Doctorado-ML/stree
1
1
Fork 0
mirror of https://github.com/Doctorado-ML/STree.git synced 2025-08-15 23:46:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update version and notebooks

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2020-06-28 10:44:29 +02:00
parent be552fdd6c
commit f5706c3159
4 changed files with 89 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
notebooks/benchmark.ipynb
View File

File diff suppressed because one or more lines are too long

118
notebooks/features.ipynb
View File

File diff suppressed because one or more lines are too long

35
notebooks/gridsearch.ipynb
View File

@@ -66,7 +66,8 @@
"id": "z9Q-YUfBDZEq", "id": "z9Q-YUfBDZEq",
"colab_type": "code", "colab_type": "code",
"colab": {}, "colab": {},
"outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b" "outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b",
"tags": []
}, },
"source": [ "source": [
"random_state=1\n", "random_state=1\n",
@@ -112,7 +113,7 @@
{ {
"output_type": "stream", "output_type": "stream",
"name": "stdout", "name": "stdout",
"text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28) y.shape (1492,)\nFraud: 33.244% 496\nValid: 66.756% 996\n" "text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28) y.shape (1492,)\nFraud: 32.976% 492\nValid: 67.024% 1000\n"
} }
] ]
}, },
@@ -137,25 +138,25 @@
" 'learning_rate': [.5, 1],\n", " 'learning_rate': [.5, 1],\n",
" 'base_estimator__tol': [.1, 1e-02],\n", " 'base_estimator__tol': [.1, 1e-02],\n",
" 'base_estimator__max_depth': [3, 5],\n", " 'base_estimator__max_depth': [3, 5],\n",
" 'base_estimator__C': [1, 3],\n", " 'base_estimator__C': [7, 55],\n",
" 'base_estimator__kernel': ['linear', 'poly', 'rbf']\n", " 'base_estimator__kernel': ['linear', 'poly', 'rbf']\n",
"}" "}"
], ],
"execution_count": 9, "execution_count": 5,
"outputs": [] "outputs": []
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"output_type": "execute_result", "output_type": "execute_result",
"data": { "data": {
"text/plain": "{'C': 1.0,\n 'degree': 3,\n 'gamma': 'scale',\n 'kernel': 'linear',\n 'max_depth': None,\n 'max_iter': 1000,\n 'min_samples_split': 0,\n 'random_state': None,\n 'tol': 0.0001}" "text/plain": "{'C': 1.0,\n 'criterion': 'gini',\n 'degree': 3,\n 'gamma': 'scale',\n 'kernel': 'linear',\n 'max_depth': None,\n 'max_features': None,\n 'max_iter': 1000,\n 'min_samples_split': 0,\n 'random_state': None,\n 'split_criteria': 'max_samples',\n 'splitter': 'random',\n 'tol': 0.0001}"
}, },
"metadata": {}, "metadata": {},
"execution_count": 14 "execution_count": 6
} }
], ],
"source": [ "source": [
@@ -168,28 +169,29 @@
"id": "CrcB8o6EDZE5", "id": "CrcB8o6EDZE5",
"colab_type": "code", "colab_type": "code",
"colab": {}, "colab": {},
"outputId": "7703413a-d563-4289-a13b-532f38f82762" "outputId": "7703413a-d563-4289-a13b-532f38f82762",
"tags": []
}, },
"source": [ "source": [
"random_state=2020\n", "random_state=2020\n",
"clf = AdaBoostClassifier(random_state=random_state)\n", "clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
"grid = GridSearchCV(clf, parameters, verbose=10, n_jobs=-1, return_train_score=True)\n", "grid = GridSearchCV(clf, parameters, verbose=10, n_jobs=-1, return_train_score=True)\n",
"grid.fit(Xtrain, ytrain)" "grid.fit(Xtrain, ytrain)"
], ],
"execution_count": 11, "execution_count": 7,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
"name": "stdout", "name": "stdout",
"text": "Fitting 5 folds for each of 96 candidates, totalling 480 fits\n[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 3.6s\n[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 4.2s\n[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 4.8s\n[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 5.3s\n[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 6.2s\n[Parallel(n_jobs=-1)]: Done 45 tasks | elapsed: 7.2s\n[Parallel(n_jobs=-1)]: Done 56 tasks | elapsed: 8.9s\n[Parallel(n_jobs=-1)]: Done 69 tasks | elapsed: 10.7s\n[Parallel(n_jobs=-1)]: Done 82 tasks | elapsed: 12.7s\n[Parallel(n_jobs=-1)]: Done 97 tasks | elapsed: 16.7s\n[Parallel(n_jobs=-1)]: Done 112 tasks | elapsed: 19.4s\n[Parallel(n_jobs=-1)]: Done 129 tasks | elapsed: 24.4s\n[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 29.3s\n[Parallel(n_jobs=-1)]: Done 165 tasks | elapsed: 32.7s\n[Parallel(n_jobs=-1)]: Done 184 tasks | elapsed: 36.4s\n[Parallel(n_jobs=-1)]: Done 205 tasks | elapsed: 39.7s\n[Parallel(n_jobs=-1)]: Done 226 tasks | elapsed: 43.7s\n[Parallel(n_jobs=-1)]: Done 249 tasks | elapsed: 46.6s\n[Parallel(n_jobs=-1)]: Done 272 tasks | elapsed: 48.8s\n[Parallel(n_jobs=-1)]: Done 297 tasks | elapsed: 52.0s\n[Parallel(n_jobs=-1)]: Done 322 tasks | elapsed: 55.9s\n[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.0min\n[Parallel(n_jobs=-1)]: Done 376 tasks | elapsed: 1.2min\n[Parallel(n_jobs=-1)]: Done 405 tasks | elapsed: 1.3min\n[Parallel(n_jobs=-1)]: Done 434 tasks | elapsed: 1.3min\n[Parallel(n_jobs=-1)]: Done 465 tasks | elapsed: 1.4min\n[Parallel(n_jobs=-1)]: Done 480 out of 480 | elapsed: 1.5min finished\n" "text": "Fitting 5 folds for each of 96 candidates, totalling 480 fits\n[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 2.0s\n[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 2.4s\n[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 2.7s\n[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 3.3s\n[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 4.3s\n[Parallel(n_jobs=-1)]: Done 45 tasks | elapsed: 5.3s\n[Parallel(n_jobs=-1)]: Done 56 tasks | elapsed: 6.6s\n[Parallel(n_jobs=-1)]: Done 69 tasks | elapsed: 8.1s\n[Parallel(n_jobs=-1)]: Done 82 tasks | elapsed: 9.4s\n[Parallel(n_jobs=-1)]: Done 97 tasks | elapsed: 10.1s\n[Parallel(n_jobs=-1)]: Done 112 tasks | elapsed: 11.1s\n[Parallel(n_jobs=-1)]: Done 129 tasks | elapsed: 12.3s\n[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 13.6s\n[Parallel(n_jobs=-1)]: Done 165 tasks | elapsed: 14.9s\n[Parallel(n_jobs=-1)]: Done 184 tasks | elapsed: 16.2s\n[Parallel(n_jobs=-1)]: Done 205 tasks | elapsed: 17.6s\n[Parallel(n_jobs=-1)]: Done 226 tasks | elapsed: 19.1s\n[Parallel(n_jobs=-1)]: Done 249 tasks | elapsed: 21.6s\n[Parallel(n_jobs=-1)]: Done 272 tasks | elapsed: 25.9s\n[Parallel(n_jobs=-1)]: Done 297 tasks | elapsed: 30.4s\n[Parallel(n_jobs=-1)]: Done 322 tasks | elapsed: 36.7s\n[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 38.1s\n[Parallel(n_jobs=-1)]: Done 376 tasks | elapsed: 39.6s\n[Parallel(n_jobs=-1)]: Done 405 tasks | elapsed: 41.9s\n[Parallel(n_jobs=-1)]: Done 434 tasks | elapsed: 44.9s\n[Parallel(n_jobs=-1)]: Done 465 tasks | elapsed: 48.2s\n[Parallel(n_jobs=-1)]: Done 480 out of 480 | elapsed: 49.2s finished\n"
}, },
{ {
"output_type": "execute_result", "output_type": "execute_result",
"data": { "data": {
"text/plain": "GridSearchCV(estimator=AdaBoostClassifier(random_state=2020), n_jobs=-1,\n param_grid={'base_estimator': [Stree(C=1, max_depth=3, tol=0.1)],\n 'base_estimator__C': [1, 3],\n 'base_estimator__kernel': ['linear', 'poly', 'rbf'],\n 'base_estimator__max_depth': [3, 5],\n 'base_estimator__tol': [0.1, 0.01],\n 'learning_rate': [0.5, 1], 'n_estimators': [10, 25]},\n return_train_score=True, verbose=10)" "text/plain": "GridSearchCV(estimator=AdaBoostClassifier(algorithm='SAMME', random_state=2020),\n n_jobs=-1,\n param_grid={'base_estimator': [Stree(C=55, max_depth=3, tol=0.01)],\n 'base_estimator__C': [7, 55],\n 'base_estimator__kernel': ['linear', 'poly', 'rbf'],\n 'base_estimator__max_depth': [3, 5],\n 'base_estimator__tol': [0.1, 0.01],\n 'learning_rate': [0.5, 1], 'n_estimators': [10, 25]},\n return_train_score=True, verbose=10)"
}, },
"metadata": {}, "metadata": {},
"execution_count": 11 "execution_count": 7
} }
] ]
}, },
@@ -199,19 +201,20 @@
"id": "ZjX88NoYDZE8", "id": "ZjX88NoYDZE8",
"colab_type": "code", "colab_type": "code",
"colab": {}, "colab": {},
"outputId": "285163c8-fa33-4915-8ae7-61c4f7844344" "outputId": "285163c8-fa33-4915-8ae7-61c4f7844344",
"tags": []
}, },
"source": [ "source": [
"print(\"Best estimator: \", grid.best_estimator_)\n", "print(\"Best estimator: \", grid.best_estimator_)\n",
"print(\"Best hyperparameters: \", grid.best_params_)\n", "print(\"Best hyperparameters: \", grid.best_params_)\n",
"print(\"Best accuracy: \", grid.best_score_)" "print(\"Best accuracy: \", grid.best_score_)"
], ],
"execution_count": 16, "execution_count": 8,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
"name": "stdout", "name": "stdout",
"text": "Best estimator: AdaBoostClassifier(base_estimator=Stree(C=1, max_depth=3, tol=0.1),\n learning_rate=0.5, n_estimators=10, random_state=2020)\nBest hyperparameters: {'base_estimator': Stree(C=1, max_depth=3, tol=0.1), 'base_estimator__C': 1, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 3, 'base_estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 10}\nBest accuracy: 0.9492316893632683\n" "text": "Best estimator: AdaBoostClassifier(algorithm='SAMME',\n base_estimator=Stree(C=55, max_depth=3, tol=0.01),\n learning_rate=0.5, n_estimators=25, random_state=2020)\nBest hyperparameters: {'base_estimator': Stree(C=55, max_depth=3, tol=0.01), 'base_estimator__C': 55, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 3, 'base_estimator__tol': 0.01, 'learning_rate': 0.5, 'n_estimators': 25}\nBest accuracy: 0.9559440559440558\n"
} }
] ]
} }

2
setup.py
View File

@@ -1,6 +1,6 @@
import setuptools import setuptools
__version__ = "0.9rc4" __version__ = "0.9rc5"
__author__ = "Ricardo Montañana Gómez" __author__ = "Ricardo Montañana Gómez"