Return File Library to /lib as it is needed by Local Discretization (factorize)
This commit is contained in:
@@ -37,7 +37,7 @@
|
||||
</tr>
|
||||
<tr>
|
||||
<td class="headerItem">Test Date:</td>
|
||||
<td class="headerValue">2024-04-30 13:59:18</td>
|
||||
<td class="headerValue">2024-04-30 20:26:57</td>
|
||||
<td></td>
|
||||
<td class="headerItem">Functions:</td>
|
||||
<td class="headerCovTableEntryHi">100.0 %</td>
|
||||
@@ -70,17 +70,17 @@
|
||||
<span id="L8"><span class="lineNum"> 8</span> : #include "bayesnet/utils/bayesnetUtils.h"</span>
|
||||
<span id="L9"><span class="lineNum"> 9</span> : #include "FeatureSelect.h"</span>
|
||||
<span id="L10"><span class="lineNum"> 10</span> : namespace bayesnet {</span>
|
||||
<span id="L11"><span class="lineNum"> 11</span> <span class="tlaGNC tlaBgGNC"> 154 : FeatureSelect::FeatureSelect(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights) :</span></span>
|
||||
<span id="L12"><span class="lineNum"> 12</span> <span class="tlaGNC"> 154 : Metrics(samples, features, className, classNumStates), maxFeatures(maxFeatures == 0 ? samples.size(0) - 1 : maxFeatures), weights(weights)</span></span>
|
||||
<span id="L11"><span class="lineNum"> 11</span> <span class="tlaGNC tlaBgGNC"> 46 : FeatureSelect::FeatureSelect(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights) :</span></span>
|
||||
<span id="L12"><span class="lineNum"> 12</span> <span class="tlaGNC"> 46 : Metrics(samples, features, className, classNumStates), maxFeatures(maxFeatures == 0 ? samples.size(0) - 1 : maxFeatures), weights(weights)</span></span>
|
||||
<span id="L13"><span class="lineNum"> 13</span> : </span>
|
||||
<span id="L14"><span class="lineNum"> 14</span> : {</span>
|
||||
<span id="L15"><span class="lineNum"> 15</span> <span class="tlaGNC"> 154 : }</span></span>
|
||||
<span id="L16"><span class="lineNum"> 16</span> <span class="tlaGNC"> 108 : void FeatureSelect::initialize()</span></span>
|
||||
<span id="L15"><span class="lineNum"> 15</span> <span class="tlaGNC"> 46 : }</span></span>
|
||||
<span id="L16"><span class="lineNum"> 16</span> <span class="tlaGNC"> 32 : void FeatureSelect::initialize()</span></span>
|
||||
<span id="L17"><span class="lineNum"> 17</span> : {</span>
|
||||
<span id="L18"><span class="lineNum"> 18</span> <span class="tlaGNC"> 108 : selectedFeatures.clear();</span></span>
|
||||
<span id="L19"><span class="lineNum"> 19</span> <span class="tlaGNC"> 108 : selectedScores.clear();</span></span>
|
||||
<span id="L20"><span class="lineNum"> 20</span> <span class="tlaGNC"> 108 : }</span></span>
|
||||
<span id="L21"><span class="lineNum"> 21</span> <span class="tlaGNC"> 2751 : double FeatureSelect::symmetricalUncertainty(int a, int b)</span></span>
|
||||
<span id="L18"><span class="lineNum"> 18</span> <span class="tlaGNC"> 32 : selectedFeatures.clear();</span></span>
|
||||
<span id="L19"><span class="lineNum"> 19</span> <span class="tlaGNC"> 32 : selectedScores.clear();</span></span>
|
||||
<span id="L20"><span class="lineNum"> 20</span> <span class="tlaGNC"> 32 : }</span></span>
|
||||
<span id="L21"><span class="lineNum"> 21</span> <span class="tlaGNC"> 822 : double FeatureSelect::symmetricalUncertainty(int a, int b)</span></span>
|
||||
<span id="L22"><span class="lineNum"> 22</span> : {</span>
|
||||
<span id="L23"><span class="lineNum"> 23</span> : /*</span>
|
||||
<span id="L24"><span class="lineNum"> 24</span> : Compute symmetrical uncertainty. Normalize* information gain (mutual</span>
|
||||
@@ -88,60 +88,60 @@
|
||||
<span id="L26"><span class="lineNum"> 26</span> : the bias due to high cardinality features. *Range [0, 1]</span>
|
||||
<span id="L27"><span class="lineNum"> 27</span> : (https://www.sciencedirect.com/science/article/pii/S0020025519303603)</span>
|
||||
<span id="L28"><span class="lineNum"> 28</span> : */</span>
|
||||
<span id="L29"><span class="lineNum"> 29</span> <span class="tlaGNC"> 8253 : auto x = samples.index({ a, "..." });</span></span>
|
||||
<span id="L30"><span class="lineNum"> 30</span> <span class="tlaGNC"> 8253 : auto y = samples.index({ b, "..." });</span></span>
|
||||
<span id="L31"><span class="lineNum"> 31</span> <span class="tlaGNC"> 2751 : auto mu = mutualInformation(x, y, weights);</span></span>
|
||||
<span id="L32"><span class="lineNum"> 32</span> <span class="tlaGNC"> 2751 : auto hx = entropy(x, weights);</span></span>
|
||||
<span id="L33"><span class="lineNum"> 33</span> <span class="tlaGNC"> 2751 : auto hy = entropy(y, weights);</span></span>
|
||||
<span id="L34"><span class="lineNum"> 34</span> <span class="tlaGNC"> 2751 : return 2.0 * mu / (hx + hy);</span></span>
|
||||
<span id="L35"><span class="lineNum"> 35</span> <span class="tlaGNC"> 8253 : }</span></span>
|
||||
<span id="L36"><span class="lineNum"> 36</span> <span class="tlaGNC"> 108 : void FeatureSelect::computeSuLabels()</span></span>
|
||||
<span id="L29"><span class="lineNum"> 29</span> <span class="tlaGNC"> 2466 : auto x = samples.index({ a, "..." });</span></span>
|
||||
<span id="L30"><span class="lineNum"> 30</span> <span class="tlaGNC"> 2466 : auto y = samples.index({ b, "..." });</span></span>
|
||||
<span id="L31"><span class="lineNum"> 31</span> <span class="tlaGNC"> 822 : auto mu = mutualInformation(x, y, weights);</span></span>
|
||||
<span id="L32"><span class="lineNum"> 32</span> <span class="tlaGNC"> 822 : auto hx = entropy(x, weights);</span></span>
|
||||
<span id="L33"><span class="lineNum"> 33</span> <span class="tlaGNC"> 822 : auto hy = entropy(y, weights);</span></span>
|
||||
<span id="L34"><span class="lineNum"> 34</span> <span class="tlaGNC"> 822 : return 2.0 * mu / (hx + hy);</span></span>
|
||||
<span id="L35"><span class="lineNum"> 35</span> <span class="tlaGNC"> 2466 : }</span></span>
|
||||
<span id="L36"><span class="lineNum"> 36</span> <span class="tlaGNC"> 32 : void FeatureSelect::computeSuLabels()</span></span>
|
||||
<span id="L37"><span class="lineNum"> 37</span> : {</span>
|
||||
<span id="L38"><span class="lineNum"> 38</span> : // Compute Simmetrical Uncertainty between features and labels</span>
|
||||
<span id="L39"><span class="lineNum"> 39</span> : // https://en.wikipedia.org/wiki/Symmetric_uncertainty</span>
|
||||
<span id="L40"><span class="lineNum"> 40</span> <span class="tlaGNC"> 906 : for (int i = 0; i < features.size(); ++i) {</span></span>
|
||||
<span id="L41"><span class="lineNum"> 41</span> <span class="tlaGNC"> 798 : suLabels.push_back(symmetricalUncertainty(i, -1));</span></span>
|
||||
<span id="L40"><span class="lineNum"> 40</span> <span class="tlaGNC"> 270 : for (int i = 0; i < features.size(); ++i) {</span></span>
|
||||
<span id="L41"><span class="lineNum"> 41</span> <span class="tlaGNC"> 238 : suLabels.push_back(symmetricalUncertainty(i, -1));</span></span>
|
||||
<span id="L42"><span class="lineNum"> 42</span> : }</span>
|
||||
<span id="L43"><span class="lineNum"> 43</span> <span class="tlaGNC"> 108 : }</span></span>
|
||||
<span id="L44"><span class="lineNum"> 44</span> <span class="tlaGNC"> 6499 : double FeatureSelect::computeSuFeatures(const int firstFeature, const int secondFeature)</span></span>
|
||||
<span id="L43"><span class="lineNum"> 43</span> <span class="tlaGNC"> 32 : }</span></span>
|
||||
<span id="L44"><span class="lineNum"> 44</span> <span class="tlaGNC"> 1960 : double FeatureSelect::computeSuFeatures(const int firstFeature, const int secondFeature)</span></span>
|
||||
<span id="L45"><span class="lineNum"> 45</span> : {</span>
|
||||
<span id="L46"><span class="lineNum"> 46</span> : // Compute Simmetrical Uncertainty between features</span>
|
||||
<span id="L47"><span class="lineNum"> 47</span> : // https://en.wikipedia.org/wiki/Symmetric_uncertainty</span>
|
||||
<span id="L48"><span class="lineNum"> 48</span> : try {</span>
|
||||
<span id="L49"><span class="lineNum"> 49</span> <span class="tlaGNC"> 6499 : return suFeatures.at({ firstFeature, secondFeature });</span></span>
|
||||
<span id="L49"><span class="lineNum"> 49</span> <span class="tlaGNC"> 1960 : return suFeatures.at({ firstFeature, secondFeature });</span></span>
|
||||
<span id="L50"><span class="lineNum"> 50</span> : }</span>
|
||||
<span id="L51"><span class="lineNum"> 51</span> <span class="tlaGNC"> 1953 : catch (const std::out_of_range& e) {</span></span>
|
||||
<span id="L52"><span class="lineNum"> 52</span> <span class="tlaGNC"> 1953 : double result = symmetricalUncertainty(firstFeature, secondFeature);</span></span>
|
||||
<span id="L53"><span class="lineNum"> 53</span> <span class="tlaGNC"> 1953 : suFeatures[{firstFeature, secondFeature}] = result;</span></span>
|
||||
<span id="L54"><span class="lineNum"> 54</span> <span class="tlaGNC"> 1953 : return result;</span></span>
|
||||
<span id="L55"><span class="lineNum"> 55</span> <span class="tlaGNC"> 1953 : }</span></span>
|
||||
<span id="L51"><span class="lineNum"> 51</span> <span class="tlaGNC"> 584 : catch (const std::out_of_range& e) {</span></span>
|
||||
<span id="L52"><span class="lineNum"> 52</span> <span class="tlaGNC"> 584 : double result = symmetricalUncertainty(firstFeature, secondFeature);</span></span>
|
||||
<span id="L53"><span class="lineNum"> 53</span> <span class="tlaGNC"> 584 : suFeatures[{firstFeature, secondFeature}] = result;</span></span>
|
||||
<span id="L54"><span class="lineNum"> 54</span> <span class="tlaGNC"> 584 : return result;</span></span>
|
||||
<span id="L55"><span class="lineNum"> 55</span> <span class="tlaGNC"> 584 : }</span></span>
|
||||
<span id="L56"><span class="lineNum"> 56</span> : }</span>
|
||||
<span id="L57"><span class="lineNum"> 57</span> <span class="tlaGNC"> 1047 : double FeatureSelect::computeMeritCFS()</span></span>
|
||||
<span id="L57"><span class="lineNum"> 57</span> <span class="tlaGNC"> 316 : double FeatureSelect::computeMeritCFS()</span></span>
|
||||
<span id="L58"><span class="lineNum"> 58</span> : {</span>
|
||||
<span id="L59"><span class="lineNum"> 59</span> <span class="tlaGNC"> 1047 : double rcf = 0;</span></span>
|
||||
<span id="L60"><span class="lineNum"> 60</span> <span class="tlaGNC"> 4816 : for (auto feature : selectedFeatures) {</span></span>
|
||||
<span id="L61"><span class="lineNum"> 61</span> <span class="tlaGNC"> 3769 : rcf += suLabels[feature];</span></span>
|
||||
<span id="L59"><span class="lineNum"> 59</span> <span class="tlaGNC"> 316 : double rcf = 0;</span></span>
|
||||
<span id="L60"><span class="lineNum"> 60</span> <span class="tlaGNC"> 1454 : for (auto feature : selectedFeatures) {</span></span>
|
||||
<span id="L61"><span class="lineNum"> 61</span> <span class="tlaGNC"> 1138 : rcf += suLabels[feature];</span></span>
|
||||
<span id="L62"><span class="lineNum"> 62</span> : }</span>
|
||||
<span id="L63"><span class="lineNum"> 63</span> <span class="tlaGNC"> 1047 : double rff = 0;</span></span>
|
||||
<span id="L64"><span class="lineNum"> 64</span> <span class="tlaGNC"> 1047 : int n = selectedFeatures.size();</span></span>
|
||||
<span id="L65"><span class="lineNum"> 65</span> <span class="tlaGNC"> 6907 : for (const auto& item : doCombinations(selectedFeatures)) {</span></span>
|
||||
<span id="L66"><span class="lineNum"> 66</span> <span class="tlaGNC"> 5860 : rff += computeSuFeatures(item.first, item.second);</span></span>
|
||||
<span id="L67"><span class="lineNum"> 67</span> <span class="tlaGNC"> 1047 : }</span></span>
|
||||
<span id="L68"><span class="lineNum"> 68</span> <span class="tlaGNC"> 1047 : return rcf / sqrt(n + (n * n - n) * rff);</span></span>
|
||||
<span id="L63"><span class="lineNum"> 63</span> <span class="tlaGNC"> 316 : double rff = 0;</span></span>
|
||||
<span id="L64"><span class="lineNum"> 64</span> <span class="tlaGNC"> 316 : int n = selectedFeatures.size();</span></span>
|
||||
<span id="L65"><span class="lineNum"> 65</span> <span class="tlaGNC"> 2086 : for (const auto& item : doCombinations(selectedFeatures)) {</span></span>
|
||||
<span id="L66"><span class="lineNum"> 66</span> <span class="tlaGNC"> 1770 : rff += computeSuFeatures(item.first, item.second);</span></span>
|
||||
<span id="L67"><span class="lineNum"> 67</span> <span class="tlaGNC"> 316 : }</span></span>
|
||||
<span id="L68"><span class="lineNum"> 68</span> <span class="tlaGNC"> 316 : return rcf / sqrt(n + (n * n - n) * rff);</span></span>
|
||||
<span id="L69"><span class="lineNum"> 69</span> : }</span>
|
||||
<span id="L70"><span class="lineNum"> 70</span> <span class="tlaGNC"> 116 : std::vector<int> FeatureSelect::getFeatures() const</span></span>
|
||||
<span id="L70"><span class="lineNum"> 70</span> <span class="tlaGNC"> 36 : std::vector<int> FeatureSelect::getFeatures() const</span></span>
|
||||
<span id="L71"><span class="lineNum"> 71</span> : {</span>
|
||||
<span id="L72"><span class="lineNum"> 72</span> <span class="tlaGNC"> 116 : if (!fitted) {</span></span>
|
||||
<span id="L73"><span class="lineNum"> 73</span> <span class="tlaGNC"> 8 : throw std::runtime_error("FeatureSelect not fitted");</span></span>
|
||||
<span id="L72"><span class="lineNum"> 72</span> <span class="tlaGNC"> 36 : if (!fitted) {</span></span>
|
||||
<span id="L73"><span class="lineNum"> 73</span> <span class="tlaGNC"> 4 : throw std::runtime_error("FeatureSelect not fitted");</span></span>
|
||||
<span id="L74"><span class="lineNum"> 74</span> : }</span>
|
||||
<span id="L75"><span class="lineNum"> 75</span> <span class="tlaGNC"> 108 : return selectedFeatures;</span></span>
|
||||
<span id="L75"><span class="lineNum"> 75</span> <span class="tlaGNC"> 32 : return selectedFeatures;</span></span>
|
||||
<span id="L76"><span class="lineNum"> 76</span> : }</span>
|
||||
<span id="L77"><span class="lineNum"> 77</span> <span class="tlaGNC"> 116 : std::vector<double> FeatureSelect::getScores() const</span></span>
|
||||
<span id="L77"><span class="lineNum"> 77</span> <span class="tlaGNC"> 36 : std::vector<double> FeatureSelect::getScores() const</span></span>
|
||||
<span id="L78"><span class="lineNum"> 78</span> : {</span>
|
||||
<span id="L79"><span class="lineNum"> 79</span> <span class="tlaGNC"> 116 : if (!fitted) {</span></span>
|
||||
<span id="L80"><span class="lineNum"> 80</span> <span class="tlaGNC"> 8 : throw std::runtime_error("FeatureSelect not fitted");</span></span>
|
||||
<span id="L79"><span class="lineNum"> 79</span> <span class="tlaGNC"> 36 : if (!fitted) {</span></span>
|
||||
<span id="L80"><span class="lineNum"> 80</span> <span class="tlaGNC"> 4 : throw std::runtime_error("FeatureSelect not fitted");</span></span>
|
||||
<span id="L81"><span class="lineNum"> 81</span> : }</span>
|
||||
<span id="L82"><span class="lineNum"> 82</span> <span class="tlaGNC"> 108 : return selectedScores;</span></span>
|
||||
<span id="L82"><span class="lineNum"> 82</span> <span class="tlaGNC"> 32 : return selectedScores;</span></span>
|
||||
<span id="L83"><span class="lineNum"> 83</span> : }</span>
|
||||
<span id="L84"><span class="lineNum"> 84</span> : }</span>
|
||||
</pre>
|
||||
|
||||
Reference in New Issue
Block a user