precomp.hpp 13.1 KB
Newer Older
wester committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383
/*M///////////////////////////////////////////////////////////////////////////////////////
//
//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
//  By downloading, copying, installing or using the software you agree to this license.
//  If you do not agree to this license, do not download, install,
//  copy or use the software.
//
//
//                        Intel License Agreement
//
// Copyright (C) 2000, Intel Corporation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
//   * Redistribution's of source code must retain the above copyright notice,
//     this list of conditions and the following disclaimer.
//
//   * Redistribution's in binary form must reproduce the above copyright notice,
//     this list of conditions and the following disclaimer in the documentation
//     and/or other materials provided with the distribution.
//
//   * The name of Intel Corporation may not be used to endorse or promote products
//     derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/

#ifndef __OPENCV_ML_PRECOMP_HPP__
#define __OPENCV_ML_PRECOMP_HPP__

#include "opencv2/core.hpp"
#include "opencv2/ml.hpp"
#include "opencv2/core/core_c.h"
#include "opencv2/core/utility.hpp"

#include "opencv2/core/private.hpp"

#include <assert.h>
#include <float.h>
#include <limits.h>
#include <math.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <time.h>
#include <vector>

/****************************************************************************************\
 *                               Main struct definitions                                  *
 \****************************************************************************************/

/* log(2*PI) */
#define CV_LOG2PI (1.8378770664093454835606594728112)

namespace cv
{
namespace ml
{
    using std::vector;

    #define CV_DTREE_CAT_DIR(idx,subset) \
        (2*((subset[(idx)>>5]&(1 << ((idx) & 31)))==0)-1)

    template<typename _Tp> struct cmp_lt_idx
    {
        cmp_lt_idx(const _Tp* _arr) : arr(_arr) {}
        bool operator ()(int a, int b) const { return arr[a] < arr[b]; }
        const _Tp* arr;
    };

    template<typename _Tp> struct cmp_lt_ptr
    {
        cmp_lt_ptr() {}
        bool operator ()(const _Tp* a, const _Tp* b) const { return *a < *b; }
    };

    static inline void setRangeVector(std::vector<int>& vec, int n)
    {
        vec.resize(n);
        for( int i = 0; i < n; i++ )
            vec[i] = i;
    }

    static inline void writeTermCrit(FileStorage& fs, const TermCriteria& termCrit)
    {
        if( (termCrit.type & TermCriteria::EPS) != 0 )
            fs << "epsilon" << termCrit.epsilon;
        if( (termCrit.type & TermCriteria::COUNT) != 0 )
            fs << "iterations" << termCrit.maxCount;
    }

    static inline TermCriteria readTermCrit(const FileNode& fn)
    {
        TermCriteria termCrit;
        double epsilon = (double)fn["epsilon"];
        if( epsilon > 0 )
        {
            termCrit.type |= TermCriteria::EPS;
            termCrit.epsilon = epsilon;
        }
        int iters = (int)fn["iterations"];
        if( iters > 0 )
        {
            termCrit.type |= TermCriteria::COUNT;
            termCrit.maxCount = iters;
        }
        return termCrit;
    }

    struct TreeParams
    {
        TreeParams();
        TreeParams( int maxDepth, int minSampleCount,
                    double regressionAccuracy, bool useSurrogates,
                    int maxCategories, int CVFolds,
                    bool use1SERule, bool truncatePrunedTree,
                    const Mat& priors );

        inline void setMaxCategories(int val)
        {
            if( val < 2 )
                CV_Error( CV_StsOutOfRange, "max_categories should be >= 2" );
            maxCategories = std::min(val, 15 );
        }
        inline void setMaxDepth(int val)
        {
            if( val < 0 )
                CV_Error( CV_StsOutOfRange, "max_depth should be >= 0" );
            maxDepth = std::min( val, 25 );
        }
        inline void setMinSampleCount(int val)
        {
            minSampleCount = std::max(val, 1);
        }
        inline void setCVFolds(int val)
        {
            if( val < 0 )
                CV_Error( CV_StsOutOfRange,
                          "params.CVFolds should be =0 (the tree is not pruned) "
                          "or n>0 (tree is pruned using n-fold cross-validation)" );
            if( val == 1 )
                val = 0;
            CVFolds = val;
        }
        inline void setRegressionAccuracy(float val)
        {
            if( val < 0 )
                CV_Error( CV_StsOutOfRange, "params.regression_accuracy should be >= 0" );
            regressionAccuracy = val;
        }

        inline int getMaxCategories() const { return maxCategories; }
        inline int getMaxDepth() const { return maxDepth; }
        inline int getMinSampleCount() const { return minSampleCount; }
        inline int getCVFolds() const { return CVFolds; }
        inline float getRegressionAccuracy() const { return regressionAccuracy; }

        CV_IMPL_PROPERTY(bool, UseSurrogates, useSurrogates)
        CV_IMPL_PROPERTY(bool, Use1SERule, use1SERule)
        CV_IMPL_PROPERTY(bool, TruncatePrunedTree, truncatePrunedTree)
        CV_IMPL_PROPERTY_S(cv::Mat, Priors, priors)

        public:
            bool  useSurrogates;
        bool  use1SERule;
        bool  truncatePrunedTree;
        Mat priors;

    protected:
        int   maxCategories;
        int   maxDepth;
        int   minSampleCount;
        int   CVFolds;
        float regressionAccuracy;
    };

    struct RTreeParams
    {
        RTreeParams();
        RTreeParams(bool calcVarImportance, int nactiveVars, TermCriteria termCrit );
        bool calcVarImportance;
        int nactiveVars;
        TermCriteria termCrit;
    };

    struct BoostTreeParams
    {
        BoostTreeParams();
        BoostTreeParams(int boostType, int weakCount, double weightTrimRate);
        int boostType;
        int weakCount;
        double weightTrimRate;
    };

    class DTreesImpl : public DTrees
    {
    public:
        struct WNode
        {
            WNode()
            {
                class_idx = sample_count = depth = complexity = 0;
                parent = left = right = split = defaultDir = -1;
                Tn = INT_MAX;
                value = maxlr = alpha = node_risk = tree_risk = tree_error = 0.;
            }

            int class_idx;
            double Tn;
            double value;

            int parent;
            int left;
            int right;
            int defaultDir;

            int split;

            int sample_count;
            int depth;
            double maxlr;

            // global pruning data
            int complexity;
            double alpha;
            double node_risk, tree_risk, tree_error;
        };

        struct WSplit
        {
            WSplit()
            {
                varIdx = next = 0;
                inversed = false;
                quality = c = 0.f;
                subsetOfs = -1;
            }

            int varIdx;
            bool inversed;
            float quality;
            int next;
            float c;
            int subsetOfs;
        };

        struct WorkData
        {
            WorkData(const Ptr<TrainData>& _data);

            Ptr<TrainData> data;
            vector<WNode> wnodes;
            vector<WSplit> wsplits;
            vector<int> wsubsets;
            vector<double> cv_Tn;
            vector<double> cv_node_risk;
            vector<double> cv_node_error;
            vector<int> cv_labels;
            vector<double> sample_weights;
            vector<int> cat_responses;
            vector<double> ord_responses;
            vector<int> sidx;
            int maxSubsetSize;
        };

        CV_WRAP_SAME_PROPERTY(int, MaxCategories, params)
        CV_WRAP_SAME_PROPERTY(int, MaxDepth, params)
        CV_WRAP_SAME_PROPERTY(int, MinSampleCount, params)
        CV_WRAP_SAME_PROPERTY(int, CVFolds, params)
        CV_WRAP_SAME_PROPERTY(bool, UseSurrogates, params)
        CV_WRAP_SAME_PROPERTY(bool, Use1SERule, params)
        CV_WRAP_SAME_PROPERTY(bool, TruncatePrunedTree, params)
        CV_WRAP_SAME_PROPERTY(float, RegressionAccuracy, params)
        CV_WRAP_SAME_PROPERTY_S(cv::Mat, Priors, params)

        DTreesImpl();
        virtual ~DTreesImpl();
        virtual void clear();

        String getDefaultName() const { return "opencv_ml_dtree"; }
        bool isTrained() const { return !roots.empty(); }
        bool isClassifier() const { return _isClassifier; }
        int getVarCount() const { return varType.empty() ? 0 : (int)(varType.size() - 1); }
        int getCatCount(int vi) const { return catOfs[vi][1] - catOfs[vi][0]; }
        int getSubsetSize(int vi) const { return (getCatCount(vi) + 31)/32; }

        virtual void setDParams(const TreeParams& _params);
        virtual void startTraining( const Ptr<TrainData>& trainData, int flags );
        virtual void endTraining();
        virtual void initCompVarIdx();
        virtual bool train( const Ptr<TrainData>& trainData, int flags );

        virtual int addTree( const vector<int>& sidx );
        virtual int addNodeAndTrySplit( int parent, const vector<int>& sidx );
        virtual const vector<int>& getActiveVars();
        virtual int findBestSplit( const vector<int>& _sidx );
        virtual void calcValue( int nidx, const vector<int>& _sidx );

        virtual WSplit findSplitOrdClass( int vi, const vector<int>& _sidx, double initQuality );

        // simple k-means, slightly modified to take into account the "weight" (L1-norm) of each vector.
        virtual void clusterCategories( const double* vectors, int n, int m, double* csums, int k, int* labels );
        virtual WSplit findSplitCatClass( int vi, const vector<int>& _sidx, double initQuality, int* subset );

        virtual WSplit findSplitOrdReg( int vi, const vector<int>& _sidx, double initQuality );
        virtual WSplit findSplitCatReg( int vi, const vector<int>& _sidx, double initQuality, int* subset );

        virtual int calcDir( int splitidx, const vector<int>& _sidx, vector<int>& _sleft, vector<int>& _sright );
        virtual int pruneCV( int root );

        virtual double updateTreeRNC( int root, double T, int fold );
        virtual bool cutTree( int root, double T, int fold, double min_alpha );
        virtual float predictTrees( const Range& range, const Mat& sample, int flags ) const;
        virtual float predict( InputArray inputs, OutputArray outputs, int flags ) const;

        virtual void writeTrainingParams( FileStorage& fs ) const;
        virtual void writeParams( FileStorage& fs ) const;
        virtual void writeSplit( FileStorage& fs, int splitidx ) const;
        virtual void writeNode( FileStorage& fs, int nidx, int depth ) const;
        virtual void writeTree( FileStorage& fs, int root ) const;
        virtual void write( FileStorage& fs ) const;

        virtual void readParams( const FileNode& fn );
        virtual int readSplit( const FileNode& fn );
        virtual int readNode( const FileNode& fn );
        virtual int readTree( const FileNode& fn );
        virtual void read( const FileNode& fn );

        virtual const std::vector<int>& getRoots() const { return roots; }
        virtual const std::vector<Node>& getNodes() const { return nodes; }
        virtual const std::vector<Split>& getSplits() const { return splits; }
        virtual const std::vector<int>& getSubsets() const { return subsets; }

        TreeParams params;

        vector<int> varIdx;
        vector<int> compVarIdx;
        vector<uchar> varType;
        vector<Vec2i> catOfs;
        vector<int> catMap;
        vector<int> roots;
        vector<Node> nodes;
        vector<Split> splits;
        vector<int> subsets;
        vector<int> classLabels;
        vector<float> missingSubst;
        vector<int> varMapping;
        bool _isClassifier;

        Ptr<WorkData> w;
    };

    template <typename T>
    static inline void readVectorOrMat(const FileNode & node, std::vector<T> & v)
    {
        if (node.type() == FileNode::MAP)
        {
            Mat m;
            node >> m;
            m.copyTo(v);
        }
        else if (node.type() == FileNode::SEQ)
        {
            node >> v;
        }
    }

}}

#endif /* __OPENCV_ML_PRECOMP_HPP__ */