi]), (ndim, 1))\n\n    np.random.seed(111)\n\n    # Generating x-y training, validation, and testing data\n    xall = scale01ToDom(np.random.rand(nall, ndim), domain)\n    if true_model is not None:\n        yall = true_model(xall, datanoise=datanoise)\n\n    if ntst > 0:\n        np.random.seed(100)\n        xtst = scale01ToDom(np.random.rand(ntst, ndim), domain)\n        if true_model is not None:\n            ytst = true_model(xtst, datanoise=datanoise)\n\n    # (1) Initialize neural network with optional parameters for object instantiation\n    net_options = {'wp_function': Poly(0),\n                   'indim': ndim, \n                   'outdim': nout,\n                   'layer_pre': True,\n                   'layer_post': True,\n                   'biasorno': True,\n                   'nonlin': True,\n                   'mlp': False, \n                   'final_layer': None,\n                   'device': device,\n                   }\n\n    # Pass in unpacked net_options dict to constructor through kwargs\n    nnet = NN('RNet', 3, 3, **net_options)\n    \n    # (1.5) Split data into training and validation, assign through member functions\n    ntrn = int(trn_factor * nall)\n    indperm = range(nall) # np.random.permutation(range(nall))\n    indtrn = indperm[:ntrn]\n    indval = indperm[ntrn:]\n    xtrn, xval = xall[indtrn, :], xall[indval, :]\n    ytrn, yval = yall[indtrn, :], yall[indval, :]\n\n    nnet.set_validation_data(xval, yval) # optional\n    nnet.set_training_data(xtrn, ytrn)\n\n    # (2) 1st build: Call build function (defaults to UQ method of variational inference) with optional parameters for fitting\n    nnet.build(datanoise=datanoise, lrate=0.01, batch_size=None, nsam=1, nepochs=5000, verbose=False)\n\n    results = nnet.evaluate(xtst, nsam = 100, msc = 2) # Return samples of predictions with variance + covariance\n    print(\"Y_eval:\", results['Y_eval'], end=\"\\n\\n\") # Printing only samples of predictions\n\n    # (3) 2nd build: Example of throwing an exception when passing in a network option through build()\n    # fit_options = {'datanoise': 0.05,\n    #                'outdim': 3,\n    #                'lrate': 0.01,\n    #                'batch_size': None,\n    #                'nsam': 1,\n    #                'nepochs': 300,\n    #                'verbose': False\n    #                }\n\n    # nnet.build(**fit_options)\n    # results = nnet.evaluate(xtst, nsam = 100, msc = 2)\n    # print(results)\n\n\nif __name__ == '__main__':\n    main()"
       ]
     }
   ],
@@ -35,7 +35,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.13.7"
+      "version": "3.12.7"
     }
   },
   "nbformat": 4,
diff --git a/docs/auto_examples/ex_nn.py b/docs/auto_examples/ex_nn.py
index db32364..893ee5c 100644
--- a/docs/auto_examples/ex_nn.py
+++ b/docs/auto_examples/ex_nn.py
@@ -7,16 +7,14 @@
 The ``build()`` and ``evaluate()`` functions similarly accept dictionaries and explicit keyword arguments during their respective function calls.
 """
 
-import sys
 import torch
 import numpy as np
 
 from pytuq.surrogates.nn import NN
-from quinn.solvers.nn_vi import NN_VI
-from quinn.nns.rnet import RNet, Poly
+from quinn.nns.rnet import Poly
 from quinn.utils.plotting import myrc
 from quinn.utils.maps import scale01ToDom
-from quinn.func.funcs import Sine, Sine10, blundell
+from quinn.func.funcs import Sine
 
 def main():
     """Main function."""
diff --git a/docs/auto_examples/ex_nn.rst b/docs/auto_examples/ex_nn.rst
index 2804ae2..5fe569f 100644
--- a/docs/auto_examples/ex_nn.rst
+++ b/docs/auto_examples/ex_nn.rst
@@ -25,21 +25,19 @@ This example demonstrates how to use the Neural Network wrapper class, ``pytuq.s
 The constructor of the NN class accepts in an optional dictionary, ``net_options``, to specify additional hyperparameters. 
 The ``build()`` and ``evaluate()`` functions similarly accept dictionaries and explicit keyword arguments during their respective function calls.
 
-.. GENERATED FROM PYTHON SOURCE LINES 9-109
+.. GENERATED FROM PYTHON SOURCE LINES 9-107
 
 .. code-block:: Python
 
 
-    import sys
     import torch
     import numpy as np
 
     from pytuq.surrogates.nn import NN
-    from quinn.solvers.nn_vi import NN_VI
-    from quinn.nns.rnet import RNet, Poly
+    from quinn.nns.rnet import Poly
     from quinn.utils.plotting import myrc
     from quinn.utils.maps import scale01ToDom
-    from quinn.func.funcs import Sine, Sine10, blundell
+    from quinn.func.funcs import Sine
 
     def main():
         """Main function."""
diff --git a/docs/auto_examples/ex_nn.zip b/docs/auto_examples/ex_nn.zip
index 4feadc4727a719eb5fc456f035afb3acf203eafc..1228e18d177d57a01b46ea1ff90ab74e87ecca11 100644
GIT binary patch
delta 213
zcmZqk`s5)V;LXe;!T<uP`rXk%CxeQW1sE8VH;R8}oGi)YF<DYXVDen1vdyZ@<-EKg
zB@uyQ4AsI64Aq-g3VdXmyiC{!tVUm?a`P^cett%y$zCeXl_-V*4deh@0U?$&f~~8F
z&&$&*s0{FCWD;RUI00@x&<<`CU7kR5Qo*`13o7%H0=!w-K=MpLm=C1iDuZ|cB`Gf5

delta 302
zcmez5(dH!{;LXe;!T<tRfqBu9UjCbM1Q-}{Hi~~|WG=2Op3KG+AXS{7Q<hp(te2M;
zUzVwmnOl%wRHESL7a!(1*^5brHOMcuL}zj;Q@N0iLU3kYs-c07LQ+m?UP@|C&gMHz
z<-EMo)0?7Sp5L(Jm@oswvCRnrADLKzX2;}B_7V=pXZi$TS*Yo2gsZTbt|rpY&uBb(
zo3e8#it~Y9-~f9HLM&(m(Ww>jd3kyTl>y$2Od`w>PouaD=sIo`U6UsJsmQT4s(=Im
Dj3-zA

diff --git a/docs/auto_examples/ex_pce.ipynb b/docs/auto_examples/ex_pce.ipynb
index 2ca2095..bfd2e5a 100644
--- a/docs/auto_examples/ex_pce.ipynb
+++ b/docs/auto_examples/ex_pce.ipynb
@@ -71,7 +71,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.13.7"
+      "version": "3.12.7"
     }
   },
   "nbformat": 4,
diff --git a/docs/auto_examples/ex_pce.zip b/docs/auto_examples/ex_pce.zip
index 68d919293e273cd51797647323fd32f6a9710c7e..09d2204d7338d4ad935baf942d3338b01e6a3e3a 100644
GIT binary patch
delta 95
zcmeBi>v7`^@MdNaVE}<t{qBvt|M)n7bac7;x0cPq{8qw@Mw9)NoMk~`JWPKd-r{3m
d0AWtB4hXSi@;W6cxUR_;ltdVpOn$1Q4gkE_8k_(C

delta 95
zcmeBi>v7`^@MdNaVE_TEz`TvT|M)nhr#D3}FiD=dS(x8Sn9+E$pOUjIP%fH>>F>i^
fd<+aA%n8;3Ar?$trz8c}HTi;)2;+juPnFaGnvogf

diff --git a/docs/auto_examples/sg_execution_times.rst b/docs/auto_examples/sg_execution_times.rst
index 846e881..86a5a16 100644
--- a/docs/auto_examples/sg_execution_times.rst
+++ b/docs/auto_examples/sg_execution_times.rst
@@ -6,7 +6,7 @@
 
 Computation times
 =================
-**00:06.413** total execution time for 3 files **from auto_examples**:
+**00:10.810** total execution time for 3 files **from auto_examples**:
 
 .. container::
 
@@ -33,7 +33,7 @@ Computation times
      - Time
      - Mem (MB)
    * - :ref:`sphx_glr_auto_examples_ex_genz_bcs.py` (``ex_genz_bcs.py``)
-     - 00:06.413
+     - 00:10.810
      - 0.0
    * - :ref:`sphx_glr_auto_examples_ex_nn.py` (``ex_nn.py``)
      - 00:00.000
diff --git a/examples/surrogates/ex_genz_bcs.ipynb b/examples/surrogates/ex_genz_bcs.ipynb
index 6fe2d1b..3e724a3 100644
--- a/examples/surrogates/ex_genz_bcs.ipynb
+++ b/examples/surrogates/ex_genz_bcs.ipynb
@@ -52,18 +52,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Setting a random number generator seed:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Random number generator\n",
-    "from scipy.stats import qmc\n",
-    "rng_seed = 4311"
+    "# Constructing PC surrogate and generating data"
    ]
   },
   {
@@ -254,33 +243,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Regression method: bcs\n",
-      "Retained Basis and Coefficients:\n",
-      "[[1 0 0 0]\n",
-      " [0 0 0 0]\n",
-      " [0 1 1 0]\n",
-      " [3 1 0 0]\n",
-      " [0 2 2 0]\n",
-      " [0 0 0 4]\n",
-      " [1 0 1 0]\n",
-      " [3 0 1 0]\n",
-      " [3 0 0 0]\n",
-      " [0 1 1 1]\n",
-      " [0 1 0 3]\n",
-      " [0 1 0 1]\n",
-      " [0 1 1 2]\n",
-      " [1 0 0 1]\n",
-      " [0 1 2 1]\n",
-      " [0 0 1 0]\n",
-      " [0 0 0 3]\n",
-      " [2 1 1 0]\n",
-      " [0 0 3 1]\n",
-      " [2 1 0 0]\n",
-      " [0 1 3 0]] [-0.97219263 -0.24303645  0.17425137  0.07702365  0.50399841 -0.06768243\n",
-      "  0.45380039 -0.37528979  0.28387471 -4.8909167  -0.13601235  1.76967257\n",
-      "  1.26856475 -0.11360014  1.69839209  0.22132661 -0.08252123 -0.24310745\n",
-      " -0.09591703  0.12068122 -0.29288557]\n",
-      "Number of retained basis terms: 21\n"
+      "Regression method: lsq\n"
      ]
     }
    ],
@@ -288,34 +251,6 @@
     "# (2) Build the linear regression object for fitting\n",
     "pce_surr.build()\n",
     "\n",
-    "# Optional verbosity output:\n",
-    "print(\"Retained Basis and Coefficients:\")\n",
-    "pce_surr.pcrv.printInfo()\n",
-    "print(\"Number of retained basis terms:\", len(pce_surr.pcrv.mindices[0]))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "After fitting, we evaluate the PCE using our training and testing data. To analyze the model's goodness of fit, we calculate the root mean square error between the surrogate results and the training and testing data."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The training RMSE error in the PCE BCS approximation is 7.21e-02\n",
-      "The testing RMSE error in the PCE BCS approximation is 1.33e-01\n"
-     ]
-    }
-   ],
-   "source": [
     "# (3) Evaluate the PC model\n",
     "y_trn_approx = pce_surr.evaluate(value_ksi_trn)\n",
     "y_tst_approx = pce_surr.evaluate(value_ksi_tst)\n"
@@ -323,12 +258,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 800x600 with 1 Axes>"
       ]
@@ -353,12 +288,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 800x600 with 1 Axes>"
       ]
@@ -417,95 +352,8 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 21,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "0 1.0\n",
-      "0 0.1\n",
-      "0 0.01\n",
-      "0 0.001\n",
-      "0 0.0001\n",
-      "0 1e-05\n",
-      "0 1e-06\n",
-      "0 1e-07\n",
-      "0 1e-08\n",
-      "0 1e-09\n",
-      "0 1e-10\n",
-      "0 1e-11\n",
-      "0 1e-12\n",
-      "0 1e-13\n",
-      "0 1e-14\n",
-      "0 1e-15\n",
-      "1 1.0\n",
-      "1 0.1\n",
-      "1 0.01\n",
-      "1 0.001\n",
-      "1 0.0001\n",
-      "1 1e-05\n",
-      "1 1e-06\n",
-      "1 1e-07\n",
-      "1 1e-08\n",
-      "1 1e-09\n",
-      "1 1e-10\n",
-      "1 1e-11\n",
-      "1 1e-12\n",
-      "1 1e-13\n",
-      "1 1e-14\n",
-      "1 1e-15\n",
-      "2 1.0\n",
-      "2 0.1\n",
-      "2 0.01\n",
-      "2 0.001\n",
-      "2 0.0001\n",
-      "2 1e-05\n",
-      "2 1e-06\n",
-      "2 1e-07\n",
-      "2 1e-08\n",
-      "2 1e-09\n",
-      "2 1e-10\n",
-      "2 1e-11\n",
-      "2 1e-12\n",
-      "2 1e-13\n",
-      "2 1e-14\n",
-      "2 1e-15\n",
-      "3 1.0\n",
-      "3 0.1\n",
-      "3 0.01\n",
-      "3 0.001\n",
-      "3 0.0001\n",
-      "3 1e-05\n",
-      "[-1.28769463e-03 -1.03122584e-02  3.82312400e-03 -5.81512540e-03\n",
-      "  4.02182946e-03  7.24999380e-03  2.82610107e-04  1.21345570e-03\n",
-      "  1.23556444e-03  2.01236671e-02  4.23960882e-03  1.78894198e-03\n",
-      "  7.54914945e-03  1.35977343e-03 -5.92043337e-03 -2.33667199e-05\n",
-      "  9.38402108e-03 -2.73063601e-03  7.90212500e-03]\n",
-      "Warning: Sigma matrix has a negative diagonal element. Setting them to zero, but this may lead to inaccuracies.\n",
-      "3 1e-06\n"
-     ]
-    },
-    {
-     "ename": "SystemExit",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "An exception has occurred, use %tb to see the full traceback.\n",
-      "\u001b[31mSystemExit\u001b[39m\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/IPython/core/interactiveshell.py:3707: UserWarning: To exit: use 'exit', 'quit', or Ctrl-D.\n",
-      "  warn(\"To exit: use 'exit', 'quit', or Ctrl-D.\", stacklevel=1)\n"
-     ]
-    }
-   ],
    "source": [
     "# BCS with default settings (default eta)"
    ]
@@ -519,9 +367,38 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Regression method: bcs\n",
+      "Retained Basis and Coefficients:\n",
+      "[[0 0 0 0]\n",
+      " [1 0 0 0]\n",
+      " [0 1 0 0]\n",
+      " [0 0 0 1]\n",
+      " [2 0 0 0]\n",
+      " [0 0 1 0]\n",
+      " [1 1 0 0]\n",
+      " [2 1 0 0]\n",
+      " [0 4 0 0]\n",
+      " [0 0 3 0]\n",
+      " [2 0 2 0]\n",
+      " [1 0 0 2]\n",
+      " [2 1 1 0]\n",
+      " [1 0 2 0]\n",
+      " [1 2 1 0]\n",
+      " [1 2 0 1]\n",
+      " [1 0 0 3]] [-0.62694767 -0.37426547 -0.08797315 -0.02795855  0.04176134 -0.03783695\n",
+      "  0.01375504  0.02559825 -0.01616989 -0.01758198 -0.02274328  0.01132392\n",
+      " -0.01835694 -0.00490663 -0.00938681 -0.00898039  0.00175116]\n",
+      "Number of retained basis terms: [17]\n"
+     ]
+    }
+   ],
    "source": [
     "# (2) Build the linear regression object for fitting\n",
     "pce_surr.build(regression='bcs', eta=1.e-10)\n",
@@ -552,9 +429,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# Plot the surrogate model's output vs. the training data output\n",
     "y_trn_mM = [y_trn[:,0].min(),y_trn[:,0].max()]\n",
@@ -571,9 +459,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# Plot the surrogate model's output vs. the testing data output\n",
     "\n",
@@ -644,7 +543,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -692,7 +591,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -742,7 +641,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -782,7 +681,7 @@
     "\n",
     "    # Loop through each fold\n",
     "    for i in range(nfolds):\n",
-    "        \n",
+    "\n",
     "        # Get the training and validation data\n",
     "        x_tr = kfold_data[i]['xtrain']\n",
     "        y_tr = kfold_data[i]['ytrain']\n",
@@ -798,11 +697,6 @@
     "\n",
     "        # Loop through each eta\n",
     "        for eta in etas:\n",
-    "            print(i, eta)\n",
-    "            np.savetxt('xx', x_tr)\n",
-    "            np.savetxt('yy', y_tr)\n",
-    "            if (i==3 and eta==0.000001):\n",
-    "                sys.exit()\n",
     "\n",
     "            # Conduct the BCS fitting. The object is automatically updated with new multiindex and coefficients received from the fitting.\n",
     "            cfs = pce_copy.build(regression = 'bcs', eta=eta)\n",
@@ -868,24 +762,364 @@
     "    return eta_opt"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### BCS build with the most optimal eta"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Instead of using a default eta, here we call the cross-validation algorithm, `optimize_eta()`, to choose the most optimal eta from a range of etas given below. \n",
+    "\n",
+    "- With the flag `plot=True`, the CV algorithm produces a graph of the training and testing (validation) data's RMSE values for each eta. The eta with the smallest RMSE for the validation data is the one chosen as the optimal eta."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Fold 1, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 0.001, 5 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 0.0001, 9 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-05, 12 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-06, 13 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-07, 16 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-08, 16 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-09, 16 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-10, 16 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-11, 16 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-12, 16 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-13, 16 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-14, 16 terms retained out of a full basis of size 17\n",
+      "Fold 1, eta 1e-15, 16 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 0.001, 5 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 0.0001, 9 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-05, 12 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-06, 16 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-07, 18 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-08, 18 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-09, 18 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-10, 18 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-11, 18 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-12, 18 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-13, 18 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-14, 18 terms retained out of a full basis of size 17\n",
+      "Fold 2, eta 1e-15, 18 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 0.001, 8 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 0.0001, 9 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-05, 12 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-06, 14 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-07, 17 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-08, 17 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-09, 18 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-10, 18 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-11, 18 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-12, 18 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-13, 18 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-14, 18 terms retained out of a full basis of size 17\n",
+      "Fold 3, eta 1e-15, 18 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 0.001, 5 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 0.0001, 11 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-05, 11 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-06, 16 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-07, 17 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-08, 17 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-09, 17 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-10, 17 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-11, 17 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-12, 17 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-13, 17 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-14, 17 terms retained out of a full basis of size 17\n",
+      "Fold 4, eta 1e-15, 17 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 0.001, 7 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 0.0001, 10 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-05, 12 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-06, 14 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-07, 14 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-08, 14 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-09, 14 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-10, 14 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-11, 14 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-12, 14 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-13, 14 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-14, 14 terms retained out of a full basis of size 17\n",
+      "Fold 5, eta 1e-15, 14 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 0.001, 7 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 0.0001, 11 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-05, 11 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-06, 16 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-07, 16 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-08, 16 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-09, 17 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-10, 17 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-11, 17 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-12, 17 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-13, 17 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-14, 17 terms retained out of a full basis of size 17\n",
+      "Fold 6, eta 1e-15, 17 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 0.001, 4 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 0.0001, 7 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-05, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-06, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-07, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-08, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-09, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-10, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-11, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-12, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-13, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-14, 13 terms retained out of a full basis of size 17\n",
+      "Fold 7, eta 1e-15, 13 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 0.001, 7 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 0.0001, 10 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-05, 11 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-06, 15 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-07, 16 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-08, 16 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-09, 16 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-10, 16 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-11, 16 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-12, 16 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-13, 16 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-14, 16 terms retained out of a full basis of size 17\n",
+      "Fold 8, eta 1e-15, 16 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 0.001, 7 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 0.0001, 8 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-05, 12 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-06, 14 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-07, 15 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-08, 15 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-09, 15 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-10, 15 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-11, 15 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-12, 15 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-13, 15 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-14, 15 terms retained out of a full basis of size 17\n",
+      "Fold 9, eta 1e-15, 15 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1.0, 3 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 0.1, 3 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 0.01, 4 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 0.001, 4 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 0.0001, 9 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-05, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-06, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-07, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-08, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-09, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-10, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-11, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-12, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-13, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-14, 14 terms retained out of a full basis of size 17\n",
+      "Fold 10, eta 1e-15, 14 terms retained out of a full basis of size 17\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x1000 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# We first create a list of possible etas to pass in: [1e-16, 1e-15, ... , 1e-2, 1e-1, 1]\n",
+    "etas = 1/np.power(10,[i for i in range(0,16)])\n",
+    "\n",
+    "# Then, we call the function to choose the optimal eta:\n",
+    "eta_opt = optimize_eta(pce_surr, etas, nfolds=10, verbose = True, plot=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "From our eta plot above, we can see that our most optimal eta falls at $1 \\times 10^{-4}$, where the validation error is the lowest. While this indicates that the model performs well at this eta value, we can still observe a tendency towards overfitting in the model. For larger eta values, the training and validation RMSE lines are close together, suggesting that the model is performing similarly on both seen and unseen datasets, as would be desired. However, as eta decreases, the training RMSE falls while the validation RMSE rises, highlighting a region where overfitting occurs. \n",
+    "\n",
+    "This behavior is expected because smaller eta values retain more basis terms, increasing the model's degrees of freedom. While this added flexibility allows the model to fit the training data more closely, it also makes the model more prone to fitting noise rather than capturing the true underlying function. Selecting the most optimal eta of $1 \\times 10^{-4}$, as compared to the earlier user-defined eta of $1 \\times 10^{-10}$, allows us to balance model complexity and generalization.\n",
+    "\n",
+    "Now, with the most optimal eta obtained, we can run the fitting again and produce parity plots for our predicted output."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Regression method: bcs\n",
+      "Retained Basis and Coefficients:\n",
+      "[[0 0 0 0]\n",
+      " [1 0 0 0]\n",
+      " [0 1 0 0]\n",
+      " [0 0 0 1]\n",
+      " [2 0 0 0]\n",
+      " [0 0 1 0]\n",
+      " [1 1 0 0]\n",
+      " [2 1 0 0]] [-0.62783727 -0.37134989 -0.08735439 -0.02919352  0.0480559  -0.03471433\n",
+      "  0.0232746   0.0196456 ]\n",
+      "Number of retained basis terms: [8]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Build the linear regression object for fitting\n",
+    "pce_surr.build(regression='bcs', eta=eta_opt)\n",
+    "\n",
+    "# Optional verbosity output:\n",
+    "print(\"Retained Basis and Coefficients:\")\n",
+    "pce_surr.pcrv.printInfo()\n",
+    "print(\"Number of retained basis terms:\", pce_surr.get_pc_terms())"
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "# Evaluate the PC model with training and testing data\n",
+    "y_trn_approx = pce_surr.evaluate(value_ksi_trn)\n",
+    "y_tst_approx = pce_surr.evaluate(value_ksi_tst)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot the surrogate model's output vs. the training data output\n",
+    "y_tst_mM = [y_trn[:,0].min(),y_trn[:,0].max()]\n",
+    "\n",
+    "fig2 = plt.figure(figsize=(8,6))\n",
+    "ax2 = fig2.add_axes([0.15, 0.15, 0.80, 0.75])\n",
+    "\n",
+    "ax2.plot(y_trn[:,0],y_trn_approx[\"Y_eval\"],\".\")\n",
+    "ax2.plot(y_tst_mM,y_tst_mM) # Diagonal line\n",
+    "\n",
+    "ax2.set_xlabel(\"Train Data y\", size=16)\n",
+    "ax2.set_ylabel(\"Predicted y\", size=16); "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot the surrogate model's output vs. the testing data output\n",
+    "y_tst_mM = [y_tst[:,0].min(),y_tst[:,0].max()]\n",
+    "\n",
+    "fig2 = plt.figure(figsize=(8,6))\n",
+    "ax2 = fig2.add_axes([0.15, 0.15, 0.80, 0.75])\n",
+    "\n",
+    "ax2.plot(y_tst[:,0],y_tst_approx[\"Y_eval\"],\".\")\n",
+    "ax2.plot(y_tst_mM,y_tst_mM) # Diagonal line\n",
+    "\n",
+    "ax2.set_xlabel(\"Test Data y\", size=16)\n",
+    "ax2.set_ylabel(\"Predicted y\", size=16); "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The training RMSE in the PCE BCS approximation is 2.02e-02\n",
+      "The testing RMSE in the PCE BCS approximation is 1.21e-02\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Evaluate goodness of fit with RMSE\n",
+    "rmse_trn = root_mean_squared_error(y_trn[:,0],y_trn_approx[\"Y_eval\"])\n",
+    "print(\"The training RMSE in the PCE BCS approximation is %.2e\"%rmse_trn)\n",
+    "\n",
+    "rmse_tst = root_mean_squared_error(y_tst[:,0],y_tst_approx[\"Y_eval\"])\n",
+    "print(\"The testing RMSE in the PCE BCS approximation is %.2e\"%rmse_tst)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In these final RMSE calculations, we can see how our training RMSE has decreased from 1.80e-02 to 1.21e-02 by building with the most optimal eta. This indicates that our model has improved in generalization and is performing better on unseen data. Though our training error is still larger than our testing error, this can be attributed to the lack of noise in our testing data, while noise is present in our training data. While the optimal eta reduces overfitting and improves generalization, the noise in our training data still impacts the training error and remains an important consideration during our evaluation of the model performance.\n",
+    "\n",
+    "While this demonstration calls the cross-validation algorithm as a function outside of the PCE class, these methods have been implemented in PyTUQ through the PCE class. The example \"Polynomial Chaos Expansion Construction\" demonstrates how to call the eta optimization methods directly from the PCE class."
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "py3.12",
    "language": "python",
    "name": "python3"
   },
@@ -899,9 +1133,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.13.7"
+   "version": "3.12.7"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 2
 }