Update demo scripts to use installed python library

demo/kaggle-higgs/higgs-cv.py

@@ -1,7 +1,5 @@
 #!/usr/bin/python
-import sys
 import numpy as np
-sys.path.append('../../wrapper')
 import xgboost as xgb
 
 ### load data in do training

demo/kaggle-higgs/higgs-numpy.py

@@ -1,14 +1,6 @@
 #!/usr/bin/python
-# this is the example script to use xgboost to train 
-import inspect
-import os
-import sys
+# this is the example script to use xgboost to train
 import numpy as np
-# add path of xgboost python module
-code_path = os.path.join(
-    os.path.split(inspect.getfile(inspect.currentframe()))[0], "../../wrapper")
-
-sys.path.append(code_path)
 
 import xgboost as xgb
 
@@ -29,7 +21,7 @@ weight = dtrain[:,31] * float(test_size) / len(label)
 sum_wpos = sum( weight[i] for i in range(len(label)) if label[i] == 1.0  )
 sum_wneg = sum( weight[i] for i in range(len(label)) if label[i] == 0.0  )
 
-# print weight statistics 
+# print weight statistics
 print ('weight statistics: wpos=%g, wneg=%g, ratio=%g' % ( sum_wpos, sum_wneg, sum_wneg/sum_wpos ))
 
 # construct xgboost.DMatrix from numpy array, treat -999.0 as missing value
@@ -42,13 +34,13 @@ param = {}
 param['objective'] = 'binary:logitraw'
 # scale weight of positive examples
 param['scale_pos_weight'] = sum_wneg/sum_wpos
-param['eta'] = 0.1 
+param['eta'] = 0.1
 param['max_depth'] = 6
 param['eval_metric'] = 'auc'
 param['silent'] = 1
 param['nthread'] = 16
 
-# you can directly throw param in, though we want to watch multiple metrics here 
+# you can directly throw param in, though we want to watch multiple metrics here
 plst = list(param.items())+[('eval_metric', 'ams@0.15')]
 
 watchlist = [ (xgmat,'train') ]

demo/kaggle-higgs/higgs-pred.py

@@ -1,9 +1,6 @@
 #!/usr/bin/python
-# make prediction 
-import sys
+# make prediction
 import numpy as np
-# add path of xgboost python module
-sys.path.append('../../wrapper/')
 import xgboost as xgb
 
 # path to where the data lies
@@ -11,7 +8,7 @@ dpath = 'data'
 
 modelfile = 'higgs.model'
 outfile = 'higgs.pred.csv'
-# make top 15% as positive 
+# make top 15% as positive
 threshold_ratio = 0.15
 
 # load in training data, directly use numpy
@@ -24,7 +21,7 @@ xgmat = xgb.DMatrix( data, missing = -999.0 )
 bst = xgb.Booster({'nthread':16}, model_file = modelfile)
 ypred = bst.predict( xgmat )
 
-res  = [ ( int(idx[i]), ypred[i] ) for i in range(len(ypred)) ] 
+res  = [ ( int(idx[i]), ypred[i] ) for i in range(len(ypred)) ]
 
 rorder = {}
 for k, v in sorted( res, key = lambda x:-x[1] ):
@@ -36,12 +33,12 @@ fo = open(outfile, 'w')
 nhit = 0
 ntot = 0
 fo.write('EventId,RankOrder,Class\n')
-for k, v in res:        
+for k, v in res:
     if rorder[k] <= ntop:
         lb = 's'
         nhit += 1
     else:
-        lb = 'b'        
+        lb = 'b'
     # change output rank order to follow Kaggle convention
     fo.write('%s,%d,%s\n' % ( k,  len(rorder)+1-rorder[k], lb ) )
     ntot += 1

demo/kaggle-higgs/speedtest.py

@@ -1,9 +1,6 @@
 #!/usr/bin/python
 # this is the example script to use xgboost to train
-import sys
 import numpy as np
-# add path of xgboost python module
-sys.path.append('../../wrapper/')
 import xgboost as xgb
 from sklearn.ensemble import GradientBoostingClassifier
 import time