exercise.ipynb

@@ -2,15 +2,8 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2024-03-04T09:40:28.904Z",
-     "iopub.status.busy": "2024-03-04T09:40:28.896Z",
-     "iopub.status.idle": "2024-03-04T09:40:28.978Z",
-     "shell.execute_reply": "2024-03-04T09:40:28.967Z"
-    }
-   },
+   "execution_count": 1,
+   "metadata": {},
    "outputs": [],
    "source": [
     "import numpy as np"
@@ -18,15 +11,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2024-03-04T10:02:39.062Z",
-     "iopub.status.busy": "2024-03-04T10:02:39.057Z",
-     "iopub.status.idle": "2024-03-04T10:02:39.068Z",
-     "shell.execute_reply": "2024-03-04T10:02:39.071Z"
-    }
-   },
+   "execution_count": 2,
+   "metadata": {},
    "outputs": [],
    "source": [
     "n_series = 32\n",
@@ -37,17 +23,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2024-03-04T10:02:41.027Z",
-     "iopub.status.busy": "2024-03-04T10:02:41.020Z",
-     "iopub.status.idle": "2024-03-04T10:02:41.036Z",
-     "shell.execute_reply": "2024-03-04T10:02:41.040Z"
-    },
-    "scrolled": true
-   },
-   "outputs": [],
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Size of one time series: 40 M\n",
+      "Size of collection: 1280 M\n",
+      "Gap size: 128 K\n",
+      "Gapped series size: 2 K\n"
+     ]
+    }
+   ],
    "source": [
     "print(f'Size of one time series: {int(time_series[0].nbytes/2**20)} M')\n",
     "print(f'Size of collection: {int(time_series.nbytes/2**20)} M')\n",
@@ -80,15 +69,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2024-03-04T10:06:08.461Z",
-     "iopub.status.busy": "2024-03-04T10:06:08.459Z",
-     "iopub.status.idle": "2024-03-04T10:06:08.466Z",
-     "shell.execute_reply": "2024-03-04T10:06:08.468Z"
-    }
-   },
+   "execution_count": 4,
+   "metadata": {},
    "outputs": [],
    "source": [
     "# compute an approximation of a power series for a collection of gapped timeseries\n",
@@ -100,6 +82,32 @@
     "       "
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "P = np.zeros_like(time_series)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5.53 s ± 1.3 s per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
+     ]
+    }
+   ],
+   "source": [
+    "%timeit power(time_series, P, gap)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -132,7 +140,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def power_improved(time_series, P, gap):\n",
+    "    for pwr in range(30):\n",
+    "        for row_idx, row_values in enumerate(time_series):\n",
+    "            P[row_idx] += (row_values[::gap]**pwr).sum()\n",
+    "    return P"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -163,21 +184,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2024-03-04T10:06:20.056Z",
-     "iopub.status.busy": "2024-03-04T10:06:20.053Z",
-     "iopub.status.idle": "2024-03-04T10:06:21.695Z",
-     "shell.execute_reply": "2024-03-04T10:06:21.700Z"
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "17.8 ms ± 1.56 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
+     ]
     }
-   },
-   "outputs": [],
+   ],
    "source": [
     "P = np.zeros(n_series, dtype='float64')\n",
     "%timeit power_improved(time_series, P, gap)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Learnings:\n",
+    "- just changing the order of the loops: 5.5 s -> 24.2 ms\n",
+    "- also enumerating and accessing the rows: 17.8 ms"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -202,12 +233,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.13.5"
+   "version": "3.13.6"
   },
   "nteract": {
    "version": "0.28.0"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }