Merge pull request #1142 from sinhrks/flake8

Enable flake8 for Python

python-package/setup.py

@@ -4,7 +4,7 @@
 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 @@
 
 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 @@
       maintainer_email='[email protected]',
       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')

python-package/setup_pip.py

@@ -4,14 +4,14 @@
 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 @@
 
 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 @@
       maintainer_email='[email protected]',
       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')

python-package/xgboost/__init__.py

@@ -10,7 +10,7 @@
 
 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

python-package/xgboost/compat.py

@@ -12,11 +12,21 @@
 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 @@ class DataFrame(object):
 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
 

python-package/xgboost/core.py

@@ -14,6 +14,7 @@
 
 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 @@ def _validate_features(self, data):
             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))

python-package/xgboost/libpath.py

@@ -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, ' +

python-package/xgboost/plotting.py

@@ -10,6 +10,7 @@
 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 @@ def plot_importance(booster, ax=None, height=0.2,
 _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)

python-package/xgboost/rabit.py

@@ -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)

python-package/xgboost/sklearn.py

@@ -366,7 +366,6 @@ def fit(self, X, y, sample_weight=None, eval_set=None, eval_metric=None,
         self.classes_ = np.unique(y)
         self.n_classes_ = len(self.classes_)
 
-
         xgb_options = self.get_xgb_params()
 
         if callable(self.objective):