Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add create from csc

Browse Source
This commit is contained in:
tqchen
2014-09-04 20:57:49 -07:00
parent 2bc1d2e73a
commit a1c6e22af9
5 changed files with 77 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
demo/guide-python/basic_walkthrough.py
View File

@@ -42,7 +42,7 @@ assert np.sum(np.abs(preds2-preds)) == 0
###
# build dmatrix from scipy.sparse
print ('start running example of build DMatrix from scipy.sparse')
print ('start running example of build DMatrix from scipy.sparse CSR Matrix')
labels = []
row = []; col = []; dat = []
i = 0
@@ -54,8 +54,14 @@ for l in open('../data/agaricus.txt.train'):
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)
dtrain = xgb.DMatrix( csr, label = labels )
watchlist = [(dtest,'eval'), (dtrain,'train')]
bst = xgb.train( param, dtrain, num_round, watchlist )
print ('start running example of build DMatrix from scipy.sparse CSC Matrix')
# we can also construct from csc matrix
csc = scipy.sparse.csc_matrix( (dat, (row,col)) )
dtrain = xgb.DMatrix(csc, label=labels)
watchlist = [(dtest,'eval'), (dtrain,'train')]
bst = xgb.train( param, dtrain, num_round, watchlist )
@@ -63,8 +69,7 @@ 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)
dtrain = xgb.DMatrix(npymat, label = labels)
watchlist = [(dtest,'eval'), (dtrain,'train')]
bst = xgb.train( param, dtrain, num_round, watchlist )