Update Python demos with tests.

demo/aft_survival/aft_survival_demo.py

@@ -1,14 +1,16 @@
 """
 Demo for survival analysis (regression) using Accelerated Failure Time (AFT) model
 """
+import os
 from sklearn.model_selection import ShuffleSplit
 import pandas as pd
 import numpy as np
 import xgboost as xgb
 
 # The Veterans' Administration Lung Cancer Trial
 # The Statistical Analysis of Failure Time Data by Kalbfleisch J. and Prentice R (1980)
-df = pd.read_csv('../data/veterans_lung_cancer.csv')
+CURRENT_DIR = os.path.dirname(__file__)
+df = pd.read_csv(os.path.join(CURRENT_DIR, '../data/veterans_lung_cancer.csv'))
 print('Training data:')
 print(df)
 
@@ -39,7 +41,7 @@
           'lambda': 0.01,
           'alpha': 0.02}
 bst = xgb.train(params, dtrain, num_boost_round=10000,
-                evals=[(dtrain, 'train'), (dvalid, 'valid')], 
+                evals=[(dtrain, 'train'), (dvalid, 'valid')],
                 early_stopping_rounds=50)
 
 # Run prediction on the validation set

demo/c-api/c-api-demo.c

@@ -20,12 +20,12 @@ if (err != 0) {                                                         \
 int main(int argc, char** argv) {
   int silent = 0;
   int use_gpu = 0;  // set to 1 to use the GPU for training
-  
+
   // load the data
   DMatrixHandle dtrain, dtest;
   safe_xgboost(XGDMatrixCreateFromFile("../data/agaricus.txt.train", silent, &dtrain));
   safe_xgboost(XGDMatrixCreateFromFile("../data/agaricus.txt.test", silent, &dtest));
-  
+
   // create the booster
   BoosterHandle booster;
   DMatrixHandle eval_dmats[2] = {dtrain, dtest};
@@ -49,7 +49,7 @@ int main(int argc, char** argv) {
   safe_xgboost(XGBoosterSetParam(booster, "gamma", "0.1"));
   safe_xgboost(XGBoosterSetParam(booster, "max_depth", "3"));
   safe_xgboost(XGBoosterSetParam(booster, "verbosity", silent ? "0" : "1"));
-  
+
   // train and evaluate for 10 iterations
   int n_trees = 10;
   const char* eval_names[2] = {"train", "test"};

demo/gpu_acceleration/README.md

@@ -1,5 +1,3 @@
 # GPU Acceleration Demo
 
-`cover_type.py` shows how to train a model on the [forest cover type](https://archive.ics.uci.edu/ml/datasets/covertype) dataset using GPU acceleration. The forest cover type dataset has 581,012 rows and 54 features, making it time consuming to process. We compare the run-time and accuracy of the GPU and CPU histogram algorithms.
-
-`memory.py` shows how to repeatedly train xgboost models while freeing memory between iterations.
+`cover_type.py` shows how to train a model on the [forest cover type](https://archive.ics.uci.edu/ml/datasets/covertype) dataset using GPU acceleration. The forest cover type dataset has 581,012 rows and 54 features, making it time consuming to process. We compare the run-time and accuracy of the GPU and CPU histogram algorithms.

demo/gpu_acceleration/cover_type.py

@@ -1,5 +1,4 @@
 import xgboost as xgb
-import numpy as np
 from sklearn.datasets import fetch_covtype
 from sklearn.model_selection import train_test_split
 import time

demo/guide-python/basic_walkthrough.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 import numpy as np
 import scipy.sparse
 import pickle

demo/guide-python/boost_from_prediction.py

@@ -1,15 +1,17 @@
-#!/usr/bin/python
+import os
 import xgboost as xgb
 
-dtrain = xgb.DMatrix('../data/agaricus.txt.train')
-dtest = xgb.DMatrix('../data/agaricus.txt.test')
+
+CURRENT_DIR = os.path.dirname(__file__)
+dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
+dtest = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.test'))
 watchlist = [(dtest, 'eval'), (dtrain, 'train')]
 ###
 # advanced: start from a initial base prediction
 #
 print('start running example to start from a initial prediction')
 # specify parameters via map, definition are same as c++ version
-param = {'max_depth': 2, 'eta': 1, 'silent': 1, 'objective': 'binary:logistic'}
+param = {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'}
 # train xgboost for 1 round
 bst = xgb.train(param, dtrain, 1, watchlist)
 # Note: we need the margin value instead of transformed prediction in

demo/guide-python/cross_validation.py

@@ -1,10 +1,11 @@
-#!/usr/bin/python
+import os
 import numpy as np
 import xgboost as xgb
 
-### load data in do training
-dtrain = xgb.DMatrix('../data/agaricus.txt.train')
-param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
+# load data in do training
+CURRENT_DIR = os.path.dirname(__file__)
+dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
+param = {'max_depth':2, 'eta':1, 'objective':'binary:logistic'}
 num_round = 2
 
 print('running cross validation')
@@ -56,7 +57,7 @@ def evalerror(preds, dtrain):
     labels = dtrain.get_label()
     return 'error', float(sum(labels != (preds > 0.0))) / len(labels)
 
-param = {'max_depth':2, 'eta':1, 'silent':1}
+param = {'max_depth':2, 'eta':1}
 # train with customized objective
 xgb.cv(param, dtrain, num_round, nfold=5, seed=0,
        obj=logregobj, feval=evalerror)

demo/guide-python/custom_objective.py

@@ -1,18 +1,19 @@
-#!/usr/bin/python
+import os
 import numpy as np
 import xgboost as xgb
 ###
 # advanced: customized loss function
 #
 print('start running example to used customized objective function')
 
-dtrain = xgb.DMatrix('../data/agaricus.txt.train')
-dtest = xgb.DMatrix('../data/agaricus.txt.test')
+CURRENT_DIR = os.path.dirname(__file__)
+dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
+dtest = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.test'))
 
 # note: for customized objective function, we leave objective as default
 # note: what we are getting is margin value in prediction
 # you must know what you are doing
-param = {'max_depth': 2, 'eta': 1, 'silent': 1}
+param = {'max_depth': 2, 'eta': 1}
 watchlist = [(dtest, 'eval'), (dtrain, 'train')]
 num_round = 2
 

demo/guide-python/evals_result.py

@@ -1,13 +1,15 @@
 ##
 #  This script demonstrate how to access the eval metrics in xgboost
 ##
-
+import os
 import xgboost as xgb
-dtrain = xgb.DMatrix('../data/agaricus.txt.train', silent=True)
-dtest = xgb.DMatrix('../data/agaricus.txt.test', silent=True)
+
+CURRENT_DIR = os.path.dirname(__file__)
+dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
+dtest = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.test'))
 
 param = [('max_depth', 2), ('objective', 'binary:logistic'), ('eval_metric', 'logloss'), ('eval_metric', 'error')]
- 
+
 num_round = 2
 watchlist = [(dtest,'eval'), (dtrain,'train')]
 

demo/guide-python/external_memory.py

@@ -1,18 +1,17 @@
-#!/usr/bin/python
-import numpy as np
-import scipy.sparse
+import os
 import xgboost as xgb
 
 ### simple example for using external memory version
 
 # this is the only difference, add a # followed by a cache prefix name
 # several cache file with the prefix will be generated
 # currently only support convert from libsvm file
-dtrain = xgb.DMatrix('../data/agaricus.txt.train#dtrain.cache')
-dtest = xgb.DMatrix('../data/agaricus.txt.test#dtest.cache')
+CURRENT_DIR = os.path.dirname(__file__)
+dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
+dtest = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.test'))
 
 # specify validations set to watch performance
-param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
+param = {'max_depth':2, 'eta':1, 'objective':'binary:logistic'}
 
 # performance notice: set nthread to be the number of your real cpu
 # some cpu offer two threads per core, for example, a 4 core cpu with 8 threads, in such case set nthread=4
@@ -21,5 +20,3 @@
 watchlist = [(dtest, 'eval'), (dtrain, 'train')]
 num_round = 2
 bst = xgb.train(param, dtrain, num_round, watchlist)
-
-

demo/guide-python/gamma_regression.py

@@ -1,4 +1,3 @@
-#!/usr/bin/python
 import xgboost as xgb
 import numpy as np
 
@@ -12,7 +11,7 @@
 
 # for gamma regression, we need to set the objective to 'reg:gamma', it also suggests
 # to set the base_score to a value between 1 to 5 if the number of iteration is small
-param = {'silent':1, 'objective':'reg:gamma', 'booster':'gbtree', 'base_score':3}
+param = {'objective':'reg:gamma', 'booster':'gbtree', 'base_score':3}
 
 # the rest of settings are the same
 watchlist = [(dtest, 'eval'), (dtrain, 'train')]

demo/guide-python/generalized_linear_model.py

@@ -1,16 +1,17 @@
-#!/usr/bin/python
+import os
 import xgboost as xgb
 ##
 #  this script demonstrate how to fit generalized linear model in xgboost
 #  basically, we are using linear model, instead of tree for our boosters
 ##
-dtrain = xgb.DMatrix('../data/agaricus.txt.train')
-dtest = xgb.DMatrix('../data/agaricus.txt.test')
+CURRENT_DIR = os.path.dirname(__file__)
+dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
+dtest = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.test'))
 # change booster to gblinear, so that we are fitting a linear model
 # alpha is the L1 regularizer
 # lambda is the L2 regularizer
 # you can also set lambda_bias which is L2 regularizer on the bias term
-param = {'silent':1, 'objective':'binary:logistic', 'booster':'gblinear',
+param = {'objective':'binary:logistic', 'booster':'gblinear',
          'alpha': 0.0001, 'lambda': 1}
 
 # normally, you do not need to set eta (step_size)

demo/guide-python/predict_first_ntree.py

@@ -1,17 +1,18 @@
-#!/usr/bin/python
+import os
 import numpy as np
 import xgboost as xgb
 
-### load data in do training
-dtrain = xgb.DMatrix('../data/agaricus.txt.train')
-dtest = xgb.DMatrix('../data/agaricus.txt.test')
-param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
+# load data in do training
+CURRENT_DIR = os.path.dirname(__file__)
+dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
+dtest = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.test'))
+param = {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'}
 watchlist = [(dtest, 'eval'), (dtrain, 'train')]
 num_round = 3
 bst = xgb.train(param, dtrain, num_round, watchlist)
 
 print('start testing prediction from first n trees')
-### predict using first 1 tree
+# predict using first 1 tree
 label = dtest.get_label()
 ypred1 = bst.predict(dtest, ntree_limit=1)
 # by default, we predict using all the trees

demo/guide-python/predict_leaf_indices.py

@@ -1,19 +1,20 @@
-#!/usr/bin/python
+import os
 import xgboost as xgb
 
-### load data in do training
-dtrain = xgb.DMatrix('../data/agaricus.txt.train')
-dtest = xgb.DMatrix('../data/agaricus.txt.test')
-param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
+# load data in do training
+CURRENT_DIR = os.path.dirname(__file__)
+dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
+dtest = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.test'))
+param = {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'}
 watchlist = [(dtest, 'eval'), (dtrain, 'train')]
 num_round = 3
 bst = xgb.train(param, dtrain, num_round, watchlist)
 
-print ('start testing predict the leaf indices')
-### predict using first 2 tree
+print('start testing predict the leaf indices')
+# predict using first 2 tree
 leafindex = bst.predict(dtest, ntree_limit=2, pred_leaf=True)
 print(leafindex.shape)
 print(leafindex)
-### predict all trees
+# predict all trees
 leafindex = bst.predict(dtest, pred_leaf=True)
 print(leafindex.shape)

demo/guide-python/sklearn_evals_result.py

@@ -20,7 +20,7 @@
 # Or you can use: clf = xgb.XGBClassifier(**param_dist)
 
 clf.fit(X_train, y_train,
-        eval_set=[(X_train, y_train), (X_test, y_test)], 
+        eval_set=[(X_train, y_train), (X_test, y_test)],
         eval_metric='logloss',
         verbose=True)
 
@@ -37,7 +37,7 @@
     for e_mtr_name, e_mtr_vals in e_mtrs.items():
         print('   - {}'.format(e_mtr_name))
         print('      - {}'.format(e_mtr_vals))
- 
+
 print('')
 print('Access complete dict:')
 print(evals_result)

demo/guide-python/sklearn_examples.py

@@ -1,4 +1,3 @@
-#!/usr/bin/python
 '''
 Created on 1 Apr 2015
 
@@ -52,9 +51,9 @@
 X = boston['data']
 xgb_model = xgb.XGBRegressor()
 clf = GridSearchCV(xgb_model,
-                   {'max_depth': [2,4,6],
-                    'n_estimators': [50,100,200]}, verbose=1)
-clf.fit(X,y)
+                   {'max_depth': [2, 4, 6],
+                    'n_estimators': [50, 100, 200]}, verbose=1)
+clf.fit(X, y)
 print(clf.best_score_)
 print(clf.best_params_)
 
@@ -73,4 +72,3 @@
 clf = xgb.XGBClassifier()
 clf.fit(X_train, y_train, early_stopping_rounds=10, eval_metric="auc",
         eval_set=[(X_test, y_test)])
-