mirror of
https://github.com/Doctorado-ML/STree.git
synced 2025-08-17 08:26:00 +00:00
#3 Add sample_weights to score, update notebooks
Update readme to use new names of notebooks
This commit is contained in:
12
README.md
12
README.md
@@ -18,21 +18,17 @@ pip install git+https://github.com/doctorado-ml/stree
|
|||||||
|
|
||||||
### Jupyter notebooks
|
### Jupyter notebooks
|
||||||
|
|
||||||
##### Slow launch but better integration
|
* [](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/benchmark.ipynb) Benchmark
|
||||||
|
|
||||||
* [](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/test.ipynb) Test notebook
|
* [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
|
||||||
|
|
||||||
##### Fast launch but have to run first commented out cell for setup
|
* [](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/test.ipynb) Test notebook
|
|
||||||
|
|
||||||
* [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test2.ipynb) Another Test notebook
|
|
||||||
|
|
||||||
* [](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/adaboost.ipynb) Adaboost
|
||||||
|
|
||||||
* [](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/gridsearch.ipynb) Gridsearch
|
||||||
|
|
||||||
* [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test_graphs.ipynb) Test Graphics notebook
|
* [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test_graphs.ipynb) Test Graphics
|
||||||
|
|
||||||
### Command line
|
### Command line
|
||||||
|
|
||||||
|
|||||||
370
notebooks/features.ipynb
Normal file
370
notebooks/features.ipynb
Normal file
@@ -0,0 +1,370 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Test smple_weight, kernels, C, sklearn estimator"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Setup\n",
|
||||||
|
"Uncomment the next cell if STree is not already installed"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"#\n",
|
||||||
|
"# Google Colab setup\n",
|
||||||
|
"#\n",
|
||||||
|
"#!pip install git+https://github.com/doctorado-ml/stree"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"import numpy as np\n",
|
||||||
|
"import pandas as pd\n",
|
||||||
|
"from sklearn.svm import SVC\n",
|
||||||
|
"from sklearn.tree import DecisionTreeClassifier\n",
|
||||||
|
"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 stree import Stree\n",
|
||||||
|
"import time"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 3,
|
||||||
|
"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"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28) y.shape (1492,)\nFraud: 33.177% 495\nValid: 66.823% 997\n"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"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",
|
||||||
|
" y = df.Class\n",
|
||||||
|
" X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
|
||||||
|
" if n_examples > 0:\n",
|
||||||
|
" # Take first n_examples samples\n",
|
||||||
|
" X = X[:n_examples, :]\n",
|
||||||
|
" y = y[:n_examples, :]\n",
|
||||||
|
" else:\n",
|
||||||
|
" # Take all the positive samples with a number of random negatives\n",
|
||||||
|
" if n_examples < 0:\n",
|
||||||
|
" Xt = X[(y == 1).ravel()]\n",
|
||||||
|
" yt = y[(y == 1).ravel()]\n",
|
||||||
|
" indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
|
||||||
|
" X = np.append(Xt, X[indices], axis=0)\n",
|
||||||
|
" y = np.append(yt, y[indices], axis=0)\n",
|
||||||
|
" print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
|
||||||
|
" print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
|
||||||
|
" print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
|
||||||
|
" Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
|
||||||
|
" return Xtrain, Xtest, ytrain, ytest\n",
|
||||||
|
"\n",
|
||||||
|
"# data = load_creditcard(-5000) # Take all true samples + 5000 of the others\n",
|
||||||
|
"# data = load_creditcard(5000) # Take the first 5000 samples\n",
|
||||||
|
"data = load_creditcard(-1000) # Take all the samples\n",
|
||||||
|
"\n",
|
||||||
|
"Xtrain = data[0]\n",
|
||||||
|
"Xtest = data[1]\n",
|
||||||
|
"ytrain = data[2]\n",
|
||||||
|
"ytest = data[3]\n",
|
||||||
|
"# Set weights inverse to its count class in dataset\n",
|
||||||
|
"weights = np.ones(Xtrain.shape[0],) * 1.00244\n",
|
||||||
|
"weights[ytrain==1] = 1.99755\n",
|
||||||
|
"weights_test = np.ones(Xtest.shape[0],) * 1.00244\n",
|
||||||
|
"weights_test[ytest==1] = 1.99755 "
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Tests"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Test smple_weights\n",
|
||||||
|
"Compute accuracy with weights in samples. The weights are set based on the inverse of the number of samples of each class"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 5,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": "Accuracy of Train without weights 0.9722222222222222\nAccuracy of Train with weights 0.9875478927203065\nAccuracy of Tests without weights 0.9508928571428571\nAccuracy of Tests with weights 0.9486607142857143\n"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"C = 23\n",
|
||||||
|
"print(\"Accuracy of Train without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtrain, ytrain))\n",
|
||||||
|
"print(\"Accuracy of Train with weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtrain, ytrain))\n",
|
||||||
|
"print(\"Accuracy of Tests without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtest, ytest))\n",
|
||||||
|
"print(\"Accuracy of Tests with weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtest, ytest))"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Test accuracy with different kernels\n",
|
||||||
|
"Compute accuracy on train and test set with default hyperparmeters of every kernel"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 6,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": "Time: 0.27s\tKernel: linear\tAccuracy_train: 0.9712643678160919\tAccuracy_test: 0.953125\nTime: 0.08s\tKernel: rbf\tAccuracy_train: 0.9932950191570882\tAccuracy_test: 0.9620535714285714\nTime: 0.05s\tKernel: poly\tAccuracy_train: 0.9923371647509579\tAccuracy_test: 0.9419642857142857\n"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"random_state=1\n",
|
||||||
|
"for kernel in ['linear', 'rbf', 'poly']:\n",
|
||||||
|
" now = time.time()\n",
|
||||||
|
" clf = Stree(C=7, kernel=kernel, random_state=random_state).fit(Xtrain, ytrain)\n",
|
||||||
|
" accuracy_train = clf.score(Xtrain, ytrain)\n",
|
||||||
|
" accuracy_test = clf.score(Xtest, ytest)\n",
|
||||||
|
" time_spent = time.time() - now\n",
|
||||||
|
" print(f\"Time: {time_spent:.2f}s\\tKernel: {kernel}\\tAccuracy_train: {accuracy_train}\\tAccuracy_test: {accuracy_test}\")\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Test diferent values of C"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 7,
|
||||||
|
"metadata": {
|
||||||
|
"tags": [
|
||||||
|
"outputPrepend"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": "************** C=0.001 ****************************\nClassifier's accuracy (train): 0.9550\nClassifier's accuracy (test) : 0.9554\nroot\nroot - Down, <cgaf> - Leaf class=1 belief= 0.977636 counts=(array([0, 1]), array([ 7, 306]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.945280 counts=(array([0, 1]), array([691, 40]))\n\n**************************************************\n************** C=0.01 ****************************\nClassifier's accuracy (train): 0.9569\nClassifier's accuracy (test) : 0.9554\nroot\nroot - Down, <cgaf> - Leaf class=1 belief= 0.983923 counts=(array([0, 1]), array([ 5, 306]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.945430 counts=(array([0, 1]), array([693, 40]))\n\n**************************************************\n************** C=1 ****************************\nClassifier's accuracy (train): 0.9665\nClassifier's accuracy (test) : 0.9576\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([311]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([4]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.951989 counts=(array([0, 1]), array([694, 35]))\n\n**************************************************\n************** C=5 ****************************\nClassifier's accuracy (train): 0.9703\nClassifier's accuracy (test) : 0.9509\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([310]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([5]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.957004 counts=(array([0, 1]), array([690, 31]))\n\n**************************************************\n************** C=17 ****************************\nClassifier's accuracy (train): 0.9799\nClassifier's accuracy (test) : 0.9531\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([310]))\nroot - Down - Up\nroot - Down - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([5]))\nroot - Down - Up - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([15]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([9]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([10]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.969653 counts=(array([0, 1]), array([671, 21]))\n\n**************************************************\n0.5032 secs\n"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"t = time.time()\n",
|
||||||
|
"for C in (.001, .01, 1, 5, 17):\n",
|
||||||
|
" clf = Stree(C=C, random_state=random_state)\n",
|
||||||
|
" clf.fit(Xtrain, ytrain)\n",
|
||||||
|
" print(f\"************** C={C} ****************************\")\n",
|
||||||
|
" print(f\"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}\")\n",
|
||||||
|
" print(f\"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}\")\n",
|
||||||
|
" print(clf)\n",
|
||||||
|
" print(f\"**************************************************\")\n",
|
||||||
|
"print(f\"{time.time() - t:.4f} secs\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Test iterator\n",
|
||||||
|
"Check different weays of using the iterator"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([310]))\nroot - Down - Up\nroot - Down - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([5]))\nroot - Down - Up - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([15]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([9]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([10]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.969653 counts=(array([0, 1]), array([671, 21]))\n"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"#check iterator\n",
|
||||||
|
"for i in list(clf):\n",
|
||||||
|
" print(i)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([310]))\nroot - Down - Up\nroot - Down - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([5]))\nroot - Down - Up - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([15]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([9]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([10]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.969653 counts=(array([0, 1]), array([671, 21]))\n"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"#check iterator again\n",
|
||||||
|
"for i in clf:\n",
|
||||||
|
" print(i)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Test STree is a sklearn estimator"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 10,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": "1 functools.partial(<function check_no_attributes_set_in_init at 0x124d443b0>, 'Stree')\n2 functools.partial(<function check_estimators_dtypes at 0x124d3b4d0>, 'Stree')\n3 functools.partial(<function check_fit_score_takes_y at 0x124d3b3b0>, 'Stree')\n4 functools.partial(<function check_sample_weights_pandas_series at 0x124d33cb0>, 'Stree')\n5 functools.partial(<function check_sample_weights_not_an_array at 0x124d33dd0>, 'Stree')\n6 functools.partial(<function check_sample_weights_list at 0x124d33ef0>, 'Stree')\n7 functools.partial(<function check_sample_weights_shape at 0x124d35050>, 'Stree')\n8 functools.partial(<function check_sample_weights_invariance at 0x124d35170>, 'Stree')\n9 functools.partial(<function check_estimators_fit_returns_self at 0x124d3e4d0>, 'Stree')\n10 functools.partial(<function check_estimators_fit_returns_self at 0x124d3e4d0>, 'Stree', readonly_memmap=True)\n11 functools.partial(<function check_complex_data at 0x124d35320>, 'Stree')\n12 functools.partial(<function check_dtype_object at 0x124d35290>, 'Stree')\n13 functools.partial(<function check_estimators_empty_data_messages at 0x124d3b5f0>, 'Stree')\n14 functools.partial(<function check_pipeline_consistency at 0x124d3b290>, 'Stree')\n15 functools.partial(<function check_estimators_nan_inf at 0x124d3b710>, 'Stree')\n16 functools.partial(<function check_estimators_overwrite_params at 0x124d44290>, 'Stree')\n17 functools.partial(<function check_estimator_sparse_data at 0x124d33b90>, 'Stree')\n18 functools.partial(<function check_estimators_pickle at 0x124d3b950>, 'Stree')\n19 functools.partial(<function check_classifier_data_not_an_array at 0x124d445f0>, 'Stree')\n20 functools.partial(<function check_classifiers_one_label at 0x124d3e050>, 'Stree')\n21 functools.partial(<function check_classifiers_classes at 0x124d3ea70>, 'Stree')\n22 functools.partial(<function check_estimators_partial_fit_n_features at 0x124d3ba70>, 'Stree')\n23 functools.partial(<function check_classifiers_train at 0x124d3e170>, 'Stree')\n24 functools.partial(<function check_classifiers_train at 0x124d3e170>, 'Stree', readonly_memmap=True)\n25 functools.partial(<function check_classifiers_train at 0x124d3e170>, 'Stree', readonly_memmap=True, X_dtype='float32')\n26 functools.partial(<function check_classifiers_regression_target at 0x124d480e0>, 'Stree')\n27 functools.partial(<function check_supervised_y_no_nan at 0x124d2d9e0>, 'Stree')\n28 functools.partial(<function check_supervised_y_2d at 0x124d3e710>, 'Stree')\n29 functools.partial(<function check_estimators_unfitted at 0x124d3e5f0>, 'Stree')\n30 functools.partial(<function check_non_transformer_estimators_n_iter at 0x124d44c20>, 'Stree')\n31 functools.partial(<function check_decision_proba_consistency at 0x124d48200>, 'Stree')\n32 functools.partial(<function check_fit2d_predict1d at 0x124d35830>, 'Stree')\n33 functools.partial(<function check_methods_subset_invariance at 0x124d359e0>, 'Stree')\n34 functools.partial(<function check_fit2d_1sample at 0x124d35b00>, 'Stree')\n35 functools.partial(<function check_fit2d_1feature at 0x124d35c20>, 'Stree')\n36 functools.partial(<function check_fit1d at 0x124d35d40>, 'Stree')\n37 functools.partial(<function check_get_params_invariance at 0x124d44e60>, 'Stree')\n38 functools.partial(<function check_set_params at 0x124d44f80>, 'Stree')\n39 functools.partial(<function check_dict_unchanged at 0x124d35440>, 'Stree')\n40 functools.partial(<function check_dont_overwrite_parameters at 0x124d35710>, 'Stree')\n41 functools.partial(<function check_fit_idempotent at 0x124d483b0>, 'Stree')\n42 functools.partial(<function check_n_features_in at 0x124d48440>, 'Stree')\n43 functools.partial(<function check_requires_y_none at 0x124d484d0>, 'Stree')\n"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"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",
|
||||||
|
" print(c, check[1])\n",
|
||||||
|
" check[1](check[0])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# Check if the classifier is a sklearn estimator\n",
|
||||||
|
"check_estimator(Stree())"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Compare to SVM"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 12,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": "== Not Weighted ===\nSVC train score ..: 0.9530651340996169\nSTree train score : 0.960727969348659\nSVC test score ...: 0.9620535714285714\nSTree test score .: 0.9642857142857143\n==== Weighted =====\nSVC train score ..: 0.960727969348659\nSTree train score : 0.960727969348659\nSVC test score ...: 0.953125\nSTree test score .: 0.9553571428571429\n*SVC test score ..: 0.9397723008352139\n*STree test score : 0.9431162390279932\n"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"svc = SVC(C=7, kernel='rbf', gamma=.001, random_state=random_state)\n",
|
||||||
|
"clf = Stree(C=17, kernel='rbf', gamma=.001, random_state=random_state)\n",
|
||||||
|
"svc.fit(Xtrain, ytrain)\n",
|
||||||
|
"clf.fit(Xtrain, ytrain)\n",
|
||||||
|
"print(\"== Not Weighted ===\")\n",
|
||||||
|
"print(\"SVC train score ..:\", svc.score(Xtrain, ytrain))\n",
|
||||||
|
"print(\"STree train score :\", clf.score(Xtrain, ytrain))\n",
|
||||||
|
"print(\"SVC test score ...:\", svc.score(Xtest, ytest))\n",
|
||||||
|
"print(\"STree test score .:\", clf.score(Xtest, ytest))\n",
|
||||||
|
"svc.fit(Xtrain, ytrain, weights)\n",
|
||||||
|
"clf.fit(Xtrain, ytrain, weights)\n",
|
||||||
|
"print(\"==== Weighted =====\")\n",
|
||||||
|
"print(\"SVC train score ..:\", svc.score(Xtrain, ytrain))\n",
|
||||||
|
"print(\"STree train score :\", clf.score(Xtrain, ytrain))\n",
|
||||||
|
"print(\"SVC test score ...:\", svc.score(Xtest, ytest))\n",
|
||||||
|
"print(\"STree test score .:\", clf.score(Xtest, ytest))\n",
|
||||||
|
"print(\"*SVC test score ..:\", svc.score(Xtest, ytest, weights_test))\n",
|
||||||
|
"print(\"*STree test score :\", clf.score(Xtest, ytest, weights_test))"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 13,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": "root\nroot - Down, <cgaf> - Leaf class=1 belief= 0.978056 counts=(array([0, 1]), array([ 7, 312]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.953103 counts=(array([0, 1]), array([691, 34]))\n\n"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"print(clf)"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3.7.6 64-bit ('general': venv)",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.7.6-final"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 2
|
||||||
|
}
|
||||||
@@ -1,337 +0,0 @@
|
|||||||
{
|
|
||||||
"cells": [
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"# Test smple_weight, kernels, C, sklearn estimator"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"# Setup\n",
|
|
||||||
"Uncomment the next cell if STree is not already installed"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 1,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"#\n",
|
|
||||||
"# Google Colab setup\n",
|
|
||||||
"#\n",
|
|
||||||
"#!pip install git+https://github.com/doctorado-ml/stree"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 2,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"import numpy as np\n",
|
|
||||||
"import pandas as pd\n",
|
|
||||||
"from sklearn.svm import SVC\n",
|
|
||||||
"from sklearn.tree import DecisionTreeClassifier\n",
|
|
||||||
"from sklearn.datasets import make_classification, load_iris, load_wine\n",
|
|
||||||
"from sklearn.model_selection import train_test_split\n",
|
|
||||||
"from stree import Stree\n",
|
|
||||||
"import time"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 3,
|
|
||||||
"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"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 4,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"output_type": "stream",
|
|
||||||
"name": "stdout",
|
|
||||||
"text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28) y.shape (1492,)\nFraud: 33.177% 495\nValid: 66.823% 997\n"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"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",
|
|
||||||
" y = df.Class\n",
|
|
||||||
" X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
|
|
||||||
" if n_examples > 0:\n",
|
|
||||||
" # Take first n_examples samples\n",
|
|
||||||
" X = X[:n_examples, :]\n",
|
|
||||||
" y = y[:n_examples, :]\n",
|
|
||||||
" else:\n",
|
|
||||||
" # Take all the positive samples with a number of random negatives\n",
|
|
||||||
" if n_examples < 0:\n",
|
|
||||||
" Xt = X[(y == 1).ravel()]\n",
|
|
||||||
" yt = y[(y == 1).ravel()]\n",
|
|
||||||
" indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
|
|
||||||
" X = np.append(Xt, X[indices], axis=0)\n",
|
|
||||||
" y = np.append(yt, y[indices], axis=0)\n",
|
|
||||||
" print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
|
|
||||||
" print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
|
|
||||||
" print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
|
|
||||||
" Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
|
|
||||||
" return Xtrain, Xtest, ytrain, ytest\n",
|
|
||||||
"\n",
|
|
||||||
"# data = load_creditcard(-5000) # Take all true samples + 5000 of the others\n",
|
|
||||||
"# data = load_creditcard(5000) # Take the first 5000 samples\n",
|
|
||||||
"data = load_creditcard(-1000) # Take all the samples\n",
|
|
||||||
"\n",
|
|
||||||
"Xtrain = data[0]\n",
|
|
||||||
"Xtest = data[1]\n",
|
|
||||||
"ytrain = data[2]\n",
|
|
||||||
"ytest = data[3]\n",
|
|
||||||
"# Set weights inverse to its count class in dataset\n",
|
|
||||||
"weights = np.ones(Xtrain.shape[0],) * 1.00244\n",
|
|
||||||
"weights[ytrain==1] = 1.99755 "
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"# Tests"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"## Test smple_weights\n",
|
|
||||||
"Compute accuracy with weights in samples. The weights are set based on the inverse of the number of samples of each class"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 5,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"output_type": "stream",
|
|
||||||
"name": "stdout",
|
|
||||||
"text": "Accuracy of Train without weights 0.9770114942528736\nAccuracy of Train with weights 0.9818007662835249\nAccuracy of Tests without weights 0.953125\nAccuracy of Tests with weights 0.9419642857142857\n"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"C = 23\n",
|
|
||||||
"print(\"Accuracy of Train without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtrain, ytrain))\n",
|
|
||||||
"print(\"Accuracy of Train with weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtrain, ytrain))\n",
|
|
||||||
"print(\"Accuracy of Tests without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtest, ytest))\n",
|
|
||||||
"print(\"Accuracy of Tests with weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtest, ytest))"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"## Test accuracy with different kernels\n",
|
|
||||||
"Compute accuracy on train and test set with default hyperparmeters of every kernel"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 6,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"output_type": "stream",
|
|
||||||
"name": "stdout",
|
|
||||||
"text": "Time: 0.20s\tKernel: linear\tAccuracy_train: 0.9712643678160919\tAccuracy_test: 0.9575892857142857\nTime: 0.09s\tKernel: rbf\tAccuracy_train: 0.9932950191570882\tAccuracy_test: 0.9620535714285714\nTime: 0.09s\tKernel: poly\tAccuracy_train: 0.9904214559386973\tAccuracy_test: 0.9508928571428571\n"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"random_state=1\n",
|
|
||||||
"for kernel in ['linear', 'rbf', 'poly']:\n",
|
|
||||||
" now = time.time()\n",
|
|
||||||
" clf = Stree(C=7, kernel=kernel, random_state=random_state).fit(Xtrain, ytrain)\n",
|
|
||||||
" accuracy_train = clf.score(Xtrain, ytrain)\n",
|
|
||||||
" accuracy_test = clf.score(Xtest, ytest)\n",
|
|
||||||
" time_spent = time.time() - now\n",
|
|
||||||
" print(f\"Time: {time_spent:.2f}s\\tKernel: {kernel}\\tAccuracy_train: {accuracy_train}\\tAccuracy_test: {accuracy_test}\")\n"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"## Test diferent values of C"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 7,
|
|
||||||
"metadata": {
|
|
||||||
"tags": [
|
|
||||||
"outputPrepend"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"output_type": "stream",
|
|
||||||
"name": "stdout",
|
|
||||||
"text": "************** C=0.001 ****************************\nClassifier's accuracy (train): 0.9550\nClassifier's accuracy (test) : 0.9509\nroot\nroot - Down\nroot - Down - Down, <cgaf> - Leaf class=1 belief= 0.980583 counts=(array([0, 1]), array([ 6, 303]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([2]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up, <cgaf> - Leaf class=0 belief= 0.943836 counts=(array([0, 1]), array([689, 41]))\n\n**************************************************\n************** C=0.01 ****************************\nClassifier's accuracy (train): 0.9569\nClassifier's accuracy (test) : 0.9576\nroot\nroot - Down\nroot - Down - Down, <cgaf> - Leaf class=1 belief= 0.990228 counts=(array([0, 1]), array([ 3, 304]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.942935 counts=(array([0, 1]), array([694, 42]))\n\n**************************************************\n************** C=1 ****************************\nClassifier's accuracy (train): 0.9665\nClassifier's accuracy (test) : 0.9598\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([311]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([4]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.951989 counts=(array([0, 1]), array([694, 35]))\n\n**************************************************\n************** C=5 ****************************\nClassifier's accuracy (train): 0.9674\nClassifier's accuracy (test) : 0.9621\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([312]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([4]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.953039 counts=(array([0, 1]), array([690, 34]))\n\n**************************************************\n************** C=17 ****************************\nClassifier's accuracy (train): 0.9770\nClassifier's accuracy (test) : 0.9509\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([314]))\nroot - Down - Up\nroot - Down - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Down - Up - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([12]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([2]))\nroot - Up - Up - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.965714 counts=(array([0, 1]), array([676, 24]))\n\n**************************************************\n0.9578 secs\n"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"t = time.time()\n",
|
|
||||||
"for C in (.001, .01, 1, 5, 17):\n",
|
|
||||||
" clf = Stree(C=C, random_state=random_state)\n",
|
|
||||||
" clf.fit(Xtrain, ytrain)\n",
|
|
||||||
" print(f\"************** C={C} ****************************\")\n",
|
|
||||||
" print(f\"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}\")\n",
|
|
||||||
" print(f\"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}\")\n",
|
|
||||||
" print(clf)\n",
|
|
||||||
" print(f\"**************************************************\")\n",
|
|
||||||
"print(f\"{time.time() - t:.4f} secs\")"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 8,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"output_type": "stream",
|
|
||||||
"name": "stdout",
|
|
||||||
"text": "[[0.88204928 0.11795072]\n [0.8640131 0.1359869 ]\n [0.94207521 0.05792479]\n [0.90219947 0.09780053]]\n"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"import numpy as np\n",
|
|
||||||
"from sklearn.preprocessing import StandardScaler\n",
|
|
||||||
"from sklearn.svm import LinearSVC\n",
|
|
||||||
"from sklearn.calibration import CalibratedClassifierCV\n",
|
|
||||||
"scaler = StandardScaler()\n",
|
|
||||||
"cclf = CalibratedClassifierCV(base_estimator=LinearSVC(), cv=5)\n",
|
|
||||||
"cclf.fit(Xtrain, ytrain)\n",
|
|
||||||
"res = cclf.predict_proba(Xtest)\n",
|
|
||||||
"print(res[:4, :])"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"## Test iterator\n",
|
|
||||||
"Check different weays of using the iterator"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 9,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"output_type": "stream",
|
|
||||||
"name": "stdout",
|
|
||||||
"text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([314]))\nroot - Down - Up\nroot - Down - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Down - Up - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([12]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([2]))\nroot - Up - Up - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.965714 counts=(array([0, 1]), array([676, 24]))\n"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"#check iterator\n",
|
|
||||||
"for i in list(clf):\n",
|
|
||||||
" print(i)"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 10,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"output_type": "stream",
|
|
||||||
"name": "stdout",
|
|
||||||
"text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([314]))\nroot - Down - Up\nroot - Down - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Down - Up - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([12]))\nroot - Up\nroot - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([2]))\nroot - Up - Up - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.965714 counts=(array([0, 1]), array([676, 24]))\n"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"#check iterator again\n",
|
|
||||||
"for i in clf:\n",
|
|
||||||
" print(i)"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {},
|
|
||||||
"source": [
|
|
||||||
"## Test STree is a sklearn estimator"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 12,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"output_type": "stream",
|
|
||||||
"name": "stdout",
|
|
||||||
"text": "1 functools.partial(<function check_no_attributes_set_in_init at 0x12bd3b5f0>, 'Stree')\n2 functools.partial(<function check_estimators_dtypes at 0x12bd31710>, 'Stree')\n3 functools.partial(<function check_fit_score_takes_y at 0x12bd315f0>, 'Stree')\n4 functools.partial(<function check_sample_weights_pandas_series at 0x12bd21ef0>, 'Stree')\n5 functools.partial(<function check_sample_weights_not_an_array at 0x12bd2d050>, 'Stree')\n6 functools.partial(<function check_sample_weights_list at 0x12bd2d170>, 'Stree')\n7 functools.partial(<function check_sample_weights_shape at 0x12bd2d290>, 'Stree')\n8 functools.partial(<function check_sample_weights_invariance at 0x12bd2d3b0>, 'Stree')\n9 functools.partial(<function check_estimators_fit_returns_self at 0x12bd37710>, 'Stree')\n10 functools.partial(<function check_estimators_fit_returns_self at 0x12bd37710>, 'Stree', readonly_memmap=True)\n11 functools.partial(<function check_complex_data at 0x12bd2d560>, 'Stree')\n12 functools.partial(<function check_dtype_object at 0x12bd2d4d0>, 'Stree')\n13 functools.partial(<function check_estimators_empty_data_messages at 0x12bd31830>, 'Stree')\n14 functools.partial(<function check_pipeline_consistency at 0x12bd314d0>, 'Stree')\n15 functools.partial(<function check_estimators_nan_inf at 0x12bd31950>, 'Stree')\n16 functools.partial(<function check_estimators_overwrite_params at 0x12bd3b4d0>, 'Stree')\n17 functools.partial(<function check_estimator_sparse_data at 0x12bd21dd0>, 'Stree')\n18 functools.partial(<function check_estimators_pickle at 0x12bd31b90>, 'Stree')\n19 functools.partial(<function check_classifier_data_not_an_array at 0x12bd3b830>, 'Stree')\n20 functools.partial(<function check_classifiers_one_label at 0x12bd37290>, 'Stree')\n21 functools.partial(<function check_classifiers_classes at 0x12bd37cb0>, 'Stree')\n22 functools.partial(<function check_estimators_partial_fit_n_features at 0x12bd31cb0>, 'Stree')\n23 functools.partial(<function check_classifiers_train at 0x12bd373b0>, 'Stree')\n24 functools.partial(<function check_classifiers_train at 0x12bd373b0>, 'Stree', readonly_memmap=True)\n25 functools.partial(<function check_classifiers_train at 0x12bd373b0>, 'Stree', readonly_memmap=True, X_dtype='float32')\n26 functools.partial(<function check_classifiers_regression_target at 0x12bd40320>, 'Stree')\n27 functools.partial(<function check_supervised_y_no_nan at 0x12bd20ef0>, 'Stree')\n28 functools.partial(<function check_supervised_y_2d at 0x12bd37950>, 'Stree')\n29 functools.partial(<function check_estimators_unfitted at 0x12bd37830>, 'Stree')\n30 functools.partial(<function check_non_transformer_estimators_n_iter at 0x12bd3be60>, 'Stree')\n31 functools.partial(<function check_decision_proba_consistency at 0x12bd40440>, 'Stree')\n32 functools.partial(<function check_fit2d_predict1d at 0x12bd2da70>, 'Stree')\n33 functools.partial(<function check_methods_subset_invariance at 0x12bd2dc20>, 'Stree')\n34 functools.partial(<function check_fit2d_1sample at 0x12bd2dd40>, 'Stree')\n35 functools.partial(<function check_fit2d_1feature at 0x12bd2de60>, 'Stree')\n36 functools.partial(<function check_fit1d at 0x12bd2df80>, 'Stree')\n37 functools.partial(<function check_get_params_invariance at 0x12bd400e0>, 'Stree')\n38 functools.partial(<function check_set_params at 0x12bd40200>, 'Stree')\n39 functools.partial(<function check_dict_unchanged at 0x12bd2d680>, 'Stree')\n40 functools.partial(<function check_dont_overwrite_parameters at 0x12bd2d950>, 'Stree')\n41 functools.partial(<function check_fit_idempotent at 0x12bd405f0>, 'Stree')\n42 functools.partial(<function check_n_features_in at 0x12bd40680>, 'Stree')\n43 functools.partial(<function check_requires_y_none at 0x12bd40710>, 'Stree')\n"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"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",
|
|
||||||
" print(c, check[1])\n",
|
|
||||||
" check[1](check[0])"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 11,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"# Check if the classifier is a sklearn estimator\n",
|
|
||||||
"from sklearn.utils.estimator_checks import check_estimator\n",
|
|
||||||
"check_estimator(Stree())"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"metadata": {
|
|
||||||
"kernelspec": {
|
|
||||||
"display_name": "Python 3.7.6 64-bit ('general': venv)",
|
|
||||||
"language": "python",
|
|
||||||
"name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39"
|
|
||||||
},
|
|
||||||
"language_info": {
|
|
||||||
"codemirror_mode": {
|
|
||||||
"name": "ipython",
|
|
||||||
"version": 3
|
|
||||||
},
|
|
||||||
"file_extension": ".py",
|
|
||||||
"mimetype": "text/x-python",
|
|
||||||
"name": "python",
|
|
||||||
"nbconvert_exporter": "python",
|
|
||||||
"pygments_lexer": "ipython3",
|
|
||||||
"version": "3.7.6-final"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"nbformat": 4,
|
|
||||||
"nbformat_minor": 2
|
|
||||||
}
|
|
||||||
@@ -11,6 +11,7 @@ import os
|
|||||||
import numpy as np
|
import numpy as np
|
||||||
from sklearn.base import BaseEstimator, ClassifierMixin
|
from sklearn.base import BaseEstimator, ClassifierMixin
|
||||||
from sklearn.svm import SVC, LinearSVC
|
from sklearn.svm import SVC, LinearSVC
|
||||||
|
from sklearn.utils import check_consistent_length
|
||||||
from sklearn.utils.multiclass import check_classification_targets
|
from sklearn.utils.multiclass import check_classification_targets
|
||||||
from sklearn.utils.validation import (
|
from sklearn.utils.validation import (
|
||||||
check_X_y,
|
check_X_y,
|
||||||
@@ -18,6 +19,8 @@ from sklearn.utils.validation import (
|
|||||||
check_is_fitted,
|
check_is_fitted,
|
||||||
_check_sample_weight,
|
_check_sample_weight,
|
||||||
)
|
)
|
||||||
|
from sklearn.utils.sparsefuncs import count_nonzero
|
||||||
|
from sklearn.metrics._classification import _weighted_sum, _check_targets
|
||||||
|
|
||||||
|
|
||||||
class Snode:
|
class Snode:
|
||||||
@@ -201,6 +204,13 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
) -> "Stree":
|
) -> "Stree":
|
||||||
"""Build the tree based on the dataset of samples and its labels
|
"""Build the tree based on the dataset of samples and its labels
|
||||||
|
|
||||||
|
:param X: dataset of samples to make predictions
|
||||||
|
:type X: np.array
|
||||||
|
:param y: samples labels
|
||||||
|
:type y: np.array
|
||||||
|
:param sample_weight: weights of the samples. Rescale C per sample.
|
||||||
|
Hi' weights force the classifier to put more emphasis on these points
|
||||||
|
:type sample_weight: np.array optional
|
||||||
:raises ValueError: if parameters C or max_depth are out of bounds
|
:raises ValueError: if parameters C or max_depth are out of bounds
|
||||||
:return: itself to be able to chain actions: fit().predict() ...
|
:return: itself to be able to chain actions: fit().predict() ...
|
||||||
:rtype: Stree
|
:rtype: Stree
|
||||||
@@ -284,7 +294,8 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
:type X: np.ndarray
|
:type X: np.ndarray
|
||||||
:param y: samples labels
|
:param y: samples labels
|
||||||
:type y: np.ndarray
|
:type y: np.ndarray
|
||||||
:param sample_weight: weight of samples (used in boosting)
|
:param sample_weight: weight of samples. Rescale C per sample.
|
||||||
|
Hi weights force the classifier to put more emphasis on these points.
|
||||||
:type sample_weight: np.ndarray
|
:type sample_weight: np.ndarray
|
||||||
:param depth: actual depth in the tree
|
:param depth: actual depth in the tree
|
||||||
:type depth: int
|
:type depth: int
|
||||||
@@ -435,20 +446,35 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
result[:, 0] = 1 - result[:, 1]
|
result[:, 0] = 1 - result[:, 1]
|
||||||
return self._reorder_results(result, indices)
|
return self._reorder_results(result, indices)
|
||||||
|
|
||||||
def score(self, X: np.array, y: np.array) -> float:
|
def score(
|
||||||
|
self, X: np.array, y: np.array, sample_weight: np.array = None
|
||||||
|
) -> float:
|
||||||
"""Compute accuracy of the prediction
|
"""Compute accuracy of the prediction
|
||||||
|
|
||||||
:param X: dataset of samples to make predictions
|
:param X: dataset of samples to make predictions
|
||||||
:type X: np.array
|
:type X: np.array
|
||||||
:param y: samples labels
|
:param y_true: samples labels
|
||||||
:type y: np.array
|
:type y_true: np.array
|
||||||
|
:param sample_weight: weights of the samples. Rescale C per sample.
|
||||||
|
Hi' weights force the classifier to put more emphasis on these points
|
||||||
|
:type sample_weight: np.array optional
|
||||||
:return: accuracy of the prediction
|
:return: accuracy of the prediction
|
||||||
:rtype: float
|
:rtype: float
|
||||||
"""
|
"""
|
||||||
# sklearn check
|
# sklearn check
|
||||||
check_is_fitted(self)
|
check_is_fitted(self)
|
||||||
yp = self.predict(X).reshape(y.shape)
|
|
||||||
return np.mean(yp == y)
|
y_pred = self.predict(X).reshape(y.shape)
|
||||||
|
# Compute accuracy for each possible representation
|
||||||
|
y_type, y_true, y_pred = _check_targets(y, y_pred)
|
||||||
|
check_consistent_length(y_true, y_pred, sample_weight)
|
||||||
|
if y_type.startswith("multilabel"):
|
||||||
|
differing_labels = count_nonzero(y_true - y_pred, axis=1)
|
||||||
|
score = differing_labels == 0
|
||||||
|
else:
|
||||||
|
score = y_true == y_pred
|
||||||
|
|
||||||
|
return _weighted_sum(score, sample_weight, normalize=True)
|
||||||
|
|
||||||
def __iter__(self) -> Siterator:
|
def __iter__(self) -> Siterator:
|
||||||
"""Create an iterator to be able to visit the nodes of the tree in preorder,
|
"""Create an iterator to be able to visit the nodes of the tree in preorder,
|
||||||
|
|||||||
Reference in New Issue
Block a user