Skip to content

Commit

Permalink
More stuff for pandas etc.
Browse files Browse the repository at this point in the history
  • Loading branch information
@kwinkunks
kwinkunks committed Sep 18, 2023
1 parent 89e9d8f commit df8a52d
Show file tree
Hide file tree
Showing 4 changed files with 154 additions and 48 deletions.
132 changes: 90 additions & 42 deletions docs/notebooks/_Pandas_accessor.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 1,
"id": "75bb8303",
"metadata": {},
"outputs": [
Expand Down Expand Up @@ -90,7 +90,7 @@
"4 4237.5 2448.6 2.472231 sandstone"
]
},
"execution_count": 2,
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -105,7 +105,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"id": "39832c6c",
"metadata": {},
"outputs": [
Expand All @@ -115,7 +115,7 @@
"1.4130434782602501"
]
},
"execution_count": 3,
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -129,20 +129,12 @@
{
"cell_type": "code",
"execution_count": 4,
"id": "92e29966",
"metadata": {},
"outputs": [],
"source": [
"from pandas.api.extensions import register_dataframe_accessor"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "372a6bf1",
"metadata": {},
"outputs": [],
"source": [
"from pandas.api.extensions import register_dataframe_accessor\n",
"\n",
"@register_dataframe_accessor(\"redflag\")\n",
"class RedflagAccessor:\n",
" def __init__(self, pandas_obj):\n",
Expand All @@ -157,7 +149,28 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 14,
"id": "b110936f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rf.dummy_re([0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "7c3963ec",
"metadata": {},
"outputs": [
Expand All @@ -167,7 +180,7 @@
"-1.0"
]
},
"execution_count": 6,
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -186,7 +199,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 6,
"id": "94f7c2cd",
"metadata": {},
"outputs": [
Expand All @@ -196,7 +209,7 @@
"array([], dtype=float64)"
]
},
"execution_count": 7,
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -207,7 +220,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 7,
"id": "62ea78b5",
"metadata": {},
"outputs": [
Expand All @@ -217,7 +230,7 @@
"array([], dtype=int64)"
]
},
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -231,17 +244,17 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 8,
"id": "84c883db",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([1.3, 1.1, 1.8, 1.6, 1.5, 1.2, 1.7, 1.9, 1.4, 1. ])"
"array([1.8, 1. , 1.2, 1.6, 1.4, 1.5, 1.1, 1.9, 1.3, 1.7])"
]
},
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -262,17 +275,17 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 9,
"id": "6427e5ee",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([1.3, 1.1, 1.8, 1.6, 1.5, 1.2, 1.7, 1.9, 1.4, 1. ])"
"array([1.8, 1. , 1.2, 1.6, 1.4, 1.5, 1.1, 1.9, 1.3, 1.7])"
]
},
"execution_count": 10,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -283,26 +296,26 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 10,
"id": "6e912a70",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[3],\n",
" [1],\n",
" [8],\n",
"array([[8],\n",
" [0],\n",
" [2],\n",
" [6],\n",
" [4],\n",
" [5],\n",
" [2],\n",
" [7],\n",
" [1],\n",
" [9],\n",
" [4],\n",
" [0]])"
" [3],\n",
" [7]])"
]
},
"execution_count": 11,
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -321,7 +334,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 11,
"id": "7ec28d7f",
"metadata": {},
"outputs": [],
Expand All @@ -338,12 +351,24 @@
" return rf.imbalance_degree(self._obj)\n",
"\n",
" def minority_classes(self):\n",
" return rf.minority_classes(self._obj)"
" return rf.minority_classes(self._obj)\n",
" \n",
"\n",
" def dummy_scores(self, task=None, random_state=None):\n",
" if task is None:\n",
" task = 'regression' if rf.is_continuous(self._obj) else 'classification'\n",
" if task == 'classification':\n",
" return rf.dummy_classification_scores(self._obj, random_state=random_state)\n",
" elif task == 'regression':\n",
" return rf.dummy_regression_scores(self._obj)\n",
" else:\n",
" raise ValueError(\"`task` must be 'classification' or 'regression', or None to decide automatically.\")\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 12,
"id": "88447a57",
"metadata": {},
"outputs": [
Expand All @@ -353,7 +378,7 @@
"-1.0"
]
},
"execution_count": 13,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -362,6 +387,29 @@
"df['Lithology'].redflag.imbalance_degree()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "5f89c66d",
"metadata": {},
"outputs": [
{
"ename": "AttributeError",
"evalue": "module 'redflag' has no attribute 'dummy_classification_scores'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn [13], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mLithology\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mredflag\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdummy_scores\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"Cell \u001b[0;32mIn [11], line 20\u001b[0m, in \u001b[0;36mSeriesAccessor.dummy_scores\u001b[0;34m(self, task, random_state)\u001b[0m\n\u001b[1;32m 18\u001b[0m task \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mregression\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m rf\u001b[38;5;241m.\u001b[39mis_continuous(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_obj) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mclassification\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m 19\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m task \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mclassification\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[0;32m---> 20\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mrf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdummy_classification_scores\u001b[49m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_obj, random_state\u001b[38;5;241m=\u001b[39mrandom_state)\n\u001b[1;32m 21\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m task \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mregression\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[1;32m 22\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m rf\u001b[38;5;241m.\u001b[39mdummy_regression_scores(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_obj)\n",
"\u001b[0;31mAttributeError\u001b[0m: module 'redflag' has no attribute 'dummy_classification_scores'"
]
}
],
"source": [
"df['Lithology'].redflag.dummy_scores()"
]
},
{
"cell_type": "markdown",
"id": "369cf2f6",
Expand Down Expand Up @@ -645,7 +693,7 @@
{
"cell_type": "code",
"execution_count": 72,
"id": "154b6ed5",
"id": "2add677d",
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -669,7 +717,7 @@
{
"cell_type": "code",
"execution_count": 73,
"id": "978b8ba6",
"id": "41775588",
"metadata": {},
"outputs": [
{
Expand All @@ -691,7 +739,7 @@
{
"cell_type": "code",
"execution_count": null,
"id": "072db9c3",
"id": "f537e306",
"metadata": {},
"outputs": [],
"source": []
Expand Down
1 change: 1 addition & 0 deletions src/redflag/__init__.py
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
from .utils import *
from .sklearn import *
from .pandas import *

# Targets
from .target import *
Expand Down
Loading

0 comments on commit df8a52d

Please sign in to comment.