Merge pull request #8090 from jorisvandenbossche/sql-date-time

ENH: add support for datetime.date/time in to_sql (GH6932)

Author: jorisvandenbossche

doc/source/v0.15.0.txt

@@ -428,6 +428,7 @@ Enhancements
 ~~~~~~~~~~~~
 
 - Added support for a ``chunksize`` parameter to ``to_sql`` function.  This allows DataFrame to be written in chunks and avoid packet-size overflow errors (:issue:`8062`)
+- Added support for writing ``datetime.date`` and ``datetime.time`` object columns with ``to_sql`` (:issue:`6932`).
 
 - Added support for bool, uint8, uint16 and uint32 datatypes in ``to_stata`` (:issue:`7097`, :issue:`7365`)
 

pandas/io/sql.py

@@ -11,6 +11,7 @@
 import re
 import numpy as np
 
+import pandas.lib as lib
 import pandas.core.common as com
 from pandas.compat import lzip, map, zip, raise_with_traceback, string_types
 from pandas.core.api import DataFrame, Series
@@ -689,13 +690,14 @@ def _get_column_names_and_types(self, dtype_mapper):
         if self.index is not None:
             for i, idx_label in enumerate(self.index):
                 idx_type = dtype_mapper(
-                    self.frame.index.get_level_values(i).dtype)
+                    self.frame.index.get_level_values(i))
                 column_names_and_types.append((idx_label, idx_type))
 
-        column_names_and_types += zip(
-            list(map(str, self.frame.columns)),
-            map(dtype_mapper, self.frame.dtypes)
-            )
+        column_names_and_types += [
+            (str(self.frame.columns[i]),
+             dtype_mapper(self.frame.iloc[:,i]))
+            for i in range(len(self.frame.columns))
+            ]
         return column_names_and_types
 
     def _create_table_statement(self):
@@ -761,30 +763,33 @@ def _harmonize_columns(self, parse_dates=None):
             except KeyError:
                 pass  # this column not in results
 
-    def _sqlalchemy_type(self, arr_or_dtype):
+    def _sqlalchemy_type(self, col):
         from sqlalchemy.types import (BigInteger, Float, Text, Boolean,
-            DateTime, Date, Interval)
+            DateTime, Date, Time, Interval)
 
-        if arr_or_dtype is date:
-            return Date
-        if com.is_datetime64_dtype(arr_or_dtype):
+        if com.is_datetime64_dtype(col):
             try:
-                tz = arr_or_dtype.tzinfo
+                tz = col.tzinfo
                 return DateTime(timezone=True)
             except:
                 return DateTime
-        if com.is_timedelta64_dtype(arr_or_dtype):
+        if com.is_timedelta64_dtype(col):
             warnings.warn("the 'timedelta' type is not supported, and will be "
                           "written as integer values (ns frequency) to the "
                           "database.", UserWarning)
             return BigInteger
-        elif com.is_float_dtype(arr_or_dtype):
+        elif com.is_float_dtype(col):
             return Float
-        elif com.is_integer_dtype(arr_or_dtype):
+        elif com.is_integer_dtype(col):
             # TODO: Refine integer size.
             return BigInteger
-        elif com.is_bool_dtype(arr_or_dtype):
+        elif com.is_bool_dtype(col):
             return Boolean
+        inferred = lib.infer_dtype(com._ensure_object(col))
+        if inferred == 'date':
+            return Date
+        if inferred == 'time':
+            return Time
         return Text
 
     def _numpy_type(self, sqltype):
@@ -913,7 +918,11 @@ def _create_sql_schema(self, frame, table_name):
     },
     'date': {
         'mysql': 'DATE',
-        'sqlite': 'TIMESTAMP',
+        'sqlite': 'DATE',
+    },
+    'time': {
+        'mysql': 'TIME',
+        'sqlite': 'TIME',
     },
     'bool': {
         'mysql': 'BOOLEAN',
@@ -1019,8 +1028,8 @@ def _create_table_statement(self):
         create_statement = template % {'name': self.name, 'columns': columns}
         return create_statement
 
-    def _sql_type_name(self, dtype):
-        pytype = dtype.type
+    def _sql_type_name(self, col):
+        pytype = col.dtype.type
         pytype_name = "text"
         if issubclass(pytype, np.floating):
             pytype_name = "float"
@@ -1034,10 +1043,14 @@ def _sql_type_name(self, dtype):
         elif issubclass(pytype, np.datetime64) or pytype is datetime:
             # Caution: np.datetime64 is also a subclass of np.number.
             pytype_name = "datetime"
-        elif pytype is datetime.date:
-            pytype_name = "date"
         elif issubclass(pytype, np.bool_):
             pytype_name = "bool"
+        elif issubclass(pytype, np.object):
+            pytype = lib.infer_dtype(com._ensure_object(col))
+            if pytype == "date":
+                pytype_name = "date"
+            elif pytype == "time":
+                pytype_name = "time"
 
         return _SQL_TYPES[pytype_name][self.pd_sql.flavor]
 

pandas/io/tests/test_sql.py

@@ -26,7 +26,7 @@
 import warnings
 import numpy as np
 
-from datetime import datetime
+from datetime import datetime, date, time
 
 from pandas import DataFrame, Series, Index, MultiIndex, isnull
 from pandas import date_range, to_datetime, to_timedelta
@@ -35,6 +35,7 @@
 from pandas.core.datetools import format as date_format
 
 import pandas.io.sql as sql
+from pandas.io.sql import read_sql_table, read_sql_query
 import pandas.util.testing as tm
 
 
@@ -976,6 +977,21 @@ def test_datetime_NaT(self):
         else:
             tm.assert_frame_equal(result, df)
 
+    def test_datetime_date(self):
+        # test support for datetime.date
+        df = DataFrame([date(2014, 1, 1), date(2014, 1, 2)], columns=["a"])
+        df.to_sql('test_date', self.conn, index=False)
+        res = read_sql_table('test_date', self.conn)
+        # comes back as datetime64
+        tm.assert_series_equal(res['a'], to_datetime(df['a']))
+
+    def test_datetime_time(self):
+        # test support for datetime.time
+        df = DataFrame([time(9, 0, 0), time(9, 1, 30)], columns=["a"])
+        df.to_sql('test_time', self.conn, index=False)
+        res = read_sql_table('test_time', self.conn)
+        tm.assert_frame_equal(res, df)
+
     def test_mixed_dtype_insert(self):
         # see GH6509
         s1 = Series(2**25 + 1,dtype=np.int32)
@@ -1269,6 +1285,21 @@ def test_roundtrip(self):
     def test_execute_sql(self):
         self._execute_sql()
 
+    def test_datetime_date(self):
+        # test support for datetime.date
+        df = DataFrame([date(2014, 1, 1), date(2014, 1, 2)], columns=["a"])
+        df.to_sql('test_date', self.conn, index=False, flavor=self.flavor)
+        res = read_sql_query('SELECT * FROM test_date', self.conn)
+        if self.flavor == 'sqlite':
+            # comes back as strings
+            tm.assert_frame_equal(res, df.astype(str))
+        elif self.flavor == 'mysql':
+            tm.assert_frame_equal(res, df)
+    
+    def test_datetime_time(self):
+        # test support for datetime.time
+        raise nose.SkipTest("datetime.time not supported for sqlite fallback")
+
 
 class TestMySQLLegacy(TestSQLiteLegacy):
     """