Update for DataFrames 0.19.0

bkamins · Jul 16, 2019 · 8f3ef03 · 8f3ef03
1 parent a6f4f8f
commit 8f3ef03
Show file tree

Hide file tree

Showing 14 changed files with 1,494 additions and 1,413 deletions.
diff --git a/01_constructors.ipynb b/01_constructors.ipynb
diff --git a/02_basicinfo.ipynb b/02_basicinfo.ipynb
diff --git a/03_missingvalues.ipynb b/03_missingvalues.ipynb
@@ -5,7 +5,7 @@
    "metadata": {},
    "source": [
     "# Introduction to DataFrames\n",
-    "**[Bogumił Kamiński](http://bogumilkaminski.pl/about/), April 30, 2019**"
+    "**[Bogumił Kamiński](http://bogumilkaminski.pl/about/), July 16, 2019**"
    ]
   },
   {
@@ -14,7 +14,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "using DataFrames # load package"
+    "using DataFrames"
    ]
   },
   {
@@ -1159,10 +1159,14 @@
   }
  ],
  "metadata": {
+  "@webio": {
+   "lastCommId": null,
+   "lastKernelId": null
+  },
   "kernelspec": {
-   "display_name": "Julia 1.0.3",
+   "display_name": "Julia 1.1.0",
    "language": "julia",
-   "name": "julia-1.0"
+   "name": "julia-1.1"
   },
   "language_info": {
    "file_extension": ".jl",

diff --git a/04_loadsave.ipynb b/04_loadsave.ipynb
@@ -5,7 +5,7 @@
    "metadata": {},
    "source": [
     "# Introduction to DataFrames\n",
-    "**[Bogumił Kamiński](http://bogumilkaminski.pl/about/), April 27, 2019**"
+    "**[Bogumił Kamiński](http://bogumilkaminski.pl/about/), July 16, 2019**"
    ]
   },
   {
@@ -14,7 +14,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "using DataFrames # load package"
+    "using DataFrames"
    ]
   },
   {
@@ -194,13 +194,13 @@
     {
      "data": {
       "text/html": [
-       "<table class=\"data-frame\"><thead><tr><th></th><th>A</th><th>B</th><th>C</th><th>D</th></tr><tr><th></th><th>Bool⍰</th><th>Int64⍰</th><th>String⍰</th><th>String⍰</th></tr></thead><tbody><p>3 rows × 4 columns</p><tr><th>1</th><td>true</td><td>1</td><td>missing</td><td>a</td></tr><tr><th>2</th><td>false</td><td>2</td><td>b</td><td>missing</td></tr><tr><th>3</th><td>true</td><td>missing</td><td>c</td><td>c</td></tr></tbody></table>"
+       "<table class=\"data-frame\"><thead><tr><th></th><th>A</th><th>B</th><th>C</th><th>D</th></tr><tr><th></th><th>Bool</th><th>Int64⍰</th><th>String⍰</th><th>String⍰</th></tr></thead><tbody><p>3 rows × 4 columns</p><tr><th>1</th><td>true</td><td>1</td><td>missing</td><td>a</td></tr><tr><th>2</th><td>false</td><td>2</td><td>b</td><td>missing</td></tr><tr><th>3</th><td>true</td><td>missing</td><td>c</td><td>c</td></tr></tbody></table>"
       ],
       "text/latex": [
        "\\begin{tabular}{r|cccc}\n",
        "\t& A & B & C & D\\\\\n",
        "\t\\hline\n",
-       "\t& Bool⍰ & Int64⍰ & String⍰ & String⍰\\\\\n",
+       "\t& Bool & Int64⍰ & String⍰ & String⍰\\\\\n",
        "\t\\hline\n",
        "\t1 & true & 1 &  & a \\\\\n",
        "\t2 & false & 2 & b &  \\\\\n",
@@ -210,7 +210,7 @@
       "text/plain": [
        "3×4 DataFrame\n",
        "│ Row │ A     │ B       │ C       │ D       │\n",
-       "│     │ \u001b[90mBool⍰\u001b[39m │ \u001b[90mInt64⍰\u001b[39m  │ \u001b[90mString⍰\u001b[39m │ \u001b[90mString⍰\u001b[39m │\n",
+       "│     │ \u001b[90mBool\u001b[39m  │ \u001b[90mInt64⍰\u001b[39m  │ \u001b[90mString⍰\u001b[39m │ \u001b[90mString⍰\u001b[39m │\n",
        "├─────┼───────┼─────────┼─────────┼─────────┤\n",
        "│ 1   │ true  │ 1       │ \u001b[90mmissing\u001b[39m │ a       │\n",
        "│ 2   │ false │ 2       │ b       │ \u001b[90mmissing\u001b[39m │\n",
@@ -241,8 +241,8 @@
     {
      "data": {
       "text/plain": [
-       "4-element Array{Union,1}:\n",
-       " Union{Missing, Bool}  \n",
+       "4-element Array{Type,1}:\n",
+       " Bool                  \n",
        " Union{Missing, Int64} \n",
        " Union{Missing, String}\n",
        " Union{Missing, String}"
@@ -635,25 +635,25 @@
      "output_type": "stream",
      "text": [
       "First run\n",
-      "  0.745948 seconds (814.64 k allocations: 40.707 MiB, 4.48% gc time)\n",
-      "  1.050906 seconds (830.88 k allocations: 42.539 MiB, 2.87% gc time)\n",
-      "  0.213652 seconds (427.49 k allocations: 21.266 MiB)\n",
-      "  0.318751 seconds (373.35 k allocations: 25.882 MiB, 9.61% gc time)\n",
+      "  1.234840 seconds (1.37 M allocations: 68.621 MiB, 3.34% gc time)\n",
+      "  1.502894 seconds (929.64 k allocations: 47.285 MiB, 1.93% gc time)\n",
+      "  0.275374 seconds (427.33 k allocations: 21.270 MiB, 5.51% gc time)\n",
+      "  0.352993 seconds (397.80 k allocations: 27.044 MiB, 3.63% gc time)\n",
       "Second run\n",
-      "  0.024630 seconds (54.97 k allocations: 1.052 MiB)\n",
-      "  0.016964 seconds (5.53 k allocations: 340.375 KiB)\n",
-      "  0.022761 seconds (4.81 k allocations: 243.089 KiB)\n",
-      "  0.018969 seconds (34.02 k allocations: 9.008 MiB)\n"
+      "  0.024408 seconds (6.57 k allocations: 292.781 KiB)\n",
+      "  0.017290 seconds (5.54 k allocations: 342.203 KiB)\n",
+      "  0.019022 seconds (4.81 k allocations: 243.089 KiB)\n",
+      "  0.042060 seconds (34.02 k allocations: 9.023 MiB, 28.03% gc time)\n"
      ]
     },
     {
      "data": {
       "text/plain": [
        "4-element Array{Int64,1}:\n",
-       " 558378\n",
-       " 558578\n",
-       "  84439\n",
-       "  54072"
+       " 558383\n",
+       " 558583\n",
+       "  84312\n",
+       "  54096"
       ]
      },
      "execution_count": 20,
@@ -663,9 +663,9 @@
    ],
    "source": [
     "bigdf = DataFrame(rand(Bool, 10^3, 10^2))\n",
-    "bigdf[1] = Int.(bigdf[1])\n",
-    "bigdf[2] = bigdf[2] .+ 0.5\n",
-    "bigdf[3] = string.(bigdf[3], \", as string\")\n",
+    "bigdf[!, 1] = Int.(bigdf[!, 1])\n",
+    "bigdf[!, 2] = bigdf[!, 2] .+ 0.5\n",
+    "bigdf[!, 3] = string.(bigdf[!, 3], \", as string\")\n",
     "println(\"First run\")\n",
     "@time CSV.write(\"bigdf1.csv\", bigdf)\n",
     "@time bigdf |> save(\"bigdf2.csv\")\n",
@@ -689,15 +689,15 @@
      "output_type": "stream",
      "text": [
       "First run\n",
-      "  0.622640 seconds (802.64 k allocations: 28.521 MiB, 2.97% gc time)\n",
-      "  1.679781 seconds (2.60 M allocations: 218.270 MiB, 8.63% gc time)\n",
-      "  0.042708 seconds (72.82 k allocations: 2.008 MiB)\n",
-      "  0.673740 seconds (639.10 k allocations: 32.375 MiB, 4.97% gc time)\n",
+      "  0.112875 seconds (86.70 k allocations: 4.845 MiB)\n",
+      "  1.787776 seconds (2.63 M allocations: 219.289 MiB, 6.75% gc time)\n",
+      "  0.044459 seconds (72.82 k allocations: 2.008 MiB)\n",
+      "  0.562682 seconds (640.06 k allocations: 32.471 MiB, 4.13% gc time)\n",
       "Second run\n",
-      "  0.048690 seconds (52.07 k allocations: 1.326 MiB)\n",
-      "  0.099486 seconds (506.49 k allocations: 108.821 MiB, 54.91% gc time)\n",
-      "  0.006630 seconds (49.60 k allocations: 951.719 KiB)\n",
-      "  0.007290 seconds (26.39 k allocations: 1.200 MiB)\n"
+      "  0.010963 seconds (2.15 k allocations: 85.773 KiB)\n",
+      "  0.101021 seconds (506.69 k allocations: 108.049 MiB, 52.35% gc time)\n",
+      "  0.007702 seconds (49.60 k allocations: 952.109 KiB)\n",
+      "  0.007236 seconds (26.39 k allocations: 1.201 MiB)\n"
      ]
     }
    ],
@@ -733,10 +733,14 @@
   }
  ],
  "metadata": {
+  "@webio": {
+   "lastCommId": null,
+   "lastKernelId": null
+  },
   "kernelspec": {
-   "display_name": "Julia 1.0.3",
+   "display_name": "Julia 1.1.0",
    "language": "julia",
-   "name": "julia-1.0"
+   "name": "julia-1.1"
   },
   "language_info": {
    "file_extension": ".jl",