DEP: Enforce numpy keyword deprecation in read_json (#49083)

Author: phofl

doc/source/user_guide/io.rst

@@ -2111,8 +2111,6 @@ is ``None``. To explicitly force ``Series`` parsing, pass ``typ=series``
 * ``convert_axes`` : boolean, try to convert the axes to the proper dtypes, default is ``True``
 * ``convert_dates`` : a list of columns to parse for dates; If ``True``, then try to parse date-like columns, default is ``True``.
 * ``keep_default_dates`` : boolean, default ``True``. If parsing dates, then parse the default date-like columns.
-* ``numpy`` : direct decoding to NumPy arrays. default is ``False``;
-  Supports numeric data only, although labels may be non-numeric. Also note that the JSON ordering **MUST** be the same for each term if ``numpy=True``.
 * ``precise_float`` : boolean, default ``False``. Set to enable usage of higher precision (strtod) function when decoding string to double values. Default (``False``) is to use fast but less precise builtin functionality.
 * ``date_unit`` : string, the timestamp unit to detect if converting dates. Default
   None. By default the timestamp precision will be detected, if this is not desired
@@ -2216,74 +2214,6 @@ Dates written in nanoseconds need to be read back in nanoseconds:
    dfju = pd.read_json(json, date_unit="ns")
    dfju
 
-The Numpy parameter
-+++++++++++++++++++
-
-.. note::
-  This param has been deprecated as of version 1.0.0 and will raise a ``FutureWarning``.
-
-  This supports numeric data only. Index and columns labels may be non-numeric, e.g. strings, dates etc.
-
-If ``numpy=True`` is passed to ``read_json`` an attempt will be made to sniff
-an appropriate dtype during deserialization and to subsequently decode directly
-to NumPy arrays, bypassing the need for intermediate Python objects.
-
-This can provide speedups if you are deserialising a large amount of numeric
-data:
-
-.. ipython:: python
-
-   randfloats = np.random.uniform(-100, 1000, 10000)
-   randfloats.shape = (1000, 10)
-   dffloats = pd.DataFrame(randfloats, columns=list("ABCDEFGHIJ"))
-
-   jsonfloats = dffloats.to_json()
-
-.. ipython:: python
-
-   %timeit pd.read_json(jsonfloats)
-
-.. ipython:: python
-   :okwarning:
-
-   %timeit pd.read_json(jsonfloats, numpy=True)
-
-The speedup is less noticeable for smaller datasets:
-
-.. ipython:: python
-
-   jsonfloats = dffloats.head(100).to_json()
-
-.. ipython:: python
-
-   %timeit pd.read_json(jsonfloats)
-
-.. ipython:: python
-   :okwarning:
-
-   %timeit pd.read_json(jsonfloats, numpy=True)
-
-.. warning::
-
-   Direct NumPy decoding makes a number of assumptions and may fail or produce
-   unexpected output if these assumptions are not satisfied:
-
-    - data is numeric.
-
-    - data is uniform. The dtype is sniffed from the first value decoded.
-      A ``ValueError`` may be raised, or incorrect output may be produced
-      if this condition is not satisfied.
-
-    - labels are ordered. Labels are only read from the first container, it is assumed
-      that each subsequent row / column has been encoded in the same order. This should be satisfied if the
-      data was encoded using ``to_json`` but may not be the case if the JSON
-      is from another source.
-
-.. ipython:: python
-   :suppress:
-
-   os.remove("test.json")
-
 .. _io.json_normalize:
 
 Normalization

doc/source/whatsnew/v2.0.0.rst

@@ -151,6 +151,7 @@ Removal of prior version deprecations/changes
 - Removed the ``numeric_only`` keyword from :meth:`Categorical.min` and :meth:`Categorical.max` in favor of ``skipna`` (:issue:`48821`)
 - Removed :func:`is_extension_type` in favor of :func:`is_extension_array_dtype` (:issue:`29457`)
 - Remove :meth:`DataFrameGroupBy.pad` and :meth:`DataFrameGroupBy.backfill` (:issue:`45076`)
+- Remove ``numpy`` argument from :func:`read_json` (:issue:`30636`)
 - Removed the ``center`` keyword in :meth:`DataFrame.expanding` (:issue:`20647`)
 - Enforced :meth:`Rolling.count` with ``min_periods=None`` to default to the size of the window (:issue:`31302`)
 

pandas/_libs/src/ujson/python/JSONtoObj.c

@@ -83,12 +83,6 @@ JSOBJ Object_npyNewArrayList(void *prv, void *decoder);
 JSOBJ Object_npyEndArrayList(void *prv, JSOBJ obj);
 int Object_npyArrayListAddItem(void *prv, JSOBJ obj, JSOBJ value);
 
-// labelled support, encode keys and values of JS object into separate numpy
-// arrays
-JSOBJ Object_npyNewObject(void *prv, void *decoder);
-JSOBJ Object_npyEndObject(void *prv, JSOBJ obj);
-int Object_npyObjectAddKey(void *prv, JSOBJ obj, JSOBJ name, JSOBJ value);
-
 // free the numpy context buffer
 void Npy_releaseContext(NpyArrContext *npyarr) {
     PRINTMARK();
@@ -374,68 +368,6 @@ int Object_npyArrayListAddItem(void *prv, JSOBJ obj, JSOBJ value) {
     return 1;
 }
 
-JSOBJ Object_npyNewObject(void *prv, void *_decoder) {
-    PyObjectDecoder *decoder = (PyObjectDecoder *)_decoder;
-    PRINTMARK();
-    if (decoder->curdim > 1) {
-        PyErr_SetString(PyExc_ValueError,
-                        "labels only supported up to 2 dimensions");
-        return NULL;
-    }
-
-    return ((JSONObjectDecoder *)decoder)->newArray(prv, decoder);
-}
-
-JSOBJ Object_npyEndObject(void *prv, JSOBJ obj) {
-    PyObject *list;
-    npy_intp labelidx;
-    NpyArrContext *npyarr = (NpyArrContext *)obj;
-    PRINTMARK();
-    if (!npyarr) {
-        return NULL;
-    }
-
-    labelidx = npyarr->dec->curdim - 1;
-
-    list = npyarr->labels[labelidx];
-    if (list) {
-        npyarr->labels[labelidx] = PyArray_FROM_O(list);
-        Py_DECREF(list);
-    }
-
-    return (PyObject *)((JSONObjectDecoder *)npyarr->dec)->endArray(prv, obj);
-}
-
-int Object_npyObjectAddKey(void *prv, JSOBJ obj, JSOBJ name, JSOBJ value) {
-    PyObject *label, *labels;
-    npy_intp labelidx;
-    // add key to label array, value to values array
-    NpyArrContext *npyarr = (NpyArrContext *)obj;
-    PRINTMARK();
-    if (!npyarr) {
-        return 0;
-    }
-
-    label = (PyObject *)name;
-    labelidx = npyarr->dec->curdim - 1;
-
-    if (!npyarr->labels[labelidx]) {
-        npyarr->labels[labelidx] = PyList_New(0);
-    }
-    labels = npyarr->labels[labelidx];
-    // only fill label array once, assumes all column labels are the same
-    // for 2-dimensional arrays.
-    if (PyList_Check(labels) && PyList_GET_SIZE(labels) <= npyarr->elcount) {
-        PyList_Append(labels, label);
-    }
-
-    if (((JSONObjectDecoder *)npyarr->dec)->arrayAddItem(prv, obj, value)) {
-        Py_DECREF(label);
-        return 1;
-    }
-    return 0;
-}
-
 int Object_objectAddKey(void *prv, JSOBJ obj, JSOBJ name, JSOBJ value) {
     int ret = PyDict_SetItem(obj, name, value);
     Py_DECREF((PyObject *)name);
@@ -494,7 +426,7 @@ static void Object_releaseObject(void *prv, JSOBJ obj, void *_decoder) {
     }
 }
 
-static char *g_kwlist[] = {"obj",      "precise_float", "numpy",
+static char *g_kwlist[] = {"obj",      "precise_float",
                            "labelled", "dtype",         NULL};
 
 PyObject *JSONToObj(PyObject *self, PyObject *args, PyObject *kwargs) {
@@ -505,7 +437,7 @@ PyObject *JSONToObj(PyObject *self, PyObject *args, PyObject *kwargs) {
     JSONObjectDecoder *decoder;
     PyObjectDecoder pyDecoder;
     PyArray_Descr *dtype = NULL;
-    int numpy = 0, labelled = 0;
+    int labelled = 0;
 
     JSONObjectDecoder dec = {
         Object_newString, Object_objectAddKey,  Object_arrayAddItem,
@@ -528,7 +460,7 @@ PyObject *JSONToObj(PyObject *self, PyObject *args, PyObject *kwargs) {
     decoder = (JSONObjectDecoder *)&pyDecoder;
 
     if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|OiiO&", g_kwlist, &arg,
-                                     &opreciseFloat, &numpy, &labelled,
+                                     &opreciseFloat, &labelled,
                                      PyArray_DescrConverter2, &dtype)) {
         Npy_releaseContext(pyDecoder.npyarr);
         return NULL;
@@ -554,19 +486,6 @@ PyObject *JSONToObj(PyObject *self, PyObject *args, PyObject *kwargs) {
     decoder->errorStr = NULL;
     decoder->errorOffset = NULL;
 
-    if (numpy) {
-        pyDecoder.dtype = dtype;
-        decoder->newArray = Object_npyNewArray;
-        decoder->endArray = Object_npyEndArray;
-        decoder->arrayAddItem = Object_npyArrayAddItem;
-
-        if (labelled) {
-            decoder->newObject = Object_npyNewObject;
-            decoder->endObject = Object_npyEndObject;
-            decoder->objectAddKey = Object_npyObjectAddKey;
-        }
-    }
-
     ret = JSON_DecodeObject(decoder, PyBytes_AS_STRING(sarg),
                             PyBytes_GET_SIZE(sarg));