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

Jump to bottom

Update dependencies, add python 3.10, 3.11 tests, ensure code compatibility #106

Open
wants to merge 7 commits into
base: develop
Choose a base branch
from
Open

Update dependencies, add python 3.10, 3.11 tests, ensure code compatibility #106

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
d9e8ea4
move click to seperate section, remove req file
mateusz-wozny Nov 20, 2023
ed5b204
improve readme
mateusz-wozny Nov 20, 2023
9d872b6
loose dependencies, update notebooks, update code to use newest featu…
mateusz-wozny May 17, 2024
fa25221
scikit poshocs~=0.7
mateusz-wozny May 17, 2024
4f5d47c
fix flake8
mateusz-wozny May 17, 2024
658aa67
Update readme, add py310 and py311
mateusz-wozny May 17, 2024
2ae819a
Update readme
mateusz-wozny May 17, 2024
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
Prev Previous commit
Next Next commit
loose dependencies, update notebooks, update code to use newest featu… 
…res, black + flake
  • Loading branch information
@mateusz-wozny
mateusz-wozny committed May 17, 2024
commit 9d872b6cef8a95cef1f70d8e57e2c7a3ad5b848f
3,660 changes: 1,830 additions & 1,830 deletions examples/datasets/analysis.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

338 changes: 162 additions & 176 deletions examples/ensemble/SOUPBagging.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,179 +1,165 @@
{
"cells": [
{
"cell_type": "markdown",
"source": [
"Unzip datasets and prepare data:"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": 4,
"outputs": [],
"source": [
"import os\n",
"\n",
"import seaborn as sns\n",
"from imblearn.metrics import geometric_mean_score\n",
"from sklearn.model_selection import cross_val_score, ShuffleSplit\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"from sklearn.pipeline import make_pipeline\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"from multi_imbalance.datasets import load_datasets\n",
"from multi_imbalance.ensemble.soup_bagging import SOUPBagging\n",
"from multi_imbalance.utils.data import load_arff_dataset\n",
"from multi_imbalance.utils.min_int_maj import maj_int_min\n",
"\n",
"%matplotlib inline\n",
"sns.set_style(\"darkgrid\")"
],
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
}
},
{
"cell_type": "code",
"execution_count": 5,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[0.49 0.29 0.48 0.5 0.56 0.24 0.35]\n",
" [0.07 0.4 0.48 0.5 0.54 0.35 0.44]\n",
" [0.56 0.4 0.48 0.5 0.49 0.37 0.46]\n",
" [0.59 0.49 0.48 0.5 0.52 0.45 0.36]\n",
" [0.23 0.32 0.48 0.5 0.55 0.25 0.35]]\n",
"[0 0 0 0 0]\n"
]
}
],
"source": [
"dataset = load_datasets()[\"new_ecoli\"]\n",
"\n",
"X, y = dataset.data, dataset.target\n",
"print(X[:5])\n",
"print(y[:5])"
],
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
}
},
{
"cell_type": "code",
"execution_count": 6,
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)"
],
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
}
},
{
"cell_type": "code",
"execution_count": 7,
"outputs": [
{
"data": {
"text/plain": "0.7550748879971014"
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"clf = KNeighborsClassifier()\n",
"vote_classifier = SOUPBagging(\n",
" clf, n_classifiers=50, maj_int_min=maj_int_min[\"new_ecoli\"]\n",
")\n",
"vote_classifier.fit(X_train, y_train)\n",
"y_pred = vote_classifier.predict(X_test)\n",
"geometric_mean_score(y_test, y_pred, correction=0.001)"
],
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
}
},
{
"cell_type": "code",
"execution_count": 8,
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/plutasnyy/anaconda3/envs/multi-imbalance/lib/python3.7/site-packages/sklearn/base.py:197: FutureWarning: From version 0.24, get_params will raise an AttributeError if a parameter cannot be retrieved as an instance attribute. Previously it would return None.\n",
" FutureWarning)\n",
"/home/plutasnyy/anaconda3/envs/multi-imbalance/lib/python3.7/site-packages/sklearn/base.py:197: FutureWarning: From version 0.24, get_params will raise an AttributeError if a parameter cannot be retrieved as an instance attribute. Previously it would return None.\n",
" FutureWarning)\n",
"/home/plutasnyy/anaconda3/envs/multi-imbalance/lib/python3.7/site-packages/sklearn/base.py:197: FutureWarning: From version 0.24, get_params will raise an AttributeError if a parameter cannot be retrieved as an instance attribute. Previously it would return None.\n",
" FutureWarning)\n",
"/home/plutasnyy/anaconda3/envs/multi-imbalance/lib/python3.7/site-packages/sklearn/base.py:197: FutureWarning: From version 0.24, get_params will raise an AttributeError if a parameter cannot be retrieved as an instance attribute. Previously it would return None.\n",
" FutureWarning)\n",
"/home/plutasnyy/anaconda3/envs/multi-imbalance/lib/python3.7/site-packages/sklearn/base.py:197: FutureWarning: From version 0.24, get_params will raise an AttributeError if a parameter cannot be retrieved as an instance attribute. Previously it would return None.\n",
" FutureWarning)\n"
]
"cells": [
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"Unzip datasets and prepare data:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"import os\n",
"\n",
"import seaborn as sns\n",
"from imblearn.metrics import geometric_mean_score\n",
"from sklearn.model_selection import cross_val_score, ShuffleSplit\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"from sklearn.pipeline import make_pipeline\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"from multi_imbalance.datasets import load_datasets\n",
"from multi_imbalance.ensemble.soup_bagging import SOUPBagging\n",
"from multi_imbalance.utils.data import load_arff_dataset\n",
"from multi_imbalance.utils.min_int_maj import maj_int_min\n",
"\n",
"%matplotlib inline\n",
"sns.set_style(\"darkgrid\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[0.49 0.29 0.48 0.5 0.56 0.24 0.35]\n",
" [0.07 0.4 0.48 0.5 0.54 0.35 0.44]\n",
" [0.56 0.4 0.48 0.5 0.49 0.37 0.46]\n",
" [0.59 0.49 0.48 0.5 0.52 0.45 0.36]\n",
" [0.23 0.32 0.48 0.5 0.55 0.25 0.35]]\n",
"[0 0 0 0 0]\n"
]
}
],
"source": [
"dataset = load_datasets()[\"new_ecoli\"]\n",
"\n",
"X, y = dataset.data, dataset.target\n",
"print(X[:5])\n",
"print(y[:5])"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"data": {
"text/plain": [
"0.7784345944274128"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"clf = KNeighborsClassifier()\n",
"vote_classifier = SOUPBagging(\n",
" clf, n_classifiers=50, maj_int_min=maj_int_min[\"new_ecoli\"]\n",
")\n",
"vote_classifier.fit(X_train, y_train)\n",
"y_pred = vote_classifier.predict(X_test)\n",
"geometric_mean_score(y_test, y_pred, correction=0.001)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[0.85148515 0.8019802 0.89108911 0.84158416 0.86138614]\n"
]
}
],
"source": [
"X, y = load_arff_dataset(f\"{os.getcwd()}/../../data/arff/new_ecoli.arff\")\n",
"clf = make_pipeline(StandardScaler(), SOUPBagging())\n",
"cv = ShuffleSplit(n_splits=5, test_size=0.3, random_state=0)\n",
"print(cross_val_score(clf, X, y, cv=cv))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.2"
}
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[0.85148515 0.8019802 0.89108911 0.84158416 0.86138614]\n"
]
}
],
"source": [
"X, y = load_arff_dataset(f\"{os.getcwd()}/../../data/arff/new_ecoli.arff\")\n",
"clf = make_pipeline(StandardScaler(), SOUPBagging())\n",
"cv = ShuffleSplit(n_splits=5, test_size=0.3, random_state=0)\n",
"print(cross_val_score(clf, X, y, cv=cv))"
],
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
}
}
],
"metadata": {
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
},
"kernelspec": {
"name": "python3",
"language": "python",
"display_name": "Python 3"
}
},
"nbformat": 4,
"nbformat_minor": 0
"nbformat": 4,
"nbformat_minor": 0
}
Loading
Loading