python package refactor into python-package

Makefile

@@ -169,7 +169,7 @@ Rcheck:
 
 # lint requires dmlc to be in current folder
 lint:
-	dmlc-core/scripts/lint.py xgboost $(LINT_LANG) src wrapper R-package
+	dmlc-core/scripts/lint.py xgboost $(LINT_LANG) src wrapper R-package python-package
 
 clean:
 	$(RM) -rf $(OBJ) $(BIN) $(MPIBIN) $(MPIOBJ) $(SLIB) *.o  */*.o */*/*.o *~ */*~ */*/*~

demo/.gitignore

@@ -1 +1,2 @@
-*.libsvm
+*.libsvm
+*.pkl

demo/README.md

@@ -1,14 +1,14 @@
 XGBoost Examples
 ====
-This folder contains all the code examples using xgboost. 
+This folder contains all the code examples using xgboost.
 
 * Contribution of examples, benchmarks is more than welcome!
 * If you like to share how you use xgboost to solve your problem, send a pull request:)
- 
+
 Features Walkthrough
 ====
-This is a list of short codes introducing different functionalities of xgboost and its wrapper.
-* Basic walkthrough of wrappers 
+This is a list of short codes introducing different functionalities of xgboost packages.
+* Basic walkthrough of packages
   [python](guide-python/basic_walkthrough.py)
   [R](../R-package/demo/basic_walkthrough.R)
   [Julia](https://github.com/antinucleon/XGBoost.jl/blob/master/demo/basic_walkthrough.jl)
@@ -20,18 +20,18 @@ This is a list of short codes introducing different functionalities of xgboost a
   [python](guide-python/boost_from_prediction.py)
   [R](../R-package/demo/boost_from_prediction.R)
   [Julia](https://github.com/antinucleon/XGBoost.jl/blob/master/demo/boost_from_prediction.jl)
-* Predicting using first n trees 
+* Predicting using first n trees
   [python](guide-python/predict_first_ntree.py)
   [R](../R-package/demo/boost_from_prediction.R)
-  [Julia](https://github.com/antinucleon/XGBoost.jl/blob/master/demo/boost_from_prediction.jl)  
+  [Julia](https://github.com/antinucleon/XGBoost.jl/blob/master/demo/boost_from_prediction.jl)
 * Generalized Linear Model
   [python](guide-python/generalized_linear_model.py)
   [R](../R-package/demo/generalized_linear_model.R)
-  [Julia](https://github.com/antinucleon/XGBoost.jl/blob/master/demo/generalized_linear_model.jl)  
+  [Julia](https://github.com/antinucleon/XGBoost.jl/blob/master/demo/generalized_linear_model.jl)
 * Cross validation
   [python](guide-python/cross_validation.py)
   [R](../R-package/demo/cross_validation.R)
-  [Julia](https://github.com/antinucleon/XGBoost.jl/blob/master/demo/cross_validation.jl)  
+  [Julia](https://github.com/antinucleon/XGBoost.jl/blob/master/demo/cross_validation.jl)
 * Predicting leaf indices
   [python](guide-python/predict_leaf_indices.py)
   [R](../R-package/demo/predict_leaf_indices.R)
@@ -48,5 +48,5 @@ However, the parameter settings can be applied to all versions
 Benchmarks
 ====
 * [Starter script for Kaggle Higgs Boson](kaggle-higgs)
-* [Kaggle Tradeshift winning solution by daxiongshu](https://github.com/daxiongshu/kaggle-tradeshift-winning-solution) 
+* [Kaggle Tradeshift winning solution by daxiongshu](https://github.com/daxiongshu/kaggle-tradeshift-winning-solution)
 

demo/guide-python/sklearn_examples.py

@@ -75,13 +75,3 @@
 clf.fit(X_train, y_train, early_stopping_rounds=10, eval_metric="auc",
         eval_set=[(X_test, y_test)])
 
-# Custom evaluation function
-from sklearn.metrics import log_loss
-
-
-def log_loss_eval(y_pred, y_true):
-    return "log-loss", log_loss(y_true.get_label(), y_pred)
-
-
-clf.fit(X_train, y_train, early_stopping_rounds=10, eval_metric=log_loss_eval,
-        eval_set=[(X_test, y_test)])

doc/python.md

@@ -14,7 +14,7 @@ A [walk through python example](https://github.com/tqchen/xgboost/blob/master/de
 =
 #### Install
 
-To install XGBoost, you need to run `make` in the root directory of the project and then in the `wrappers` directory run
+To install XGBoost, you need to run `make` in the root directory of the project and then in the `python-package` directory run
 
 ```shell
 python setup.py install

python-package/.gitignore

@@ -0,0 +1,3 @@
+build
+dist
+*.egg*

python-package/README.md

@@ -0,0 +1,7 @@
+XGBoost Python Package
+======================
+* To make the python module, type ```./build.sh``` in the root directory of project
+* Make sure you have [setuptools](https://pypi.python.org/pypi/setuptools)
+* Install with `python setup.py install` from this directory.
+* Refer also to the walk through example in [demo folder](../demo/guide-python)
+* **NOTE**: if you want to run XGBoost process in parallel using the fork backend for joblib/multiprocessing, you must build XGBoost without support for OpenMP by `make no_omp=1`. Otherwise, use the forkserver (in Python 3.4) or spawn backend. See the sklearn_parallel.py demo.

python-package/setup.py

@@ -0,0 +1,21 @@
+# pylint: disable=invalid-name
+"""Setup xgboost package."""
+from __future__ import absolute_import
+import sys
+from setuptools import setup
+sys.path.insert(0, '.')
+import xgboost
+
+LIB_PATH = xgboost.core.find_lib_path()
+
+setup(name='xgboost',
+      version=xgboost.__version__,
+      description=xgboost.__doc__,
+      install_requires=[
+          'numpy',
+          'scipy',
+      ],
+      zip_safe=False,
+      packages=['xgboost'],
+      data_files=[('xgboost', [LIB_PATH[0]])],
+      url='https://github.com/dmlc/xgboost')