Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added idxmin implementation #34

Merged
merged 1 commit into from
Feb 13, 2024
Merged

Added idxmin implementation #34

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
66 changes: 66 additions & 0 deletions docs/user-guide/advanced/Pandas_API.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2511,6 +2511,72 @@
"tab.max()"
]
},
{
"cell_type": "markdown",
"id": "d98b298c",
"metadata": {},
"source": [
"### Table.idxmin()\n",
"\n",
"```\n",
"Table.idxmax(axis=0, skipna=True, numeric_only=False)\n",
"```\n",
"\n",
"Return index of first occurrence of minimum over requested axis.\n",
"\n",
"**Parameters:**\n",
"\n",
"| Name | Type | Description | Default |\n",
"| :----------: | :--: | :------------------------------------------------------------------------------- | :-----: |\n",
"| axis | int | The axis to calculate the idxmin across 0 is columns, 1 is rows. | 0 |\n",
"| skipna | bool | Ignore any null values along the axis. | True |\n",
"| numeric_only | bool | Only use columns of the table that are of a numeric data type. | False |\n",
"\n",
"**Returns:**\n",
"\n",
"| Type | Description |\n",
"| :----------------: | :------------------------------------------------------------------- |\n",
"| Dictionary | A dictionary where the key represents the column name / row number and the values are the result of calling `idxmin` on that column / row. |"
]
},
{
"cell_type": "markdown",
"id": "143f5483",
"metadata": {},
"source": [
"**Examples:**\n",
"\n",
"Calculate the idxmin across the columns of a table"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "da7cbf8f",
"metadata": {},
"outputs": [],
"source": [
"tab.idxmin()"
]
},
{
"cell_type": "markdown",
"id": "fb531e00",
"metadata": {},
"source": [
"Calculate the idxmin across the rows of a table using only columns thar are of a numeric data type"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9907226a",
"metadata": {},
"outputs": [],
"source": [
"tab.idxmin(axis=1, numeric_only=True)"
]
},
{
"cell_type": "markdown",
"id": "301ab2c2",
Expand Down
26 changes: 19 additions & 7 deletions src/pykx/pandas_api/pandas_meta.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ def preparse_computations(tab, axis=0, skipna=True, numeric_only=False, bool_onl
skipna,
axis
)
return (res, cols if axis == 0 else q.til(len(res)))
return (res, cols if axis == 0 else q.til(len(res)), cols)


# The simple computation functions all return a tuple of the results and the col names the results
Expand Down Expand Up @@ -212,33 +212,45 @@ def abs(self, numeric_only=False):

@convert_result
def all(self, axis=0, bool_only=False, skipna=True):
res, cols = preparse_computations(self, axis, skipna, bool_only=bool_only)
res, cols, _ = preparse_computations(self, axis, skipna, bool_only=bool_only)
return (q('{"b"$x}', [all(x) for x in res]), cols)

@convert_result
def any(self, axis=0, bool_only=False, skipna=True):
res, cols = preparse_computations(self, axis, skipna, bool_only=bool_only)
res, cols, _ = preparse_computations(self, axis, skipna, bool_only=bool_only)
return (q('{"b"$x}', [any(x) for x in res]), cols)

@convert_result
def max(self, axis=0, skipna=True, numeric_only=False):
res, cols = preparse_computations(self, axis, skipna, numeric_only)
res, cols, _ = preparse_computations(self, axis, skipna, numeric_only)
return (q(
'{[row] {$[11h=type x; {[x1; y1] $[x1 > y1; x1; y1]} over x; max x]} each row}',
res
), cols)

@convert_result
def min(self, axis=0, skipna=True, numeric_only=False):
res, cols = preparse_computations(self, axis, skipna, numeric_only)
res, cols, _ = preparse_computations(self, axis, skipna, numeric_only)
return (q(
'{[row] {$[11h=type x; {[x1; y1] $[x1 < y1; x1; y1]} over x; min x]} each row}',
res
), cols)

@convert_result
def idxmin(self, axis=0, skipna=True, numeric_only=False):
tab = self
axis = q('{$[11h~type x; `index`columns?x; x]}', axis)
res, cols, ix = preparse_computations(tab, axis, skipna, numeric_only)
return (q(
'''{[row;tab;axis]
row:{$[11h~type x; {[x1; y1] $[x1 < y1; x1; y1]} over x; min x]} each row;
m:$[0~axis; (::); flip] value flip tab;
$[0~axis; (::); cols tab] m {$[abs type y;x]?y}' row}
''', res, tab[ix], axis), cols)

@convert_result
def prod(self, axis=0, skipna=True, numeric_only=False, min_count=0):
res, cols = preparse_computations(self, axis, skipna, numeric_only)
res, cols, _ = preparse_computations(self, axis, skipna, numeric_only)
return (q(
'{[row; minc] {$[y > 0; $[y>count[x]; 0N; prd x]; prd x]}[;minc] each row}',
res,
Expand All @@ -247,7 +259,7 @@ def prod(self, axis=0, skipna=True, numeric_only=False, min_count=0):

@convert_result
def sum(self, axis=0, skipna=True, numeric_only=False, min_count=0):
res, cols = preparse_computations(self, axis, skipna, numeric_only)
res, cols, _ = preparse_computations(self, axis, skipna, numeric_only)
return (q(
'{[row; minc]'
'{$[y > 0;'
Expand Down
23 changes: 23 additions & 0 deletions tests/test_pandas_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1811,6 +1811,29 @@ def test_pandas_max(q):
assert float(qmax[i]) == float(pmax[i])


def test_pandas_idxmin(q):
tab = q('([] sym: 100?`foo`bar`baz`qux; price: 250.0f - 100?500.0f; ints: 100 - 100?200)')
df = tab.pd()

p_m = df.idxmin()
q_m = tab.idxmin()
for c in q.key(q_m).py():
assert p_m[c] == q_m[c].py()

q_m = tab.idxmin(axis=1, numeric_only=True, skipna=True)
p_m = df.idxmin(axis=1, numeric_only=True, skipna=True)
for c in q.key(q_m).py():
assert p_m[c] == q_m[c].py()

tab = q('([]price: 250.0f - 100?500.0f; ints: 100 - 100?200)')
df = tab.pd()

q_m = tab.idxmin(axis=1)
p_m = df.idxmin(axis=1)
for c in q.key(q_m).py():
assert p_m[c] == q_m[c].py()


def test_pandas_all(q):
tab = q(
'([] sym: 100?`foo`bar`baz`qux; price: 250.0f - 100?500.0f; ints: 100 - 100?200;'
Expand Down
Loading