Skip to content

Commit

Permalink
Pandas API Addons: add_prefix and add_sufix
Browse files Browse the repository at this point in the history
  • Loading branch information
@marcosvm13
marcosvm13 committed Dec 4, 2023
1 parent 7de2b7c commit d769d80
Show file tree
Hide file tree
Showing 3 changed files with 215 additions and 2 deletions.
122 changes: 121 additions & 1 deletion docs/user-guide/advanced/Pandas_API.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1519,6 +1519,126 @@
"tab.rename(columns={'y': 'symbol', 'z': 'price'}).head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Table.add_prefix()\n",
"\n",
"```\n",
"Table.add_prefix(columns)\n",
"```\n",
"\n",
"Rename columns adding a prefix in a table and return the resulting Table object.\n",
"\n",
"**Parameters:**\n",
"\n",
"| Name | Type | Description | Default |\n",
"| :-----: | :-------------: | :------------------------------------------------------------------ | :--------: |\n",
"| prefix | str | The string that will be concatenated with the name of the columns | _required_ |\n",
"| axis | int | Axis to add prefix on. | 0 |\n",
"\n",
"**Returns:**\n",
"\n",
"| Type | Description |\n",
"| :---: | :----------------------------------------------------------------- |\n",
"| Table | A table with the given column(s) renamed adding a prefix. |"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Examples:**\n",
"\n",
"he initial table to which a prefix will be added to its columns"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tab.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Add \"col_\" to table columns:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tab.add_prefix(prefix=\"col_\").head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Table.add_suffix()\n",
"\n",
"```\n",
"Table.add_sufix(suffix, axis)\n",
"```\n",
"\n",
"Rename columns adding a suffix in a table and return the resulting Table object.\n",
"\n",
"**Parameters:**\n",
"\n",
"| Name | Type | Description | Default |\n",
"| :-----: | :-------------: | :------------------------------------------------------------------ | :--------: |\n",
"| suffix | str | The string that will be concatenated with the name of the columns | _required_ |\n",
"| axis | int | Axis to add suffix on. | 0 |\n",
"\n",
"**Returns:**\n",
"\n",
"| Type | Description |\n",
"| :---: | :----------------------------------------------------------------- |\n",
"| Table | A table with the given column(s) renamed adding a suffix. |"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Examples:**\n",
"\n",
"The initial table to which a suffix will be added to its columns"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tab.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Add \"_col\" to table columns:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tab.add_suffix(prefix=\"_col\").head()"
]
},
{
"cell_type": "markdown",
"id": "10582eaa",
Expand Down Expand Up @@ -2989,7 +3109,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.3"
"version": "3.11.5"
}
},
"nbformat": 4,
Expand Down
54 changes: 53 additions & 1 deletion src/pykx/pandas_api/pandas_indexing.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -328,6 +328,32 @@ def _rename_columns(tab, labels):
tab, labels) # noqa
else:
return q('{c:cols x; c:@[c;c?key y;y]; c xcol x}', tab, labels)


def _pre_suf_fix_columns(tab, fix, suf= True):
if "Keyed" in str(type(tab)):
f = ("c: `$ (string c) ,\: string y;" if suf
else "c: `$(string y) ,/: string c;")
return q("{c:cols value x;"
+ f
+ "key[x]!c xcol value x}",
tab, fix) # noqa
else:
f = ("c: `$(string c) ,\: string y;" if suf
else "c: `$ (string y) ,/: string c;")
return q('{c:cols x;' + f + 'c xcol x}', tab, fix)


def _pre_suf_fix_index(tab, fix, suf= True):
if "Keyed" in str(type(tab)):
f = ("idx: `$(string idx) ,\: string y;" if suf
else " idx: `$(string y) ,/: string idx;" )
return q("{idx:first flip key x;"
+ f
+ "([] idx)!value x}",
tab, fix) # noqa
else:
return ValueError('nyi')


class PandasIndexing:
Expand Down Expand Up @@ -453,6 +479,32 @@ def rename(self, labels=None, index=None, columns=None, axis=0,
t = _rename_columns(t, columns)

return t

def add_suffix(self, suffix=None, axis=0):
t = self
if suffix:
if axis == 0:
t = _pre_suf_fix_columns(t, suffix, suf=True)
elif axis == 1:
t = _pre_suf_fix_index(t, suffix, suf=True)
else:
raise ValueError(f'No axis named {axis}')
else:
raise ValueError("missing 1 required positional argument: 'suffix'")
return t

def add_prefix(self, prefix=None, axis=0):
t = self
if prefix:
if axis == 0:
t = _pre_suf_fix_columns(t, prefix, suf=False)
elif axis == 1:
t = _pre_suf_fix_index(t, prefix, suf=False)
else:
raise ValueError(f'No axis named {axis}')
else:
raise ValueError("missing 1 required positional argument: 'prefix'")
return t

def sample(self, n=None, frac=None, replace=False, weights=None,
random_state=None, axis=None, ignore_index=False):
Expand Down Expand Up @@ -566,7 +618,7 @@ def __init__(self, tab):
def __getitem__(self, loc):
if not isinstance(loc, tuple) or len(loc) != 2:
raise ValueError('Expected 2 values for call to Table.at[]')
if q('{y in keys x}', self.tab, loc[1]):
if q('{y in keys x(string y)}', self.tab, loc[1]):
raise QError('Can\'t get the value of a key in a KeyedTable using at.')
return q('{x[y][z]}', self.tab, loc[0], loc[1])

Expand Down
41 changes: 41 additions & 0 deletions tests/test_pandas_api.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1402,6 +1402,47 @@ def test_df_rename(kx, q):
t.rename(columns={'x': 'xXx'}, errors='raise')


def test_df_add_prefix(kx, q):
q('sym:`aaa`bbb`ccc')
t = q('([] 10?sym; til 10; 10?10; 10?1f)')

rez = t.add_prefix("col_")

assert(q('{x~y}', rez, t.pd().add_prefix("col_")))

kt = kx.q('([idx:til 5] til 5; 5?5; 5?1f; (5;5)#100?" ")')
kt_res = kx.q('([idx: `col_0`col_1`col_2`col_3`col_4] til 5)')

rez = kt.add_prefix("col_")
assert(q('{x~y}', rez, kt.pd().add_prefix("col_")))

rez = kt.add_prefix("col_", axis=1)
assert(q('{x~y}', kx.q("{(0!x) `idx}",rez), kx.q("{(0!x) `idx}",kt_res)))

with pytest.raises(ValueError):
t.add_prefix()

def test_df_add_suffix(kx, q):
q('sym:`aaa`bbb`ccc')
t = q('([] 10?sym; til 10; 10?10; 10?1f)')

rez = t.add_suffix("_col")

assert(q('{x~y}', rez, t.pd().add_suffix("_col")))

kt = kx.q('([idx:til 5] til 5; 5?5; 5?1f; (5;5)#100?" ")')
kt_res = kx.q('([idx: `0_col`1_col`2_col`3_col`4_col] til 5)')

rez = kt.add_suffix("_col", axis=1)
assert(q('{x~y}', kx.q("{(0!x) `idx}",rez), kx.q("{(0!x) `idx}",kt_res)))


rez = kt.add_suffix("_col")
assert(q('{x~y}', rez, kt.pd().add_suffix("_col")))

with pytest.raises(ValueError):
t.add_suffix()

@pytest.mark.pandas_api
@pytest.mark.xfail(reason='Flaky randomization')
def test_df_sample(kx, q):
Expand Down

0 comments on commit d769d80

Please sign in to comment.