deploy: 1193a85

libAtoms · Jan 31, 2024 · 82adc2c · 82adc2c
1 parent d3d83ca
commit 82adc2c
Show file tree

Hide file tree

Showing 20 changed files with 142 additions and 196 deletions.
diff --git a/_sources/examples.daisy_chain_mlip_fitting.ipynb b/_sources/examples.daisy_chain_mlip_fitting.ipynb
@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -22,7 +21,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -88,19 +86,14 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "nbsphinx": "hidden"
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# set random seed, so that MD runs, etc are reproducible and we can check for RMSEs. \n",
-    "# this cell is hidden from tutorials. \n",
-    "random_seed = 20230301\n",
-    "np.random.seed(random_seed)"
+    "rng = np.random.default_rng(20230301)"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -127,7 +120,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -157,7 +149,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -196,15 +187,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# regenerate smiles_confgis with a random seed set for testing purposes\n",
+    "# regenerate smiles_configs with a random seed set for testing purposes\n",
     "# this cell is hidden from docs. \n",
     "\n",
     "outputs = OutputSpec(\"1.ch.rdkit.xyz\", overwrite=True)\n",
-    "smiles_configs = smiles.smiles(all_smiles, outputs=outputs, randomSeed=random_seed)"
+    "# set seed for smiles generation to a value from our (reproducible) random number generator\n",
+    "smiles_configs = smiles.smiles(all_smiles, outputs=outputs, randomSeed=int(rng.integers(np.iinfo(np.int32).max,\n",
+    "                                                                                        dtype=np.int32)))"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -252,7 +244,7 @@
     "# add random seet for testing purposes\n",
     "# this cell is hidden from tutorials. \n",
     "\n",
-    "md_params[\"autopara_rng_seed\"] = random_seed"
+    "md_params[\"rng\"] = rng"
    ]
   },
   {
@@ -272,7 +264,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -301,7 +292,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -353,7 +343,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -373,7 +362,7 @@
     "    inputs=md_soap_global,\n",
     "    outputs=outputs,\n",
     "    num=100,                    # target number of structures to pick\n",
-    "    at_descs_info_key=\"SOAP\")\n",
+    "    at_descs_info_key=\"SOAP\", rng=rng)\n",
     "    \n",
     "\n",
     "train_fname = \"6.1.train.xyz\"\n",
@@ -402,7 +391,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -482,7 +470,9 @@
     "# set to None for github testing purposes\n",
     "# This cell is hidden from being rendered in the docs. \n",
     "# remote_info = None\n",
-    "gap_params[\"rnd_seed\"] = random_seed "
+    "\n",
+    "# set seed for gap fitting to a value from our (reproducible) random number generator\n",
+    "gap_params[\"rnd_seed\"] = rng.integers(2 ** 31) "
    ]
   },
   {
@@ -501,7 +491,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -528,11 +517,14 @@
     "    num_cores = 2,\n",
     "    partitions = \"standard\")\n",
     "\n",
+    "# note - set OMP_NUM_THREADS to prevent GAP evaluation from using OpenMP, \n",
+    "# as it clashes with multiprocessing.pool, which wfl uses\n",
     "remote_info = RemoteInfo(\n",
     "    sys_name = \"github\",\n",
     "    job_name = \"gap-eval\",\n",
     "    resources = resources,\n",
     "    check_interval = 10, \n",
+    "    env_vars = [\"OMP_NUM_THREADS=1\"],\n",
     "    input_files = [\"gap.xml*\"])\n",
     "\n",
     "gap_calc_autopara_info = AutoparaInfo(\n",
@@ -549,7 +541,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -629,13 +620,13 @@
     "\n",
     "ref_errors = {\n",
     "    'atomization_energy/atom': {\n",
-    "        'train': {'RMSE': 0.01784008096943666, 'MAE': 0.014956982529185385, 'count': 50}, \n",
-    "        '_ALL_': {'RMSE': 0.01810274269833562, 'MAE': 0.015205129586306461, 'count': 100}, \n",
-    "        'test': {'RMSE': 0.018361647458989924, 'MAE': 0.015453276643427535, 'count': 50}}, \n",
+    "        'train': {'RMSE': 0.026086070005729697, 'MAE': 0.02188233965637977, 'count': 50},\n",
+    "        '_ALL_': {'RMSE': 0.02631013293566519, 'MAE': 0.02217457525203221, 'count': 100},\n",
+    "        'test': {'RMSE': 0.026532303741682858, 'MAE': 0.02246681084768465, 'count': 50}},\n",
     "    'forces/comp': {\n",
-    "        'train': {'RMSE': 0.6064186755127647, 'MAE': 0.440771517768513, 'count': 5037}, \n",
-    "        '_ALL_': {'RMSE': 0.6150461768441347, 'MAE': 0.44579797424459006, 'count': 10074}, \n",
-    "        'test': {'RMSE': 0.6235543194385854, 'MAE': 0.450824430720667, 'count': 5037}}\n",
+    "        'train': {'RMSE': 0.6700484048236104, 'MAE': 0.48912067870708253, 'count': 5097},\n",
+    "        '_ALL_': {'RMSE': 0.674843619212047, 'MAE': 0.49305958821652923, 'count': 10188},\n",
+    "        'test': {'RMSE': 0.6796105918104188, 'MAE': 0.49700313992928696, 'count': 5091}}\n",
     "}\n",
     "\n",
     "print(errors)\n",
@@ -659,7 +650,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "dev",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -673,9 +664,8 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.9.16"
   },
-  "orig_nbformat": 4,
   "vscode": {
    "interpreter": {
     "hash": "793ab331f77558158f2e16fabf356357fde3f61b8f3bb6d95e9b59dbfcb88650"

diff --git a/_sources/examples.select_fps.ipynb b/_sources/examples.select_fps.ipynb
@@ -29,8 +29,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import wfl, pathlib\n",
+    "import numpy as np\n",
     "import yaml\n",
+    "import pathlib\n",
+    "import wfl\n",
     "from wfl.configset import ConfigSet, OutputSpec\n",
     "from wfl.descriptors.quippy import calculate as calc_descriptors\n",
     "from wfl.select.by_descriptor import greedy_fps_conf_global\n",
@@ -53,7 +55,7 @@
     "# Step 2: Sampling\n",
     "fps_out          = OutputSpec(files=work_dir/\"out_fps.xyz\")\n",
     "nsamples         = 8\n",
-    "selected_configs = greedy_fps_conf_global(inputs=md_desc, outputs=fps_out, num=nsamples, at_descs_info_key='desc', keep_descriptor_info=False)"
+    "selected_configs = greedy_fps_conf_global(inputs=md_desc, outputs=fps_out, num=nsamples, at_descs_info_key='desc', keep_descriptor_info=False, rng=np.random.default_rng())"
    ]
   },
   {

diff --git a/_sources/wfl.utils.rst b/_sources/wfl.utils.rst
@@ -132,14 +132,6 @@ wfl.utils.round\_sig\_figs module
    :undoc-members:
    :show-inheritance:
 
-wfl.utils.vector\_utils module
-------------------------------
-
-.. automodule:: wfl.utils.vector_utils
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
 wfl.utils.version module
 ------------------------
 

diff --git a/command_line.automatic_docs.html b/command_line.automatic_docs.html
@@ -892,7 +892,7 @@ <h3>cur<a class="headerlink" href="#wfl-select-cur" title="Permalink to this hea
 <dl class="std option">
 <dt class="sig sig-object std" id="cmdoption-wfl-select-cur-stochastic-seed">
 <span class="sig-name descname"><span class="pre">--stochastic-seed</span></span><span class="sig-prename descclassname"> <span class="pre">&lt;stochastic_seed&gt;</span></span><a class="headerlink" href="#cmdoption-wfl-select-cur-stochastic-seed" title="Permalink to this definition">#</a></dt>
-<dd><p>seed for <cite>np.random.seed()</cite> in stochastic CUR.</p>
+<dd><p>seed for <cite>np.random.default_rng()</cite> in stochastic CUR.</p>
 </dd></dl>
 
 <dl class="std option">

diff --git a/examples.daisy_chain_mlip_fitting.html b/examples.daisy_chain_mlip_fitting.html
@@ -470,6 +470,15 @@ <h2>Imports<a class="headerlink" href="#Imports" title="Permalink to this headin
 </pre></div>
 </div>
 </div>
+<div class="nbinput nblast docutils container">
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span> 
+</pre></div>
+</div>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># set random seed, so that MD runs, etc are reproducible and we can check for RMSEs.</span>
+<span class="n">rng</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">default_rng</span><span class="p">(</span><span class="mi">20230301</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
 </div>
 <div class="section" id="Reference-calculator">
 <h2>Reference calculator<a class="headerlink" href="#Reference-calculator" title="Permalink to this heading">#</a></h2>
@@ -540,11 +549,13 @@ <h2>Generate initial structures<a class="headerlink" href="#Generate-initial-str
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span> 
 </pre></div>
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># regenerate smiles_confgis with a random seed set for testing purposes</span>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># regenerate smiles_configs with a random seed set for testing purposes</span>
 <span class="c1"># this cell is hidden from docs.</span>
 
 <span class="n">outputs</span> <span class="o">=</span> <span class="n">OutputSpec</span><span class="p">(</span><span class="s2">&quot;1.ch.rdkit.xyz&quot;</span><span class="p">,</span> <span class="n">overwrite</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-<span class="n">smiles_configs</span> <span class="o">=</span> <span class="n">smiles</span><span class="o">.</span><span class="n">smiles</span><span class="p">(</span><span class="n">all_smiles</span><span class="p">,</span> <span class="n">outputs</span><span class="o">=</span><span class="n">outputs</span><span class="p">,</span> <span class="n">randomSeed</span><span class="o">=</span><span class="n">random_seed</span><span class="p">)</span>
+<span class="c1"># set seed for smiles generation to a value from our (reproducible) random number generator</span>
+<span class="n">smiles_configs</span> <span class="o">=</span> <span class="n">smiles</span><span class="o">.</span><span class="n">smiles</span><span class="p">(</span><span class="n">all_smiles</span><span class="p">,</span> <span class="n">outputs</span><span class="o">=</span><span class="n">outputs</span><span class="p">,</span> <span class="n">randomSeed</span><span class="o">=</span><span class="nb">int</span><span class="p">(</span><span class="n">rng</span><span class="o">.</span><span class="n">integers</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">iinfo</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span><span class="o">.</span><span class="n">max</span><span class="p">,</span>
+                                                                                        <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)))</span>
 </pre></div>
 </div>
 </div>
@@ -675,7 +686,7 @@ <h2>Sub-select with CUR<a class="headerlink" href="#Sub-select-with-CUR" title="
     <span class="n">inputs</span><span class="o">=</span><span class="n">md_soap_global</span><span class="p">,</span>
     <span class="n">outputs</span><span class="o">=</span><span class="n">outputs</span><span class="p">,</span>
     <span class="n">num</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span>                    <span class="c1"># target number of structures to pick</span>
-    <span class="n">at_descs_info_key</span><span class="o">=</span><span class="s2">&quot;SOAP&quot;</span><span class="p">)</span>
+    <span class="n">at_descs_info_key</span><span class="o">=</span><span class="s2">&quot;SOAP&quot;</span><span class="p">,</span> <span class="n">rng</span><span class="o">=</span><span class="n">rng</span><span class="p">)</span>
 
 
 <span class="n">train_fname</span> <span class="o">=</span> <span class="s2">&quot;6.1.train.xyz&quot;</span>
@@ -801,11 +812,14 @@ <h2>Evaluate structures with GAP<a class="headerlink" href="#Evaluate-structures
     <span class="n">num_cores</span> <span class="o">=</span> <span class="mi">2</span><span class="p">,</span>
     <span class="n">partitions</span> <span class="o">=</span> <span class="s2">&quot;standard&quot;</span><span class="p">)</span>
 
+<span class="c1"># note - set OMP_NUM_THREADS to prevent GAP evaluation from using OpenMP,</span>
+<span class="c1"># as it clashes with multiprocessing.pool, which wfl uses</span>
 <span class="n">remote_info</span> <span class="o">=</span> <span class="n">RemoteInfo</span><span class="p">(</span>
     <span class="n">sys_name</span> <span class="o">=</span> <span class="s2">&quot;github&quot;</span><span class="p">,</span>
     <span class="n">job_name</span> <span class="o">=</span> <span class="s2">&quot;gap-eval&quot;</span><span class="p">,</span>
     <span class="n">resources</span> <span class="o">=</span> <span class="n">resources</span><span class="p">,</span>
     <span class="n">check_interval</span> <span class="o">=</span> <span class="mi">10</span><span class="p">,</span>
+    <span class="n">env_vars</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;OMP_NUM_THREADS=1&quot;</span><span class="p">],</span>
     <span class="n">input_files</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;gap.xml*&quot;</span><span class="p">])</span>
 
 <span class="n">gap_calc_autopara_info</span> <span class="o">=</span> <span class="n">AutoparaInfo</span><span class="p">(</span>