Assorted _libs cleanups

pandas/_libs/algos_common_helper.pxi.in

@@ -523,7 +523,7 @@ def put2d_{{name}}_{{dest_type}}(ndarray[{{c_type}}, ndim=2, cast=True] values,
         Py_ssize_t i, j, k
 
     k = len(values)
-    for j from 0 <= j < k:
+    for j in range(k):
         i = indexer[j]
         out[i] = values[j, loc]
 

pandas/_libs/algos_take_helper.pxi.in

@@ -46,7 +46,7 @@ def get_dispatch(dtypes):
     fv = fill_value
 
     %(nogil_str)s
-    %(tab)sfor i from 0 <= i < n:
+    %(tab)sfor i in range(n):
     %(tab)s    idx = indexer[i]
     %(tab)s    if idx == -1:
     %(tab)s        out[i] = fv
@@ -74,24 +74,24 @@ def get_dispatch(dtypes):
             values.strides[1] == sizeof(%(c_type_out)s) and
             sizeof(%(c_type_out)s) * n >= 256):
 
-            for i from 0 <= i < n:
+            for i in range(n):
                 idx = indexer[i]
                 if idx == -1:
-                    for j from 0 <= j < k:
+                    for j in range(k):
                         out[i, j] = fv
                 else:
                     v = &values[idx, 0]
                     o = &out[i, 0]
                     memmove(o, v, <size_t>(sizeof(%(c_type_out)s) * k))
             return
 
-    for i from 0 <= i < n:
+    for i in range(n):
         idx = indexer[i]
         if idx == -1:
-            for j from 0 <= j < k:
+            for j in range(k):
                 out[i, j] = fv
         else:
-            for j from 0 <= j < k:
+            for j in range(k):
                 out[i, j] = %(preval)svalues[idx, j]%(postval)s
 """
 
@@ -108,8 +108,8 @@ def get_dispatch(dtypes):
 
     fv = fill_value
 
-    for i from 0 <= i < n:
-        for j from 0 <= j < k:
+    for i in range(n):
+        for j in range(k):
             idx = indexer[j]
             if idx == -1:
                 out[i, j] = fv
@@ -246,13 +246,13 @@ def take_2d_multi_{{name}}_{{dest}}(ndarray[{{c_type_in}}, ndim=2] values,
     k = len(idx1)
 
     fv = fill_value
-    for i from 0 <= i < n:
+    for i in range(n):
         idx = idx0[i]
         if idx == -1:
-            for j from 0 <= j < k:
+            for j in range(k):
                 out[i, j] = fv
         else:
-            for j from 0 <= j < k:
+            for j in range(k):
                 if idx1[j] == -1:
                     out[i, j] = fv
                 else:

pandas/_libs/hashtable_func_helper.pxi.in

@@ -161,18 +161,18 @@ def duplicated_{{dtype}}({{scalar}}[:] values, object keep='first'):
         {{endif}}
     elif keep == 'first':
         {{if dtype == 'object'}}
-        for i from 0 <= i < n:
+        for i in range(n):
             kh_put_{{ttype}}(table, <PyObject*> values[i], &ret)
             out[i] = ret == 0
         {{else}}
         with nogil:
-            for i from 0 <= i < n:
+            for i in range(n):
                 kh_put_{{ttype}}(table, values[i], &ret)
                 out[i] = ret == 0
         {{endif}}
     else:
         {{if dtype == 'object'}}
-        for i from 0 <= i < n:
+        for i in range(n):
             value = values[i]
             k = kh_get_{{ttype}}(table, <PyObject*> value)
             if k != table.n_buckets:
@@ -185,7 +185,7 @@ def duplicated_{{dtype}}({{scalar}}[:] values, object keep='first'):
                 out[i] = 0
         {{else}}
         with nogil:
-            for i from 0 <= i < n:
+            for i in range(n):
                 value = values[i]
                 k = kh_get_{{ttype}}(table, value)
                 if k != table.n_buckets:

pandas/_libs/lib.pyx

@@ -37,29 +37,30 @@ cdef int64_t NPY_NAT = util.get_nat()
 from util cimport is_array, is_nan
 
 
-def values_from_object(object o):
+def values_from_object(object obj):
     """ return my values or the object if we are say an ndarray """
-    cdef f
+    cdef func  # TODO: Does declaring this without a type accomplish anything?
 
-    f = getattr(o, 'get_values', None)
-    if f is not None:
-        o = f()
+    func = getattr(obj, 'get_values', None)
+    if func is not None:
+        obj = func()
 
-    return o
+    return obj
 
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def memory_usage_of_objects(ndarray[object, ndim=1] arr):
+def memory_usage_of_objects(object[:] arr):
     """ return the memory usage of an object array in bytes,
     does not include the actual bytes of the pointers """
-    cdef Py_ssize_t i, n
-    cdef int64_t s = 0
+    cdef:
+        Py_ssize_t i, n
+        int64_t size = 0
 
     n = len(arr)
-    for i from 0 <= i < n:
-        s += arr[i].__sizeof__()
-    return s
+    for i in range(n):
+        size += arr[i].__sizeof__()
+    return size
 
 
 # ----------------------------------------------------------------------
@@ -138,10 +139,10 @@ def fast_unique_multiple(list arrays):
         dict table = {}
         object val, stub = 0
 
-    for i from 0 <= i < k:
+    for i in range(k):
         buf = arrays[i]
         n = len(buf)
-        for j from 0 <= j < n:
+        for j in range(n):
             val = buf[j]
             if val not in table:
                 table[val] = stub
@@ -165,10 +166,10 @@ def fast_unique_multiple_list(list lists, bint sort=True):
         dict table = {}
         object val, stub = 0
 
-    for i from 0 <= i < k:
+    for i in range(k):
         buf = lists[i]
         n = len(buf)
-        for j from 0 <= j < n:
+        for j in range(n):
             val = buf[j]
             if val not in table:
                 table[val] = stub
@@ -208,7 +209,7 @@ def fast_unique_multiple_list_gen(object gen, bint sort=True):
 
     for buf in gen:
         n = len(buf)
-        for j from 0 <= j < n:
+        for j in range(n):
             val = buf[j]
             if val not in table:
                 table[val] = stub
@@ -669,15 +670,15 @@ def count_level_2d(ndarray[uint8_t, ndim=2, cast=True] mask,
     if axis == 0:
         counts = np.zeros((max_bin, k), dtype='i8')
         with nogil:
-            for i from 0 <= i < n:
-                for j from 0 <= j < k:
+            for i in range(n):
+                for j in range(k):
                     counts[labels[i], j] += mask[i, j]
 
     else:  # axis == 1
         counts = np.zeros((n, max_bin), dtype='i8')
         with nogil:
-            for i from 0 <= i < n:
-                for j from 0 <= j < k:
+            for i in range(n):
+                for j in range(k):
                     counts[i, labels[j]] += mask[i, j]
 
     return counts

pandas/_libs/ops.pyx

@@ -1,5 +1,4 @@
 # -*- coding: utf-8 -*-
-# cython: profile=False
 import operator
 
 from cpython cimport (PyFloat_Check, PyBool_Check,
@@ -21,7 +20,7 @@ from missing cimport checknull
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def scalar_compare(ndarray[object] values, object val, object op):
+def scalar_compare(object[:] values, object val, object op):
     """
     Compare each element of `values` array with the scalar `val`, with
     the comparison operation described by `op`.
@@ -73,7 +72,7 @@ def scalar_compare(ndarray[object] values, object val, object op):
             else:
                 try:
                     result[i] = PyObject_RichCompareBool(x, val, flag)
-                except (TypeError):
+                except TypeError:
                     result[i] = True
     elif flag == Py_EQ:
         for i in range(n):
@@ -85,7 +84,7 @@ def scalar_compare(ndarray[object] values, object val, object op):
             else:
                 try:
                     result[i] = PyObject_RichCompareBool(x, val, flag)
-                except (TypeError):
+                except TypeError:
                     result[i] = False
 
     else:
@@ -103,7 +102,7 @@ def scalar_compare(ndarray[object] values, object val, object op):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def vec_compare(ndarray[object] left, ndarray[object] right, object op):
+def vec_compare(object[:] left, object[:] right, object op):
     """
     Compare the elements of `left` with the elements of `right` pointwise,
     with the comparison operation described by `op`.
@@ -126,8 +125,8 @@ def vec_compare(ndarray[object] left, ndarray[object] right, object op):
         int flag
 
     if n != len(right):
-        raise ValueError('Arrays were different lengths: %d vs %d'
-                         % (n, len(right)))
+        raise ValueError('Arrays were different lengths: {n} vs {nright}'
+                         .format(n=n, nright=len(right)))
 
     if op is operator.lt:
         flag = Py_LT
@@ -170,7 +169,7 @@ def vec_compare(ndarray[object] left, ndarray[object] right, object op):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def scalar_binop(ndarray[object] values, object val, object op):
+def scalar_binop(object[:] values, object val, object op):
     """
     Apply the given binary operator `op` between each element of the array
     `values` and the scalar `val`.
@@ -187,13 +186,13 @@ def scalar_binop(ndarray[object] values, object val, object op):
     """
     cdef:
         Py_ssize_t i, n = len(values)
-        ndarray[object] result
+        object[:] result
         object x
 
     result = np.empty(n, dtype=object)
     if val is None or is_nan(val):
-        result.fill(val)
-        return result
+        result[:] = val
+        return result.base  # `.base` to access underlying np.ndarray
 
     for i in range(n):
         x = values[i]
@@ -202,12 +201,12 @@ def scalar_binop(ndarray[object] values, object val, object op):
         else:
             result[i] = op(x, val)
 
-    return maybe_convert_bool(result)
+    return maybe_convert_bool(result.base)
 
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def vec_binop(ndarray[object] left, ndarray[object] right, object op):
+def vec_binop(object[:] left, object[:] right, object op):
     """
     Apply the given binary operator `op` pointwise to the elements of
     arrays `left` and `right`.
@@ -224,11 +223,11 @@ def vec_binop(ndarray[object] left, ndarray[object] right, object op):
     """
     cdef:
         Py_ssize_t i, n = len(left)
-        ndarray[object] result
+        object[:] result
 
     if n != len(right):
-        raise ValueError('Arrays were different lengths: %d vs %d'
-                         % (n, len(right)))
+        raise ValueError('Arrays were different lengths: {n} vs {nright}'
+                         .format(n=n, nright=len(right)))
 
     result = np.empty(n, dtype=object)
 
@@ -245,7 +244,7 @@ def vec_binop(ndarray[object] left, ndarray[object] right, object op):
             else:
                 raise
 
-    return maybe_convert_bool(result)
+    return maybe_convert_bool(result.base)  # `.base` to access np.ndarray
 
 
 def maybe_convert_bool(ndarray[object] arr,
@@ -270,7 +269,7 @@ def maybe_convert_bool(ndarray[object] arr,
     if false_values is not None:
         false_vals = false_vals | set(false_values)
 
-    for i from 0 <= i < n:
+    for i in range(n):
         val = arr[i]
 
         if PyBool_Check(val):