Merge branch 'master' of github.com:jakevdp/sklearn_scipy2013

Author: jakevdp

.gitignore

@@ -8,3 +8,6 @@ notebooks/figures/downloads/
 *.pkl
 datasets
 joblib
+
+.DS_Store
+*.zip

fetch_data.py

@@ -95,3 +95,4 @@ def check_sentiment140(datasets_folder):
     from sklearn.datasets import fetch_lfw_people
     fetch_lfw_people(min_faces_per_person=70, resize=0.4,
                      data_home=datasets_folder)
+    print("=> Success!")

notebooks/10_distributed_model_selection_and_assessment.ipynb

@@ -1595,13 +1595,55 @@
      "cell_type": "code",
      "collapsed": false,
      "input": [
+      "from IPython.parallel import Client\n",
+      "client = Client()\n",
+      "len(client)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": []
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "from sklearn.svm import SVC\n",
+      "\n",
       "lb_view = client.load_balanced_view()\n",
       "model = SVC()"
      ],
      "language": "python",
      "metadata": {},
      "outputs": []
     },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "from sklearn.datasets import load_digits\n",
+      "from pyrallel.mmap_utils import persist_cv_splits, warm_mmap_on_cv_splits\n",
+      "\n",
+      "digits = load_digits()\n",
+      "digits_split_filenames = persist_cv_splits(digits.data, digits.target,\n",
+      "    name='digits', random_state=42)\n",
+      "digits_split_filenames"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": []
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "from pyrallel.mmap_utils import warm_mmap_on_cv_splits\n",
+      "\n",
+      "warm_mmap_on_cv_splits(client, digits_split_filenames)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": []
+    },
     {
      "cell_type": "code",
      "collapsed": false,
@@ -1655,6 +1697,18 @@
      "metadata": {},
      "outputs": []
     },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "search = RandomizedGridSeach(lb_view)\n",
+      "search.launch_for_splits(model, svc_params, digits_split_filenames)\n",
+      "%time search.wait()"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": []
+    },
     {
      "cell_type": "heading",
      "level": 2,