Merge pull request #32 from MolecularAI/3.1.3

3.1.3 Docs

docs/sphinx-builddir/doctrees/nbsphinx/notebooks/preprocess_data.ipynb

@@ -1055,10 +1055,10 @@
     "    response_type=\"regression\",\n",
     "    training_dataset_file=\"../tests/data/sdf/example.sdf\",\n",
     "    deduplication_strategy=KeepAllNoDeduplication(),\n",
-    "    log_transform=\"True\", # flags to use a transform\n",
+    "    log_transform=True, # flags to use a transform\n",
     "    log_transform_base=LogBase.LOG10, # Log10 base will be used\n",
-    "    log_transform_negative=\"True\", # The negated log transform will be applied\n",
-    "    log_transform_unit_conversion=6 # THe unit conversion for pXC50 values is 6\n",
+    "    log_transform_negative=LogNegative.TRUE, # The negated log transform will be applied\n",
+    "    log_transform_unit_conversion=6 # The unit conversion for pXC50 values is 6\n",
     ")\n",
     "\n",
     "pxc50_data = Dataset(\n",

docs/sphinx-builddir/html/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: b0c96d5f832cdd38d138271da4ddabf1
+config: cd8105a3e394e54ace4ef41b1def0634
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/sphinx-builddir/html/README.html

@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>QSARtuna 𓆛: QSAR using Optimization for Hyperparameter Tuning (formerly Optuna AZ and QPTUNA) &mdash; QSARtuna 3.1.2 documentation</title>
+  <title>QSARtuna 𓆛: QSAR using Optimization for Hyperparameter Tuning (formerly Optuna AZ and QPTUNA) &mdash; QSARtuna 3.1.3 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
       <link rel="stylesheet" href="_static/autodoc_pydantic.css" type="text/css" />
@@ -274,31 +274,28 @@ <h2>Run from Python/Jupyter Notebook<a class="headerlink" href="#run-from-python
 <span class="kn">from</span> <span class="nn">qsartuna.config.optconfig</span> <span class="kn">import</span> <span class="p">(</span>
     <span class="n">OptimizationConfig</span><span class="p">,</span>
     <span class="n">SVR</span><span class="p">,</span>
-    <span class="n">RandomForest</span><span class="p">,</span>
+    <span class="n">RandomForestRegressor</span><span class="p">,</span>
     <span class="n">Ridge</span><span class="p">,</span>
     <span class="n">Lasso</span><span class="p">,</span>
-    <span class="n">PLS</span><span class="p">,</span>
-    <span class="n">XGBregressor</span><span class="p">,</span>
+    <span class="n">XGBRegressor</span><span class="p">,</span>
 <span class="p">)</span>
 <span class="kn">from</span> <span class="nn">qsartuna.datareader</span> <span class="kn">import</span> <span class="n">Dataset</span>
-<span class="kn">from</span> <span class="nn">qsartuna.descriptors</span> <span class="kn">import</span> <span class="n">ECFP</span><span class="p">,</span> <span class="n">MACCS_keys</span><span class="p">,</span> <span class="n">ECFP_counts</span>
+<span class="kn">from</span> <span class="nn">qsartuna.descriptors</span> <span class="kn">import</span> <span class="n">ECFP</span><span class="p">,</span> <span class="n">MACCS_keys</span><span class="p">,</span> <span class="n">ECFP_counts</span><span class="p">,</span> <span class="n">PathFP</span>
 
-<span class="c1">##</span>
 <span class="c1"># Prepare hyperparameter optimization configuration.</span>
 <span class="n">config</span> <span class="o">=</span> <span class="n">OptimizationConfig</span><span class="p">(</span>
     <span class="n">data</span><span class="o">=</span><span class="n">Dataset</span><span class="p">(</span>
         <span class="n">input_column</span><span class="o">=</span><span class="s2">&quot;canonical&quot;</span><span class="p">,</span>
         <span class="n">response_column</span><span class="o">=</span><span class="s2">&quot;molwt&quot;</span><span class="p">,</span>
         <span class="n">training_dataset_file</span><span class="o">=</span><span class="s2">&quot;tests/data/DRD2/subset-50/train.csv&quot;</span><span class="p">,</span>
     <span class="p">),</span>
-    <span class="n">descriptors</span><span class="o">=</span><span class="p">[</span><span class="n">ECFP</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span> <span class="n">ECFP_counts</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span> <span class="n">MACCS_keys</span><span class="o">.</span><span class="n">new</span><span class="p">()],</span>
+    <span class="n">descriptors</span><span class="o">=</span><span class="p">[</span><span class="n">ECFP</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span> <span class="n">ECFP_counts</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span> <span class="n">MACCS_keys</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span> <span class="n">PathFP</span><span class="o">.</span><span class="n">new</span><span class="p">()],</span>
     <span class="n">algorithms</span><span class="o">=</span><span class="p">[</span>
         <span class="n">SVR</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span>
-        <span class="n">RandomForest</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span>
+        <span class="n">RandomForestRegressor</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span>
         <span class="n">Ridge</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span>
         <span class="n">Lasso</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span>
-        <span class="n">PLS</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span>
-        <span class="n">XGBregressor</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span>
+        <span class="n">XGBRegressor</span><span class="o">.</span><span class="n">new</span><span class="p">(),</span>
     <span class="p">],</span>
     <span class="n">settings</span><span class="o">=</span><span class="n">OptimizationConfig</span><span class="o">.</span><span class="n">Settings</span><span class="p">(</span>
         <span class="n">mode</span><span class="o">=</span><span class="n">ModelMode</span><span class="o">.</span><span class="n">REGRESSION</span><span class="p">,</span>
@@ -308,22 +305,17 @@ <h2>Run from Python/Jupyter Notebook<a class="headerlink" href="#run-from-python
     <span class="p">),</span>
 <span class="p">)</span>
 
-<span class="c1">##</span>
 <span class="c1"># Run Optuna Study.</span>
 <span class="n">study</span> <span class="o">=</span> <span class="n">optimize</span><span class="p">(</span><span class="n">config</span><span class="p">,</span> <span class="n">study_name</span><span class="o">=</span><span class="s2">&quot;my_study&quot;</span><span class="p">)</span>
 
-<span class="c1">##</span>
 <span class="c1"># Get the best Trial from the Study and make a Build (Training) configuration for it.</span>
 <span class="n">buildconfig</span> <span class="o">=</span> <span class="n">buildconfig_best</span><span class="p">(</span><span class="n">study</span><span class="p">)</span>
-<span class="c1"># Optional: write out JSON of the best configuration.</span>
-<span class="kn">import</span> <span class="nn">json</span>
-<span class="nb">print</span><span class="p">(</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">buildconfig</span><span class="o">.</span><span class="n">json</span><span class="p">(),</span> <span class="n">indent</span><span class="o">=</span><span class="mi">2</span><span class="p">))</span>
+<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">&quot;best_config.txt&quot;</span><span class="p">,</span> <span class="s2">&quot;w&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
+    <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">buildconfig</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">))</span>
 
-<span class="c1">##</span>
 <span class="c1"># Build (re-Train) and save the best model.</span>
 <span class="n">build_best</span><span class="p">(</span><span class="n">buildconfig</span><span class="p">,</span> <span class="s2">&quot;target/best.pkl&quot;</span><span class="p">)</span>
 
-<span class="c1">##</span>
 <span class="c1"># Build (Train) and save the model on the merged train+test data.</span>
 <span class="n">build_merged</span><span class="p">(</span><span class="n">buildconfig</span><span class="p">,</span> <span class="s2">&quot;target/merged.pkl&quot;</span><span class="p">)</span>
 </pre></div>

docs/sphinx-builddir/html/_modules/index.html

@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Overview: module code &mdash; QSARtuna 3.1.2 documentation</title>
+  <title>Overview: module code &mdash; QSARtuna 3.1.3 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
       <link rel="stylesheet" href="../_static/autodoc_pydantic.css" type="text/css" />

docs/sphinx-builddir/html/_modules/optunaz/automl.html

@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>optunaz.automl &mdash; QSARtuna 3.1.2 documentation</title>
+  <title>optunaz.automl &mdash; QSARtuna 3.1.3 documentation</title>
       <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/autodoc_pydantic.css" type="text/css" />

docs/sphinx-builddir/html/_modules/optunaz/builder.html

@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>optunaz.builder &mdash; QSARtuna 3.1.2 documentation</title>
+  <title>optunaz.builder &mdash; QSARtuna 3.1.3 documentation</title>
       <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/autodoc_pydantic.css" type="text/css" />
@@ -98,8 +98,27 @@ <h1>Source code for optunaz.builder</h1><div class="highlight"><pre>
     <span class="n">estimator</span> <span class="o">=</span> <span class="n">buildconfig</span><span class="o">.</span><span class="n">algorithm</span><span class="o">.</span><span class="n">estimator</span><span class="p">()</span>
     <span class="k">if</span> <span class="n">merge_train_and_test_data</span><span class="p">:</span>
         <span class="n">train_smiles</span><span class="p">,</span> <span class="n">train_y</span><span class="p">,</span> <span class="n">train_aux</span> <span class="o">=</span> <span class="n">buildconfig</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">get_merged_sets</span><span class="p">()</span>
+        <span class="n">test_smiles</span><span class="p">,</span> <span class="n">test_y</span><span class="p">,</span> <span class="n">test_aux</span><span class="p">,</span> <span class="n">test_X</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span>
     <span class="k">else</span><span class="p">:</span>
-        <span class="n">train_smiles</span><span class="p">,</span> <span class="n">train_y</span><span class="p">,</span> <span class="n">train_aux</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">buildconfig</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">get_sets</span><span class="p">()</span>
+        <span class="p">(</span>
+            <span class="n">train_smiles</span><span class="p">,</span>
+            <span class="n">train_y</span><span class="p">,</span>
+            <span class="n">train_aux</span><span class="p">,</span>
+            <span class="n">test_smiles</span><span class="p">,</span>
+            <span class="n">test_y</span><span class="p">,</span>
+            <span class="n">test_aux</span><span class="p">,</span>
+        <span class="p">)</span> <span class="o">=</span> <span class="n">buildconfig</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">get_sets</span><span class="p">()</span>
+        <span class="k">if</span> <span class="n">test_smiles</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">test_smiles</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
+            <span class="n">test_X</span><span class="p">,</span> <span class="n">failed_idx</span> <span class="o">=</span> <span class="n">descriptor_from_config</span><span class="p">(</span>
+                <span class="n">test_smiles</span><span class="p">,</span> <span class="n">buildconfig</span><span class="o">.</span><span class="n">descriptor</span><span class="p">,</span> <span class="n">cache</span><span class="o">=</span><span class="n">cache</span>
+            <span class="p">)</span>
+            <span class="n">test_y</span><span class="p">,</span> <span class="n">test_smiles</span><span class="p">,</span> <span class="n">test_aux</span> <span class="o">=</span> <span class="n">remove_failed_idx</span><span class="p">(</span>
+                <span class="n">failed_idx</span><span class="p">,</span> <span class="n">test_y</span><span class="p">,</span> <span class="n">test_smiles</span><span class="p">,</span> <span class="n">test_aux</span>
+            <span class="p">)</span>
+            <span class="k">if</span> <span class="n">test_aux</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+                <span class="n">test_X</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">hstack</span><span class="p">((</span><span class="n">test_X</span><span class="p">,</span> <span class="n">test_aux</span><span class="p">))</span>
+        <span class="k">else</span><span class="p">:</span>
+            <span class="n">test_X</span> <span class="o">=</span> <span class="kc">None</span>
 
     <span class="n">train_X</span><span class="p">,</span> <span class="n">failed_idx</span> <span class="o">=</span> <span class="n">descriptor_from_config</span><span class="p">(</span>
         <span class="n">train_smiles</span><span class="p">,</span> <span class="n">buildconfig</span><span class="o">.</span><span class="n">descriptor</span><span class="p">,</span> <span class="n">cache</span><span class="o">=</span><span class="n">cache</span>
@@ -116,15 +135,22 @@ <h1>Source code for optunaz.builder</h1><div class="highlight"><pre>
     <span class="n">estimator</span><span class="o">.</span><span class="n">X_</span> <span class="o">=</span> <span class="n">train_X</span>
     <span class="n">estimator</span><span class="o">.</span><span class="n">y_</span> <span class="o">=</span> <span class="n">train_y</span>
     <span class="n">estimator</span><span class="o">.</span><span class="n">aux_</span> <span class="o">=</span> <span class="n">train_aux</span>
-
-    <span class="k">if</span> <span class="n">merge_train_and_test_data</span><span class="p">:</span>
-        <span class="n">train_scores</span> <span class="o">=</span> <span class="n">get_merged_train_score</span><span class="p">(</span><span class="n">estimator</span><span class="p">,</span> <span class="n">buildconfig</span><span class="p">,</span> <span class="n">cache</span><span class="o">=</span><span class="n">cache</span><span class="p">)</span>
-        <span class="n">test_scores</span> <span class="o">=</span> <span class="kc">None</span>
-    <span class="k">else</span><span class="p">:</span>
+    <span class="n">estimator</span><span class="o">.</span><span class="n">test_smiles_</span> <span class="o">=</span> <span class="n">test_smiles</span>
+    <span class="n">estimator</span><span class="o">.</span><span class="n">test_X_</span> <span class="o">=</span> <span class="n">test_X</span>
+    <span class="n">estimator</span><span class="o">.</span><span class="n">test_y_</span> <span class="o">=</span> <span class="n">test_y</span>
+    <span class="n">estimator</span><span class="o">.</span><span class="n">test_aux_</span> <span class="o">=</span> <span class="n">test_aux</span>
+
+    <span class="k">if</span> <span class="p">(</span>
+        <span class="ow">not</span> <span class="n">merge_train_and_test_data</span>
+        <span class="ow">and</span> <span class="n">test_smiles</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
+        <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">test_smiles</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span>
+    <span class="p">):</span>
         <span class="n">train_scores</span><span class="p">,</span> <span class="n">test_scores</span> <span class="o">=</span> <span class="n">get_train_test_scores</span><span class="p">(</span>
-            <span class="n">estimator</span><span class="p">,</span> <span class="n">buildconfig</span><span class="p">,</span> <span class="n">cache</span><span class="o">=</span><span class="n">cache</span>
+            <span class="n">estimator</span><span class="p">,</span> <span class="n">buildconfig</span><span class="p">,</span> <span class="n">train_X</span><span class="p">,</span> <span class="n">train_y</span><span class="p">,</span> <span class="n">test_X</span><span class="p">,</span> <span class="n">test_y</span>
         <span class="p">)</span>
-
+    <span class="k">else</span><span class="p">:</span>
+        <span class="n">train_scores</span> <span class="o">=</span> <span class="n">get_merged_train_score</span><span class="p">(</span><span class="n">estimator</span><span class="p">,</span> <span class="n">buildconfig</span><span class="p">,</span> <span class="n">train_X</span><span class="p">,</span> <span class="n">train_y</span><span class="p">)</span>
+        <span class="n">test_scores</span> <span class="o">=</span> <span class="kc">None</span>
     <span class="k">return</span> <span class="n">estimator</span><span class="p">,</span> <span class="n">train_scores</span><span class="p">,</span> <span class="n">test_scores</span></div>
 </pre></div>
 

docs/sphinx-builddir/html/_modules/optunaz/config.html

@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>optunaz.config &mdash; QSARtuna 3.1.2 documentation</title>
+  <title>optunaz.config &mdash; QSARtuna 3.1.3 documentation</title>
       <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/autodoc_pydantic.css" type="text/css" />

docs/sphinx-builddir/html/_modules/optunaz/config/build_from_opt.html

@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>optunaz.config.build_from_opt &mdash; QSARtuna 3.1.2 documentation</title>
+  <title>optunaz.config.build_from_opt &mdash; QSARtuna 3.1.3 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/autodoc_pydantic.css" type="text/css" />