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

Use as_frame=False for fetch_open_ml(), and svd_solver=full for PCA, fixes #358

main
Aurélien Geron 2021-03-02 09:19:21 +13:00
parent 9fede98b42
commit 5663779ae8
1 changed files with 18 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
08_dimensionality_reduction.ipynb
View File

@ -184,7 +184,7 @@
"source": [ "source": [
"from sklearn.decomposition import PCA\n", "from sklearn.decomposition import PCA\n",
"\n", "\n",
"pca = PCA(n_components = 2)\n", "pca = PCA(n_components=2)\n",
"X2D = pca.fit_transform(X)" "X2D = pca.fit_transform(X)"
] ]
}, },
@ -761,6 +761,13 @@
"# MNIST compression" "# MNIST compression"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Warning:** since Scikit-Learn 0.24, `fetch_openml()` returns a Pandas `DataFrame` by default. To avoid this and keep the same code as in the book, we set `as_frame=True`."
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 31, "execution_count": 31,
@ -769,7 +776,7 @@
"source": [ "source": [
"from sklearn.datasets import fetch_openml\n", "from sklearn.datasets import fetch_openml\n",
"\n", "\n",
"mnist = fetch_openml('mnist_784', version=1)\n", "mnist = fetch_openml('mnist_784', version=1, as_frame=False)\n",
"mnist.target = mnist.target.astype(np.uint8)" "mnist.target = mnist.target.astype(np.uint8)"
] ]
}, },
@ -863,7 +870,7 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"pca = PCA(n_components = 154)\n", "pca = PCA(n_components=154)\n",
"X_reduced = pca.fit_transform(X_train)\n", "X_reduced = pca.fit_transform(X_train)\n",
"X_recovered = pca.inverse_transform(X_reduced)" "X_recovered = pca.inverse_transform(X_reduced)"
] ]
@ -1101,15 +1108,15 @@
"\n", "\n",
"for n_components in (2, 10, 154):\n", "for n_components in (2, 10, 154):\n",
" print(\"n_components =\", n_components)\n", " print(\"n_components =\", n_components)\n",
" regular_pca = PCA(n_components=n_components)\n", " regular_pca = PCA(n_components=n_components, svd_solver=\"full\")\n",
" inc_pca = IncrementalPCA(n_components=n_components, batch_size=500)\n", " inc_pca = IncrementalPCA(n_components=n_components, batch_size=500)\n",
" rnd_pca = PCA(n_components=n_components, random_state=42, svd_solver=\"randomized\")\n", " rnd_pca = PCA(n_components=n_components, random_state=42, svd_solver=\"randomized\")\n",
"\n", "\n",
" for pca in (regular_pca, inc_pca, rnd_pca):\n", " for name, pca in ((\"PCA\", regular_pca), (\"Inc PCA\", inc_pca), (\"Rnd PCA\", rnd_pca)):\n",
" t1 = time.time()\n", " t1 = time.time()\n",
" pca.fit(X_train)\n", " pca.fit(X_train)\n",
" t2 = time.time()\n", " t2 = time.time()\n",
" print(\" {}: {:.1f} seconds\".format(pca.__class__.__name__, t2 - t1))" " print(\" {}: {:.1f} seconds\".format(name, t2 - t1))"
] ]
}, },
{ {
@ -1130,12 +1137,12 @@
"sizes = [1000, 10000, 20000, 30000, 40000, 50000, 70000, 100000, 200000, 500000]\n", "sizes = [1000, 10000, 20000, 30000, 40000, 50000, 70000, 100000, 200000, 500000]\n",
"for n_samples in sizes:\n", "for n_samples in sizes:\n",
" X = np.random.randn(n_samples, 5)\n", " X = np.random.randn(n_samples, 5)\n",
" pca = PCA(n_components = 2, svd_solver=\"randomized\", random_state=42)\n", " pca = PCA(n_components=2, svd_solver=\"randomized\", random_state=42)\n",
" t1 = time.time()\n", " t1 = time.time()\n",
" pca.fit(X)\n", " pca.fit(X)\n",
" t2 = time.time()\n", " t2 = time.time()\n",
" times_rpca.append(t2 - t1)\n", " times_rpca.append(t2 - t1)\n",
" pca = PCA(n_components = 2)\n", " pca = PCA(n_components=2, svd_solver=\"full\")\n",
" t1 = time.time()\n", " t1 = time.time()\n",
" pca.fit(X)\n", " pca.fit(X)\n",
" t2 = time.time()\n", " t2 = time.time()\n",
@ -1169,12 +1176,12 @@
"sizes = [1000, 2000, 3000, 4000, 5000, 6000]\n", "sizes = [1000, 2000, 3000, 4000, 5000, 6000]\n",
"for n_features in sizes:\n", "for n_features in sizes:\n",
" X = np.random.randn(2000, n_features)\n", " X = np.random.randn(2000, n_features)\n",
" pca = PCA(n_components = 2, random_state=42, svd_solver=\"randomized\")\n", " pca = PCA(n_components=2, random_state=42, svd_solver=\"randomized\")\n",
" t1 = time.time()\n", " t1 = time.time()\n",
" pca.fit(X)\n", " pca.fit(X)\n",
" t2 = time.time()\n", " t2 = time.time()\n",
" times_rpca.append(t2 - t1)\n", " times_rpca.append(t2 - t1)\n",
" pca = PCA(n_components = 2)\n", " pca = PCA(n_components=2, svd_solver=\"full\")\n",
" t1 = time.time()\n", " t1 = time.time()\n",
" pca.fit(X)\n", " pca.fit(X)\n",
" t2 = time.time()\n", " t2 = time.time()\n",
@ -2252,7 +2259,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.7.8" "version": "3.7.9"
} }
}, },
"nbformat": 4, "nbformat": 4,