mirror of
https://github.com/Doctorado-ML/STree.git
synced 2025-08-15 15:36:00 +00:00
Put pandas requirements in notebooks clean requirements.txt
This commit is contained in:
Ricardo Montañana Gómez
committed by
GitHub
GitHub
parent
147dad684c
commit
f438124057
@@ -20,15 +20,13 @@ pip install git+https://github.com/doctorado-ml/stree
|
||||
|
||||
- [](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/benchmark.ipynb) Benchmark
|
||||
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
|
||||
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Test features
|
||||
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/adaboost.ipynb) Adaboost
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
|
||||
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/gridsearch.ipynb) Gridsearch
|
||||
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test_graphs.ipynb) Test Graphics
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/ensemble.ipynb) Ensembles
|
||||
|
||||
## Hyperparameters
|
||||
|
||||
|
||||
@@ -17,23 +17,25 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#\n",
|
||||
"# Google Colab setup\n",
|
||||
"#\n",
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree"
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree\n",
|
||||
"!pip install pandas"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import datetime, time\n",
|
||||
"import os\n",
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
@@ -47,11 +49,10 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"if not os.path.isfile('data/creditcard.csv'):\n",
|
||||
" !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
|
||||
" !tar xzf creditcard.tgz"
|
||||
@@ -66,19 +67,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"2021-01-14 11:30:51\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(datetime.date.today(), time.strftime(\"%H:%M:%S\"))"
|
||||
]
|
||||
@@ -92,7 +85,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -104,20 +97,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Fraud: 0.173% 492\n",
|
||||
"Valid: 99.827% 284,315\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
|
||||
"print(\"Valid: {0:.3f}% {1:,}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))"
|
||||
@@ -125,7 +109,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -137,20 +121,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"X shape: (284807, 29)\n",
|
||||
"y shape: (284807,)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Remove unneeded features\n",
|
||||
"y = df.Class.values\n",
|
||||
@@ -167,7 +142,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -178,7 +153,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -188,7 +163,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -198,7 +173,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -208,7 +183,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -218,7 +193,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -235,7 +210,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -260,194 +235,15 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"************************** Linear Tree **********************\n",
|
||||
"Train Model Linear Tree took: 10.25 seconds\n",
|
||||
"=========== Linear Tree - Train 199,364 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 1.000000 1.000000 1.000000 199020\n",
|
||||
" 1 1.000000 1.000000 1.000000 344\n",
|
||||
"\n",
|
||||
" accuracy 1.000000 199364\n",
|
||||
" macro avg 1.000000 1.000000 1.000000 199364\n",
|
||||
"weighted avg 1.000000 1.000000 1.000000 199364\n",
|
||||
"\n",
|
||||
"=========== Linear Tree - Test 85,443 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 0.999578 0.999613 0.999596 85295\n",
|
||||
" 1 0.772414 0.756757 0.764505 148\n",
|
||||
"\n",
|
||||
" accuracy 0.999192 85443\n",
|
||||
" macro avg 0.885996 0.878185 0.882050 85443\n",
|
||||
"weighted avg 0.999184 0.999192 0.999188 85443\n",
|
||||
"\n",
|
||||
"Confusion Matrix in Train\n",
|
||||
"[[199020 0]\n",
|
||||
" [ 0 344]]\n",
|
||||
"Confusion Matrix in Test\n",
|
||||
"[[85262 33]\n",
|
||||
" [ 36 112]]\n",
|
||||
"************************** Naive Bayes **********************\n",
|
||||
"Train Model Naive Bayes took: 0.09943 seconds\n",
|
||||
"=========== Naive Bayes - Train 199,364 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 0.999692 0.978238 0.988849 199020\n",
|
||||
" 1 0.061538 0.825581 0.114539 344\n",
|
||||
"\n",
|
||||
" accuracy 0.977975 199364\n",
|
||||
" macro avg 0.530615 0.901910 0.551694 199364\n",
|
||||
"weighted avg 0.998073 0.977975 0.987340 199364\n",
|
||||
"\n",
|
||||
"=========== Naive Bayes - Test 85,443 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 0.999712 0.977994 0.988734 85295\n",
|
||||
" 1 0.061969 0.837838 0.115403 148\n",
|
||||
"\n",
|
||||
" accuracy 0.977751 85443\n",
|
||||
" macro avg 0.530841 0.907916 0.552068 85443\n",
|
||||
"weighted avg 0.998088 0.977751 0.987221 85443\n",
|
||||
"\n",
|
||||
"Confusion Matrix in Train\n",
|
||||
"[[194689 4331]\n",
|
||||
" [ 60 284]]\n",
|
||||
"Confusion Matrix in Test\n",
|
||||
"[[83418 1877]\n",
|
||||
" [ 24 124]]\n",
|
||||
"************************** Stree (SVM Tree) **********************\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/rmontanana/.virtualenvs/general/lib/python3.8/site-packages/sklearn/svm/_base.py:976: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
|
||||
" warnings.warn(\"Liblinear failed to converge, increase \"\n",
|
||||
"/Users/rmontanana/.virtualenvs/general/lib/python3.8/site-packages/sklearn/svm/_base.py:976: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
|
||||
" warnings.warn(\"Liblinear failed to converge, increase \"\n",
|
||||
"/Users/rmontanana/.virtualenvs/general/lib/python3.8/site-packages/sklearn/svm/_base.py:976: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
|
||||
" warnings.warn(\"Liblinear failed to converge, increase \"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Train Model Stree (SVM Tree) took: 28.47 seconds\n",
|
||||
"=========== Stree (SVM Tree) - Train 199,364 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 0.999623 0.999864 0.999744 199020\n",
|
||||
" 1 0.908784 0.781977 0.840625 344\n",
|
||||
"\n",
|
||||
" accuracy 0.999488 199364\n",
|
||||
" macro avg 0.954204 0.890921 0.920184 199364\n",
|
||||
"weighted avg 0.999467 0.999488 0.999469 199364\n",
|
||||
"\n",
|
||||
"=========== Stree (SVM Tree) - Test 85,443 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 0.999637 0.999918 0.999777 85295\n",
|
||||
" 1 0.943548 0.790541 0.860294 148\n",
|
||||
"\n",
|
||||
" accuracy 0.999555 85443\n",
|
||||
" macro avg 0.971593 0.895229 0.930036 85443\n",
|
||||
"weighted avg 0.999540 0.999555 0.999536 85443\n",
|
||||
"\n",
|
||||
"Confusion Matrix in Train\n",
|
||||
"[[198993 27]\n",
|
||||
" [ 75 269]]\n",
|
||||
"Confusion Matrix in Test\n",
|
||||
"[[85288 7]\n",
|
||||
" [ 31 117]]\n",
|
||||
"************************** Neural Network **********************\n",
|
||||
"Train Model Neural Network took: 9.76 seconds\n",
|
||||
"=========== Neural Network - Train 199,364 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 0.999247 0.999844 0.999545 199020\n",
|
||||
" 1 0.862222 0.563953 0.681898 344\n",
|
||||
"\n",
|
||||
" accuracy 0.999092 199364\n",
|
||||
" macro avg 0.930734 0.781899 0.840722 199364\n",
|
||||
"weighted avg 0.999010 0.999092 0.998997 199364\n",
|
||||
"\n",
|
||||
"=========== Neural Network - Test 85,443 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 0.999356 0.999871 0.999613 85295\n",
|
||||
" 1 0.894231 0.628378 0.738095 148\n",
|
||||
"\n",
|
||||
" accuracy 0.999228 85443\n",
|
||||
" macro avg 0.946793 0.814125 0.868854 85443\n",
|
||||
"weighted avg 0.999173 0.999228 0.999160 85443\n",
|
||||
"\n",
|
||||
"Confusion Matrix in Train\n",
|
||||
"[[198989 31]\n",
|
||||
" [ 150 194]]\n",
|
||||
"Confusion Matrix in Test\n",
|
||||
"[[85284 11]\n",
|
||||
" [ 55 93]]\n",
|
||||
"************************** SVC (linear) **********************\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/rmontanana/.virtualenvs/general/lib/python3.8/site-packages/sklearn/svm/_base.py:976: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
|
||||
" warnings.warn(\"Liblinear failed to converge, increase \"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Train Model SVC (linear) took: 8.207 seconds\n",
|
||||
"=========== SVC (linear) - Train 199,364 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 0.999237 0.999859 0.999548 199020\n",
|
||||
" 1 0.872727 0.558140 0.680851 344\n",
|
||||
"\n",
|
||||
" accuracy 0.999097 199364\n",
|
||||
" macro avg 0.935982 0.778999 0.840199 199364\n",
|
||||
"weighted avg 0.999018 0.999097 0.998998 199364\n",
|
||||
"\n",
|
||||
"=========== SVC (linear) - Test 85,443 samples =============\n",
|
||||
" precision recall f1-score support\n",
|
||||
"\n",
|
||||
" 0 0.999344 0.999894 0.999619 85295\n",
|
||||
" 1 0.910891 0.621622 0.738956 148\n",
|
||||
"\n",
|
||||
" accuracy 0.999239 85443\n",
|
||||
" macro avg 0.955117 0.810758 0.869287 85443\n",
|
||||
"weighted avg 0.999191 0.999239 0.999168 85443\n",
|
||||
"\n",
|
||||
"Confusion Matrix in Train\n",
|
||||
"[[198992 28]\n",
|
||||
" [ 152 192]]\n",
|
||||
"Confusion Matrix in Test\n",
|
||||
"[[85286 9]\n",
|
||||
" [ 56 92]]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Train & Test models\n",
|
||||
"models = {\n",
|
||||
" 'Linear Tree':linear_tree, 'Naive Bayes': naive_bayes, 'Stree (SVM Tree)': stree, \n",
|
||||
" 'Linear Tree':linear_tree, 'Naive Bayes': naive_bayes, 'Stree ': stree, \n",
|
||||
" 'Neural Network': mlp, 'SVC (linear)': svc\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
@@ -464,26 +260,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"**************************************************************************************************************\n",
|
||||
"*The best f1 model is Stree (SVM Tree), with a f1 score: 0.8603 in 28.4743 seconds with 0.7 samples in train dataset\n",
|
||||
"**************************************************************************************************************\n",
|
||||
"Model: Linear Tree\t Time: 10.25 seconds\t f1: 0.7645\n",
|
||||
"Model: Naive Bayes\t Time: 0.10 seconds\t f1: 0.1154\n",
|
||||
"Model: Stree (SVM Tree)\t Time: 28.47 seconds\t f1: 0.8603\n",
|
||||
"Model: Neural Network\t Time: 9.76 seconds\t f1: 0.7381\n",
|
||||
"Model: SVC (linear)\t Time: 8.21 seconds\t f1: 0.739\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"*\"*110)\n",
|
||||
"print(f\"*The best f1 model is {best_model}, with a f1 score: {best_f1:.4} in {best_time:.6} seconds with {train_size:,} samples in train dataset\")\n",
|
||||
@@ -508,32 +289,9 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'C': 0.01,\n",
|
||||
" 'criterion': 'entropy',\n",
|
||||
" 'degree': 3,\n",
|
||||
" 'gamma': 'scale',\n",
|
||||
" 'kernel': 'linear',\n",
|
||||
" 'max_depth': None,\n",
|
||||
" 'max_features': None,\n",
|
||||
" 'max_iter': 1000.0,\n",
|
||||
" 'min_samples_split': 0,\n",
|
||||
" 'random_state': 2020,\n",
|
||||
" 'split_criteria': 'impurity',\n",
|
||||
" 'splitter': 'random',\n",
|
||||
" 'tol': 0.0001}"
|
||||
]
|
||||
},
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"stree.get_params()"
|
||||
]
|
||||
@@ -556,7 +314,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.2"
|
||||
"version": "3.8.2-final"
|
||||
},
|
||||
"toc": {
|
||||
"base_numbering": 1,
|
||||
@@ -610,4 +368,4 @@
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
}
|
||||
@@ -17,38 +17,43 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#\n",
|
||||
"# Google Colab setup\n",
|
||||
"#\n",
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree"
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree\n",
|
||||
"!pip install pandas"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import time\n",
|
||||
"import os\n",
|
||||
"import random\n",
|
||||
"import warnings\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np\n",
|
||||
"from sklearn.ensemble import AdaBoostClassifier, BaggingClassifier\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"from sklearn.exceptions import ConvergenceWarning\n",
|
||||
"from stree import Stree\n",
|
||||
"\n",
|
||||
"warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"if not os.path.isfile('data/creditcard.csv'):\n",
|
||||
" !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
|
||||
" !tar xzf creditcard.tgz"
|
||||
@@ -56,30 +61,15 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Fraud: 0.173% 492\n",
|
||||
"Valid: 99.827% 284315\n",
|
||||
"X.shape (100492, 28) y.shape (100492,)\n",
|
||||
"Fraud: 0.651% 654\n",
|
||||
"Valid: 99.349% 99838\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"random_state=1\n",
|
||||
"\n",
|
||||
"def load_creditcard(n_examples=0):\n",
|
||||
" import pandas as pd\n",
|
||||
" import numpy as np\n",
|
||||
" import random\n",
|
||||
" df = pd.read_csv('data/creditcard.csv')\n",
|
||||
" print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
|
||||
" print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
|
||||
@@ -130,21 +120,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Score Train: 0.9984504719663368\n",
|
||||
"Score Test: 0.9983415151917209\n",
|
||||
"Took 26.09 seconds\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"now = time.time()\n",
|
||||
"clf = Stree(max_depth=3, random_state=random_state, max_iter=1e3)\n",
|
||||
@@ -163,7 +143,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -174,21 +154,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Kernel: linear\tTime: 43.49 seconds\tScore Train: 0.9980098\tScore Test: 0.9980762\n",
|
||||
"Kernel: rbf\tTime: 8.86 seconds\tScore Train: 0.9934891\tScore Test: 0.9934987\n",
|
||||
"Kernel: poly\tTime: 41.14 seconds\tScore Train: 0.9972279\tScore Test: 0.9973133\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for kernel in ['linear', 'rbf', 'poly']:\n",
|
||||
" now = time.time()\n",
|
||||
@@ -208,7 +178,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -219,21 +189,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Kernel: linear\tTime: 187.51 seconds\tScore Train: 0.9984505\tScore Test: 0.9983083\n",
|
||||
"Kernel: rbf\tTime: 73.65 seconds\tScore Train: 0.9993461\tScore Test: 0.9985074\n",
|
||||
"Kernel: poly\tTime: 52.19 seconds\tScore Train: 0.9993461\tScore Test: 0.9987727\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for kernel in ['linear', 'rbf', 'poly']:\n",
|
||||
" now = time.time()\n",
|
||||
@@ -261,9 +221,9 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.2"
|
||||
"version": "3.8.2-final"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
}
|
||||
@@ -17,24 +17,27 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#\n",
|
||||
"# Google Colab setup\n",
|
||||
"#\n",
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree"
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree\n",
|
||||
"!pip install pandas"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import time\n",
|
||||
"import random\n",
|
||||
"import warnings\n",
|
||||
"import os\n",
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"from sklearn.svm import SVC\n",
|
||||
@@ -42,6 +45,7 @@
|
||||
"from sklearn.utils.estimator_checks import check_estimator\n",
|
||||
"from sklearn.datasets import make_classification, load_iris, load_wine\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"from sklearn.utils.class_weight import compute_sample_weight\n",
|
||||
"from sklearn.exceptions import ConvergenceWarning\n",
|
||||
"from stree import Stree\n",
|
||||
"warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)"
|
||||
@@ -49,13 +53,12 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"if not os.path.isfile('data/creditcard.csv'):\n",
|
||||
" !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
|
||||
" !tar xzf creditcard.tgz"
|
||||
@@ -63,31 +66,15 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Fraud: 0.173% 492\n",
|
||||
"Valid: 99.827% 284315\n",
|
||||
"X.shape (5492, 28) y.shape (5492,)\n",
|
||||
"Fraud: 9.086% 499\n",
|
||||
"Valid: 90.914% 4993\n",
|
||||
"[0.09079084 0.09079084 0.09079084 0.09079084] [0.09101942 0.09101942 0.09101942 0.09101942]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"random_state=1\n",
|
||||
"\n",
|
||||
"def load_creditcard(n_examples=0):\n",
|
||||
" import pandas as pd\n",
|
||||
" import numpy as np\n",
|
||||
" import random\n",
|
||||
" df = pd.read_csv('data/creditcard.csv')\n",
|
||||
" print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
|
||||
" print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
|
||||
@@ -119,17 +106,8 @@
|
||||
"Xtest = data[1]\n",
|
||||
"ytrain = data[2]\n",
|
||||
"ytest = data[3]\n",
|
||||
"_, data = np.unique(ytrain, return_counts=True)\n",
|
||||
"wtrain = (data[1] / np.sum(data), data[0] / np.sum(data))\n",
|
||||
"_, data = np.unique(ytest, return_counts=True)\n",
|
||||
"wtest = (data[1] / np.sum(data), data[0] / np.sum(data))\n",
|
||||
"# Set weights inverse to its count class in dataset\n",
|
||||
"weights = np.ones(Xtrain.shape[0],)\n",
|
||||
"weights[ytrain==0] = wtrain[0]\n",
|
||||
"weights[ytrain==1] = wtrain[1]\n",
|
||||
"weights_test = np.ones(Xtest.shape[0],)\n",
|
||||
"weights_test[ytest==0] = wtest[0]\n",
|
||||
"weights_test[ytest==1] = wtest[1]\n",
|
||||
"weights = compute_sample_weight(\"balanced\", ytrain)\n",
|
||||
"weights_test = compute_sample_weight(\"balanced\", ytest)\n",
|
||||
"print(weights[:4], weights_test[:4])"
|
||||
]
|
||||
},
|
||||
@@ -150,22 +128,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Accuracy of Train without weights 0.9849115504682622\n",
|
||||
"Accuracy of Train with weights 0.9849115504682622\n",
|
||||
"Accuracy of Tests without weights 0.9848300970873787\n",
|
||||
"Accuracy of Tests with weights 0.9805825242718447\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"C = 23\n",
|
||||
"print(\"Accuracy of Train without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtrain, ytrain))\n",
|
||||
@@ -184,21 +151,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Time: 26.59s\tKernel: linear\tAccuracy_train: 0.9846514047866806\tAccuracy_test: 0.9848300970873787\n",
|
||||
"Time: 0.56s\tKernel: rbf\tAccuracy_train: 0.9947970863683663\tAccuracy_test: 0.9866504854368932\n",
|
||||
"Time: 0.23s\tKernel: poly\tAccuracy_train: 0.9955775234131113\tAccuracy_test: 0.9824029126213593\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"random_state=1\n",
|
||||
"for kernel in ['linear', 'rbf', 'poly']:\n",
|
||||
@@ -219,77 +176,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"************** C=0.001 ****************************\n",
|
||||
"Classifier's accuracy (train): 0.9823\n",
|
||||
"Classifier's accuracy (test) : 0.9836\n",
|
||||
"root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4391 counts=(array([0, 1]), array([3495, 349]))\n",
|
||||
"root - Down, <cgaf> - Leaf class=0 belief= 0.981455 impurity=0.1332 counts=(array([0, 1]), array([3493, 66]))\n",
|
||||
"root - Up, <cgaf> - Leaf class=1 belief= 0.992982 impurity=0.0603 counts=(array([0, 1]), array([ 2, 283]))\n",
|
||||
"\n",
|
||||
"**************************************************\n",
|
||||
"************** C=0.01 ****************************\n",
|
||||
"Classifier's accuracy (train): 0.9834\n",
|
||||
"Classifier's accuracy (test) : 0.9842\n",
|
||||
"root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4391 counts=(array([0, 1]), array([3495, 349]))\n",
|
||||
"root - Down, <cgaf> - Leaf class=0 belief= 0.982288 impurity=0.1284 counts=(array([0, 1]), array([3494, 63]))\n",
|
||||
"root - Up, <cgaf> - Leaf class=1 belief= 0.996516 impurity=0.0335 counts=(array([0, 1]), array([ 1, 286]))\n",
|
||||
"\n",
|
||||
"**************************************************\n",
|
||||
"************** C=1 ****************************\n",
|
||||
"Classifier's accuracy (train): 0.9844\n",
|
||||
"Classifier's accuracy (test) : 0.9848\n",
|
||||
"root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4391 counts=(array([0, 1]), array([3495, 349]))\n",
|
||||
"root - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1236 counts=(array([0, 1]), array([3493, 60]))\n",
|
||||
"root - Down - Down, <cgaf> - Leaf class=0 belief= 0.983108 impurity=0.1236 counts=(array([0, 1]), array([3492, 60]))\n",
|
||||
"root - Down - Up, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([1]))\n",
|
||||
"root - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0593 counts=(array([0, 1]), array([ 2, 289]))\n",
|
||||
"root - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([2]))\n",
|
||||
"root - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([289]))\n",
|
||||
"\n",
|
||||
"**************************************************\n",
|
||||
"************** C=5 ****************************\n",
|
||||
"Classifier's accuracy (train): 0.9847\n",
|
||||
"Classifier's accuracy (test) : 0.9848\n",
|
||||
"root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4391 counts=(array([0, 1]), array([3495, 349]))\n",
|
||||
"root - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1236 counts=(array([0, 1]), array([3493, 60]))\n",
|
||||
"root - Down - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1236 counts=(array([0, 1]), array([3492, 60]))\n",
|
||||
"root - Down - Down - Down, <cgaf> - Leaf class=0 belief= 0.983385 impurity=0.1220 counts=(array([0, 1]), array([3492, 59]))\n",
|
||||
"root - Down - Down - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([1]))\n",
|
||||
"root - Down - Up, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([1]))\n",
|
||||
"root - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0593 counts=(array([0, 1]), array([ 2, 289]))\n",
|
||||
"root - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([2]))\n",
|
||||
"root - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([289]))\n",
|
||||
"\n",
|
||||
"**************************************************\n",
|
||||
"************** C=17 ****************************\n",
|
||||
"Classifier's accuracy (train): 0.9847\n",
|
||||
"Classifier's accuracy (test) : 0.9848\n",
|
||||
"root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4391 counts=(array([0, 1]), array([3495, 349]))\n",
|
||||
"root - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1236 counts=(array([0, 1]), array([3493, 60]))\n",
|
||||
"root - Down - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1220 counts=(array([0, 1]), array([3492, 59]))\n",
|
||||
"root - Down - Down - Down, <cgaf> - Leaf class=0 belief= 0.983380 impurity=0.1220 counts=(array([0, 1]), array([3491, 59]))\n",
|
||||
"root - Down - Down - Up, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([1]))\n",
|
||||
"root - Down - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=1.0000 counts=(array([0, 1]), array([1, 1]))\n",
|
||||
"root - Down - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([1]))\n",
|
||||
"root - Down - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([1]))\n",
|
||||
"root - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0593 counts=(array([0, 1]), array([ 2, 289]))\n",
|
||||
"root - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([2]))\n",
|
||||
"root - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([289]))\n",
|
||||
"\n",
|
||||
"**************************************************\n",
|
||||
"59.0161 secs\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"t = time.time()\n",
|
||||
"for C in (.001, .01, 1, 5, 17):\n",
|
||||
@@ -313,29 +204,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4391 counts=(array([0, 1]), array([3495, 349]))\n",
|
||||
"root - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1236 counts=(array([0, 1]), array([3493, 60]))\n",
|
||||
"root - Down - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1220 counts=(array([0, 1]), array([3492, 59]))\n",
|
||||
"root - Down - Down - Down, <cgaf> - Leaf class=0 belief= 0.983380 impurity=0.1220 counts=(array([0, 1]), array([3491, 59]))\n",
|
||||
"root - Down - Down - Up, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([1]))\n",
|
||||
"root - Down - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=1.0000 counts=(array([0, 1]), array([1, 1]))\n",
|
||||
"root - Down - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([1]))\n",
|
||||
"root - Down - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([1]))\n",
|
||||
"root - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0593 counts=(array([0, 1]), array([ 2, 289]))\n",
|
||||
"root - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([2]))\n",
|
||||
"root - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([289]))\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#check iterator\n",
|
||||
"for i in list(clf):\n",
|
||||
@@ -344,29 +217,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4391 counts=(array([0, 1]), array([3495, 349]))\n",
|
||||
"root - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1236 counts=(array([0, 1]), array([3493, 60]))\n",
|
||||
"root - Down - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1220 counts=(array([0, 1]), array([3492, 59]))\n",
|
||||
"root - Down - Down - Down, <cgaf> - Leaf class=0 belief= 0.983380 impurity=0.1220 counts=(array([0, 1]), array([3491, 59]))\n",
|
||||
"root - Down - Down - Up, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([1]))\n",
|
||||
"root - Down - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=1.0000 counts=(array([0, 1]), array([1, 1]))\n",
|
||||
"root - Down - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([1]))\n",
|
||||
"root - Down - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([1]))\n",
|
||||
"root - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0593 counts=(array([0, 1]), array([ 2, 289]))\n",
|
||||
"root - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([2]))\n",
|
||||
"root - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([289]))\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#check iterator again\n",
|
||||
"for i in clf:\n",
|
||||
@@ -382,75 +237,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"1 functools.partial(<function check_no_attributes_set_in_init at 0x16817f670>, 'Stree')\n",
|
||||
"2 functools.partial(<function check_estimators_dtypes at 0x168179820>, 'Stree')\n",
|
||||
"3 functools.partial(<function check_fit_score_takes_y at 0x168179700>, 'Stree')\n",
|
||||
"4 functools.partial(<function check_sample_weights_pandas_series at 0x168174040>, 'Stree')\n",
|
||||
"5 functools.partial(<function check_sample_weights_not_an_array at 0x168174160>, 'Stree')\n",
|
||||
"6 functools.partial(<function check_sample_weights_list at 0x168174280>, 'Stree')\n",
|
||||
"7 functools.partial(<function check_sample_weights_shape at 0x1681743a0>, 'Stree')\n",
|
||||
"8 functools.partial(<function check_sample_weights_invariance at 0x1681744c0>, 'Stree', kind='ones')\n",
|
||||
"10 functools.partial(<function check_estimators_fit_returns_self at 0x16817b8b0>, 'Stree')\n",
|
||||
"11 functools.partial(<function check_estimators_fit_returns_self at 0x16817b8b0>, 'Stree', readonly_memmap=True)\n",
|
||||
"12 functools.partial(<function check_complex_data at 0x168174670>, 'Stree')\n",
|
||||
"13 functools.partial(<function check_dtype_object at 0x1681745e0>, 'Stree')\n",
|
||||
"14 functools.partial(<function check_estimators_empty_data_messages at 0x1681799d0>, 'Stree')\n",
|
||||
"15 functools.partial(<function check_pipeline_consistency at 0x1681795e0>, 'Stree')\n",
|
||||
"16 functools.partial(<function check_estimators_nan_inf at 0x168179af0>, 'Stree')\n",
|
||||
"17 functools.partial(<function check_estimators_overwrite_params at 0x16817f550>, 'Stree')\n",
|
||||
"18 functools.partial(<function check_estimator_sparse_data at 0x168172ee0>, 'Stree')\n",
|
||||
"19 functools.partial(<function check_estimators_pickle at 0x168179d30>, 'Stree')\n",
|
||||
"20 functools.partial(<function check_estimator_get_tags_default_keys at 0x168181790>, 'Stree')\n",
|
||||
"21 functools.partial(<function check_classifier_data_not_an_array at 0x16817f8b0>, 'Stree')\n",
|
||||
"22 functools.partial(<function check_classifiers_one_label at 0x16817b430>, 'Stree')\n",
|
||||
"23 functools.partial(<function check_classifiers_classes at 0x16817bd30>, 'Stree')\n",
|
||||
"24 functools.partial(<function check_estimators_partial_fit_n_features at 0x168179e50>, 'Stree')\n",
|
||||
"25 functools.partial(<function check_classifiers_train at 0x16817b550>, 'Stree')\n",
|
||||
"26 functools.partial(<function check_classifiers_train at 0x16817b550>, 'Stree', readonly_memmap=True)\n",
|
||||
"27 functools.partial(<function check_classifiers_train at 0x16817b550>, 'Stree', readonly_memmap=True, X_dtype='float32')\n",
|
||||
"28 functools.partial(<function check_classifiers_regression_target at 0x168181280>, 'Stree')\n",
|
||||
"29 functools.partial(<function check_supervised_y_no_nan at 0x1681720d0>, 'Stree')\n",
|
||||
"30 functools.partial(<function check_supervised_y_2d at 0x16817baf0>, 'Stree')\n",
|
||||
"31 functools.partial(<function check_estimators_unfitted at 0x16817b9d0>, 'Stree')\n",
|
||||
"32 functools.partial(<function check_non_transformer_estimators_n_iter at 0x16817fdc0>, 'Stree')\n",
|
||||
"33 functools.partial(<function check_decision_proba_consistency at 0x1681813a0>, 'Stree')\n",
|
||||
"34 functools.partial(<function check_parameters_default_constructible at 0x16817fb80>, 'Stree')\n",
|
||||
"35 functools.partial(<function check_methods_sample_order_invariance at 0x168174d30>, 'Stree')\n",
|
||||
"36 functools.partial(<function check_methods_subset_invariance at 0x168174c10>, 'Stree')\n",
|
||||
"37 functools.partial(<function check_fit2d_1sample at 0x168174e50>, 'Stree')\n",
|
||||
"38 functools.partial(<function check_fit2d_1feature at 0x168174f70>, 'Stree')\n",
|
||||
"39 functools.partial(<function check_get_params_invariance at 0x168181040>, 'Stree')\n",
|
||||
"40 functools.partial(<function check_set_params at 0x168181160>, 'Stree')\n",
|
||||
"41 functools.partial(<function check_dict_unchanged at 0x168174790>, 'Stree')\n",
|
||||
"42 functools.partial(<function check_dont_overwrite_parameters at 0x168174940>, 'Stree')\n",
|
||||
"43 functools.partial(<function check_fit_idempotent at 0x168181550>, 'Stree')\n",
|
||||
"44 functools.partial(<function check_n_features_in at 0x1681815e0>, 'Stree')\n",
|
||||
"45 functools.partial(<function check_fit1d at 0x1681790d0>, 'Stree')\n",
|
||||
"46 functools.partial(<function check_fit2d_predict1d at 0x168174a60>, 'Stree')\n",
|
||||
"47 functools.partial(<function check_requires_y_none at 0x168181670>, 'Stree')\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Make checks one by one\n",
|
||||
"c = 0\n",
|
||||
"checks = check_estimator(Stree(), generate_only=True)\n",
|
||||
"for check in checks:\n",
|
||||
" c += 1\n",
|
||||
" if c == 9:\n",
|
||||
" pass\n",
|
||||
" else:\n",
|
||||
" print(c, check[1])\n",
|
||||
" check[1](check[0])"
|
||||
" print(c, check[1])\n",
|
||||
" check[1](check[0])"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -552,9 +351,9 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.8.2-final"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
}
|
||||
@@ -18,19 +18,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#\n",
|
||||
"# Google Colab setup\n",
|
||||
"#\n",
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree"
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree\n",
|
||||
"!pip install pandas"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
@@ -38,6 +39,10 @@
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import random\n",
|
||||
"import os\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np\n",
|
||||
"from sklearn.ensemble import AdaBoostClassifier\n",
|
||||
"from sklearn.svm import LinearSVC\n",
|
||||
"from sklearn.model_selection import GridSearchCV, train_test_split\n",
|
||||
@@ -46,7 +51,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
@@ -54,7 +59,6 @@
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"if not os.path.isfile('data/creditcard.csv'):\n",
|
||||
" !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
|
||||
" !tar xzf creditcard.tgz"
|
||||
@@ -62,7 +66,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
@@ -70,26 +74,11 @@
|
||||
"outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Fraud: 0.173% 492\n",
|
||||
"Valid: 99.827% 284315\n",
|
||||
"X.shape (1492, 28) y.shape (1492,)\n",
|
||||
"Fraud: 33.177% 495\n",
|
||||
"Valid: 66.823% 997\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"random_state=1\n",
|
||||
"\n",
|
||||
"def load_creditcard(n_examples=0):\n",
|
||||
" import pandas as pd\n",
|
||||
" import numpy as np\n",
|
||||
" import random\n",
|
||||
" df = pd.read_csv('data/creditcard.csv')\n",
|
||||
" print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
|
||||
" print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
|
||||
@@ -132,7 +121,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
@@ -176,39 +165,16 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'C': 1.0,\n",
|
||||
" 'criterion': 'entropy',\n",
|
||||
" 'degree': 3,\n",
|
||||
" 'gamma': 'scale',\n",
|
||||
" 'kernel': 'linear',\n",
|
||||
" 'max_depth': None,\n",
|
||||
" 'max_features': None,\n",
|
||||
" 'max_iter': 100000.0,\n",
|
||||
" 'min_samples_split': 0,\n",
|
||||
" 'random_state': None,\n",
|
||||
" 'split_criteria': 'impurity',\n",
|
||||
" 'splitter': 'random',\n",
|
||||
" 'tol': 0.0001}"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"Stree().get_params()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
@@ -216,69 +182,7 @@
|
||||
"outputId": "7703413a-d563-4289-a13b-532f38f82762",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Fitting 5 folds for each of 1008 candidates, totalling 5040 fits\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[Parallel(n_jobs=-1)]: Using backend LokyBackend with 16 concurrent workers.\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 40 tasks | elapsed: 1.6s\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 130 tasks | elapsed: 3.1s\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 256 tasks | elapsed: 5.5s\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 418 tasks | elapsed: 9.3s\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 616 tasks | elapsed: 18.6s\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 850 tasks | elapsed: 28.2s\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 1120 tasks | elapsed: 35.4s\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 1426 tasks | elapsed: 43.5s\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 1768 tasks | elapsed: 51.3s\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 2146 tasks | elapsed: 1.0min\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 2560 tasks | elapsed: 1.2min\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 3010 tasks | elapsed: 1.4min\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 3496 tasks | elapsed: 1.7min\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 4018 tasks | elapsed: 2.1min\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 4576 tasks | elapsed: 2.6min\n",
|
||||
"[Parallel(n_jobs=-1)]: Done 5040 out of 5040 | elapsed: 2.9min finished\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"GridSearchCV(estimator=AdaBoostClassifier(algorithm='SAMME', random_state=1),\n",
|
||||
" n_jobs=-1,\n",
|
||||
" param_grid=[{'base_estimator': [Stree(C=55, max_depth=7,\n",
|
||||
" random_state=1,\n",
|
||||
" split_criteria='max_samples',\n",
|
||||
" tol=0.1)],\n",
|
||||
" 'base_estimator__C': [1, 7, 55],\n",
|
||||
" 'base_estimator__kernel': ['linear'],\n",
|
||||
" 'base_estimator__max_depth': [3, 5, 7],\n",
|
||||
" 'base_estimator__split_criteria': ['max_samples',\n",
|
||||
" 'impuri...\n",
|
||||
" {'base_estimator': [Stree(random_state=1)],\n",
|
||||
" 'base_estimator__C': [1, 7, 55],\n",
|
||||
" 'base_estimator__gamma': [0.1, 1, 10],\n",
|
||||
" 'base_estimator__kernel': ['rbf'],\n",
|
||||
" 'base_estimator__max_depth': [3, 5, 7],\n",
|
||||
" 'base_estimator__split_criteria': ['max_samples',\n",
|
||||
" 'impurity'],\n",
|
||||
" 'base_estimator__tol': [0.1, 0.01],\n",
|
||||
" 'learning_rate': [0.5, 1],\n",
|
||||
" 'n_estimators': [10, 25]}],\n",
|
||||
" return_train_score=True, verbose=5)"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
|
||||
"grid = GridSearchCV(clf, parameters, verbose=5, n_jobs=-1, return_train_score=True)\n",
|
||||
@@ -287,7 +191,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
@@ -295,20 +199,7 @@
|
||||
"outputId": "285163c8-fa33-4915-8ae7-61c4f7844344",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Best estimator: AdaBoostClassifier(algorithm='SAMME',\n",
|
||||
" base_estimator=Stree(C=55, max_depth=7, random_state=1,\n",
|
||||
" split_criteria='max_samples', tol=0.1),\n",
|
||||
" learning_rate=0.5, n_estimators=25, random_state=1)\n",
|
||||
"Best hyperparameters: {'base_estimator': Stree(C=55, max_depth=7, random_state=1, split_criteria='max_samples', tol=0.1), 'base_estimator__C': 55, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 7, 'base_estimator__split_criteria': 'max_samples', 'base_estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 25}\n",
|
||||
"Best accuracy: 0.9511777695988222\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"Best estimator: \", grid.best_estimator_)\n",
|
||||
"print(\"Best hyperparameters: \", grid.best_params_)\n",
|
||||
@@ -354,9 +245,9 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.2"
|
||||
"version": "3.8.2-final"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
}
|
||||
@@ -1,4 +1 @@
|
||||
numpy
|
||||
scikit-learn
|
||||
pandas
|
||||
ipympl
|
||||
scikit-learn>0.24
|
||||
Reference in New Issue
Block a user