more tests

Author: MatthewCaseres

str_performance.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -73,7 +73,7 @@
        "2      2     C          0.9"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -85,15 +85,22 @@
     "        'value|float': [0.3, 0.5, 0.9]\n",
     "    }\n",
     ")\n",
+    "df2_int = pd.DataFrame(\n",
+    "    {\n",
+    "        'x|int':[0, 1, 2],\n",
+    "        'value|float': [0.3, 0.5, 0.9]\n",
+    "    }\n",
+    ")\n",
     "str_lookup = Table(df2)\n",
-    "int_lookup = np.array([0.3, 0.5, 0.9])\n",
+    "int_lookup = Table(df2_int)\n",
+    "int_lookup_raw = np.array([0.3, 0.5, 0.9])\n",
     "df2_index = df2.reset_index()\n",
     "df2_index"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -106,35 +113,22 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 18,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([1, 2, 1, 2])"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
    "source": [
-    "np.tile(np.array([1,2]), 2)"
+    "## length 100k"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "8.8 ms ± 486 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
+      "12.9 ms ± 1.61 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
      ]
     }
    ],
@@ -145,107 +139,99 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1.03 s ± 61.7 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
+      "360 µs ± 55.7 µs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)\n"
      ]
     }
    ],
    "source": [
     "%%timeit\n",
-    "str_lookup[long_str_array]"
+    "int_lookup[int_array]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "105 µs ± 7.44 µs per loop (mean ± std. dev. of 7 runs, 10,000 loops each)\n"
+      "141 µs ± 30.4 µs per loop (mean ± std. dev. of 7 runs, 10,000 loops each)\n"
      ]
     }
    ],
    "source": [
     "%%timeit\n",
-    "int_lookup[int_array]"
+    "int_lookup_raw[int_array]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Length 10 mil"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "19.9 ms ± 3.22 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
+      "872 ms ± 47.9 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
    "source": [
     "%%timeit\n",
-    "int_lookup[long_int_array]"
+    "str_lookup[long_str_array]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "83.80952380952382"
-      ]
-     },
-     "execution_count": 24,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "38.3 ms ± 2.88 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
+     ]
     }
    ],
    "source": [
-    "# how many times slower is the one of size 100_000\n",
-    "8.8/.105"
+    "%%timeit\n",
+    "int_lookup[long_int_array]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "51.75879396984925"
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "17.4 ms ± 576 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
+     ]
     }
    ],
    "source": [
-    "# how many times slower is the one of size 10_000_000\n",
-    "1030/19.9"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assert np.all(str_lookup[str_array] == int_lookup[int_array])"
+    "%%timeit\n",
+    "int_lookup_raw[long_int_array]"
    ]
   }
  ],