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

Merge pull request #5 from dmlc/master

Browse Source 
Update to latest version
This commit is contained in:
Johan Manders
2015-11-03 20:37:20 +01:00
parent 7c79c9ac3a e436c94419
commit 96f221e0d0
95 changed files with 2074 additions and 962 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python-package/xgboost/build-python.sh
View File

@@ -11,6 +11,8 @@
pushd xgboost
#remove the pre-compiled .so and trigger the system's on-the-fly compiling
make clean
if make python; then
echo "Successfully build multi-thread xgboost"
else

2
python-package/xgboost/core.py
View File

@@ -249,7 +249,7 @@ class DMatrix(object):
csr = scipy.sparse.csr_matrix(data)
self._init_from_csr(csr)
except:
raise TypeError('can not intialize DMatrix from {}'.format(type(data).__name__))
raise TypeError('can not initialize DMatrix from {}'.format(type(data).__name__))
if label is not None:
self.set_label(label)
if weight is not None:

3
python-package/xgboost/libpath.py
View File

@@ -36,9 +36,10 @@ def find_lib_path():
else:
dll_path = [os.path.join(p, 'libxgboostwrapper.so') for p in dll_path]
lib_path = [p for p in dll_path if os.path.exists(p) and os.path.isfile(p)]
#From github issues, most of installation errors come from machines w/o compilers
if len(lib_path) == 0 and not os.environ.get('XGBOOST_BUILD_DOC', False):
raise XGBoostLibraryNotFound(
'Cannot find XGBoost Libarary in the candicate path, ' +
'did you run build.sh in root path?\n'
'did you install compilers and run build.sh in root path?\n'
'List of candidates:\n' + ('\n'.join(dll_path)))
return lib_path

40
python-package/xgboost/plotting.py
View File

@@ -7,11 +7,12 @@ from __future__ import absolute_import
import re
import numpy as np
from .core import Booster
from .sklearn import XGBModel
from io import BytesIO
def plot_importance(booster, ax=None, height=0.2,
xlim=None, title='Feature importance',
xlim=None, ylim=None, title='Feature importance',
xlabel='F score', ylabel='Features',
grid=True, **kwargs):
@@ -19,14 +20,16 @@ def plot_importance(booster, ax=None, height=0.2,
Parameters
----------
booster : Booster or dict
Booster instance, or dict taken by Booster.get_fscore()
booster : Booster, XGBModel or dict
Booster or XGBModel instance, or dict taken by Booster.get_fscore()
ax : matplotlib Axes, default None
Target axes instance. If None, new figure and axes will be created.
height : float, default 0.2
Bar height, passed to ax.barh()
xlim : tuple, default None
Tuple passed to axes.xlim()
ylim : tuple, default None
Tuple passed to axes.ylim()
title : str, default "Feature importance"
Axes title. To disable, pass None.
xlabel : str, default "F score"
@@ -46,12 +49,14 @@ def plot_importance(booster, ax=None, height=0.2,
except ImportError:
raise ImportError('You must install matplotlib to plot importance')
if isinstance(booster, Booster):
if isinstance(booster, XGBModel):
importance = booster.booster().get_fscore()
elif isinstance(booster, Booster):
importance = booster.get_fscore()
elif isinstance(booster, dict):
importance = booster
else:
raise ValueError('tree must be Booster or dict instance')
raise ValueError('tree must be Booster, XGBModel or dict instance')
if len(importance) == 0:
raise ValueError('Booster.get_fscore() results in empty')
@@ -73,12 +78,19 @@ def plot_importance(booster, ax=None, height=0.2,
ax.set_yticklabels(labels)
if xlim is not None:
if not isinstance(xlim, tuple) or len(xlim, 2):
if not isinstance(xlim, tuple) or len(xlim) != 2:
raise ValueError('xlim must be a tuple of 2 elements')
else:
xlim = (0, max(values) * 1.1)
ax.set_xlim(xlim)
if ylim is not None:
if not isinstance(ylim, tuple) or len(ylim) != 2:
raise ValueError('ylim must be a tuple of 2 elements')
else:
ylim = (-1, len(importance))
ax.set_ylim(ylim)
if title is not None:
ax.set_title(title)
if xlabel is not None:
@@ -142,8 +154,8 @@ def to_graphviz(booster, num_trees=0, rankdir='UT',
Parameters
----------
booster : Booster
Booster instance
booster : Booster, XGBModel
Booster or XGBModel instance
num_trees : int, default 0
Specify the ordinal number of target tree
rankdir : str, default "UT"
@@ -165,8 +177,11 @@ def to_graphviz(booster, num_trees=0, rankdir='UT',
except ImportError:
raise ImportError('You must install graphviz to plot tree')
if not isinstance(booster, Booster):
raise ValueError('booster must be Booster instance')
if not isinstance(booster, (Booster, XGBModel)):
raise ValueError('booster must be Booster or XGBModel instance')
if isinstance(booster, XGBModel):
booster = booster.booster()
tree = booster.get_dump()[num_trees]
tree = tree.split()
@@ -193,8 +208,8 @@ def plot_tree(booster, num_trees=0, rankdir='UT', ax=None, **kwargs):
Parameters
----------
booster : Booster
Booster instance
booster : Booster, XGBModel
Booster or XGBModel instance
num_trees : int, default 0
Specify the ordinal number of target tree
rankdir : str, default "UT"
@@ -216,7 +231,6 @@ def plot_tree(booster, num_trees=0, rankdir='UT', ax=None, **kwargs):
except ImportError:
raise ImportError('You must install matplotlib to plot tree')
if ax is None:
_, ax = plt.subplots(1, 1)

45
python-package/xgboost/sklearn.py
View File

@@ -54,6 +54,14 @@ class XGBModel(XGBModelBase):
Subsample ratio of the training instance.
colsample_bytree : float
Subsample ratio of columns when constructing each tree.
colsample_bylevel : float
Subsample ratio of columns for each split, in each level.
reg_alpha : float (xgb's alpha)
L2 regularization term on weights
reg_lambda : float (xgb's lambda)
L1 regularization term on weights
scale_pos_weight : float
Balancing of positive and negative weights.
base_score:
The initial prediction score of all instances, global bias.
@@ -66,7 +74,8 @@ class XGBModel(XGBModelBase):
def __init__(self, max_depth=3, learning_rate=0.1, n_estimators=100,
silent=True, objective="reg:linear",
nthread=-1, gamma=0, min_child_weight=1, max_delta_step=0,
subsample=1, colsample_bytree=1,
subsample=1, colsample_bytree=1, colsample_bylevel=1,
reg_alpha=0, reg_lambda=1, scale_pos_weight=1,
base_score=0.5, seed=0, missing=None):
if not SKLEARN_INSTALLED:
raise XGBoostError('sklearn needs to be installed in order to use this module')
@@ -82,6 +91,10 @@ class XGBModel(XGBModelBase):
self.max_delta_step = max_delta_step
self.subsample = subsample
self.colsample_bytree = colsample_bytree
self.colsample_bylevel = colsample_bylevel
self.reg_alpha = reg_alpha
self.reg_lambda = reg_lambda
self.scale_pos_weight = scale_pos_weight
self.base_score = base_score
self.seed = seed
@@ -190,7 +203,7 @@ class XGBModel(XGBModelBase):
if evals_result:
for val in evals_result.items():
evals_result_key = val[1].keys()[0]
evals_result_key = list(val[1].keys())[0]
evals_result[val[0]][evals_result_key] = val[1][evals_result_key]
self.evals_result_ = evals_result
@@ -199,10 +212,12 @@ class XGBModel(XGBModelBase):
self.best_iteration = self._Booster.best_iteration
return self
def predict(self, data):
def predict(self, data, output_margin=False, ntree_limit=0):
# pylint: disable=missing-docstring,invalid-name
test_dmatrix = DMatrix(data, missing=self.missing)
return self.booster().predict(test_dmatrix)
return self.booster().predict(test_dmatrix,
output_margin=output_margin,
ntree_limit=ntree_limit)
def evals_result(self):
"""Return the evaluation results.
@@ -251,14 +266,16 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
n_estimators=100, silent=True,
objective="binary:logistic",
nthread=-1, gamma=0, min_child_weight=1,
max_delta_step=0, subsample=1, colsample_bytree=1,
max_delta_step=0, subsample=1, colsample_bytree=1, colsample_bylevel=1,
reg_alpha=0, reg_lambda=1, scale_pos_weight=1,
base_score=0.5, seed=0, missing=None):
super(XGBClassifier, self).__init__(max_depth, learning_rate,
n_estimators, silent, objective,
nthread, gamma, min_child_weight,
max_delta_step, subsample,
colsample_bytree,
base_score, seed, missing)
colsample_bytree, colsample_bylevel,
reg_alpha, reg_lambda,
scale_pos_weight, base_score, seed, missing)
def fit(self, X, y, sample_weight=None, eval_set=None, eval_metric=None,
early_stopping_rounds=None, verbose=True):
@@ -341,7 +358,7 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
if evals_result:
for val in evals_result.items():
evals_result_key = val[1].keys()[0]
evals_result_key = list(val[1].keys())[0]
evals_result[val[0]][evals_result_key] = val[1][evals_result_key]
self.evals_result_ = evals_result
@@ -351,9 +368,11 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
return self
def predict(self, data):
def predict(self, data, output_margin=False, ntree_limit=0):
test_dmatrix = DMatrix(data, missing=self.missing)
class_probs = self.booster().predict(test_dmatrix)
class_probs = self.booster().predict(test_dmatrix,
output_margin=output_margin,
ntree_limit=ntree_limit)
if len(class_probs.shape) > 1:
column_indexes = np.argmax(class_probs, axis=1)
else:
@@ -361,9 +380,11 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
column_indexes[class_probs > 0.5] = 1
return self._le.inverse_transform(column_indexes)
def predict_proba(self, data):
def predict_proba(self, data, output_margin=False, ntree_limit=0):
test_dmatrix = DMatrix(data, missing=self.missing)
class_probs = self.booster().predict(test_dmatrix)
class_probs = self.booster().predict(test_dmatrix,
output_margin=output_margin,
ntree_limit=ntree_limit)
if self.objective == "multi:softprob":
return class_probs
else:

45
python-package/xgboost/training.py
View File

@@ -10,7 +10,8 @@ import numpy as np
from .core import Booster, STRING_TYPES
def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
early_stopping_rounds=None, evals_result=None, verbose_eval=True):
maximize=False, early_stopping_rounds=None, evals_result=None,
verbose_eval=True, learning_rates=None, xgb_model=None):
# pylint: disable=too-many-statements,too-many-branches, attribute-defined-outside-init
"""Train a booster with given parameters.
@@ -29,6 +30,8 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
Customized objective function.
feval : function
Customized evaluation function.
maximize : bool
Whether to maximize feval.
early_stopping_rounds: int
Activates early stopping. Validation error needs to decrease at least
every <early_stopping_rounds> round(s) to continue training.
@@ -46,13 +49,27 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
verbose_eval : bool
If `verbose_eval` then the evaluation metric on the validation set, if
given, is printed at each boosting stage.
learning_rates: list or function
Learning rate for each boosting round (yields learning rate decay).
- list l: eta = l[boosting round]
- function f: eta = f(boosting round, num_boost_round)
xgb_model : file name of stored xgb model or 'Booster' instance
Xgb model to be loaded before training (allows training continuation).
Returns
-------
booster : a trained booster model
"""
evals = list(evals)
bst = Booster(params, [dtrain] + [d[0] for d in evals])
ntrees = 0
if xgb_model is not None:
if not isinstance(xgb_model, STRING_TYPES):
xgb_model = xgb_model.save_raw()
bst = Booster(params, [dtrain] + [d[0] for d in evals], model_file=xgb_model)
ntrees = len(bst.get_dump())
else:
bst = Booster(params, [dtrain] + [d[0] for d in evals])
if evals_result is not None:
if not isinstance(evals_result, dict):
@@ -65,6 +82,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
if not early_stopping_rounds:
for i in range(num_boost_round):
bst.update(dtrain, i, obj)
ntrees += 1
if len(evals) != 0:
bst_eval_set = bst.eval_set(evals, i, feval)
if isinstance(bst_eval_set, STRING_TYPES):
@@ -78,7 +96,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
res = re.findall("([0-9a-zA-Z@]+[-]*):-?([0-9.]+).", msg)
for key in evals_name:
evals_idx = evals_name.index(key)
res_per_eval = len(res) / len(evals_name)
res_per_eval = len(res) // len(evals_name)
for r in range(res_per_eval):
res_item = res[(evals_idx*res_per_eval) + r]
res_key = res_item[0]
@@ -87,6 +105,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
evals_result[key][res_key].append(res_val)
else:
evals_result[key][res_key] = [res_val]
bst.best_iteration = (ntrees - 1)
return bst
else:
@@ -94,7 +113,8 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
if len(evals) < 1:
raise ValueError('For early stopping you need at least one set in evals.')
sys.stderr.write("Will train until {} error hasn't decreased in {} rounds.\n".format(\
if verbose_eval:
sys.stderr.write("Will train until {} error hasn't decreased in {} rounds.\n".format(\
evals[-1][1], early_stopping_rounds))
# is params a list of tuples? are we using multiple eval metrics?
@@ -110,6 +130,8 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
maximize_metrics = ('auc', 'map', 'ndcg')
if any(params['eval_metric'].startswith(x) for x in maximize_metrics):
maximize_score = True
if feval is not None:
maximize_score = maximize
if maximize_score:
best_score = 0.0
@@ -117,10 +139,19 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
best_score = float('inf')
best_msg = ''
best_score_i = 0
best_score_i = ntrees
if isinstance(learning_rates, list) and len(learning_rates) != num_boost_round:
raise ValueError("Length of list 'learning_rates' has to equal 'num_boost_round'.")
for i in range(num_boost_round):
if learning_rates is not None:
if isinstance(learning_rates, list):
bst.set_param({'eta': learning_rates[i]})
else:
bst.set_param({'eta': learning_rates(i, num_boost_round)})
bst.update(dtrain, i, obj)
ntrees += 1
bst_eval_set = bst.eval_set(evals, i, feval)
if isinstance(bst_eval_set, STRING_TYPES):
@@ -135,7 +166,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
res = re.findall("([0-9a-zA-Z@]+[-]*):-?([0-9.]+).", msg)
for key in evals_name:
evals_idx = evals_name.index(key)
res_per_eval = len(res) / len(evals_name)
res_per_eval = len(res) // len(evals_name)
for r in range(res_per_eval):
res_item = res[(evals_idx*res_per_eval) + r]
res_key = res_item[0]
@@ -149,7 +180,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
if (maximize_score and score > best_score) or \
(not maximize_score and score < best_score):
best_score = score
best_score_i = i
best_score_i = (ntrees - 1)
best_msg = msg
elif i - best_score_i >= early_stopping_rounds:
sys.stderr.write("Stopping. Best iteration:\n{}\n\n".format(best_msg))