diff --git a/Auto-SKLearn_AutoML/Classification.ipynb b/Auto-SKLearn_AutoML/Classification.ipynb
index 8908132d3548381bafbf08857dfba18dca59a159..a7f8b9eab53c7b7ce9f8a185e3c32d0a99d648ad 100644
--- a/Auto-SKLearn_AutoML/Classification.ipynb
+++ b/Auto-SKLearn_AutoML/Classification.ipynb
@@ -7,98 +7,49 @@
"source": [
"# Classification\n",
"\n",
- "**_NOTE_** autosklearn only will run in linux (feb 26, 2022)\n",
+ "**_NOTE_** \n",
+ "\n",
+ "The module `autosklearn` will only run in Linux environments, such as Google Collab or Jupyter Hub. Attempting to run this notebook will fail if you are not in a Linux environment.\n",
"\n",
"Example coming from [here](https://automl.github.io/auto-sklearn/master/examples/20_basic/example_classification.html#sphx-glr-examples-20-basic-example-classification-py)"
]
},
- {
- "cell_type": "markdown",
- "id": "c5dad4c0",
- "metadata": {},
- "source": [
- "**Classification doesn't work with current version of scipy/github and requires different packages/updates to run notebook**\n",
- "- Note from professor Colbry: Notebook can't be fixed in classtime, write note of what needs to be fixed and push to gitlab as is."
- ]
- },
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": null,
"id": "c69433ce",
"metadata": {},
- "outputs": [
- {
- "ename": "ModuleNotFoundError",
- "evalue": "No module named 'autosklearn'",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
- "\u001b[1;32m<ipython-input-1-13292483524a>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 6\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mpickle\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 7\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 8\u001b[1;33m \u001b[1;32mimport\u001b[0m \u001b[0mautosklearn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclassification\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
- "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'autosklearn'"
- ]
- }
- ],
+ "outputs": [],
"source": [
- "# import\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.datasets import fetch_openml\n",
- "import autosklearn.classification\n",
"import pandas as pd\n",
"\n",
"import sklearn.datasets\n",
"import sklearn.metrics\n",
- "# Fixed import model_selection\n",
"import sklearn.model_selection\n",
"import pickle\n",
"\n",
- "import autosklearn.classification #cannot import classification from autosklearn"
+ "import autosklearn.classification "
]
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": null,
"id": "642c1f1a",
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Note: you may need to restart the kernel to use updated packages.\n"
- ]
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "ERROR: Invalid requirement: '#loading'\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"pip install auto-sklearn #loading infinitely"
]
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": null,
"id": "2b1e1930",
"metadata": {},
- "outputs": [
- {
- "ename": "AttributeError",
- "evalue": "module 'sklearn' has no attribute 'model_selection'",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",
- "\u001b[1;32m<ipython-input-3-935236cbcd87>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 2\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msklearn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdatasets\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload_breast_cancer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mreturn_X_y\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0mX_train\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mX_test\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my_test\u001b[0m \u001b[1;33m=\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 4\u001b[1;33m \u001b[0msklearn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmodel_selection\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtrain_test_split\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrandom_state\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
- "\u001b[1;31mAttributeError\u001b[0m: module 'sklearn' has no attribute 'model_selection'"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# split the dataset\n",
"X, y = sklearn.datasets.load_breast_cancer(return_X_y=True)\n",
@@ -108,22 +59,10 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": null,
"id": "15e5f821",
"metadata": {},
- "outputs": [
- {
- "ename": "NameError",
- "evalue": "name 'autosklearn' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)",
- "\u001b[1;32m<ipython-input-6-6c1473e893d3>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[1;31m# Fit the classifier\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m automl = autosklearn.classification.AutoSklearnClassifier(\n\u001b[0m\u001b[0;32m 3\u001b[0m \u001b[0mtime_left_for_this_task\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m120\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mper_run_time_limit\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m30\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mtmp_folder\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'/tmp/autosklearn_classification_example_tmp'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
- "\u001b[1;31mNameError\u001b[0m: name 'autosklearn' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# Fit the classifier\n",
"automl = autosklearn.classification.AutoSklearnClassifier(\n",
@@ -136,22 +75,10 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": null,
"id": "2d4e4d9f",
"metadata": {},
- "outputs": [
- {
- "ename": "NameError",
- "evalue": "name 'automl' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m<ipython-input-11-6dfffdcd8374>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Different Models run by autosklearn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mautoml\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mleaderboard\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m: name 'automl' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# Different Models run by autosklearn\n",
"print(automl.leaderboard())"
@@ -159,22 +86,10 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": null,
"id": "72e580e7",
"metadata": {},
- "outputs": [
- {
- "ename": "NameError",
- "evalue": "name 'automl' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m<ipython-input-12-ab76765f6a20>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Show the different models\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mpprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mautoml\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshow_models\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindent\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m4\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m: name 'automl' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# Show the different models\n",
"pprint(automl.show_models(), indent=4)"
@@ -182,22 +97,10 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": null,
"id": "027039cd",
"metadata": {},
- "outputs": [
- {
- "ename": "NameError",
- "evalue": "name 'automl' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m<ipython-input-13-596897413c8d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Predict the test labels\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mpredictions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mautoml\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Accuracy score:\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetrics\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0maccuracy_score\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_test\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpredictions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
- "\u001b[0;31mNameError\u001b[0m: name 'automl' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# Predict the test labels\n",
"predictions = automl.predict(X_test)\n",
@@ -206,22 +109,10 @@
},
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": null,
"id": "acd372ea",
"metadata": {},
- "outputs": [
- {
- "ename": "NameError",
- "evalue": "name 'automl' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m<ipython-input-14-14e40d77d77d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Export the model with the highest rank\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mclf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mautoml\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshow_models\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m7\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'sklearn_classifier'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mpickle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdump\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mclf\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'model.pickle'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'wb'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
- "\u001b[0;31mNameError\u001b[0m: name 'automl' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# Export the model with the highest rank\n",
"clf = automl.show_models()[7]['sklearn_classifier']\n",
@@ -230,22 +121,10 @@
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": null,
"id": "a3324782",
"metadata": {},
- "outputs": [
- {
- "ename": "NameError",
- "evalue": "name 'clf' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m<ipython-input-15-b9c89d294f77>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mclf\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m: name 'clf' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"clf"
]
@@ -261,7 +140,7 @@
],
"metadata": {
"kernelspec": {
- "display_name": "Python 3",
+ "display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@@ -275,7 +154,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.8.8"
+ "version": "3.9.12"
}
},
"nbformat": 4,