schuetoliver
/
handson-ml
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add parser='auto' to fetch_openml(), and normalized_stress=False to MDS(), to avoid warnings

main
Aurélien Geron 2023-11-14 13:38:44 +13:00
parent d67673a290
commit c919a818f5
1 changed files with 24 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
08_dimensionality_reduction.ipynb
View File

@ -775,7 +775,7 @@
"source": [ "source": [
"from sklearn.datasets import fetch_openml\n", "from sklearn.datasets import fetch_openml\n",
"\n", "\n",
"mnist = fetch_openml('mnist_784', as_frame=False)\n", "mnist = fetch_openml('mnist_784', as_frame=False, parser=\"auto\")\n",
"X_train, y_train = mnist.data[:60_000], mnist.target[:60_000]\n", "X_train, y_train = mnist.data[:60_000], mnist.target[:60_000]\n",
"X_test, y_test = mnist.data[60_000:], mnist.target[60_000:]\n", "X_test, y_test = mnist.data[60_000:], mnist.target[60_000:]\n",
"\n", "\n",
@ -785,6 +785,13 @@
"d = np.argmax(cumsum >= 0.95) + 1 # d equals 154" "d = np.argmax(cumsum >= 0.95) + 1 # d equals 154"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note: I added `parser=\"auto\"` when calling `fetch_openml()` to avoid a warning about the fact that the default value for that parameter will change in the future (it's irrelevant in this case). Please see the [documentation](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_openml.html) for more details."
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 21, "execution_count": 21,
@ -1388,6 +1395,13 @@
"plt.show()" "plt.show()"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note: I added `normalized_stress=False` below to avoid a warning about the fact that the default value for that hyperparameter will change in the future. Please see the [documentation](https://scikit-learn.org/stable/modules/generated/sklearn.manifold.MDS.html) for more details."
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 46, "execution_count": 46,
@ -1396,7 +1410,7 @@
"source": [ "source": [
"from sklearn.manifold import MDS\n", "from sklearn.manifold import MDS\n",
"\n", "\n",
"mds = MDS(n_components=2, random_state=42)\n", "mds = MDS(n_components=2, normalized_stress=False, random_state=42)\n",
"X_reduced_mds = mds.fit_transform(X_swiss)" "X_reduced_mds = mds.fit_transform(X_swiss)"
] ]
}, },
@ -2418,7 +2432,8 @@
} }
], ],
"source": [ "source": [
"%time X_mds_reduced = MDS(n_components=2, random_state=42).fit_transform(X_sample)\n", "%time X_mds_reduced = MDS(n_components=2, normalized_stress=False,\n",
" random_state=42).fit_transform(X_sample)\n",
"plot_digits(X_mds_reduced, y_sample)\n", "plot_digits(X_mds_reduced, y_sample)\n",
"plt.show()" "plt.show()"
] ]
@ -2464,8 +2479,10 @@
} }
], ],
"source": [ "source": [
"pca_mds = make_pipeline(PCA(n_components=0.95, random_state=42),\n", "pca_mds = make_pipeline(\n",
" MDS(n_components=2, random_state=42))\n", " PCA(n_components=0.95, random_state=42),\n",
" MDS(n_components=2, normalized_stress=False, random_state=42)\n",
")\n",
"\n", "\n",
"%time X_pca_mds_reduced = pca_mds.fit_transform(X_sample)\n", "%time X_pca_mds_reduced = pca_mds.fit_transform(X_sample)\n",
"plot_digits(X_pca_mds_reduced, y_sample)\n", "plot_digits(X_pca_mds_reduced, y_sample)\n",
@ -2552,7 +2569,7 @@
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "Python 3", "display_name": "Python 3 (ipykernel)",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -2566,7 +2583,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.10.6" "version": "3.10.13"
} }
}, },
"nbformat": 4, "nbformat": 4,