Deploying to gh-pages from @ 969019c 🚀

_modules/lidar_prod/tasks/building_validation.html

@@ -155,6 +155,7 @@ <h1>Source code for lidar_prod.tasks.building_validation</h1><div class="highlig
 <span class="kn">import</span> <span class="nn">geopandas</span>
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">import</span> <span class="nn">pdal</span>
+<span class="kn">import</span> <span class="nn">yaml</span>
 <span class="kn">from</span> <span class="nn">tqdm</span> <span class="kn">import</span> <span class="n">tqdm</span>
 
 <span class="kn">from</span> <span class="nn">lidar_prod.tasks.utils</span> <span class="kn">import</span> <span class="p">(</span>
@@ -543,7 +544,24 @@ <h1>Source code for lidar_prod.tasks.building_validation</h1><div class="highlig
     <span class="n">min_confidence_refutation</span><span class="p">:</span> <span class="nb">float</span>
     <span class="n">min_frac_refutation</span><span class="p">:</span> <span class="nb">float</span>
     <span class="n">min_entropy_uncertainty</span><span class="p">:</span> <span class="nb">float</span>
-    <span class="n">min_frac_entropy_uncertain</span><span class="p">:</span> <span class="nb">float</span></div>
+    <span class="n">min_frac_entropy_uncertain</span><span class="p">:</span> <span class="nb">float</span>
+
+<div class="viewcode-block" id="thresholds.dump">
+<a class="viewcode-back" href="../../../apidoc/lidar_prod.tasks.html#lidar_prod.tasks.building_validation.thresholds.dump">[docs]</a>
+    <span class="k">def</span> <span class="nf">dump</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">filename</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
+        <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">filename</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">yaml</span><span class="o">.</span><span class="n">safe_dump</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">,</span> <span class="n">f</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="thresholds.load">
+<a class="viewcode-back" href="../../../apidoc/lidar_prod.tasks.html#lidar_prod.tasks.building_validation.thresholds.load">[docs]</a>
+    <span class="nd">@staticmethod</span>
+    <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="n">filename</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
+        <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="s2">&quot;r&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
+            <span class="n">data</span> <span class="o">=</span> <span class="n">yaml</span><span class="o">.</span><span class="n">safe_load</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
+
+        <span class="k">return</span> <span class="n">thresholds</span><span class="p">(</span><span class="o">**</span><span class="n">data</span><span class="p">)</span></div>
+</div>
 
 </pre></div>
 

_modules/lidar_prod/tasks/building_validation_optimization.html

@@ -350,23 +350,23 @@ <h1>Source code for lidar_prod.tasks.building_validation_optimization</h1><div c
 
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="n">clusters</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_load_clusters</span><span class="p">()</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">_set_thresholds_from_pickle_if_available</span><span class="p">()</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">_set_thresholds_from_file_if_available</span><span class="p">()</span>
         <span class="n">decisions</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">bv</span><span class="o">.</span><span class="n">_make_group_decision</span><span class="p">(</span><span class="n">c</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">clusters</span><span class="p">])</span>
         <span class="n">mts_gt</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">c</span><span class="o">.</span><span class="n">target</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">clusters</span><span class="p">])</span>
         <span class="n">metrics_dict</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">evaluate_decisions</span><span class="p">(</span><span class="n">mts_gt</span><span class="p">,</span> <span class="n">decisions</span><span class="p">)</span>
         <span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="se">\n</span><span class="s2"> Results:</span><span class="se">\n</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_results_logs_str</span><span class="p">(</span><span class="n">metrics_dict</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
         <span class="k">return</span> <span class="n">metrics_dict</span></div>
 
 
-    <span class="k">def</span> <span class="nf">_set_thresholds_from_pickle_if_available</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+    <span class="k">def</span> <span class="nf">_set_thresholds_from_file_if_available</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
         <span class="k">try</span><span class="p">:</span>
-            <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">paths</span><span class="o">.</span><span class="n">building_validation_thresholds_pickle</span><span class="p">,</span> <span class="s2">&quot;rb&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
-                <span class="bp">self</span><span class="o">.</span><span class="n">bv</span><span class="o">.</span><span class="n">thresholds</span> <span class="o">=</span> <span class="n">pickle</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">bv</span><span class="o">.</span><span class="n">thresholds</span> <span class="o">=</span> <span class="n">thresholds</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">paths</span><span class="o">.</span><span class="n">building_validation_thresholds</span><span class="p">)</span>
+
         <span class="k">except</span> <span class="ne">FileNotFoundError</span><span class="p">:</span>
             <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
                 <span class="s2">&quot;Using default thresholds from hydra config to perform decisions. &quot;</span>
-                <span class="s2">&quot;You may want to specify different thresholds via a pickled object by specifying &quot;</span>
-                <span class="s2">&quot;building_validation.optimization.paths.building_validation_thresholds_pickle&quot;</span><span class="p">,</span>
+                <span class="s2">&quot;You may want to specify different thresholds via a yaml file by specifying &quot;</span>
+                <span class="s2">&quot;building_validation.optimization.paths.building_validation_thresholds&quot;</span><span class="p">,</span>
                 <span class="ne">UserWarning</span><span class="p">,</span>
             <span class="p">)</span>
 
@@ -381,7 +381,7 @@ <h1>Source code for lidar_prod.tasks.building_validation_optimization</h1><div c
 
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Updated las will be saved in </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">paths</span><span class="o">.</span><span class="n">results_output_dir</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">_set_thresholds_from_pickle_if_available</span><span class="p">()</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">_set_thresholds_from_file_if_available</span><span class="p">()</span>
         <span class="k">for</span> <span class="n">prepared_las_path</span><span class="p">,</span> <span class="n">target_las_path</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="p">(</span>
             <span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">prepared_las_filepaths</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">out_las_filepaths</span><span class="p">),</span>
             <span class="n">total</span><span class="o">=</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">prepared_las_filepaths</span><span class="p">),</span>
@@ -523,11 +523,10 @@ <h1>Source code for lidar_prod.tasks.building_validation_optimization</h1><div c
         <span class="n">best_rules</span> <span class="o">=</span> <span class="n">thresholds</span><span class="p">(</span><span class="o">**</span><span class="n">best</span><span class="o">.</span><span class="n">params</span><span class="p">)</span>
         <span class="k">return</span> <span class="n">best_rules</span>
 
-    <span class="k">def</span> <span class="nf">_dump_best_rules</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">best_trial_params</span><span class="p">):</span>
-<span class="w">        </span><span class="sd">&quot;&quot;&quot;Serializes best thresholds.&quot;&quot;&quot;</span>
-        <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">paths</span><span class="o">.</span><span class="n">building_validation_thresholds_pickle</span><span class="p">,</span> <span class="s2">&quot;wb&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
-            <span class="n">pickle</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="n">best_trial_params</span><span class="p">,</span> <span class="n">f</span><span class="p">)</span>
-            <span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Pickled best params to </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">paths</span><span class="o">.</span><span class="n">building_validation_thresholds_pickle</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
+    <span class="k">def</span> <span class="nf">_dump_best_rules</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">best_trial_params</span><span class="p">:</span> <span class="n">thresholds</span><span class="p">):</span>
+<span class="w">        </span><span class="sd">&quot;&quot;&quot;Saves best thresholds to a yaml file.&quot;&quot;&quot;</span>
+        <span class="n">best_trial_params</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">paths</span><span class="o">.</span><span class="n">building_validation_thresholds</span><span class="p">)</span>
+        <span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Saved best params to </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">paths</span><span class="o">.</span><span class="n">building_validation_thresholds</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
 
     <span class="k">def</span> <span class="nf">_dump_clusters</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">clusters</span><span class="p">):</span>
 <span class="w">        </span><span class="sd">&quot;&quot;&quot;Serializes the list of cluster-level information objects.&quot;&quot;&quot;</span>

_sources/guides/thresholds_optimization.md.txt

@@ -37,7 +37,7 @@ building_validation.optimization.paths.results_output_dir=[path/to/save/results]
 
 ### Evaluation of optimized thresholds on a test set
 
-Once an optimal solution was found, you may want to evaluate the decision process on unseen data to evaluate generalization capability. For that, you will need another test folder of corrected data in the same format as before (a different `input_las_dir`). You need to specify that no optimization is required using the `todo` params. You also need to give the path to the pickled decision thresholds from the previous step, and specify a different `results_output_dir` so that prepared data of test and val test are not pooled together.
+Once an optimal solution was found, you may want to evaluate the decision process on unseen data to evaluate generalization capability. For that, you will need another test folder of corrected data in the same format as before (a different `input_las_dir`). You need to specify that no optimization is required using the `todo` params. You also need to give the path to the decision thresholds file (yaml file) from the previous step, and specify a different `results_output_dir` so that prepared data of test and val test are not pooled together.
 
 
 ```bash
@@ -48,7 +48,7 @@ python lidar_prod/run.py \
 building_validation.optimization.todo='prepare+evaluate+update' \
 building_validation.optimization.paths.input_las_dir=[path/to/labelled/test/dataset/] \
 building_validation.optimization.paths.results_output_dir=[path/to/save/results] \
-building_validation.optimization.paths.building_validation_thresholds_pickle=[path/to/optimized_thresholds.pickle]
+building_validation.optimization.paths.building_validation_thresholds=[path/to/optimized_thresholds.yaml]
 ```
 
 ### Utils
@@ -57,4 +57,4 @@ Debug mode: to run on a single file during development, add a `+building_validat
 
 
 Reference:
-- [Deb et al. (2002) - A fast and elitist multiobjective genetic algorithm\: NSGA-II](https://ieeexplore.ieee.org/document/996017)).
+- [Deb et al. (2002) - A fast and elitist multiobjective genetic algorithm\: NSGA-II](https://ieeexplore.ieee.org/document/996017).