add feature name (#280)

docs/Python-API.md

@@ -345,9 +345,19 @@ The methods of each Class is in alphabetical order.
         Evaluation result list.
 
 
+####feature_name()
+
+    Get feature names.
+
+    Returns
+    -------
+    result : array
+        Array of feature names.
+
+
 ####feature_importance(importance_type="split")
 
-    Feature importances.
+    Get feature importances.
 
     Parameters
     ----------
@@ -359,7 +369,7 @@ The methods of each Class is in alphabetical order.
     Returns
     -------
     result : array
-        Array of feature importances
+        Array of feature importances.
 
 
 ####predict(data, num_iteration=-1, raw_score=False, pred_leaf=False, data_has_header=False, is_reshape=True)

examples/python-guide/simple_example.py

@@ -58,7 +58,8 @@ model_json = gbm.dump_model()
 with open('model.json', 'w+') as f:
     json.dump(model_json, f, indent=4)
 
+print('Feature names:', gbm.feature_name())
+
 print('Calculate feature importances...')
 # feature importances
 print('Feature importances:', list(gbm.feature_importance()))
-# print('Feature importances:', list(gbm.feature_importance("gain")))

include/LightGBM/boosting.h

@@ -167,6 +167,12 @@ public:
   */
   virtual int MaxFeatureIdx() const = 0;
 
+  /*!
+  * \brief Get feature names of this model
+  * \return Feature names of this model
+  */
+  virtual std::vector<std::string> FeatureNames() const = 0;
+
   /*!
   * \brief Get index of label column
   * \return index of label column

include/LightGBM/c_api.h

@@ -365,13 +365,28 @@ LIGHTGBM_C_EXPORT int LGBM_BoosterGetCurrentIteration(BoosterHandle handle, int*
 LIGHTGBM_C_EXPORT int LGBM_BoosterGetEvalCounts(BoosterHandle handle, int* out_len);
 
 /*!
-* \brief Get Name of eval
+* \brief Get name of eval
 * \param out_len total number of eval results
 * \param out_strs names of eval result, need to pre-allocate memory before call this
 * \return 0 when succeed, -1 when failure happens
 */
 LIGHTGBM_C_EXPORT int LGBM_BoosterGetEvalNames(BoosterHandle handle, int* out_len, char** out_strs);
 
+/*!
+* \brief Get name of features
+* \param out_len total number of features
+* \param out_strs names of features, need to pre-allocate memory before call this
+* \return 0 when succeed, -1 when failure happens
+*/
+LIGHTGBM_C_EXPORT int LGBM_BoosterGetFeatureNames(BoosterHandle handle, int* out_len, char** out_strs);
+
+/*!
+* \brief Get number of features
+* \param out_len total number of features
+* \return 0 when succeed, -1 when failure happens
+*/
+LIGHTGBM_C_EXPORT int LGBM_BoosterGetNumFeature(BoosterHandle handle, int* out_len);
+
 /*!
 * \brief get evaluation for training data and validation data
 Note: 1. you should call LGBM_BoosterGetEvalNames first to get the name of evaluation results

python-package/lightgbm/basic.py

@@ -1582,15 +1582,41 @@ class Booster(object):
         return predictor.predict(data, num_iteration, raw_score, pred_leaf, data_has_header, is_reshape)
 
     def _to_predictor(self):
-        """Convert to predictor
-        """
+        """Convert to predictor"""
         predictor = _InnerPredictor(booster_handle=self.handle)
         predictor.pandas_categorical = self.pandas_categorical
         return predictor
 
+    def feature_name(self):
+        """
+        Get feature names.
+
+        Returns
+        -------
+        result : array
+            Array of feature names.
+        """
+        out_num_feature = ctypes.c_int(0)
+        """Get num of features"""
+        _safe_call(_LIB.LGBM_BoosterGetNumFeature(
+            self.handle,
+            ctypes.byref(out_num_feature)))
+        num_feature = out_num_feature.value
+        """Get name of features"""
+        tmp_out_len = ctypes.c_int(0)
+        string_buffers = [ctypes.create_string_buffer(255) for i in range_(num_feature)]
+        ptr_string_buffers = (ctypes.c_char_p * num_feature)(*map(ctypes.addressof, string_buffers))
+        _safe_call(_LIB.LGBM_BoosterGetFeatureNames(
+            self.handle,
+            ctypes.byref(tmp_out_len),
+            ptr_string_buffers))
+        if num_feature != tmp_out_len.value:
+            raise ValueError("Length of feature names doesn't equal with num_feature")
+        return [string_buffers[i].value.decode() for i in range_(num_feature)]
+
     def feature_importance(self, importance_type='split'):
         """
-        Feature importances
+        Get feature importances
 
         Parameters
         ----------
@@ -1601,7 +1627,8 @@ class Booster(object):
 
         Returns
         -------
-        Array of feature importances
+        result : array
+            Array of feature importances.
         """
         if importance_type not in ["split", "gain"]:
             raise KeyError("importance_type must be split or gain")

src/boosting/gbdt.h

@@ -176,6 +176,12 @@ public:
   */
   inline int MaxFeatureIdx() const override { return max_feature_idx_; }
 
+  /*!
+  * \brief Get feature names of this model
+  * \return Feature names of this model
+  */
+  inline std::vector<std::string> FeatureNames() const override { return feature_names_; }
+
   /*!
   * \brief Get index of label column
   * \return index of label column

src/c_api.cpp

@@ -225,6 +225,15 @@ public:
     return idx;
   }
 
+  int GetFeatureNames(char** out_strs) const {
+    int idx = 0;
+    for (const auto& name : boosting_->FeatureNames()) {
+      std::strcpy(out_strs[idx], name.c_str());
+      ++idx;
+    }
+    return idx;
+  }
+
   const Boosting* GetBoosting() const { return boosting_.get(); }
 
 private:
@@ -724,6 +733,20 @@ LIGHTGBM_C_EXPORT int LGBM_BoosterGetEvalNames(BoosterHandle handle, int* out_le
   API_END();
 }
 
+LIGHTGBM_C_EXPORT int LGBM_BoosterGetFeatureNames(BoosterHandle handle, int* out_len, char** out_strs) {
+  API_BEGIN();
+  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
+  *out_len = ref_booster->GetFeatureNames(out_strs);
+  API_END();
+}
+
+LIGHTGBM_C_EXPORT int LGBM_BoosterGetNumFeature(BoosterHandle handle, int* out_len) {
+  API_BEGIN();
+  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
+  *out_len = ref_booster->GetBoosting()->MaxFeatureIdx() + 1;
+  API_END();
+}
+
 LIGHTGBM_C_EXPORT int LGBM_BoosterGetEval(BoosterHandle handle,
   int data_idx,
   int* out_len,

tests/python_package_test/test_engine.py

@@ -124,6 +124,12 @@ class TestEngine(unittest.TestCase):
                metrics='l1', verbose_eval=False,
                callbacks=[lgb.reset_parameter(learning_rate=lambda i: 0.1 - 0.001 * i)])
 
+    def test_feature_name(self):
+        lgb_train, _ = template.test_template(return_data=True)
+        feature_names = ['f' + str(i) for i in range(13)]
+        gbm = lgb.train({'verbose': -1}, lgb_train, num_boost_round=10, feature_name=feature_names)
+        self.assertListEqual(feature_names, gbm.feature_name())
+
     def test_save_load_copy_pickle(self):
         gbm = template.test_template(num_round=20, return_model=True)
         _, ret_origin = template.test_template(init_model=gbm)