Merge branch 'master' into allow_empty_partitions

R-package/demo/basic_walkthrough.R

@@ -64,8 +64,8 @@ raw = xgb.save.raw(bst)
 # load binary model to R
 bst3 <- xgb.load(raw)
 pred3 <- predict(bst3, test$data)
-# pred2 should be identical to pred
-print(paste("sum(abs(pred3-pred))=", sum(abs(pred2-pred))))
+# pred3 should be identical to pred
+print(paste("sum(abs(pred3-pred))=", sum(abs(pred3-pred))))
 
 #----------------Advanced features --------------
 # to use advanced features, we need to put data in xgb.DMatrix

demo/README.md

@@ -88,6 +88,7 @@ Please send pull requests if you find ones that are missing here.
 ## Tutorials
 
 - [XGBoost Official RMarkdown Tutorials](https://xgboost.readthedocs.org/en/latest/R-package/index.html#tutorials)
+- [An Introduction to XGBoost R Package](http://dmlc.ml/rstats/2016/03/10/xgboost.html) by Tong He
 - [Open Source Tools & Data Science Competitions](http://www.slideshare.net/odsc/owen-zhangopen-sourcetoolsanddscompetitions1) by Owen Zhang - XGBoost parameter tuning tips
 * [Feature Importance Analysis with XGBoost in Tax audit](http://fr.slideshare.net/MichaelBENESTY/feature-importance-analysis-with-xgboost-in-tax-audit)
 * [Winning solution of Kaggle Higgs competition: what a single model can do](http://no2147483647.wordpress.com/2014/09/17/winning-solution-of-kaggle-higgs-competition-what-a-single-model-can-do/)
@@ -102,7 +103,6 @@ Please send pull requests if you find ones that are missing here.
 - [Notes on eXtreme Gradient Boosting](http://startup.ml/blog/xgboost) by ARSHAK NAVRUZYAN ([iPython Notebook](https://github.com/startupml/koan/blob/master/eXtreme%20Gradient%20Boosting.ipynb))
 - [Complete Guide to Parameter Tuning in XGBoost](http://www.analyticsvidhya.com/blog/2016/03/complete-guide-parameter-tuning-xgboost-with-codes-python/) by Aarshay Jain
 
-
 ## Usecases
 If you have particular usecase of xgboost that you would like to highlight.
 Send a PR to add a one sentence description:)

python-package/xgboost/core.py

@@ -144,7 +144,8 @@ def _maybe_pandas_data(data, feature_names, feature_types):
 
     data_dtypes = data.dtypes
     if not all(dtype.name in PANDAS_DTYPE_MAPPER for dtype in data_dtypes):
-        raise ValueError('DataFrame.dtypes for data must be int, float or bool')
+        bad_fields = [data.columns[i] for i, dtype in enumerate(data_dtypes) if dtype.name not in PANDAS_DTYPE_MAPPER ]  
+        raise ValueError('DataFrame.dtypes for data must be int, float or bool.\nDid not expect the data types in fie    lds '+', '.join(bad_fields))
 
     if feature_names is None:
         feature_names = data.columns.format()