setup data in 03

Author: Ray Bell

03_array.ipynb

@@ -36,6 +36,29 @@
     "* [Array examples](https://examples.dask.org/array.html)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%run prep.py -d random"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -67,23 +90,12 @@
     "We do exactly this with Python and NumPy in the following example:"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "**Create random dataset**"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# create data if it doesn't already exist\n",
-    "from prep import random_array\n",
-    "random_array()  \n",
-    "\n",
     "# Load data with h5py\n",
     "# this creates a pointer to the data, but does not actually load\n",
     "import h5py\n",
@@ -155,15 +167,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Compute the mean of the array"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "# Compute the mean of the array\n",
     "sums = []\n",
     "lengths = []\n",
     "for i in range(0, 1000000000, 1000000):\n",
@@ -173,7 +177,7 @@
     "\n",
     "total = sum(sums)\n",
     "length = sum(lengths)\n",
-    "print(total / length)\n"
+    "print(total / length)"
    ]
   },
   {
@@ -510,8 +514,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from prep import create_weather  # Prep data if it doesn't exist\n",
-    "create_weather()"
+    "%run prep.py -d weather"
    ]
   },
   {
@@ -637,7 +640,7 @@
    },
    "outputs": [],
    "source": [
-    "# complete the following\n",
+    "# complete the following:\n",
     "fig = plt.figure(figsize=(16, 8))\n",
     "plt.imshow(..., cmap='RdBu_r')"
    ]
@@ -755,7 +758,7 @@
     "\n",
     "result = x[:, ::2, ::2]\n",
     "\n",
-    "da.to_zarr(result, os.path.join('data', 'myfile.zarr'), overwrite=True)\n"
+    "da.to_zarr(result, os.path.join('data', 'myfile.zarr'), overwrite=True)"
    ]
   },
   {
@@ -830,7 +833,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Notice that the most time consuming function is `distances`."
+    "Notice that the most time consuming function is `distances`:"
    ]
   },
   {
@@ -973,7 +976,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,