ENH: Allow to_sql to recognize single sql type pandas-dev#11886

ENH: support decimal option in PythonParser pandas-dev#12933

closes pandas-dev#12933

Author: Camilo Cota <ccota@riplife.es>

Closes pandas-dev#13189 from camilocot/12933 and squashes the following commits:

465272e [Camilo Cota] Benchmark decimal option in read_csv for c engine
9f42d0c [Camilo Cota] double backticks around decimal and engine='python'
dc8ca62 [Camilo Cota] fix test_empty_decimal_marker comment
49613fe [Camilo Cota] Assert read_csv error message in test_empty_decimal_marker
d821052 [Camilo Cota] fix test_empty_decimal_marker comment
f71509d [Camilo Cota] Include descritive what's new line
803356e [Camilo Cota] set nonnum regex in init method
1472d80 [Camilo Cota] Include the issue number in what's new
b560fda [Camilo Cota] Fix what's new
dc7acd1 [Camilo Cota] ENH: support decimal option in PythonParser pandas-dev#12933

ENH: Allow to_sql to recognize single sql type pandas-dev#11886

PEP pandas-dev#3

doc/source/whatsnew/v0.18.2.txt

@@ -74,6 +74,8 @@ Other enhancements
 
     pd.Timestamp(year=2012, month=1, day=1, hour=8, minute=30)
 
+- ``DataFrame.to_sql `` now allows a single value as the SQL type for all columns (:issue:`11886`).
+
 - The ``pd.read_csv()`` with ``engine='python'`` has gained support for the ``decimal`` option (:issue:`12933`)
 
 - ``Index.astype()`` now accepts an optional boolean argument ``copy``, which allows optional copying if the requirements on dtype are satisfied (:issue:`13209`)
@@ -89,7 +91,7 @@ Other enhancements
 
 - ``pd.read_html()`` has gained support for the ``decimal`` option (:issue:`12907`)
 
-
+- ``DataFrame.to_sql `` now allows a single value as the SQL type for all columns (:issue:`11886`).
 
 .. _whatsnew_0182.api:
 

pandas/io/sql.py

@@ -18,6 +18,7 @@
                            string_types, text_type)
 from pandas.core.api import DataFrame, Series
 from pandas.core.common import isnull
+from pandas.core.generic import is_dictlike
 from pandas.core.base import PandasObject
 from pandas.types.api import DatetimeTZDtype
 from pandas.tseries.tools import to_datetime
@@ -550,9 +551,10 @@ def to_sql(frame, name, con, flavor='sqlite', schema=None, if_exists='fail',
     chunksize : int, default None
         If not None, then rows will be written in batches of this size at a
         time.  If None, all rows will be written at once.
-    dtype : dict of column name to SQL type, default None
+    dtype : single SQLtype or dict of column name to SQL type, default None
         Optional specifying the datatype for columns. The SQL type should
         be a SQLAlchemy type, or a string for sqlite3 fallback connection.
+        If all columns are of the same type, one single value can be used.
 
     """
     if if_exists not in ('fail', 'replace', 'append'):
@@ -1231,11 +1233,16 @@ def to_sql(self, frame, name, if_exists='fail', index=True,
         chunksize : int, default None
             If not None, then rows will be written in batches of this size at a
             time.  If None, all rows will be written at once.
-        dtype : dict of column name to SQL type, default None
+        dtype : single SQL type or dict of column name to SQL type, default
+            None
             Optional specifying the datatype for columns. The SQL type should
-            be a SQLAlchemy type.
+            be a SQLAlchemy type. If all columns are of the same type, one
+            single value can be used.
 
         """
+        if dtype and not is_dictlike(dtype):
+            dtype = {col_name: dtype for col_name in frame}
+
         if dtype is not None:
             from sqlalchemy.types import to_instance, TypeEngine
             for col, my_type in dtype.items():
@@ -1644,11 +1651,15 @@ def to_sql(self, frame, name, if_exists='fail', index=True,
         chunksize : int, default None
             If not None, then rows will be written in batches of this
             size at a time. If None, all rows will be written at once.
-        dtype : dict of column name to SQL type, default None
+        dtype : single SQL type or dict of column name to SQL type, default
+            None
             Optional specifying the datatype for columns. The SQL type should
-            be a string.
+            be a string. If all columns are of the same type, one single value
+            can be used.
 
         """
+        if dtype and not is_dictlike(dtype):
+            dtype = {col_name: dtype for col_name in frame}
         if dtype is not None:
             for col, my_type in dtype.items():
                 if not isinstance(my_type, str):

pandas/io/tests/parser/common.py

@@ -1302,17 +1302,17 @@ def test_read_duplicate_names(self):
 
     def test_inf_parsing(self):
         data = """\
-,A
-a,inf
-b,-inf
-c,+Inf
-d,-Inf
-e,INF
-f,-INF
-g,+INf
-h,-INf
-i,inF
-j,-inF"""
+        ,A
+        a,inf
+        b,-inf
+        c,+Inf
+        d,-Inf
+        e,INF
+        f,-INF
+        g,+INf
+        h,-INf
+        i,inF
+        j,-inF"""
         inf = float('inf')
         expected = Series([inf, -inf] * 5)
 

pandas/io/tests/test_sql.py

@@ -1552,6 +1552,19 @@ def test_dtype(self):
         self.assertTrue(isinstance(sqltype, sqlalchemy.String))
         self.assertEqual(sqltype.length, 10)
 
+    def test_to_sql_single_dtype(self):
+        cols = ['A', 'B']
+        data = [('a', 'b'),
+                ('c', 'd')]
+        df = DataFrame(data, columns=cols)
+        df.to_sql('single_dtype_test', self.conn, dtype=sqlalchemy.TEXT)
+        meta = sqlalchemy.schema.MetaData(bind=self.conn)
+        meta.reflect()
+        sqltypea = meta.tables['single_dtype_test'].columns['A'].type
+        sqltypeb = meta.tables['single_dtype_test'].columns['B'].type
+        self.assertTrue(isinstance(sqltypea, sqlalchemy.TEXT))
+        self.assertTrue(isinstance(sqltypeb, sqlalchemy.TEXT))
+
     def test_notnull_dtype(self):
         cols = {'Bool': Series([True, None]),
                 'Date': Series([datetime(2012, 5, 1), None]),
@@ -2025,6 +2038,21 @@ def test_dtype(self):
         self.assertRaises(ValueError, df.to_sql,
                           'error', self.conn, dtype={'B': bool})
 
+    def test_to_sql_single_dtype(self):
+        if self.flavor == 'mysql':
+            raise nose.SkipTest('Not applicable to MySQL legacy')
+        self.drop_table('single_dtype_test')
+        cols = ['A', 'B']
+        data = [('a', 'b'),
+                ('c', 'd')]
+        df = DataFrame(data, columns=cols)
+        df.to_sql('single_dtype_test', self.conn, dtype='STRING')
+        self.assertEqual(
+            self._get_sqlite_column_type('single_dtype_test', 'A'), 'STRING')
+        self.assertEqual(
+            self._get_sqlite_column_type('single_dtype_test', 'B'), 'STRING')
+        self.drop_table('single_dtype_test')
+
     def test_notnull_dtype(self):
         if self.flavor == 'mysql':
             raise nose.SkipTest('Not applicable to MySQL legacy')