move python example
This commit is contained in:
tqchen
@@ -0,0 +1,2 @@
|
||||
This folder contains processed example dataset used by the demos.
|
||||
Copyright of the dataset belongs to the original copyright holder
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,126 @@
|
||||
0 cap-shape=bell i
|
||||
1 cap-shape=conical i
|
||||
2 cap-shape=convex i
|
||||
3 cap-shape=flat i
|
||||
4 cap-shape=knobbed i
|
||||
5 cap-shape=sunken i
|
||||
6 cap-surface=fibrous i
|
||||
7 cap-surface=grooves i
|
||||
8 cap-surface=scaly i
|
||||
9 cap-surface=smooth i
|
||||
10 cap-color=brown i
|
||||
11 cap-color=buff i
|
||||
12 cap-color=cinnamon i
|
||||
13 cap-color=gray i
|
||||
14 cap-color=green i
|
||||
15 cap-color=pink i
|
||||
16 cap-color=purple i
|
||||
17 cap-color=red i
|
||||
18 cap-color=white i
|
||||
19 cap-color=yellow i
|
||||
20 bruises?=bruises i
|
||||
21 bruises?=no i
|
||||
22 odor=almond i
|
||||
23 odor=anise i
|
||||
24 odor=creosote i
|
||||
25 odor=fishy i
|
||||
26 odor=foul i
|
||||
27 odor=musty i
|
||||
28 odor=none i
|
||||
29 odor=pungent i
|
||||
30 odor=spicy i
|
||||
31 gill-attachment=attached i
|
||||
32 gill-attachment=descending i
|
||||
33 gill-attachment=free i
|
||||
34 gill-attachment=notched i
|
||||
35 gill-spacing=close i
|
||||
36 gill-spacing=crowded i
|
||||
37 gill-spacing=distant i
|
||||
38 gill-size=broad i
|
||||
39 gill-size=narrow i
|
||||
40 gill-color=black i
|
||||
41 gill-color=brown i
|
||||
42 gill-color=buff i
|
||||
43 gill-color=chocolate i
|
||||
44 gill-color=gray i
|
||||
45 gill-color=green i
|
||||
46 gill-color=orange i
|
||||
47 gill-color=pink i
|
||||
48 gill-color=purple i
|
||||
49 gill-color=red i
|
||||
50 gill-color=white i
|
||||
51 gill-color=yellow i
|
||||
52 stalk-shape=enlarging i
|
||||
53 stalk-shape=tapering i
|
||||
54 stalk-root=bulbous i
|
||||
55 stalk-root=club i
|
||||
56 stalk-root=cup i
|
||||
57 stalk-root=equal i
|
||||
58 stalk-root=rhizomorphs i
|
||||
59 stalk-root=rooted i
|
||||
60 stalk-root=missing i
|
||||
61 stalk-surface-above-ring=fibrous i
|
||||
62 stalk-surface-above-ring=scaly i
|
||||
63 stalk-surface-above-ring=silky i
|
||||
64 stalk-surface-above-ring=smooth i
|
||||
65 stalk-surface-below-ring=fibrous i
|
||||
66 stalk-surface-below-ring=scaly i
|
||||
67 stalk-surface-below-ring=silky i
|
||||
68 stalk-surface-below-ring=smooth i
|
||||
69 stalk-color-above-ring=brown i
|
||||
70 stalk-color-above-ring=buff i
|
||||
71 stalk-color-above-ring=cinnamon i
|
||||
72 stalk-color-above-ring=gray i
|
||||
73 stalk-color-above-ring=orange i
|
||||
74 stalk-color-above-ring=pink i
|
||||
75 stalk-color-above-ring=red i
|
||||
76 stalk-color-above-ring=white i
|
||||
77 stalk-color-above-ring=yellow i
|
||||
78 stalk-color-below-ring=brown i
|
||||
79 stalk-color-below-ring=buff i
|
||||
80 stalk-color-below-ring=cinnamon i
|
||||
81 stalk-color-below-ring=gray i
|
||||
82 stalk-color-below-ring=orange i
|
||||
83 stalk-color-below-ring=pink i
|
||||
84 stalk-color-below-ring=red i
|
||||
85 stalk-color-below-ring=white i
|
||||
86 stalk-color-below-ring=yellow i
|
||||
87 veil-type=partial i
|
||||
88 veil-type=universal i
|
||||
89 veil-color=brown i
|
||||
90 veil-color=orange i
|
||||
91 veil-color=white i
|
||||
92 veil-color=yellow i
|
||||
93 ring-number=none i
|
||||
94 ring-number=one i
|
||||
95 ring-number=two i
|
||||
96 ring-type=cobwebby i
|
||||
97 ring-type=evanescent i
|
||||
98 ring-type=flaring i
|
||||
99 ring-type=large i
|
||||
100 ring-type=none i
|
||||
101 ring-type=pendant i
|
||||
102 ring-type=sheathing i
|
||||
103 ring-type=zone i
|
||||
104 spore-print-color=black i
|
||||
105 spore-print-color=brown i
|
||||
106 spore-print-color=buff i
|
||||
107 spore-print-color=chocolate i
|
||||
108 spore-print-color=green i
|
||||
109 spore-print-color=orange i
|
||||
110 spore-print-color=purple i
|
||||
111 spore-print-color=white i
|
||||
112 spore-print-color=yellow i
|
||||
113 population=abundant i
|
||||
114 population=clustered i
|
||||
115 population=numerous i
|
||||
116 population=scattered i
|
||||
117 population=several i
|
||||
118 population=solitary i
|
||||
119 habitat=grasses i
|
||||
120 habitat=leaves i
|
||||
121 habitat=meadows i
|
||||
122 habitat=paths i
|
||||
123 habitat=urban i
|
||||
124 habitat=waste i
|
||||
125 habitat=woods i
|
||||
@@ -0,0 +1,6 @@
|
||||
XGBoost Python Feature Walkthrough
|
||||
====
|
||||
* [Basic walkthrough of wrappers](guide-python/basic.py)
|
||||
* [Cutomize loss function, and evaluation metric](guide-python/custom_objective.py)
|
||||
* [Boosting from existing prediction](guide-python/boost_from_prediction.py)
|
||||
* [Predicting using first n trees](guide-python/predict_first_ntree.py)
|
||||
Executable
+70
@@ -0,0 +1,70 @@
|
||||
#!/usr/bin/python
|
||||
import sys
|
||||
import numpy as np
|
||||
import scipy.sparse
|
||||
# append the path to xgboost, you may need to change the following line
|
||||
# alternatively, you can add the path to PYTHONPATH environment variable
|
||||
sys.path.append('../../wrapper')
|
||||
import xgboost as xgb
|
||||
|
||||
### simple example
|
||||
# load file from text file, also binary buffer generated by xgboost
|
||||
dtrain = xgb.DMatrix('../data/agaricus.txt.train')
|
||||
dtest = xgb.DMatrix('../data/agaricus.txt.test')
|
||||
|
||||
# specify parameters via map, definition are same as c++ version
|
||||
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
|
||||
|
||||
# specify validations set to watch performance
|
||||
watchlist = [(dtest,'eval'), (dtrain,'train')]
|
||||
num_round = 2
|
||||
bst = xgb.train(param, dtrain, num_round, watchlist)
|
||||
|
||||
# this is prediction
|
||||
preds = bst.predict(dtest)
|
||||
labels = dtest.get_label()
|
||||
print ('error=%f' % ( sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) /float(len(preds))))
|
||||
bst.save_model('0001.model')
|
||||
# dump model
|
||||
bst.dump_model('dump.raw.txt')
|
||||
# dump model with feature map
|
||||
bst.dump_model('dump.nice.txt','../data/featmap.txt')
|
||||
|
||||
# save dmatrix into binary buffer
|
||||
dtest.save_binary('dtest.buffer')
|
||||
bst.save_model('xgb.model')
|
||||
# load model and data in
|
||||
bst2 = xgb.Booster(model_file='xgb.model')
|
||||
dtest2 = xgb.DMatrix('dtest.buffer')
|
||||
preds2 = bst2.predict(dtest2)
|
||||
# assert they are the same
|
||||
assert np.sum(np.abs(preds2-preds)) == 0
|
||||
|
||||
###
|
||||
# build dmatrix from scipy.sparse
|
||||
print ('start running example of build DMatrix from scipy.sparse')
|
||||
labels = []
|
||||
row = []; col = []; dat = []
|
||||
i = 0
|
||||
for l in open('../data/agaricus.txt.train'):
|
||||
arr = l.split()
|
||||
labels.append( int(arr[0]))
|
||||
for it in arr[1:]:
|
||||
k,v = it.split(':')
|
||||
row.append(i); col.append(int(k)); dat.append(float(v))
|
||||
i += 1
|
||||
csr = scipy.sparse.csr_matrix( (dat, (row,col)) )
|
||||
dtrain = xgb.DMatrix( csr )
|
||||
dtrain.set_label(labels)
|
||||
watchlist = [(dtest,'eval'), (dtrain,'train')]
|
||||
bst = xgb.train( param, dtrain, num_round, watchlist )
|
||||
|
||||
print ('start running example of build DMatrix from numpy array')
|
||||
# NOTE: npymat is numpy array, we will convert it into scipy.sparse.csr_matrix in internal implementation,then convert to DMatrix
|
||||
npymat = csr.todense()
|
||||
dtrain = xgb.DMatrix( npymat)
|
||||
dtrain.set_label(labels)
|
||||
watchlist = [(dtest,'eval'), (dtrain,'train')]
|
||||
bst = xgb.train( param, dtrain, num_round, watchlist )
|
||||
|
||||
|
||||
Executable
+26
@@ -0,0 +1,26 @@
|
||||
#!/usr/bin/python
|
||||
import sys
|
||||
import numpy as np
|
||||
sys.path.append('../../wrapper')
|
||||
import xgboost as xgb
|
||||
|
||||
dtrain = xgb.DMatrix('../data/agaricus.txt.train')
|
||||
dtest = xgb.DMatrix('../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' }
|
||||
# train xgboost for 1 round
|
||||
bst = xgb.train( param, dtrain, 1, watchlist )
|
||||
# Note: we need the margin value instead of transformed prediction in set_base_margin
|
||||
# do predict with output_margin=True, will always give you margin values before logistic transformation
|
||||
ptrain = bst.predict(dtrain, output_margin=True)
|
||||
ptest = bst.predict(dtest, output_margin=True)
|
||||
dtrain.set_base_margin(ptrain)
|
||||
dtest.set_base_margin(ptest)
|
||||
|
||||
print ('this is result of running from initial prediction')
|
||||
bst = xgb.train( param, dtrain, 1, watchlist )
|
||||
Executable
+44
@@ -0,0 +1,44 @@
|
||||
#!/usr/bin/python
|
||||
import sys
|
||||
import numpy as np
|
||||
sys.path.append('../../wrapper')
|
||||
import xgboost as xgb
|
||||
###
|
||||
# advanced: cutomsized loss function
|
||||
#
|
||||
print ('start running example to used cutomized objective function')
|
||||
|
||||
dtrain = xgb.DMatrix('../data/agaricus.txt.train')
|
||||
dtest = xgb.DMatrix('../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 }
|
||||
watchlist = [(dtest,'eval'), (dtrain,'train')]
|
||||
num_round = 2
|
||||
|
||||
# user define objective function, given prediction, return gradient and second order gradient
|
||||
# this is loglikelihood loss
|
||||
def logregobj(preds, dtrain):
|
||||
labels = dtrain.get_label()
|
||||
preds = 1.0 / (1.0 + np.exp(-preds))
|
||||
grad = preds - labels
|
||||
hess = preds * (1.0-preds)
|
||||
return grad, hess
|
||||
|
||||
# user defined evaluation function, return a pair metric_name, result
|
||||
# NOTE: when you do customized loss function, the default prediction value is margin
|
||||
# this may make buildin evalution metric not function properly
|
||||
# for example, we are doing logistic loss, the prediction is score before logistic transformation
|
||||
# the buildin evaluation error assumes input is after logistic transformation
|
||||
# Take this in mind when you use the customization, and maybe you need write customized evaluation function
|
||||
def evalerror(preds, dtrain):
|
||||
labels = dtrain.get_label()
|
||||
# return a pair metric_name, result
|
||||
# since preds are margin(before logistic transformation, cutoff at 0)
|
||||
return 'error', float(sum(labels != (preds > 0.0))) / len(labels)
|
||||
|
||||
# training with customized objective, we can also do step by step training
|
||||
# simply look at xgboost.py's implementation of train
|
||||
bst = xgb.train(param, dtrain, num_round, watchlist, logregobj, evalerror)
|
||||
Executable
+22
@@ -0,0 +1,22 @@
|
||||
#!/usr/bin/python
|
||||
import sys
|
||||
import numpy as np
|
||||
sys.path.append('../../wrapper')
|
||||
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' }
|
||||
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
|
||||
label = dtest.get_label()
|
||||
ypred1 = bst.predict(dtest, ntree_limit=1)
|
||||
# by default, we predict using all the trees
|
||||
ypred2 = bst.predict(dtest)
|
||||
print ('error of ypred1=%f' % (np.sum((ypred1>0.5)!=label) /float(len(label))))
|
||||
print ('error of ypred2=%f' % (np.sum((ypred2>0.5)!=label) /float(len(label))))
|
||||
Executable
+6
@@ -0,0 +1,6 @@
|
||||
#!/bin/bash
|
||||
python basic_walkthrough.py
|
||||
python custom_objective.py
|
||||
python boost_from_prediction.py
|
||||
python boost_from_prediction.py
|
||||
rm *~ *.model *.buffer
|
||||
Reference in New Issue
Block a user