Merge branch 'main' into sql_nullable

Author: phofl

.github/workflows/scorecards.yml

@@ -11,7 +11,6 @@
 [![Package Status](https://img.shields.io/pypi/status/pandas.svg)](https://pypi.org/project/pandas/)
 [![License](https://img.shields.io/pypi/l/pandas.svg)](https://github.com/pandas-dev/pandas/blob/main/LICENSE)
 [![Coverage](https://codecov.io/github/pandas-dev/pandas/coverage.svg?branch=main)](https://codecov.io/gh/pandas-dev/pandas)
-[![OpenSSF Scorecard](https://api.securityscorecards.dev/projects/github.com/pandas-dev/pandas/badge)](https://api.securityscorecards.dev/projects/github.com/pandas-dev/pandas)
 [![Downloads](https://static.pepy.tech/personalized-badge/pandas?period=month&units=international_system&left_color=black&right_color=orange&left_text=PyPI%20downloads%20per%20month)](https://pepy.tech/project/pandas)
 [![Slack](https://img.shields.io/badge/join_Slack-information-brightgreen.svg?logo=slack)](https://pandas.pydata.org/docs/dev/development/community.html?highlight=slack#community-slack)
 [![Powered by NumFOCUS](https://img.shields.io/badge/powered%20by-NumFOCUS-orange.svg?style=flat&colorA=E1523D&colorB=007D8A)](https://numfocus.org)

README.md

@@ -112,7 +112,7 @@ The pandas method is :func:`read_csv`, which works similarly.
 .. ipython:: python
 
    url = (
-       "https://raw.github.com/pandas-dev/"
+       "https://raw.githubusercontent.com/pandas-dev/"
        "pandas/main/pandas/tests/io/data/csv/tips.csv"
    )
    tips = pd.read_csv(url)

doc/source/getting_started/comparison/comparison_with_sas.rst

@@ -100,7 +100,7 @@ In pandas, you pass the URL or local path of the CSV file to :func:`~pandas.read
 .. ipython:: python
 
    url = (
-       "https://raw.github.com/pandas-dev"
+       "https://raw.githubusercontent.com/pandas-dev"
        "/pandas/main/pandas/tests/io/data/csv/tips.csv"
    )
    tips = pd.read_csv(url)

doc/source/getting_started/comparison/comparison_with_spreadsheets.rst

@@ -17,7 +17,7 @@ structure.
 .. ipython:: python
 
     url = (
-        "https://raw.github.com/pandas-dev"
+        "https://raw.githubusercontent.com/pandas-dev"
         "/pandas/main/pandas/tests/io/data/csv/tips.csv"
     )
     tips = pd.read_csv(url)

doc/source/getting_started/comparison/comparison_with_sql.rst

@@ -108,7 +108,7 @@ the data set if presented with a url.
 .. ipython:: python
 
    url = (
-       "https://raw.github.com/pandas-dev"
+       "https://raw.githubusercontent.com/pandas-dev"
        "/pandas/main/pandas/tests/io/data/csv/tips.csv"
    )
    tips = pd.read_csv(url)

doc/source/getting_started/comparison/comparison_with_stata.rst

@@ -5790,21 +5790,6 @@ Specifying this will return an iterator through chunks of the query result:
     for chunk in pd.read_sql_query("SELECT * FROM data_chunks", engine, chunksize=5):
         print(chunk)
 
-You can also run a plain query without creating a ``DataFrame`` with
-:func:`~pandas.io.sql.execute`. This is useful for queries that don't return values,
-such as INSERT. This is functionally equivalent to calling ``execute`` on the
-SQLAlchemy engine or db connection object. Again, you must use the SQL syntax
-variant appropriate for your database.
-
-.. code-block:: python
-
-   from pandas.io import sql
-
-   sql.execute("SELECT * FROM table_name", engine)
-   sql.execute(
-       "INSERT INTO table_name VALUES(?, ?, ?)", engine, params=[("id", 1, 12.2, True)]
-   )
-
 
 Engine connection examples
 ''''''''''''''''''''''''''

doc/source/user_guide/io.rst

@@ -487,6 +487,7 @@ Other API changes
   or :attr:`~DataFrame.iloc` (thus, ``df.loc[:, :]`` or ``df.iloc[:, :]``) now returns a
   new DataFrame (shallow copy) instead of the original DataFrame, consistent with other
   methods to get a full slice (for example ``df.loc[:]`` or ``df[:]``) (:issue:`49469`)
+- Disallow computing ``cumprod`` for :class:`Timedelta` object; previously this returned incorrect values (:issue:`50246`)
 -
 
 .. ---------------------------------------------------------------------------

doc/source/whatsnew/v2.0.0.rst

@@ -417,12 +417,13 @@ def _accumulate(self, name: str, *, skipna: bool = True, **kwargs):
 
         data = self._ndarray.copy()
 
-        if name in {"cumsum", "cumprod"}:
-            # TODO: cumprod should not work here GH#48111
-            func = np.cumsum if name == "cumsum" else np.cumprod
+        if name == "cumsum":
+            func = np.cumsum
             result = cast(np.ndarray, nanops.na_accum_func(data, func, skipna=skipna))
 
             return type(self)._simple_new(result, freq=None, dtype=self.dtype)
+        elif name == "cumprod":
+            raise TypeError("cumprod not supported for Timedelta.")
 
         else:
             return super()._accumulate(name, skipna=skipna, **kwargs)

pandas/core/arrays/timedeltas.py

@@ -192,9 +192,7 @@ def execute(sql, con, params=None):
     ----------
     sql : string
         SQL query to be executed.
-    con : SQLAlchemy connectable(engine/connection) or sqlite3 connection
-        Using SQLAlchemy makes it possible to use any DB supported by the
-        library.
+    con : SQLAlchemy connection or sqlite3 connection
         If a DBAPI2 object, only sqlite3 is supported.
     params : list or tuple, optional, default: None
         List of parameters to pass to execute method.
@@ -203,6 +201,10 @@ def execute(sql, con, params=None):
     -------
     Results Iterable
     """
+    sqlalchemy = import_optional_dependency("sqlalchemy", errors="ignore")
+
+    if sqlalchemy is not None and isinstance(con, (str, sqlalchemy.engine.Engine)):
+        raise TypeError("pandas.io.sql.execute requires a connection")  # GH50185
     with pandasSQL_builder(con, need_transaction=True) as pandas_sql:
         args = _convert_params(sql, params)
         return pandas_sql.execute(*args)

pandas/io/sql.py

@@ -311,7 +311,7 @@ def andrews_curves(
         :context: close-figs
 
         >>> df = pd.read_csv(
-        ...     'https://raw.github.com/pandas-dev/'
+        ...     'https://raw.githubusercontent.com/pandas-dev/'
         ...     'pandas/main/pandas/tests/io/data/csv/iris.csv'
         ... )
         >>> pd.plotting.andrews_curves(df, 'Name')
@@ -443,7 +443,7 @@ def parallel_coordinates(
         :context: close-figs
 
         >>> df = pd.read_csv(
-        ...     'https://raw.github.com/pandas-dev/'
+        ...     'https://raw.githubusercontent.com/pandas-dev/'
         ...     'pandas/main/pandas/tests/io/data/csv/iris.csv'
         ... )
         >>> pd.plotting.parallel_coordinates(

pandas/plotting/_misc.py

@@ -30,7 +30,7 @@
 @pytest.mark.network
 @tm.network(
     url=(
-        "https://raw.github.com/pandas-dev/pandas/main/"
+        "https://raw.githubusercontent.com/pandas-dev/pandas/main/"
         "pandas/tests/io/parser/data/salaries.csv"
     ),
     check_before_test=True,
@@ -40,7 +40,7 @@ def test_url(all_parsers, csv_dir_path):
     kwargs = {"sep": "\t"}
 
     url = (
-        "https://raw.github.com/pandas-dev/pandas/main/"
+        "https://raw.githubusercontent.com/pandas-dev/pandas/main/"
         "pandas/tests/io/parser/data/salaries.csv"
     )
     url_result = parser.read_csv(url, **kwargs)

pandas/tests/io/parser/common/test_file_buffer_url.py

@@ -663,6 +663,11 @@ def psql_insert_copy(table, conn, keys, data_iter):
     tm.assert_frame_equal(result, expected)
 
 
+def test_execute_typeerror(sqlite_iris_engine):
+    with pytest.raises(TypeError, match="pandas.io.sql.execute requires a connection"):
+        sql.execute("select * from iris", sqlite_iris_engine)
+
+
 class MixInBase:
     def teardown_method(self):
         # if setup fails, there may not be a connection to close.
@@ -956,7 +961,8 @@ def test_roundtrip_chunksize(self, test_frame1):
 
     def test_execute_sql(self):
         # drop_sql = "DROP TABLE IF EXISTS test"  # should already be done
-        iris_results = sql.execute("SELECT * FROM iris", con=self.conn)
+        with sql.pandasSQL_builder(self.conn) as pandas_sql:
+            iris_results = pandas_sql.execute("SELECT * FROM iris")
         row = iris_results.fetchone()
         tm.equalContents(row, [5.1, 3.5, 1.4, 0.2, "Iris-setosa"])
 
@@ -2798,7 +2804,8 @@ def format_query(sql, *args):
 
 def tquery(query, con=None):
     """Replace removed sql.tquery function"""
-    res = sql.execute(query, con=con).fetchall()
+    with sql.pandasSQL_builder(con) as pandas_sql:
+        res = pandas_sql.execute(query).fetchall()
     return None if res is None else list(res)
 
 
@@ -2863,7 +2870,8 @@ def test_execute(self, sqlite_buildin):
         ins = "INSERT INTO test VALUES (?, ?, ?, ?)"
 
         row = frame.iloc[0]
-        sql.execute(ins, sqlite_buildin, params=tuple(row))
+        with sql.pandasSQL_builder(sqlite_buildin) as pandas_sql:
+            pandas_sql.execute(ins, tuple(row))
         sqlite_buildin.commit()
 
         result = sql.read_sql("select * from test", sqlite_buildin)
@@ -2898,11 +2906,12 @@ def test_execute_fail(self, sqlite_buildin):
         cur = sqlite_buildin.cursor()
         cur.execute(create_sql)
 
-        sql.execute('INSERT INTO test VALUES("foo", "bar", 1.234)', sqlite_buildin)
-        sql.execute('INSERT INTO test VALUES("foo", "baz", 2.567)', sqlite_buildin)
+        with sql.pandasSQL_builder(sqlite_buildin) as pandas_sql:
+            pandas_sql.execute('INSERT INTO test VALUES("foo", "bar", 1.234)')
+            pandas_sql.execute('INSERT INTO test VALUES("foo", "baz", 2.567)')
 
-        with pytest.raises(sql.DatabaseError, match="Execution failed on sql"):
-            sql.execute('INSERT INTO test VALUES("foo", "bar", 7)', sqlite_buildin)
+            with pytest.raises(sql.DatabaseError, match="Execution failed on sql"):
+                pandas_sql.execute('INSERT INTO test VALUES("foo", "bar", 7)')
 
     def test_execute_closed_connection(self):
         create_sql = """
@@ -2918,7 +2927,8 @@ def test_execute_closed_connection(self):
             cur = conn.cursor()
             cur.execute(create_sql)
 
-            sql.execute('INSERT INTO test VALUES("foo", "bar", 1.234)', conn)
+            with sql.pandasSQL_builder(conn) as pandas_sql:
+                pandas_sql.execute('INSERT INTO test VALUES("foo", "bar", 1.234)')
 
         msg = "Cannot operate on a closed database."
         with pytest.raises(sqlite3.ProgrammingError, match=msg):

pandas/tests/io/test_sql.py

@@ -129,3 +129,9 @@ def test_cummethods_bool_in_object_dtype(self, method, expected):
         ser = pd.Series([False, True, np.nan, False])
         result = getattr(ser, method)()
         tm.assert_series_equal(result, expected)
+
+    def test_cumprod_timedelta(self):
+        # GH#48111
+        ser = pd.Series([pd.Timedelta(days=1), pd.Timedelta(days=3)])
+        with pytest.raises(TypeError, match="cumprod not supported for Timedelta"):
+            ser.cumprod()

pandas/tests/series/test_cumulative.py

@@ -48,7 +48,7 @@ classifiers = [
 
 [project.urls]
 homepage = 'https://pandas.pydata.org'
-documentation = 'https://pandas.pydata.org/pandas-docs/stable'
+documentation = 'https://pandas.pydata.org/docs/'
 repository = 'https://github.com/pandas-dev/pandas'
 
 [project.entry-points."pandas_plotting_backends"]