mirror of
https://github.com/fenago/data-science.git
synced 2026-05-04 08:31:59 +00:00
138 lines
3.3 KiB
Plaintext
138 lines
3.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"colab": {},
|
|
"colab_type": "code",
|
|
"id": "om9yhBqIyrLD"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from sklearn import datasets, model_selection, linear_model\n",
|
|
"\n",
|
|
"# load the data\n",
|
|
"diabetes = datasets.load_diabetes()\n",
|
|
"\n",
|
|
"# target\n",
|
|
"y = diabetes.target\n",
|
|
"\n",
|
|
"# features\n",
|
|
"X = diabetes.data\n",
|
|
"\n",
|
|
"# initialise the ridge regression\n",
|
|
"reg = linear_model.Ridge()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"colab": {},
|
|
"colab_type": "code",
|
|
"id": "6VemB0iGzG8T"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from scipy import stats\n",
|
|
"\n",
|
|
"# alpha ~ gamma(1,1)\n",
|
|
"param_dist = {'alpha': stats.gamma(a=1, loc=1, scale=2)}"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/",
|
|
"height": 245
|
|
},
|
|
"colab_type": "code",
|
|
"executionInfo": {
|
|
"elapsed": 2593,
|
|
"status": "ok",
|
|
"timestamp": 1571317362660,
|
|
"user": {
|
|
"displayName": "Andrew Worsley",
|
|
"photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mAp-Td-yKvu76Tg0Swzal8U17btuwNIXFmWVwZo=s64",
|
|
"userId": "11337101975325054847"
|
|
},
|
|
"user_tz": -660
|
|
},
|
|
"id": "Nni22PRlzUuL",
|
|
"outputId": "15deef80-db48-426c-9539-2fcd9e7e85ac"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# set up the random search to sample 100 values and score on negative mean squared error\n",
|
|
"rscv = model_selection.RandomizedSearchCV(estimator=reg, param_distributions=param_dist, n_iter=100, scoring='neg_mean_squared_error')\n",
|
|
"\n",
|
|
"# start the search\n",
|
|
"rscv.fit(X,y)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/",
|
|
"height": 121
|
|
},
|
|
"colab_type": "code",
|
|
"executionInfo": {
|
|
"elapsed": 2586,
|
|
"status": "ok",
|
|
"timestamp": 1571317362662,
|
|
"user": {
|
|
"displayName": "Andrew Worsley",
|
|
"photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mAp-Td-yKvu76Tg0Swzal8U17btuwNIXFmWVwZo=s64",
|
|
"userId": "11337101975325054847"
|
|
},
|
|
"user_tz": -660
|
|
},
|
|
"id": "shd5Br5eznmb",
|
|
"outputId": "66d160c8-3dca-428b-9e34-e05f0044c9f3"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"\n",
|
|
"# convert the results dictionary to a pandas data frame\n",
|
|
"results = pd.DataFrame(rscv.cv_results_)\n",
|
|
"\n",
|
|
"# show the top 5 hyperparamaterizations\n",
|
|
"print(results.loc[:,['params','rank_test_score']].sort_values('rank_test_score').head(5))"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"colab": {
|
|
"collapsed_sections": [],
|
|
"name": "tuning_using_randomizedsearchcv.ipynb",
|
|
"provenance": []
|
|
},
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.8.6"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 1
|
|
}
|