deploy: 3b3cf4c

Author: gperdrizet

.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file records the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: ae31d2ebb2d31cd3713ed60be8bf64ce
+config: 1c0e5fa47ecf51999eee0eaf240c9679
 tags: 645f666f9bcd5a90fca523b33c5a78b7

_downloads/4ea8accded0d0e1c11374d507ee5380c/05-feature_interactions.ipynb

@@ -349,7 +349,7 @@
     "    data=data,\n",
     "    objective_func=objective_feature_interactions,\n",
     "    max_time=run_time,\n",
-    "    step_spread=step_spread,\n",
+    "    initial_step_spread=step_spread,\n",
     "    perturb_fraction=perturb_fraction,\n",
     "    temperature=temperature,\n",
     "    T_max=T_max,\n",

_downloads/5bf5751b91a019b446398b28327656d7/06-checkpoint_example.ipynb

@@ -127,7 +127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "7068938b",
    "metadata": {},
    "outputs": [
@@ -164,14 +164,13 @@
     }
    ],
    "source": [
-    "# Create climber with checkpoint file\n",
-    "checkpoint_file = '../data/single_run_checkpoint.pkl'\n",
+    "checkpoint_file = '../data/checkpoint_example.pkl'\n",
     "\n",
     "climber = HillClimber(\n",
     "    data=data,\n",
     "    objective_func=objective_same_mean_std_different_distributions,\n",
     "    max_time=3,  # 3 minutes\n",
-    "    step_spread=2.0,\n",
+    "    initial_step_spread=2.0,\n",
     "    perturb_fraction=0.3,\n",
     "    temperature=1000.0,\n",
     "    cooling_rate=0.001,\n",
@@ -181,11 +180,11 @@
     ")\n",
     "\n",
     "print(\"Starting optimization with periodic checkpointing...\")\n",
-    "best_data, steps_df = climber.climb()\n",
+    "best_data, history_df = climber.climb()\n",
     "\n",
     "print(f\"\\nOptimization completed!\")\n",
-    "print(f\"Final objective: {steps_df['Objective value'].iloc[-1]:.4f}\")\n",
-    "print(f\"Total steps: {len(steps_df)}\")"
+    "print(f\"Final objective: {history_df['Objective value'].iloc[-1]:.4f}\")\n",
+    "print(f\"Total improvements: {len(history_df)}\")"
    ]
   },
   {
@@ -198,7 +197,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "fd27d5cd",
    "metadata": {},
    "outputs": [
@@ -244,11 +243,11 @@
     "resumed_climber.max_time = 2  # Run for 2 more minutes (total 5 minutes)\n",
     "\n",
     "# Continue optimization\n",
-    "resumed_best_data, resumed_steps_df = resumed_climber.climb()\n",
+    "resumed_best_data, resumed_history_df = resumed_climber.climb()\n",
     "\n",
     "print(f\"\\nResumed optimization completed!\")\n",
-    "print(f\"Final objective: {resumed_steps_df['Objective value'].iloc[-1]:.4f}\")\n",
-    "print(f\"Total steps after resume: {len(resumed_steps_df)}\")"
+    "print(f\"Final objective: {resumed_history_df['Objective value'].iloc[-1]:.4f}\")\n",
+    "print(f\"Total improvements after resume: {len(resumed_history_df)}\")"
    ]
   },
   {
@@ -261,7 +260,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "3484e957",
    "metadata": {},
    "outputs": [
@@ -305,7 +304,7 @@
     "    data=data,\n",
     "    objective_func=objective_same_mean_std_different_distributions,\n",
     "    max_time=3,  # 3 minutes\n",
-    "    step_spread=2.0,\n",
+    "    initial_step_spread=2.0,\n",
     "    perturb_fraction=0.3,\n",
     "    temperature=100.0,  # T_min\n",
     "    T_max=1000.0,  # T_max\n",
@@ -317,11 +316,11 @@
     ")\n",
     "\n",
     "print(\"Starting replica exchange optimization with checkpointing...\")\n",
-    "best_data_replica, steps_df_replica = replica_climber.climb()\n",
+    "best_data_replica, history_df_replica = replica_climber.climb()\n",
     "\n",
     "print(\"\\nReplica exchange optimization completed!\")\n",
-    "print(f\"Final objective: {steps_df_replica['Objective value'].iloc[-1]:.4f}\")\n",
-    "print(f\"Total steps: {len(steps_df_replica)}\")"
+    "print(f\"Final objective: {history_df_replica['Objective value'].iloc[-1]:.4f}\")\n",
+    "print(f\"Total improvements: {len(history_df_replica)}\")"
    ]
   },
   {
@@ -367,7 +366,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "42d31f16",
    "metadata": {},
    "outputs": [
@@ -400,10 +399,12 @@
     "    # Show first replica info\n",
     "    first_replica = checkpoint_data['replicas'][0]\n",
     "    print(f\"\\nFirst replica state:\")\n",
-    "    print(f\"  - Step: {first_replica['step']}\")\n",
+    "    print(f\"  - Perturbation num: {first_replica['perturbation_num']}\")\n",
     "    print(f\"  - Best objective: {first_replica['best_objective']:.4f}\")\n",
     "    print(f\"  - Current temperature: {first_replica['temperature']:.2f}\")\n",
     "    print(f\"  - Hyperparameters: {list(first_replica['hyperparameters'].keys())}\")\n",
+    "    print(f\"  - Num accepted: {first_replica['num_accepted']}\")\n",
+    "    print(f\"  - Num improvements: {first_replica['num_improvements']}\")\n",
     "else:\n",
     "    print(\"Checkpoint file not found\")"
    ]

_downloads/7cac5e3eb3cf2b2a8cb6480f2cbb6aea/04-entropy_pearson.ipynb

@@ -326,7 +326,7 @@
     "    data=data,\n",
     "    objective_func=objective_low_correlation_low_entropy,\n",
     "    max_time=run_time,\n",
-    "    step_spread=step_spread,\n",
+    "    initial_step_spread=step_spread,\n",
     "    perturb_fraction=perturb_fraction,\n",
     "    temperature=temperature,\n",
     "    T_max=T_max,\n",

_downloads/ccdc6e7f5698205511edc82076e3e802/02-pearson_spearman.ipynb

@@ -5,14 +5,14 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>hill_climber.climber_functions &mdash; Hill Climber 2.1.5 documentation</title>
+  <title>hill_climber.climber_functions &mdash; Hill Climber 3.0.0 documentation</title>
       <link rel="stylesheet" type="text/css" href="../../_static/pygments.css?v=b86133f3" />
       <link rel="stylesheet" type="text/css" href="../../_static/css/theme.css?v=e59714d7" />
 
 
       <script src="../../_static/jquery.js?v=5d32c60e"></script>
       <script src="../../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
-      <script src="../../_static/documentation_options.js?v=786ba454"></script>
+      <script src="../../_static/documentation_options.js?v=acc74ff5"></script>
       <script src="../../_static/doctools.js?v=9bcbadda"></script>
       <script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
       <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
@@ -43,12 +43,12 @@
               <p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="../../installation.html">Installation</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../quickstart.html">Quick Start</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../user_guide.html">User Guide</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../dashboard.html">Real-Time Monitoring Dashboard</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../api.html">API Reference</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../notebooks.html">Example Notebooks</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../advanced.html">Advanced Topics</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../quickstart.html">Quick start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../user_guide.html">User guide</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../dashboard.html">Real-time monitoring dashboard</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../api.html">API reference</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../notebooks.html">Example notebooks</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../advanced.html">Advanced topics</a></li>
 </ul>
 
         </div>
@@ -91,7 +91,7 @@ <h1>Source code for hill_climber.climber_functions</h1><div class="highlight"><p
 <span class="sd">    </span>
 <span class="sd">    Args:</span>
 <span class="sd">        data_array (np.ndarray): 2D numpy array to perturb with shape (N, M).</span>
-<span class="sd">        step_spread (float): Standard deviation of normal distribution for perturbation.</span>
+<span class="sd">        step_spread (np.ndarray): Standard deviation of normal distribution for perturbation (per-feature).</span>
 <span class="sd">        n_perturb (int): Number of elements to perturb.</span>
 <span class="sd">        min_bounds (np.ndarray): 1D array of minimum bounds for each column.</span>
 <span class="sd">        max_bounds (np.ndarray): 1D array of maximum bounds for each column.</span>
@@ -108,7 +108,7 @@ <h1>Source code for hill_climber.climber_functions</h1><div class="highlight"><p
 
         <span class="n">row_idx</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">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">n_rows</span><span class="p">)</span>
         <span class="n">col_idx</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">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">n_cols</span><span class="p">)</span>
-        <span class="n">perturbation</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">normal</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">step_spread</span><span class="p">)</span>
+        <span class="n">perturbation</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">normal</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">step_spread</span><span class="p">[</span><span class="n">col_idx</span><span class="p">])</span>
         <span class="n">new_value</span> <span class="o">=</span> <span class="n">result</span><span class="p">[</span><span class="n">row_idx</span><span class="p">,</span> <span class="n">col_idx</span><span class="p">]</span> <span class="o">+</span> <span class="n">perturbation</span>
 
         <span class="c1"># Reflect values back into bounds instead of clipping</span>
@@ -152,8 +152,8 @@ <h1>Source code for hill_climber.climber_functions</h1><div class="highlight"><p
 <span class="sd">            Note: HillClimber uses 0.001 as its default.</span>
 <span class="sd">        bounds (tuple, optional): Tuple of (min_bounds, max_bounds) arrays for each column.</span>
 <span class="sd">            If None, uses data min/max. Default is None.</span>
-<span class="sd">        step_spread (float): Standard deviation of normal distribution for perturbations.</span>
-<span class="sd">            Default is 1.0.</span>
+<span class="sd">        step_spread (float or np.ndarray): Standard deviation of normal distribution for perturbations.</span>
+<span class="sd">            Can be a scalar (same for all features) or array (per-feature). Default is 1.0.</span>
 <span class="sd">        </span>
 <span class="sd">    Returns:</span>
 <span class="sd">        np.ndarray: Perturbed numpy array with same shape as input.</span>
@@ -171,6 +171,10 @@ <h1>Source code for hill_climber.climber_functions</h1><div class="highlight"><p
     <span class="k">else</span><span class="p">:</span>
         <span class="n">min_bounds</span><span class="p">,</span> <span class="n">max_bounds</span> <span class="o">=</span> <span class="n">bounds</span>
 
+    <span class="c1"># Ensure step_spread is an array (broadcast scalar if needed)</span>
+    <span class="k">if</span> <span class="n">np</span><span class="o">.</span><span class="n">isscalar</span><span class="p">(</span><span class="n">step_spread</span><span class="p">):</span>
+        <span class="n">step_spread</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">full</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">step_spread</span><span class="p">)</span>
+    
     <span class="c1"># Call JIT-compiled function</span>
     <span class="k">return</span> <span class="n">_perturb_core</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">step_spread</span><span class="p">,</span> <span class="n">n_perturb</span><span class="p">,</span> <span class="n">min_bounds</span><span class="p">,</span> <span class="n">max_bounds</span><span class="p">)</span></div>