Use bst_float consistently throughout (#1824)

* Fix various typos

* Add override to functions that are overridden

gcc gives warnings about functions that are being overridden by not
being marked as oveirridden. This fixes it.

* Use bst_float consistently

Use bst_float for all the variables that involve weight,
leaf value, gradient, hessian, gain, loss_chg, predictions,
base_margin, feature values.

In some cases, when due to additions and so on the value can
take a larger value, double is used.

This ensures that type conversions are minimal and reduces loss of
precision.

python-package/xgboost/compat.py

@@ -64,7 +64,7 @@ try:
 except ImportError:
     SKLEARN_INSTALLED = False
 
-    # used for compatiblity without sklearn
+    # used for compatibility without sklearn
     XGBModelBase = object
     XGBClassifierBase = object
     XGBRegressorBase = object

python-package/xgboost/core.py

@@ -19,7 +19,7 @@ from .compat import STRING_TYPES, PY3, DataFrame, py_str, PANDAS_INSTALLED
 
 
 class XGBoostError(Exception):
-    """Error throwed by xgboost trainer."""
+    """Error thrown by xgboost trainer."""
     pass
 
 
@@ -387,7 +387,7 @@ class DMatrix(object):
             The field name of the information
 
         data: numpy array
-            The array ofdata to be set
+            The array of data to be set
         """
         _check_call(_LIB.XGDMatrixSetFloatInfo(self.handle,
                                                c_str(field),
@@ -403,7 +403,7 @@ class DMatrix(object):
             The field name of the information
 
         data: numpy array
-            The array ofdata to be set
+            The array of data to be set
         """
         _check_call(_LIB.XGDMatrixSetUIntInfo(self.handle,
                                               c_str(field),
@@ -980,11 +980,11 @@ class Booster(object):
 
     def save_raw(self):
         """
-        Save the model to a in memory buffer represetation
+        Save the model to a in memory buffer representation
 
         Returns
         -------
-        a in memory buffer represetation of the model
+        a in memory buffer representation of the model
         """
         length = ctypes.c_ulong()
         cptr = ctypes.POINTER(ctypes.c_char)()

python-package/xgboost/libpath.py

@@ -7,7 +7,7 @@ import sys
 
 
 class XGBoostLibraryNotFound(Exception):
-    """Error throwed by when xgboost is not found"""
+    """Error thrown by when xgboost is not found"""
     pass
 
 

python-package/xgboost/plotting.py

@@ -157,7 +157,7 @@ def to_graphviz(booster, num_trees=0, rankdir='UT',
                 yes_color='#0000FF', no_color='#FF0000', **kwargs):
 
     """Convert specified tree to graphviz instance. IPython can automatically plot the
-    returned graphiz instance. Otherwise, you shoud call .render() method
+    returned graphiz instance. Otherwise, you should call .render() method
     of the returned graphiz instance.
 
     Parameters
@@ -169,9 +169,9 @@ def to_graphviz(booster, num_trees=0, rankdir='UT',
     rankdir : str, default "UT"
         Passed to graphiz via graph_attr
     yes_color : str, default '#0000FF'
-        Edge color when meets the node condigion.
+        Edge color when meets the node condition.
     no_color : str, default '#FF0000'
-        Edge color when doesn't meet the node condigion.
+        Edge color when doesn't meet the node condition.
     kwargs :
         Other keywords passed to graphviz graph_attr
 

python-package/xgboost/rabit.py

@@ -12,7 +12,7 @@ from .compat import pickle
 
 
 def _init_rabit():
-    """internal libary initializer."""
+    """internal library initializer."""
     if _LIB is not None:
         _LIB.RabitGetRank.restype = ctypes.c_int
         _LIB.RabitGetWorldSize.restype = ctypes.c_int
@@ -21,7 +21,7 @@ def _init_rabit():
 
 
 def init(args=None):
-    """Initialize the rabit libary with arguments"""
+    """Initialize the rabit library with arguments"""
     if args is None:
         args = []
     arr = (ctypes.c_char_p * len(args))()
@@ -156,7 +156,7 @@ def allreduce(data, op, prepare_fun=None):
         Reduction operators, can be MIN, MAX, SUM, BITOR
     prepare_fun: function
         Lazy preprocessing function, if it is not None, prepare_fun(data)
-        will be called by the function before performing allreduce, to intialize the data
+        will be called by the function before performing allreduce, to initialize the data
         If the result of Allreduce can be recovered directly,
         then prepare_fun will NOT be called
 

python-package/xgboost/sklearn.py

@@ -142,7 +142,7 @@ class XGBModel(XGBModelBase):
         self._Booster = None
 
     def __setstate__(self, state):
-        # backward compatiblity code
+        # backward compatibility code
         # load booster from raw if it is raw
         # the booster now support pickle
         bst = state["_Booster"]

python-package/xgboost/training.py

@@ -148,7 +148,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
     evals_result: dict
         This dictionary stores the evaluation results of all the items in watchlist.
         Example: with a watchlist containing [(dtest,'eval'), (dtrain,'train')] and
-        a paramater containing ('eval_metric': 'logloss')
+        a parameter containing ('eval_metric': 'logloss')
         Returns: {'train': {'logloss': ['0.48253', '0.35953']},
                   'eval': {'logloss': ['0.480385', '0.357756']}}
     verbose_eval : bool or int
@@ -291,7 +291,7 @@ def cv(params, dtrain, num_boost_round=10, nfold=3, stratified=False, folds=None
        fpreproc=None, as_pandas=True, verbose_eval=None, show_stdv=True,
        seed=0, callbacks=None):
     # pylint: disable = invalid-name
-    """Cross-validation with given paramaters.
+    """Cross-validation with given parameters.
 
     Parameters
     ----------