Pushing the docs to dev/ for branch: main, commit 9d7f5b97fd8f4432107e5586df82bb5f6b3817e7

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -28,6 +28,7 @@
     n_features=n_features,
     n_nonzero_coefs=n_nonzero_coefs,
     random_state=0,
+    data_transposed=True,
 )
 
 (idx,) = w.nonzero()

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\nimport numpy as np\nfrom sklearn.linear_model import OrthogonalMatchingPursuit\nfrom sklearn.linear_model import OrthogonalMatchingPursuitCV\nfrom sklearn.datasets import make_sparse_coded_signal\n\nn_components, n_features = 512, 100\nn_nonzero_coefs = 17\n\n# generate the data\n\n# y = Xw\n# |x|_0 = n_nonzero_coefs\n\ny, X, w = make_sparse_coded_signal(\n    n_samples=1,\n    n_components=n_components,\n    n_features=n_features,\n    n_nonzero_coefs=n_nonzero_coefs,\n    random_state=0,\n)\n\n(idx,) = w.nonzero()\n\n# distort the clean signal\ny_noisy = y + 0.05 * np.random.randn(len(y))\n\n# plot the sparse signal\nplt.figure(figsize=(7, 7))\nplt.subplot(4, 1, 1)\nplt.xlim(0, 512)\nplt.title(\"Sparse signal\")\nplt.stem(idx, w[idx], use_line_collection=True)\n\n# plot the noise-free reconstruction\nomp = OrthogonalMatchingPursuit(n_nonzero_coefs=n_nonzero_coefs, normalize=False)\nomp.fit(X, y)\ncoef = omp.coef_\n(idx_r,) = coef.nonzero()\nplt.subplot(4, 1, 2)\nplt.xlim(0, 512)\nplt.title(\"Recovered signal from noise-free measurements\")\nplt.stem(idx_r, coef[idx_r], use_line_collection=True)\n\n# plot the noisy reconstruction\nomp.fit(X, y_noisy)\ncoef = omp.coef_\n(idx_r,) = coef.nonzero()\nplt.subplot(4, 1, 3)\nplt.xlim(0, 512)\nplt.title(\"Recovered signal from noisy measurements\")\nplt.stem(idx_r, coef[idx_r], use_line_collection=True)\n\n# plot the noisy reconstruction with number of non-zeros set by CV\nomp_cv = OrthogonalMatchingPursuitCV(normalize=False)\nomp_cv.fit(X, y_noisy)\ncoef = omp_cv.coef_\n(idx_r,) = coef.nonzero()\nplt.subplot(4, 1, 4)\nplt.xlim(0, 512)\nplt.title(\"Recovered signal from noisy measurements with CV\")\nplt.stem(idx_r, coef[idx_r], use_line_collection=True)\n\nplt.subplots_adjust(0.06, 0.04, 0.94, 0.90, 0.20, 0.38)\nplt.suptitle(\"Sparse signal recovery with Orthogonal Matching Pursuit\", fontsize=16)\nplt.show()"
+        "import matplotlib.pyplot as plt\nimport numpy as np\nfrom sklearn.linear_model import OrthogonalMatchingPursuit\nfrom sklearn.linear_model import OrthogonalMatchingPursuitCV\nfrom sklearn.datasets import make_sparse_coded_signal\n\nn_components, n_features = 512, 100\nn_nonzero_coefs = 17\n\n# generate the data\n\n# y = Xw\n# |x|_0 = n_nonzero_coefs\n\ny, X, w = make_sparse_coded_signal(\n    n_samples=1,\n    n_components=n_components,\n    n_features=n_features,\n    n_nonzero_coefs=n_nonzero_coefs,\n    random_state=0,\n    data_transposed=True,\n)\n\n(idx,) = w.nonzero()\n\n# distort the clean signal\ny_noisy = y + 0.05 * np.random.randn(len(y))\n\n# plot the sparse signal\nplt.figure(figsize=(7, 7))\nplt.subplot(4, 1, 1)\nplt.xlim(0, 512)\nplt.title(\"Sparse signal\")\nplt.stem(idx, w[idx], use_line_collection=True)\n\n# plot the noise-free reconstruction\nomp = OrthogonalMatchingPursuit(n_nonzero_coefs=n_nonzero_coefs, normalize=False)\nomp.fit(X, y)\ncoef = omp.coef_\n(idx_r,) = coef.nonzero()\nplt.subplot(4, 1, 2)\nplt.xlim(0, 512)\nplt.title(\"Recovered signal from noise-free measurements\")\nplt.stem(idx_r, coef[idx_r], use_line_collection=True)\n\n# plot the noisy reconstruction\nomp.fit(X, y_noisy)\ncoef = omp.coef_\n(idx_r,) = coef.nonzero()\nplt.subplot(4, 1, 3)\nplt.xlim(0, 512)\nplt.title(\"Recovered signal from noisy measurements\")\nplt.stem(idx_r, coef[idx_r], use_line_collection=True)\n\n# plot the noisy reconstruction with number of non-zeros set by CV\nomp_cv = OrthogonalMatchingPursuitCV(normalize=False)\nomp_cv.fit(X, y_noisy)\ncoef = omp_cv.coef_\n(idx_r,) = coef.nonzero()\nplt.subplot(4, 1, 4)\nplt.xlim(0, 512)\nplt.title(\"Recovered signal from noisy measurements with CV\")\nplt.stem(idx_r, coef[idx_r], use_line_collection=True)\n\nplt.subplots_adjust(0.06, 0.04, 0.94, 0.90, 0.20, 0.38)\nplt.suptitle(\"Sparse signal recovery with Orthogonal Matching Pursuit\", fontsize=16)\nplt.show()"
       ]
     }
   ],