Fix typos, via a Levenshtein-style corrector (pandas-dev#30341)

Author: bwignall

pandas/_config/config.py

@@ -57,10 +57,10 @@
 DeprecatedOption = namedtuple("DeprecatedOption", "key msg rkey removal_ver")
 RegisteredOption = namedtuple("RegisteredOption", "key defval doc validator cb")
 
-# holds deprecated option metdata
+# holds deprecated option metadata
 _deprecated_options: Dict[str, DeprecatedOption] = {}
 
-# holds registered option metdata
+# holds registered option metadata
 _registered_options: Dict[str, RegisteredOption] = {}
 
 # holds the current values for registered options

pandas/_libs/groupby.pyx

@@ -791,7 +791,7 @@ def group_quantile(ndarray[float64_t] out,
                 out[i] = NaN
             else:
                 # Calculate where to retrieve the desired value
-                # Casting to int will intentionaly truncate result
+                # Casting to int will intentionally truncate result
                 idx = grp_start + <int64_t>(q * <float64_t>(non_na_sz - 1))
 
                 val = values[sort_arr[idx]]

pandas/_libs/index.pyx

@@ -288,7 +288,7 @@ cdef class IndexEngine:
 
     def get_indexer_non_unique(self, targets):
         """
-        Return an indexer suitable for takng from a non unique index
+        Return an indexer suitable for taking from a non unique index
         return the labels in the same order ast the target
         and a missing indexer into the targets (which correspond
         to the -1 indices in the results

pandas/_libs/lib.pyx

@@ -510,7 +510,7 @@ def maybe_booleans_to_slice(ndarray[uint8_t] mask):
 @cython.boundscheck(False)
 def array_equivalent_object(left: object[:], right: object[:]) -> bool:
     """
-    Perform an element by element comparion on 1-d object arrays
+    Perform an element by element comparison on 1-d object arrays
     taking into account nan positions.
     """
     cdef:

pandas/_libs/src/klib/khash.h

@@ -498,7 +498,7 @@ PANDAS_INLINE khint_t __ac_Wang_hash(khint_t key)
  */
 #define kh_n_buckets(h) ((h)->n_buckets)
 
-/* More conenient interfaces */
+/* More convenient interfaces */
 
 /*! @function
   @abstract     Instantiate a hash set containing integer keys

pandas/_libs/src/ujson/lib/ultrajsondec.c

@@ -150,7 +150,7 @@ FASTCALL_ATTR JSOBJ FASTCALL_MSVC decode_numeric(struct DecoderState *ds) {
             case '7':
             case '8':
             case '9': {
-                // FIXME: Check for arithemtic overflow here
+                // FIXME: Check for arithmetic overflow here
                 // PERF: Don't do 64-bit arithmetic here unless we know we have
                 // to
                 intValue = intValue * 10ULL + (JSLONG)(chr - 48);
@@ -235,7 +235,7 @@ FASTCALL_ATTR JSOBJ FASTCALL_MSVC decode_numeric(struct DecoderState *ds) {
     }
 
 BREAK_FRC_LOOP:
-    // FIXME: Check for arithemtic overflow here
+    // FIXME: Check for arithmetic overflow here
     ds->lastType = JT_DOUBLE;
     ds->start = offset;
     return ds->dec->newDouble(
@@ -282,7 +282,7 @@ FASTCALL_ATTR JSOBJ FASTCALL_MSVC decode_numeric(struct DecoderState *ds) {
     }
 
 BREAK_EXP_LOOP:
-    // FIXME: Check for arithemtic overflow here
+    // FIXME: Check for arithmetic overflow here
     ds->lastType = JT_DOUBLE;
     ds->start = offset;
     return ds->dec->newDouble(

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

@@ -1632,7 +1632,7 @@ char **NpyArr_encodeLabels(PyArrayObject *labels, PyObjectEncoder *enc,
                 sprintf(buf, "%" NPY_INT64_FMT, value);
                 len = strlen(cLabel);
             }
-        } else { // Fallack to string representation
+        } else { // Fallback to string representation
             PyObject *str = PyObject_Str(item);
             if (str == NULL) {
                 Py_DECREF(item);

pandas/_libs/tslibs/timestamps.pyx

@@ -324,7 +324,7 @@ class Timestamp(_Timestamp):
 
         Function is not implemented. Use pd.to_datetime().
         """
-        raise NotImplementedError("Timestamp.strptime() is not implmented."
+        raise NotImplementedError("Timestamp.strptime() is not implemented."
                                   "Use to_datetime() to parse date strings.")
 
     @classmethod

pandas/core/arrays/sparse/dtype.py

@@ -290,7 +290,7 @@ def update_dtype(self, dtype):
         Returns
         -------
         SparseDtype
-            A new SparseDtype with the corret `dtype` and fill value
+            A new SparseDtype with the correct `dtype` and fill value
             for that `dtype`.
 
         Raises

pandas/core/arrays/string_.py

@@ -86,7 +86,7 @@ def __from_arrow__(self, array):
 
         results = []
         for arr in chunks:
-            # using _from_sequence to ensure None is convered to NA
+            # using _from_sequence to ensure None is converted to NA
             str_arr = StringArray._from_sequence(np.array(arr))
             results.append(str_arr)
 
@@ -153,7 +153,7 @@ class StringArray(PandasArray):
     ...
     ValueError: StringArray requires an object-dtype ndarray of strings.
 
-    For comparision methods, this returns a :class:`pandas.BooleanArray`
+    For comparison methods, this returns a :class:`pandas.BooleanArray`
 
     >>> pd.array(["a", None, "c"], dtype="string") == "a"
     <BooleanArray>

pandas/core/groupby/base.py

@@ -1,5 +1,5 @@
 """
-Provide basic components for groupby. These defintiions
+Provide basic components for groupby. These definitions
 hold the whitelist of methods that are exposed on the
 SeriesGroupBy and the DataFrameGroupBy objects.
 """

pandas/core/ops/mask_ops.py

@@ -1,5 +1,5 @@
 """
-Ops for masked ararys.
+Ops for masked arrays.
 """
 from typing import Optional, Union
 

pandas/io/formats/format.py

@@ -1640,7 +1640,7 @@ def _get_format_datetime64_from_values(
     """ given values and a date_format, return a string format """
 
     if isinstance(values, np.ndarray) and values.ndim > 1:
-        # We don't actaully care about the order of values, and DatetimeIndex
+        # We don't actually care about the order of values, and DatetimeIndex
         #  only accepts 1D values
         values = values.ravel()
 

pandas/io/gbq.py

@@ -65,7 +65,7 @@ def read_gbq(
 
         *New in version 0.2.0 of pandas-gbq*.
     dialect : str, default 'legacy'
-        Note: The default value is changing to 'standard' in a future verion.
+        Note: The default value is changing to 'standard' in a future version.
 
         SQL syntax dialect to use. Value can be one of:
 

pandas/io/json/_json.py

@@ -314,7 +314,7 @@ def __init__(
         timedeltas = obj.select_dtypes(include=["timedelta"]).columns
         if len(timedeltas):
             obj[timedeltas] = obj[timedeltas].applymap(lambda x: x.isoformat())
-        # Convert PeriodIndex to datetimes before serialzing
+        # Convert PeriodIndex to datetimes before serializing
         if is_period_dtype(obj.index):
             obj.index = obj.index.to_timestamp()
 

pandas/io/parsers.py

@@ -3492,7 +3492,7 @@ def _get_empty_meta(columns, index_col, index_names, dtype=None):
     # 2) index_names (column names)
     #
     # Both must be non-null to ensure a successful construction. Otherwise,
-    # we have to create a generic emtpy Index.
+    # we have to create a generic empty Index.
     if (index_col is None or index_col is False) or index_names is None:
         index = Index([])
     else:

pandas/tests/extension/json/array.py

@@ -183,7 +183,7 @@ def _values_for_factorize(self):
 
     def _values_for_argsort(self):
         # Disable NumPy's shape inference by including an empty tuple...
-        # If all the elemnts of self are the same size P, NumPy will
+        # If all the elements of self are the same size P, NumPy will
         # cast them to an (N, P) array, instead of an (N,) array of tuples.
         frozen = [()] + [tuple(x.items()) for x in self]
         return np.array(frozen, dtype=object)[1:]

pandas/tests/indexes/datetimes/test_date_range.py

@@ -798,7 +798,7 @@ def test_daterange_bug_456(self):
         # GH #456
         rng1 = bdate_range("12/5/2011", "12/5/2011")
         rng2 = bdate_range("12/2/2011", "12/5/2011")
-        rng2._data.freq = BDay()  # TODO: shouldnt this already be set?
+        rng2._data.freq = BDay()  # TODO: shouldn't this already be set?
 
         result = rng1.union(rng2)
         assert isinstance(result, DatetimeIndex)
@@ -855,7 +855,7 @@ def test_daterange_bug_456(self):
         # GH #456
         rng1 = bdate_range("12/5/2011", "12/5/2011", freq="C")
         rng2 = bdate_range("12/2/2011", "12/5/2011", freq="C")
-        rng2._data.freq = CDay()  # TODO: shouldnt this already be set?
+        rng2._data.freq = CDay()  # TODO: shouldn't this already be set?
 
         result = rng1.union(rng2)
         assert isinstance(result, DatetimeIndex)

pandas/tests/indexes/datetimes/test_tools.py

@@ -1061,7 +1061,7 @@ class TestToDatetimeUnit:
     @pytest.mark.parametrize("cache", [True, False])
     def test_unit(self, cache):
         # GH 11758
-        # test proper behavior with erros
+        # test proper behavior with errors
 
         with pytest.raises(ValueError):
             to_datetime([1], unit="D", format="%Y%m%d", cache=cache)

pandas/tests/indexes/timedeltas/test_indexing.py

@@ -228,7 +228,7 @@ def test_insert(self):
     def test_delete(self):
         idx = timedelta_range(start="1 Days", periods=5, freq="D", name="idx")
 
-        # prserve freq
+        # preserve freq
         expected_0 = timedelta_range(start="2 Days", periods=4, freq="D", name="idx")
         expected_4 = timedelta_range(start="1 Days", periods=4, freq="D", name="idx")
 
@@ -257,7 +257,7 @@ def test_delete(self):
     def test_delete_slice(self):
         idx = timedelta_range(start="1 days", periods=10, freq="D", name="idx")
 
-        # prserve freq
+        # preserve freq
         expected_0_2 = timedelta_range(start="4 days", periods=7, freq="D", name="idx")
         expected_7_9 = timedelta_range(start="1 days", periods=7, freq="D", name="idx")
 

pandas/tests/plotting/test_converter.py

@@ -84,7 +84,7 @@ def test_matplotlib_formatters(self):
         units = pytest.importorskip("matplotlib.units")
 
         # Can't make any assertion about the start state.
-        # We we check that toggling converters off remvoes it, and toggling it
+        # We we check that toggling converters off removes it, and toggling it
         # on restores it.
 
         with cf.option_context("plotting.matplotlib.register_converters", True):