Module: XGBoost
- Defined in:
- lib/xgboost.rb,
lib/xgboost/ffi.rb,
lib/xgboost/model.rb,
lib/xgboost/utils.rb,
lib/xgboost/ranker.rb,
lib/xgboost/booster.rb,
lib/xgboost/dmatrix.rb,
lib/xgboost/version.rb,
lib/xgboost/regressor.rb,
lib/xgboost/classifier.rb
Defined Under Namespace
Modules: FFI, Utils Classes: Booster, Classifier, DMatrix, Error, Model, Ranker, Regressor
Constant Summary collapse
- VERSION =
"0.7.1"
Class Attribute Summary collapse
-
.ffi_lib ⇒ Object
Returns the value of attribute ffi_lib.
Class Method Summary collapse
- .cv(params, dtrain, num_boost_round: 10, nfold: 3, seed: 0, shuffle: true, verbose_eval: nil, show_stdv: true, early_stopping_rounds: nil) ⇒ Object
- .lib_version ⇒ Object
- .train(params, dtrain, num_boost_round: 10, evals: nil, early_stopping_rounds: nil, verbose_eval: true) ⇒ Object
Class Attribute Details
.ffi_lib ⇒ Object
Returns the value of attribute ffi_lib.
20 21 22 |
# File 'lib/xgboost.rb', line 20 def ffi_lib @ffi_lib end |
Class Method Details
.cv(params, dtrain, num_boost_round: 10, nfold: 3, seed: 0, shuffle: true, verbose_eval: nil, show_stdv: true, early_stopping_rounds: nil) ⇒ Object
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 |
# File 'lib/xgboost.rb', line 90 def cv(params, dtrain, num_boost_round: 10, nfold: 3, seed: 0, shuffle: true, verbose_eval: nil, show_stdv: true, early_stopping_rounds: nil) rand_idx = (0...dtrain.num_row).to_a rand_idx.shuffle!(random: Random.new(seed)) if shuffle kstep = (rand_idx.size / nfold.to_f).ceil test_id = rand_idx.each_slice(kstep).to_a[0...nfold] train_id = [] nfold.times do |i| idx = test_id.dup idx.delete_at(i) train_id << idx.flatten end folds = train_id.zip(test_id) cvfolds = [] folds.each do |(train_idx, test_idx)| fold_dtrain = dtrain.slice(train_idx) fold_dvalid = dtrain.slice(test_idx) booster = Booster.new(params: params) booster.set_param("num_feature", dtrain.num_col) cvfolds << [booster, fold_dtrain, fold_dvalid] end eval_hist = {} if early_stopping_rounds best_score = nil best_iter = nil end num_boost_round.times do |iteration| scores = {} cvfolds.each do |(booster, fold_dtrain, fold_dvalid)| booster.update(fold_dtrain, iteration) = booster.eval_set([[fold_dtrain, "train"], [fold_dvalid, "test"]], iteration) res = .split.map { |x| x.split(":") }[1..-1].map { |k, v| [k, v.to_f] } res.each do |k, v| (scores[k] ||= []) << v end end = ["[#{iteration}]"] last_mean = nil means = {} scores.each do |eval_name, vals| mean = mean(vals) stdev = stdev(vals) (eval_hist["#{eval_name}-mean"] ||= []) << mean (eval_hist["#{eval_name}-std"] ||= []) << stdev means[eval_name] = mean last_mean = mean if show_stdv << "%s:%g+%g" % [eval_name, mean, stdev] else << "%s:%g" % [eval_name, mean] end end if early_stopping_rounds score = last_mean # TODO handle larger better if best_score.nil? || score < best_score best_score = score best_iter = iteration elsif iteration - best_iter >= early_stopping_rounds eval_hist.each_key do |k| eval_hist[k] = eval_hist[k][0..best_iter] end break end end # put at end to keep output consistent with Python puts .join("\t") if verbose_eval end eval_hist end |
.lib_version ⇒ Object
175 176 177 178 179 180 181 |
# File 'lib/xgboost.rb', line 175 def lib_version major = ::FFI::MemoryPointer.new(:int) minor = ::FFI::MemoryPointer.new(:int) patch = ::FFI::MemoryPointer.new(:int) FFI.XGBoostVersion(major, minor, patch) "#{major.read_int}.#{minor.read_int}.#{patch.read_int}" end |
.train(params, dtrain, num_boost_round: 10, evals: nil, early_stopping_rounds: nil, verbose_eval: true) ⇒ Object
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 |
# File 'lib/xgboost.rb', line 45 def train(params, dtrain, num_boost_round: 10, evals: nil, early_stopping_rounds: nil, verbose_eval: true) booster = Booster.new(params: params) num_feature = dtrain.num_col booster.set_param("num_feature", num_feature) booster.feature_names = dtrain.feature_names booster.feature_types = dtrain.feature_types evals ||= [] if early_stopping_rounds best_score = nil best_iter = nil = nil end num_boost_round.times do |iteration| booster.update(dtrain, iteration) if evals.any? = booster.eval_set(evals, iteration) res = .split.map { |x| x.split(":") }[1..-1].map { |k, v| [k, v.to_f] } if early_stopping_rounds && iteration == 0 metric = res[-1][0] puts "Will train until #{metric} hasn't improved in #{early_stopping_rounds.to_i} rounds." if verbose_eval end puts if verbose_eval score = res[-1][1] # TODO handle larger better if best_score.nil? || score < best_score best_score = score best_iter = iteration = elsif early_stopping_rounds && iteration - best_iter >= early_stopping_rounds booster.best_iteration = best_iter puts "Stopping. Best iteration:\n#{}" if verbose_eval break end end end booster end |