Added reshaping examples

Author: FlipWebApps

Numpy and Pandas.ipynb

@@ -2,10 +2,8 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 2,
+   "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd\n",
@@ -22,10 +20,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 123,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 3,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -59,7 +55,8 @@
       "\n",
       "2d numpy array with different number of multiple elements in the second dimension\n",
       "\n",
-      "[[5, 6] [10, 11] [15, 16] [20] [25] [30]]\n",
+      "[list([5, 6]) list([10, 11]) list([15, 16]) list([20]) list([25])\n",
+      " list([30])]\n",
       "Dimensions: 1\n",
       "Shape: (6,)\n",
       "<class 'numpy.ndarray'>\n",
@@ -139,10 +136,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 124,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 4,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -246,10 +241,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 112,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 5,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -298,33 +291,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 113,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 6,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "Select single column by single value (df[])\n",
-      "0     5\n",
-      "1    10\n",
-      "2    15\n",
-      "3    20\n",
-      "4    25\n",
-      "5    30\n",
-      "Name: 1, dtype: int64\n",
+      "0     6\n",
+      "1    11\n",
+      "2    16\n",
+      "3    21\n",
+      "4    26\n",
+      "5    31\n",
+      "Name: 1, dtype: int32\n",
       "<class 'pandas.core.series.Series'>\n",
       "\n",
       "Select single (or multiple) columns by list (df[[]])\n",
       "    1\n",
-      "0   5\n",
-      "1  10\n",
-      "2  15\n",
-      "3  20\n",
-      "4  25\n",
-      "5  30\n",
+      "0   6\n",
+      "1  11\n",
+      "2  16\n",
+      "3  21\n",
+      "4  26\n",
+      "5  31\n",
       "<class 'pandas.core.frame.DataFrame'>\n"
      ]
     }
@@ -351,10 +342,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 127,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 7,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -422,10 +411,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 126,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 8,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -471,10 +458,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 121,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 9,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -507,12 +492,12 @@
       "\n",
       "Adding single column DataFrame and 2d (x,1) arrays:\n",
       "    1\n",
-      "0  10\n",
-      "1  20\n",
-      "2  30\n",
-      "3  40\n",
-      "4  50\n",
-      "5  60\n",
+      "0  11\n",
+      "1  21\n",
+      "2  31\n",
+      "3  41\n",
+      "4  51\n",
+      "5  61\n",
       "<class 'pandas.core.frame.DataFrame'>\n",
       "\n",
       "Adding single column DataFrame and 1d np arrays:\n",
@@ -589,13 +574,123 @@
     "\n",
     "tt = t.reshape(-1)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Reshaping\n",
+    "1D -> 2D e.g. scikit-learn requires that 1D array of output variables be shaped as a 2D array with one column and outcomes for each column.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1d numpy array:\n",
+      "[ 5 10 15 20 25 30]\n",
+      "(6,)\n",
+      "reshaped to 2D:\n",
+      "[[ 5]\n",
+      " [10]\n",
+      " [15]\n",
+      " [20]\n",
+      " [25]\n",
+      " [30]]\n",
+      "(6, 1)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"1d numpy array:\")\n",
+    "print(np_array1d)\n",
+    "print(np_array1d.shape)\n",
+    "\n",
+    "# reshape\n",
+    "print(\"reshaped to 2D:\")\n",
+    "data = np_array1d.reshape((np_array1d.shape[0], 1))\n",
+    "print(data)\n",
+    "print(data.shape)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "2D -> 3D e.g. scikit-learn requires that 1D array of output variables be shaped as a 2D array with one column and outcomes for each column.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2d numpy array:\n",
+      "[[ 5  6]\n",
+      " [10 11]\n",
+      " [15 16]\n",
+      " [20 21]\n",
+      " [25 26]\n",
+      " [30 31]]\n",
+      "(6, 2)\n",
+      "reshaped to 2D:\n",
+      "[[[ 5]\n",
+      "  [ 6]]\n",
+      "\n",
+      " [[10]\n",
+      "  [11]]\n",
+      "\n",
+      " [[15]\n",
+      "  [16]]\n",
+      "\n",
+      " [[20]\n",
+      "  [21]]\n",
+      "\n",
+      " [[25]\n",
+      "  [26]]\n",
+      "\n",
+      " [[30]\n",
+      "  [31]]]\n",
+      "(6, 2, 1)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"2d numpy array:\")\n",
+    "print(np_array2d62)\n",
+    "print(np_array2d62.shape)\n",
+    "\n",
+    "# reshape\n",
+    "print(\"reshaped to 2D:\")\n",
+    "data = np_array2d62.reshape((np_array2d62.shape[0], np_array2d62.shape[1], 1))\n",
+    "print(data)\n",
+    "print(data.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python [default]",
+   "display_name": "Anaconda",
    "language": "python",
-   "name": "python3"
+   "name": "anaconda"
   },
   "language_info": {
    "codemirror_mode": {
@@ -607,7 +702,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.4"
   }
  },
  "nbformat": 4,