{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# NumPy basics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "# Set seed for reproducibility\n",
    "np.random.seed(seed=123)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Scalars"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('sk_id_curr: ', array(100001))\n",
      "('sk_id_curr ndim: ', 0)\n",
      "('sk_id_curr shape:', ())\n",
      "('sk_id_curr size: ', 1)\n",
      "('sk_id_curr dtype: ', dtype('int64'))\n"
     ]
    }
   ],
   "source": [
    "sk_id_curr = np.array(100001)\n",
    "print (\"sk_id_curr: \", sk_id_curr)\n",
    "\n",
    "# Number of dimensions\n",
    "print (\"sk_id_curr ndim: \", sk_id_curr.ndim)\n",
    "\n",
    "# Dimensions\n",
    "print (\"sk_id_curr shape:\", sk_id_curr.shape)\n",
    "\n",
    "# Size of elements\n",
    "print (\"sk_id_curr size: \", sk_id_curr.size)\n",
    "\n",
    "# Data type\n",
    "print (\"sk_id_curr dtype: \", sk_id_curr.dtype)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1-D Array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('sk_id_curr:', array([100001, 100005, 100013, 100028, 100038, 100042]))\n",
      "('sk_id_curr ndim: ', 1)\n",
      "('sk_id_curr shape:', (6,))\n",
      "('sk_id_curr size: ', 6)\n",
      "('sk_id_curr dtype: ', dtype('int64'))\n"
     ]
    }
   ],
   "source": [
    "sk_id_curr = np.array([100001, 100005, 100013, 100028, 100038, 100042])\n",
    "print (\"sk_id_curr:\", sk_id_curr)\n",
    "print (\"sk_id_curr ndim: \", sk_id_curr.ndim)\n",
    "print (\"sk_id_curr shape:\", sk_id_curr.shape)\n",
    "print (\"sk_id_curr size: \", sk_id_curr.size)\n",
    "print (\"sk_id_curr dtype: \", sk_id_curr.dtype)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2-D array (matrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('sk_id_curr:', array([[100001, 100005],\n",
      "       [100013, 100028],\n",
      "       [100038, 100042]]))\n",
      "('sk_id_curr ndim: ', 2)\n",
      "('sk_id_curr shape:', (3, 2))\n",
      "('sk_id_curr size: ', 6)\n",
      "('sk_id_curr dtype: ', dtype('int64'))\n"
     ]
    }
   ],
   "source": [
    "sk_id_curr = np.array([[100001, 100005], [100013, 100028], [100038, 100042]])\n",
    "print (\"sk_id_curr:\", sk_id_curr)\n",
    "print (\"sk_id_curr ndim: \", sk_id_curr.ndim)\n",
    "print (\"sk_id_curr shape:\", sk_id_curr.shape)\n",
    "print (\"sk_id_curr size: \", sk_id_curr.size)\n",
    "print (\"sk_id_curr dtype: \", sk_id_curr.dtype)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Functions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('np.zeros((2,2)):', array([[0., 0.],\n",
      "       [0., 0.]]))\n",
      "('np.ones((2,2)):', array([[1., 1.],\n",
      "       [1., 1.]]))\n",
      "('np.eye((2)):', array([[1., 0.],\n",
      "       [0., 1.]]))\n",
      "('np.random.random((2,2)):', array([[0.69646919, 0.28613933],\n",
      "       [0.22685145, 0.55131477]]))\n"
     ]
    }
   ],
   "source": [
    "print (\"np.zeros((2,2)):\", np.zeros((2,2)))\n",
    "print (\"np.ones((2,2)):\", np.ones((2,2)))\n",
    "print (\"np.eye((2)):\", np.eye((2)))\n",
    "print (\"np.random.random((2,2)):\", np.random.random((2,2)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Accessing\n",
    "\n",
    "## Indexing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('sk_id_curr[0]: ', 100001)\n",
      "('sk_id_curr: ', array([     0, 100005, 100013, 100028, 100038, 100042]))\n"
     ]
    }
   ],
   "source": [
    "sk_id_curr = np.array([100001, 100005, 100013, 100028, 100038, 100042])\n",
    "print (\"sk_id_curr[0]: \", sk_id_curr[0])\n",
    "sk_id_curr[0] = 0\n",
    "print (\"sk_id_curr: \", sk_id_curr)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Slicing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[100001 100005 111111]\n",
      " [100013 100028 222222]\n",
      " [100038 100042 333333]]\n",
      "('sk_id_curr column 1: ', array([100005, 100028, 100042]))\n",
      "('sk_id_curr row 0: ', array([100001, 100005, 111111]))\n",
      "('sk_id_curr rows 0,1,2 & cols 1,2:', array([[100005, 111111],\n",
      "       [100028, 222222],\n",
      "       [100042, 333333]]))\n"
     ]
    }
   ],
   "source": [
    "sk_id_curr = np.array([[100001, 100005, 111111], [100013, 100028, 222222], [100038, 100042, 333333]])\n",
    "print (sk_id_curr)\n",
    "print (\"sk_id_curr column 1: \", sk_id_curr[:, 1]) \n",
    "print (\"sk_id_curr row 0: \", sk_id_curr[0, :]) \n",
    "print (\"sk_id_curr rows 0,1,2 & cols 1,2:\", sk_id_curr[:3, 1:3]) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Boolean array indexing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('sk_id_curr:', array([[100001, 100005, 111111],\n",
      "       [100013, 100028, 222222],\n",
      "       [100038, 100042, 333333]]))\n",
      "('sk_id_curr > 111111:', array([[False, False, False],\n",
      "       [False, False,  True],\n",
      "       [False, False,  True]]))\n",
      "('sk_id_curr[sk_id_curr > 111111]:', array([222222, 333333]))\n"
     ]
    }
   ],
   "source": [
    "sk_id_curr = np.array([[100001, 100005, 111111], [100013, 100028, 222222], [100038, 100042, 333333]])\n",
    "print (\"sk_id_curr:\", sk_id_curr)\n",
    "print (\"sk_id_curr > 111111:\", sk_id_curr > 111111)\n",
    "print (\"sk_id_curr[sk_id_curr > 111111]:\", sk_id_curr[sk_id_curr > 111111])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Array math\n",
    "\n",
    "## Basic math"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('x + y:', array([[2., 4.],\n",
      "       [6., 8.]]))\n",
      "('x - y:', array([[0., 0.],\n",
      "       [0., 0.]]))\n",
      "('x * y:', array([[ 1.,  4.],\n",
      "       [ 9., 16.]]))\n"
     ]
    }
   ],
   "source": [
    "x = np.array([[1,2], [3,4]], dtype=np.float64)\n",
    "y = np.array([[1,2], [3,4]], dtype=np.float64)\n",
    "print (\"x + y:\", np.add(x, y)) # or x + y\n",
    "print (\"x - y:\", np.subtract(x, y)) # or x - y\n",
    "print (\"x * y:\", np.multiply(x, y)) # or x * y"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Dot product"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 58.  64.]\n",
      " [139. 154.]]\n"
     ]
    }
   ],
   "source": [
    "a = np.array([[1,2,3], [4,5,6]], dtype=np.float64) # we can specify dtype\n",
    "b = np.array([[7,8], [9,10], [11, 12]], dtype=np.float64)\n",
    "print (a.dot(b))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Sum across a dimension"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1 2]\n",
      " [3 4]]\n",
      "('sum all: ', 10)\n",
      "('sum by col: ', array([4, 6]))\n",
      "('sum by row: ', array([3, 7]))\n"
     ]
    }
   ],
   "source": [
    "x = np.array([[1,2],[3,4]])\n",
    "print (x)\n",
    "print (\"sum all: \", np.sum(x)) # adds all elements\n",
    "print (\"sum by col: \", np.sum(x, axis=0)) # add numbers in each column\n",
    "print (\"sum by row: \", np.sum(x, axis=1)) # add numbers in each row"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Transposing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('x:', array([[1, 2],\n",
      "       [3, 4]]))\n",
      "('x.T:', array([[1, 3],\n",
      "       [2, 4]]))\n"
     ]
    }
   ],
   "source": [
    "print (\"x:\", x)\n",
    "print (\"x.T:\", x.T)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Broadcasting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "('z:', array([[ 6,  8],\n",
      "       [ 8, 10]]))\n"
     ]
    }
   ],
   "source": [
    "x = np.array([[1,2], [3,4]])\n",
    "y = np.array([5, 6])\n",
    "z = x + y\n",
    "print (\"z:\", z)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Reshaping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1 2]\n",
      " [3 4]\n",
      " [5 6]]\n",
      "('x.shape: ', (3, 2))\n",
      "('y.shape: ', (2, 3))\n",
      "('y:', array([[1, 2, 3],\n",
      "       [4, 5, 6]]))\n"
     ]
    }
   ],
   "source": [
    "x = np.array([[1,2], [3,4], [5,6]])\n",
    "print (x)\n",
    "print (\"x.shape: \", x.shape)\n",
    "y = np.reshape(x, (2, 3))\n",
    "print (\"y.shape: \", y.shape)\n",
    "print (\"y:\", y)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}