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

Enable flake8

Browse Source
This commit is contained in:
sinhrks
2016-04-24 16:34:46 +09:00
parent b3c9e6a0db
commit 8fc2456c87
19 changed files with 282 additions and 199 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
python-package/setup.py
View File

@@ -4,7 +4,7 @@ from __future__ import absolute_import
import sys
import os
from setuptools import setup, find_packages
#import subprocess
# import subprocess
sys.path.insert(0, '.')
CURRENT_DIR = os.path.dirname(__file__)
@@ -18,12 +18,12 @@ exec(compile(open(libpath_py, "rb").read(), libpath_py, 'exec'), libpath, libpat
LIB_PATH = libpath['find_lib_path']()
print("Install libxgboost from: %s" % LIB_PATH)
#Please use setup_pip.py for generating and deploying pip installation
#detailed instruction in setup_pip.py
# Please use setup_pip.py for generating and deploying pip installation
# detailed instruction in setup_pip.py
setup(name='xgboost',
version=open(os.path.join(CURRENT_DIR, 'xgboost/VERSION')).read().strip(),
#version='0.4a23',
description = "XGBoost Python Package",
# version='0.4a23',
description="XGBoost Python Package",
long_description=open(os.path.join(CURRENT_DIR, 'README.rst')).read(),
install_requires=[
'numpy',
@@ -33,8 +33,8 @@ setup(name='xgboost',
maintainer_email='phunter.lau@gmail.com',
zip_safe=False,
packages=find_packages(),
#this will use MANIFEST.in during install where we specify additional files,
#this is the golden line
# this will use MANIFEST.in during install where we specify additional files,
# this is the golden line
include_package_data=True,
data_files=[('xgboost', LIB_PATH)],
url='https://github.com/dmlc/xgboost')

38
python-package/setup_pip.py
View File

@@ -4,14 +4,14 @@ from __future__ import absolute_import
import sys
import os
from setuptools import setup, find_packages
#import subprocess
# import subprocess
sys.path.insert(0, '.')
#this script is for packing and shipping pip installation
#it builds xgboost code on the fly and packs for pip
#please don't use this file for installing from github
# this script is for packing and shipping pip installation
# it builds xgboost code on the fly and packs for pip
# please don't use this file for installing from github
if os.name != 'nt': #if not windows, compile and install
if os.name != 'nt': # if not windows, compile and install
os.system('sh ./xgboost/build-python.sh')
else:
print('Windows users please use github installation.')
@@ -28,12 +28,12 @@ exec(compile(open(libpath_py, "rb").read(), libpath_py, 'exec'), libpath, libpat
LIB_PATH = libpath['find_lib_path']()
#to deploy to pip, please use
#make pythonpack
#python setup.py register sdist upload
#and be sure to test it firstly using "python setup.py register sdist upload -r pypitest"
# to deploy to pip, please use
# make pythonpack
# python setup.py register sdist upload
# and be sure to test it firstly using "python setup.py register sdist upload -r pypitest"
setup(name='xgboost',
#version=open(os.path.join(CURRENT_DIR, 'xgboost/VERSION')).read().strip(),
# version=open(os.path.join(CURRENT_DIR, 'xgboost/VERSION')).read().strip(),
version='0.4a30',
description=open(os.path.join(CURRENT_DIR, 'README.rst')).read(),
install_requires=[
@@ -44,15 +44,15 @@ setup(name='xgboost',
maintainer_email='phunter.lau@gmail.com',
zip_safe=False,
packages=find_packages(),
#don't need this and don't use this, give everything to MANIFEST.in
#package_dir = {'':'xgboost'},
#package_data = {'': ['*.txt','*.md','*.sh'],
# don't need this and don't use this, give everything to MANIFEST.in
# package_dir = {'':'xgboost'},
# package_data = {'': ['*.txt','*.md','*.sh'],
# }
#this will use MANIFEST.in during install where we specify additional files,
#this is the golden line
# this will use MANIFEST.in during install where we specify additional files,
# this is the golden line
include_package_data=True,
#!!! don't use data_files for creating pip installation,
#otherwise install_data process will copy it to
#root directory for some machines, and cause confusions on building
#data_files=[('xgboost', LIB_PATH)],
# !!! don't use data_files for creating pip installation,
# otherwise install_data process will copy it to
# root directory for some machines, and cause confusions on building
# data_files=[('xgboost', LIB_PATH)],
url='https://github.com/dmlc/xgboost')

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

@@ -10,7 +10,7 @@ import os
from .core import DMatrix, Booster
from .training import train, cv
from . import rabit
from . import rabit # noqa
try:
from .sklearn import XGBModel, XGBClassifier, XGBRegressor
from .plotting import plot_importance, plot_tree, to_graphviz

16
python-package/xgboost/compat.py
View File

@@ -12,11 +12,21 @@ PY3 = (sys.version_info[0] == 3)
if PY3:
# pylint: disable=invalid-name, redefined-builtin
STRING_TYPES = str,
py_str = lambda x: x.decode('utf-8')
def py_str(x):
return x.decode('utf-8')
else:
# pylint: disable=invalid-name
STRING_TYPES = basestring,
py_str = lambda x: x
def py_str(x):
return x
try:
import cPickle as pickle # noqa
except ImportError:
import pickle # noqa
# pandas
try:
@@ -34,7 +44,7 @@ except ImportError:
try:
from sklearn.base import BaseEstimator
from sklearn.base import RegressorMixin, ClassifierMixin
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import LabelEncoder # noqa
from sklearn.cross_validation import KFold, StratifiedKFold
SKLEARN_INSTALLED = True

22
python-package/xgboost/core.py
View File

@@ -14,6 +14,7 @@ from .libpath import find_lib_path
from .compat import STRING_TYPES, PY3, DataFrame, py_str
class XGBoostError(Exception):
"""Error throwed by xgboost trainer."""
pass
@@ -82,6 +83,7 @@ def _load_lib():
# load the XGBoost library globally
_LIB = _load_lib()
def _check_call(ret):
"""Check the return value of C API call
@@ -129,7 +131,6 @@ def c_array(ctype, values):
return (ctype * len(values))(*values)
PANDAS_DTYPE_MAPPER = {'int8': 'int', 'int16': 'int', 'int32': 'int', 'int64': 'int',
'uint8': 'int', 'uint16': 'int', 'uint32': 'int', 'uint64': 'int',
'float16': 'float', 'float32': 'float', 'float64': 'float',
@@ -144,8 +145,12 @@ def _maybe_pandas_data(data, feature_names, feature_types):
data_dtypes = data.dtypes
if not all(dtype.name in PANDAS_DTYPE_MAPPER for dtype in data_dtypes):
bad_fields = [data.columns[i] for i, dtype in enumerate(data_dtypes) if dtype.name not in PANDAS_DTYPE_MAPPER ]
raise ValueError('DataFrame.dtypes for data must be int, float or bool.\nDid not expect the data types in fie lds '+', '.join(bad_fields))
bad_fields = [data.columns[i] for i, dtype in
enumerate(data_dtypes) if dtype.name not in PANDAS_DTYPE_MAPPER]
msg = """DataFrame.dtypes for data must be int, float or bool.
Did not expect the data types in fields """
raise ValueError(msg + ', '.join(bad_fields))
if feature_names is None:
feature_names = data.columns.format()
@@ -174,6 +179,7 @@ def _maybe_pandas_label(label):
return label
class DMatrix(object):
"""Data Matrix used in XGBoost.
@@ -1041,8 +1047,14 @@ class Booster(object):
if self.feature_names != data.feature_names:
dat_missing = set(self.feature_names) - set(data.feature_names)
my_missing = set(data.feature_names) - set(self.feature_names)
msg = 'feature_names mismatch: {0} {1}'
if dat_missing: msg +='\nexpected ' + ', '.join(str(s) for s in dat_missing) +' in input data'
if my_missing: msg +='\ntraining data did not have the following fields: ' + ', '.join(str(s) for s in my_missing)
if dat_missing:
msg += '\nexpected ' + ', '.join(str(s) for s in dat_missing) + ' in input data'
if my_missing:
msg += '\ntraining data did not have the following fields: ' + ', '.join(str(s) for s in my_missing)
raise ValueError(msg.format(self.feature_names,
data.feature_names))

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

@@ -36,7 +36,8 @@ def find_lib_path():
else:
dll_path = [os.path.join(p, 'libxgboost.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
# 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, ' +

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

@@ -10,6 +10,7 @@ import numpy as np
from .core import Booster
from .sklearn import XGBModel
def plot_importance(booster, ax=None, height=0.2,
xlim=None, ylim=None, title='Feature importance',
xlabel='F score', ylabel='Features',
@@ -105,6 +106,7 @@ _LEAFPAT = re.compile(r'(\d+):(leaf=.+)')
_EDGEPAT = re.compile(r'yes=(\d+),no=(\d+),missing=(\d+)')
_EDGEPAT2 = re.compile(r'yes=(\d+),no=(\d+)')
def _parse_node(graph, text):
"""parse dumped node"""
match = _NODEPAT.match(text)

22
python-package/xgboost/rabit.py
View File

@@ -1,11 +1,12 @@
"""Distributed XGBoost Rabit related API."""
from __future__ import absolute_import
import sys
import atexit
import ctypes
import numpy as np
from .core import _LIB, c_str, STRING_TYPES
from .compat import pickle
def _init_rabit():
"""internal libary initializer."""
@@ -15,6 +16,7 @@ def _init_rabit():
_LIB.RabitIsDistributed.restype = ctypes.c_int
_LIB.RabitVersionNumber.restype = ctypes.c_int
def init(args=None):
"""Initialize the rabit libary with arguments"""
if args is None:
@@ -73,6 +75,7 @@ def tracker_print(msg):
sys.stdout.write(msg)
sys.stdout.flush()
def get_processor_name():
"""Get the processor name.
@@ -127,14 +130,14 @@ def broadcast(data, root):
# enumeration of dtypes
DTYPE_ENUM__ = {
np.dtype('int8') : 0,
np.dtype('uint8') : 1,
np.dtype('int32') : 2,
np.dtype('uint32') : 3,
np.dtype('int64') : 4,
np.dtype('uint64') : 5,
np.dtype('float32') : 6,
np.dtype('float64') : 7
np.dtype('int8'): 0,
np.dtype('uint8'): 1,
np.dtype('int32'): 2,
np.dtype('uint32'): 3,
np.dtype('int64'): 4,
np.dtype('uint64'): 5,
np.dtype('float32'): 6,
np.dtype('float64'): 7
}
@@ -175,6 +178,7 @@ def allreduce(data, op, prepare_fun=None):
op, None, None)
else:
func_ptr = ctypes.CFUNCTYPE(None, ctypes.c_void_p)
def pfunc(args):
"""prepare function."""
prepare_fun(data)

1
python-package/xgboost/sklearn.py
View File

@@ -366,7 +366,6 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
self.classes_ = np.unique(y)
self.n_classes_ = len(self.classes_)
xgb_options = self.get_xgb_params()
if callable(self.objective):

43
python-package/xgboost/training.py
View File

@@ -6,12 +6,12 @@ from __future__ import absolute_import
import sys
import re
import os
import numpy as np
from .core import Booster, STRING_TYPES
from .compat import (SKLEARN_INSTALLED, XGBStratifiedKFold, XGBKFold)
from .core import Booster, STRING_TYPES, XGBoostError
from .compat import (SKLEARN_INSTALLED, XGBStratifiedKFold)
from . import rabit
def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
maximize=False, early_stopping_rounds=None, evals_result=None,
verbose_eval=True, learning_rates=None, xgb_model=None):
@@ -97,7 +97,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
verbose_eval = True if verbose_eval_every_line > 0 else False
if rabit.get_rank() != 0:
verbose_eval = False;
verbose_eval = False
if xgb_model is not None:
if not isinstance(xgb_model, STRING_TYPES):
@@ -135,8 +135,9 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
if isinstance(params, list):
if len(params) != len(dict(params).items()):
params = dict(params)
rabit.tracker_print("Multiple eval metrics have been passed: " \
"'{0}' will be used for early stopping.\n\n".format(params['eval_metric']))
msg = ("Multiple eval metrics have been passed: "
"'{0}' will be used for early stopping.\n\n")
rabit.tracker_print(msg.format(params['eval_metric']))
else:
params = dict(params)
@@ -173,7 +174,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
# Distributed code: need to resume to this point.
# Skip the first update if it is a recovery step.
if version % 2 == 0:
if version % 2 == 0:
bst.update(dtrain, i, obj)
bst.save_rabit_checkpoint()
version += 1
@@ -203,7 +204,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
evals_idx = evals_name.index(key)
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_item = res[(evals_idx * res_per_eval) + r]
res_key = res_item[0]
res_val = res_item[1]
if res_key in evals_result[key]:
@@ -224,7 +225,8 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
elif i - best_iteration >= early_stopping_rounds:
best_msg = bst.attr('best_msg')
if verbose_eval:
rabit.tracker_print("Stopping. Best iteration:\n{}\n\n".format(best_msg))
msg = "Stopping. Best iteration:\n{}\n\n"
rabit.tracker_print(msg.format(best_msg))
break
# do checkpoint after evaluation, in case evaluation also updates booster.
bst.save_rabit_checkpoint()
@@ -290,6 +292,7 @@ def mknfold(dall, nfold, param, seed, evals=(), fpreproc=None, stratified=False,
ret.append(CVPack(dtrain, dtest, plst))
return ret
def aggcv(rlist, show_stdv=True, verbose_eval=None, as_pandas=True, trial=0):
# pylint: disable=invalid-name
"""
@@ -405,8 +408,8 @@ def cv(params, dtrain, num_boost_round=10, nfold=3, stratified=False, folds=None
-------
evaluation history : list(string)
"""
if stratified == True and not SKLEARN_INSTALLED:
raise XGBoostError('sklearn needs to be installed in order to use stratified cv')
if stratified is True and not SKLEARN_INSTALLED:
raise XGBoostError('sklearn needs to be installed in order to use stratified cv')
if isinstance(metrics, str):
metrics = [metrics]
@@ -417,7 +420,7 @@ def cv(params, dtrain, num_boost_round=10, nfold=3, stratified=False, folds=None
if 'eval_metric' in params:
params['eval_metric'] = _metrics
else:
params= dict((k, v) for k, v in params.items())
params = dict((k, v) for k, v in params.items())
if len(metrics) == 0 and 'eval_metric' in params:
if isinstance(params['eval_metric'], list):
@@ -428,12 +431,14 @@ def cv(params, dtrain, num_boost_round=10, nfold=3, stratified=False, folds=None
params.pop("eval_metric", None)
if early_stopping_rounds is not None:
if len(metrics) > 1:
raise ValueError('Check your params. '\
'Early stopping works with single eval metric only.')
msg = ('Check your params. '
'Early stopping works with single eval metric only.')
raise ValueError(msg)
if verbose_eval:
sys.stderr.write("Will train until cv error hasn't decreased in {} rounds.\n".format(\
early_stopping_rounds))
msg = "Will train until cv error hasn't decreased in {} rounds.\n"
sys.stderr.write(msg.format(early_stopping_rounds))
maximize_score = False
if len(metrics) == 1:
@@ -466,10 +471,10 @@ def cv(params, dtrain, num_boost_round=10, nfold=3, stratified=False, folds=None
best_score = score
best_score_i = i
elif i - best_score_i >= early_stopping_rounds:
results = results[:best_score_i+1]
results = results[:best_score_i + 1]
if verbose_eval:
sys.stderr.write("Stopping. Best iteration:\n[{}] cv-mean:{}\tcv-std:{}\n".
format(best_score_i, results[-1][0], results[-1][1]))
msg = "Stopping. Best iteration:\n[{}] cv-mean:{}\tcv-std:{}\n"
sys.stderr.write(msg.format(best_score_i, results[-1][0], results[-1][1]))
break
if as_pandas:
try: