balkian/sitc
1
0
Fork 0
mirror of https://github.com/gsi-upm/sitc synced 2024-11-14 10:32:29 +00:00
Code Issues Releases Wiki Activity

Update 2_6_Model_Tuning.ipynb

Browse Source 
Fixed typos.
This commit is contained in:
Carlos A. Iglesias 2022-02-28 12:45:40 +01:00 committed by GitHub
parent a209d18a5b
commit 11a1ea80d3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
ml1/2_6_Model_Tuning.ipynb
View File

@ -39,7 +39,7 @@
"* [Train classifier](#Train-classifier)\n", "* [Train classifier](#Train-classifier)\n",
"* [More about Pipelines](#More-about-Pipelines)\n", "* [More about Pipelines](#More-about-Pipelines)\n",
"* [Tuning the algorithm](#Tuning-the-algorithm)\n", "* [Tuning the algorithm](#Tuning-the-algorithm)\n",
"\t* [Grid Search for Parameter optimization](#Grid-Search-for-Parameter-optimization)\n", "\t* [Grid Search for Hyperparameter optimization](#Grid-Search-for-Hyperparameter-optimization)\n",
"* [Evaluating the algorithm](#Evaluating-the-algorithm)\n", "* [Evaluating the algorithm](#Evaluating-the-algorithm)\n",
"\t* [K-Fold validation](#K-Fold-validation)\n", "\t* [K-Fold validation](#K-Fold-validation)\n",
"* [References](#References)\n" "* [References](#References)\n"
@ -56,9 +56,9 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"In the previous [notebook](2_5_2_Decision_Tree_Model.ipynb), we got an accuracy of 9.47. Could we get a better accuracy if we tune the parameters of the estimator?\n", "In the previous [notebook](2_5_2_Decision_Tree_Model.ipynb), we got an accuracy of 9.47. Could we get a better accuracy if we tune the hyperparameters of the estimator?\n",
"\n", "\n",
"The goal of this notebook is to learn how to tune an algorithm by opimizing its parameters using grid search." "The goal of this notebook is to learn how to tune an algorithm by opimizing its hyperparameters using grid search."
] ]
}, },
{ {
@ -300,21 +300,21 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"You can try different values for these parameters and observe the results." "You can try different values for these hyperparameters and observe the results."
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Grid Search for Parameter optimization" "### Grid Search for Hyperparameter optimization"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Changing manually the parameters to find their optimal values is not practical. Instead, we can consider to find the optimal value of the parameters as an *optimization problem*. \n", "Changing manually the hyperparameters to find their optimal values is not practical. Instead, we can consider to find the optimal value of the parameters as an *optimization problem*. \n",
"\n", "\n",
"The sklearn comes with several optimization techniques for this purpose, such as **grid search** and **randomized search**. In this notebook we are going to introduce the former one." "The sklearn comes with several optimization techniques for this purpose, such as **grid search** and **randomized search**. In this notebook we are going to introduce the former one."
] ]
@ -405,7 +405,7 @@
"source": [ "source": [
"We have got an *improvement* from 0.947 to 0.953 with k-fold.\n", "We have got an *improvement* from 0.947 to 0.953 with k-fold.\n",
"\n", "\n",
"We are now to try to fit the best combination of the parameters of the algorithm. It can take some time to compute it." "We are now to try to fit the best combination of the hyperparameters of the algorithm. It can take some time to compute it."
] ]
}, },
{ {
@ -414,12 +414,12 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Set the parameters by cross-validation\n", "# Set the hyperparameters by cross-validation\n",
"\n", "\n",
"from sklearn.metrics import classification_report, recall_score, precision_score, make_scorer\n", "from sklearn.metrics import classification_report, recall_score, precision_score, make_scorer\n",
"\n", "\n",
"# set of parameters to test\n", "# set of hyperparameters to test\n",
"tuned_parameters = [{'max_depth': np.arange(3, 10),\n", "tuned_hyperparameters = [{'max_depth': np.arange(3, 10),\n",
"# 'max_weights': [1, 10, 100, 1000]},\n", "# 'max_weights': [1, 10, 100, 1000]},\n",
" 'criterion': ['gini', 'entropy'], \n", " 'criterion': ['gini', 'entropy'], \n",
" 'splitter': ['best', 'random'],\n", " 'splitter': ['best', 'random'],\n",
@ -431,7 +431,7 @@
"scores = ['precision', 'recall']\n", "scores = ['precision', 'recall']\n",
"\n", "\n",
"for score in scores:\n", "for score in scores:\n",
" print(\"# Tuning hyper-parameters for %s\" % score)\n", " print(\"# Tuning hyper-hyperparameters for %s\" % score)\n",
" print()\n", " print()\n",
"\n", "\n",
" if score == 'precision':\n", " if score == 'precision':\n",
@ -440,10 +440,10 @@
" scorer = make_scorer(recall_score, average='weighted', zero_division=0)\n", " scorer = make_scorer(recall_score, average='weighted', zero_division=0)\n",
" \n", " \n",
" # cv = the fold of the cross-validation cv, defaulted to 5\n", " # cv = the fold of the cross-validation cv, defaulted to 5\n",
" gs = GridSearchCV(DecisionTreeClassifier(), tuned_parameters, cv=10, scoring=scorer)\n", " gs = GridSearchCV(DecisionTreeClassifier(), tuned_hyperparameters, cv=10, scoring=scorer)\n",
" gs.fit(x_train, y_train)\n", " gs.fit(x_train, y_train)\n",
"\n", "\n",
" print(\"Best parameters set found on development set:\")\n", " print(\"Best hyperparameters set found on development set:\")\n",
" print()\n", " print()\n",
" print(gs.best_params_)\n", " print(gs.best_params_)\n",
" print()\n", " print()\n",
@ -520,7 +520,7 @@
"* [Plot the decision surface of a decision tree on the iris dataset](https://scikit-learn.org/stable/auto_examples/tree/plot_iris_dtc.html)\n", "* [Plot the decision surface of a decision tree on the iris dataset](https://scikit-learn.org/stable/auto_examples/tree/plot_iris_dtc.html)\n",
"* [scikit-learn : Machine Learning Simplified](https://learning.oreilly.com/library/view/scikit-learn-machine/9781788833479/), Raúl Garreta; Guillermo Moncecchi, Packt Publishing, 2017.\n", "* [scikit-learn : Machine Learning Simplified](https://learning.oreilly.com/library/view/scikit-learn-machine/9781788833479/), Raúl Garreta; Guillermo Moncecchi, Packt Publishing, 2017.\n",
"* [Python Machine Learning](https://learning.oreilly.com/library/view/python-machine-learning/9781789955750/), Sebastian Raschka, Packt Publishing, 2019.\n", "* [Python Machine Learning](https://learning.oreilly.com/library/view/python-machine-learning/9781789955750/), Sebastian Raschka, Packt Publishing, 2019.\n",
"* [Parameter estimation using grid search with cross-validation](http://scikit-learn.org/stable/auto_examples/model_selection/grid_search_digits.html)\n", "* [Hyperparameter estimation using grid search with cross-validation](http://scikit-learn.org/stable/auto_examples/model_selection/grid_search_digits.html)\n",
"* [Decision trees in python with scikit-learn and pandas](http://chrisstrelioff.ws/sandbox/2015/06/08/decision_trees_in_python_with_scikit_learn_and_pandas.html)" "* [Decision trees in python with scikit-learn and pandas](http://chrisstrelioff.ws/sandbox/2015/06/08/decision_trees_in_python_with_scikit_learn_and_pandas.html)"
] ]
}, },