ENH: Reflect changes from numpy namespace refactor Part 3 (#54579)

* ENH: Reflect changes from numpy namespace refactor part 3

* ENH: Move to fixtures for dtype access

Author: mtsokol

asv_bench/benchmarks/algos/isin.py

@@ -247,7 +247,7 @@ def setup(self, series_type, vals_type):
         elif series_type == "long":
             ser_vals = np.arange(N_many)
         elif series_type == "long_floats":
-            ser_vals = np.arange(N_many, dtype=np.float_)
+            ser_vals = np.arange(N_many, dtype=np.float64)
 
         self.series = Series(ser_vals).astype(object)
 
@@ -258,7 +258,7 @@ def setup(self, series_type, vals_type):
         elif vals_type == "long":
             values = np.arange(N_many)
         elif vals_type == "long_floats":
-            values = np.arange(N_many, dtype=np.float_)
+            values = np.arange(N_many, dtype=np.float64)
 
         self.values = values.astype(object)
 

doc/source/getting_started/comparison/comparison_with_sql.rst

@@ -107,7 +107,7 @@ methods.
 .. ipython:: python
 
     frame = pd.DataFrame(
-        {"col1": ["A", "B", np.NaN, "C", "D"], "col2": ["F", np.NaN, "G", "H", "I"]}
+        {"col1": ["A", "B", np.nan, "C", "D"], "col2": ["F", np.nan, "G", "H", "I"]}
     )
     frame
 

doc/source/user_guide/enhancingperf.rst

@@ -183,8 +183,8 @@ can be improved by passing an ``np.ndarray``.
       ...:     return s * dx
       ...: cpdef np.ndarray[double] apply_integrate_f(np.ndarray col_a, np.ndarray col_b,
       ...:                                            np.ndarray col_N):
-      ...:     assert (col_a.dtype == np.float_
-      ...:             and col_b.dtype == np.float_ and col_N.dtype == np.int_)
+      ...:     assert (col_a.dtype == np.float64
+      ...:             and col_b.dtype == np.float64 and col_N.dtype == np.int_)
       ...:     cdef Py_ssize_t i, n = len(col_N)
       ...:     assert (len(col_a) == len(col_b) == n)
       ...:     cdef np.ndarray[double] res = np.empty(n)

doc/source/user_guide/gotchas.rst

@@ -327,7 +327,7 @@ present in the more domain-specific statistical programming language `R
    ``numpy.unsignedinteger`` | ``uint8, uint16, uint32, uint64``
    ``numpy.object_`` | ``object_``
    ``numpy.bool_`` | ``bool_``
-   ``numpy.character`` | ``string_, unicode_``
+   ``numpy.character`` | ``bytes_, str_``
 
 The R language, by contrast, only has a handful of built-in data types:
 ``integer``, ``numeric`` (floating-point), ``character``, and

doc/source/user_guide/io.rst

@@ -4881,7 +4881,7 @@ unspecified columns of the given DataFrame. The argument ``selector``
 defines which table is the selector table (which you can make queries from).
 The argument ``dropna`` will drop rows from the input ``DataFrame`` to ensure
 tables are synchronized.  This means that if a row for one of the tables
-being written to is entirely ``np.NaN``, that row will be dropped from all tables.
+being written to is entirely ``np.nan``, that row will be dropped from all tables.
 
 If ``dropna`` is False, **THE USER IS RESPONSIBLE FOR SYNCHRONIZING THE TABLES**.
 Remember that entirely ``np.Nan`` rows are not written to the HDFStore, so if

doc/source/whatsnew/v0.24.0.rst

@@ -556,7 +556,7 @@ You must pass in the ``line_terminator`` explicitly, even in this case.
 
 .. _whatsnew_0240.bug_fixes.nan_with_str_dtype:
 
-Proper handling of ``np.NaN`` in a string data-typed column with the Python engine
+Proper handling of ``np.nan`` in a string data-typed column with the Python engine
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 There was bug in :func:`read_excel` and :func:`read_csv` with the Python

pandas/_libs/algos.pyx

@@ -59,7 +59,7 @@ from pandas._libs.util cimport get_nat
 
 cdef:
     float64_t FP_ERR = 1e-13
-    float64_t NaN = <float64_t>np.NaN
+    float64_t NaN = <float64_t>np.nan
     int64_t NPY_NAT = get_nat()
 
 

pandas/_libs/groupby.pyx

@@ -52,7 +52,7 @@ from pandas._libs.missing cimport checknull
 
 cdef int64_t NPY_NAT = util.get_nat()
 
-cdef float64_t NaN = <float64_t>np.NaN
+cdef float64_t NaN = <float64_t>np.nan
 
 cdef enum InterpolationEnumType:
     INTERPOLATION_LINEAR,

pandas/_libs/lib.pyx

@@ -144,7 +144,7 @@ cdef:
     object oINT64_MIN = <int64_t>INT64_MIN
     object oUINT64_MAX = <uint64_t>UINT64_MAX
 
-    float64_t NaN = <float64_t>np.NaN
+    float64_t NaN = <float64_t>np.nan
 
 # python-visible
 i8max = <int64_t>INT64_MAX

pandas/_libs/tslibs/util.pxd

@@ -75,7 +75,7 @@ cdef inline bint is_integer_object(object obj) noexcept nogil:
 
 cdef inline bint is_float_object(object obj) noexcept nogil:
     """
-    Cython equivalent of `isinstance(val, (float, np.float_))`
+    Cython equivalent of `isinstance(val, (float, np.float64))`
 
     Parameters
     ----------
@@ -91,7 +91,7 @@ cdef inline bint is_float_object(object obj) noexcept nogil:
 
 cdef inline bint is_complex_object(object obj) noexcept nogil:
     """
-    Cython equivalent of `isinstance(val, (complex, np.complex_))`
+    Cython equivalent of `isinstance(val, (complex, np.complex128))`
 
     Parameters
     ----------