searching_algorithm.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Searching algorithms"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import modules"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Module for math operations\n",
    "import math\n",
    "# Module for random number\n",
    "from random import randint\n",
    "# Module for timing\n",
    "import time\n",
    "# Module for dataframe manipulation\n",
    "import pandas as pd\n",
    "# Module for linear algebra calculation\n",
    "import numpy as np\n",
    "# Module for data visualization with plotnine\n",
    "from plotnine import *\n",
    "import plotnine"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Binary search algorithm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Linear search\n",
    "def LinearSearch(lys, element):\n",
    "    for i in range (len(lys)):\n",
    "        if lys[i] == element:\n",
    "            return i\n",
    "    return -1\n",
    "\n",
    "# Binary search\n",
    "def BinarySearch(lys, val):\n",
    "    first = 0\n",
    "    last = len(lys) - 1\n",
    "    index = -1\n",
    "    while (first <= last) and (index == -1):\n",
    "        mid = (first + last) // 2\n",
    "        if lys[mid] == val:\n",
    "            index = mid\n",
    "        else:\n",
    "            if val < lys[mid]:\n",
    "                last = mid - 1\n",
    "            else:\n",
    "                first = mid + 1\n",
    "    return index"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Random number"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Function for random number\n",
    "def random_with_N_digits(n:str):\n",
    "    range_start = 10 ** (n-1)\n",
    "    range_end = (10 ** n) - 1\n",
    "    return randint(range_start, range_end)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Implementation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Generate the random number\n",
    "list_random = []\n",
    "for i in range(50000000):\n",
    "    random = random_with_N_digits(16)\n",
    "    list_random.append(random)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "50000000"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(list_random)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5622880"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index = randint(a = 0, b = 9999999)\n",
    "index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5622880\n",
      "Python script is ran in 0.6124255657 seconds\n"
     ]
    }
   ],
   "source": [
    "# Linear search\n",
    "start = time.time()\n",
    "output = LinearSearch(lys = list_random, element = list_random[index])\n",
    "print(output)\n",
    "end = time.time()\n",
    "dur = round(end - start, ndigits = 10)\n",
    "print('Python script is ran in {} seconds'.format(dur))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Sort list\n",
    "list_random.sort()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5622880\n",
      "Python script is ran in 0.0004997253 seconds\n"
     ]
    }
   ],
   "source": [
    "# Binary search\n",
    "start = time.time()\n",
    "output = BinarySearch(lys = list_random, val = list_random[index])\n",
    "print(output)\n",
    "end = time.time()\n",
    "dur = round(end - start, ndigits = 10)\n",
    "print('Python script is ran in {} seconds'.format(dur))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Simulation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 iteration with 1000000 data -> Linear search 0.054092478750000006 and Binary search 4.9948690000000004e-05\n",
      "1 iteration with 2000000 data -> Linear search 0.11823313235000002 and Binary search 5.011559e-05\n",
      "2 iteration with 3000000 data -> Linear search 0.18282837868 and Binary search 0.0\n",
      "3 iteration with 4000000 data -> Linear search 0.28234910965 and Binary search 0.00010006428\n",
      "4 iteration with 5000000 data -> Linear search 0.25613040923 and Binary search 0.00010011195999999999\n",
      "5 iteration with 6000000 data -> Linear search 0.38807137013 and Binary search 0.00010020733\n",
      "6 iteration with 7000000 data -> Linear search 0.44982182979 and Binary search 5.1903720000000004e-05\n",
      "7 iteration with 8000000 data -> Linear search 0.40378472804000004 and Binary search 0.00010018348999999999\n",
      "8 iteration with 9000000 data -> Linear search 0.65786724092 and Binary search 5.0091739999999996e-05\n",
      "9 iteration with 10000000 data -> Linear search 0.64276418684 and Binary search 0.0\n",
      "10 iteration with 11000000 data -> Linear search 0.54479446412 and Binary search 5.004406e-05\n",
      "11 iteration with 12000000 data -> Linear search 0.53962194921 and Binary search 5.0091739999999996e-05\n",
      "12 iteration with 13000000 data -> Linear search 0.6055282116 and Binary search 0.0\n",
      "13 iteration with 14000000 data -> Linear search 0.65355434418 and Binary search 0.00010006428\n",
      "14 iteration with 15000000 data -> Linear search 1.3124878645 and Binary search 5.0258639999999996e-05\n",
      "15 iteration with 16000000 data -> Linear search 1.00207269191 and Binary search 5.002022e-05\n"
     ]
    }
   ],
   "source": [
    "# List for saving the result\n",
    "list_length = []\n",
    "list_algorithm = []\n",
    "list_time = []\n",
    "list_repetition = []\n",
    "\n",
    "# Length of data\n",
    "length = 1000000\n",
    "\n",
    "for i in range(25):\n",
    "    list_length_linear = []\n",
    "    list_length_binary = []\n",
    "    for _ in range(10):\n",
    "        # Generate dummy data\n",
    "        list_random = []\n",
    "        for _ in range(length):\n",
    "            random = random_with_N_digits(16)\n",
    "            list_random.append(random)\n",
    "        # Get an index\n",
    "        index = randint(a = 0, b = length - 1)\n",
    "        # Linear search\n",
    "        start_linear = time.time()\n",
    "        output_linear = LinearSearch(\n",
    "            lys = list_random,\n",
    "            element = list_random[index]\n",
    "        )\n",
    "        end_linear = time.time()\n",
    "        dur_linear = round(end_linear - start_linear, ndigits = 10)\n",
    "        # Sort list\n",
    "        list_random.sort()\n",
    "        # Binary search\n",
    "        start_binary = time.time()\n",
    "        output_binary = BinarySearch(\n",
    "            lys = list_random,\n",
    "            val = list_random[index]\n",
    "        )\n",
    "        end_binary = time.time()\n",
    "        dur_binary = round(end_binary - start_binary, ndigits = 10)\n",
    "        # Append\n",
    "        list_length_linear.append(dur_linear)\n",
    "        list_length_binary.append(dur_binary)\n",
    "    # Aggregate\n",
    "    avg_linear = np.mean(list_length_linear)\n",
    "    avg_binary = np.mean(list_length_binary)\n",
    "    std_linear = np.std(list_length_linear)\n",
    "    std_binary = np.std(list_length_binary)\n",
    "    # Append the result into list\n",
    "    list_length += [length, length]\n",
    "    list_algorithm += ['Linear Search', 'Binary Search']\n",
    "    list_time += [avg_linear, avg_binary]\n",
    "    list_std += [std_linear, std_binary]\n",
    "    # Status\n",
    "    print('{} iteration with {} data -> Linear search {} and Binary search {}'\n",
    "          .format(i, length, avg_linear, avg_binary))\n",
    "    length += 1000000"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 iteration 9 subiteration with 1000000 data -> Linear search 0.02521407605 and Binary search 0.0\n",
      "1 iteration 9 subiteration with 2000000 data -> Linear search 0.10357222556999998 and Binary search 0.0\n",
      "2 iteration 9 subiteration with 3000000 data -> Linear search 0.20184190271999997 and Binary search 5.0067899999999995e-05\n",
      "3 iteration 9 subiteration with 4000000 data -> Linear search 0.19178800582 and Binary search 0.0\n",
      "4 iteration 9 subiteration with 5000000 data -> Linear search 0.18162820338000002 and Binary search 0.0\n",
      "5 iteration 9 subiteration with 6000000 data -> Linear search 0.2769510746 and Binary search 0.0\n",
      "6 iteration 9 subiteration with 7000000 data -> Linear search 0.25197918416 and Binary search 0.0\n",
      "7 iteration 9 subiteration with 8000000 data -> Linear search 0.40313000678 and Binary search 0.0\n",
      "8 iteration 9 subiteration with 9000000 data -> Linear search 0.45368177891000006 and Binary search 0.0\n",
      "9 iteration 9 subiteration with 10000000 data -> Linear search 0.42329297065999993 and Binary search 0.00015017986\n",
      "10 iteration 9 subiteration with 11000000 data -> Linear search 0.62357845307 and Binary search 5.0067899999999995e-05\n",
      "11 iteration 9 subiteration with 12000000 data -> Linear search 0.45845260620999995 and Binary search 5.004406e-05\n",
      "12 iteration 9 subiteration with 13000000 data -> Linear search 0.7790304660799998 and Binary search 0.0\n",
      "13 iteration 9 subiteration with 14000000 data -> Linear search 0.55329079629 and Binary search 5.0139430000000005e-05\n",
      "14 iteration 9 subiteration with 15000000 data -> Linear search 0.51841354371 and Binary search 4.999638e-05\n",
      "15 iteration 9 subiteration with 16000000 data -> Linear search 0.7083779811900002 and Binary search 5.0067899999999995e-05\n",
      "16 iteration 9 subiteration with 17000000 data -> Linear search 0.7588955402299999 and Binary search 5.002022e-05\n",
      "17 iteration 9 subiteration with 18000000 data -> Linear search 0.92823784351 and Binary search 0.0\n",
      "18 iteration 9 subiteration with 19000000 data -> Linear search 1.1218131780699998 and Binary search 9.961128e-05\n",
      "19 iteration 9 subiteration with 20000000 data -> Linear search 0.95230505466 and Binary search 0.00010006428\n",
      "20 iteration 9 subiteration with 21000000 data -> Linear search 1.17558131218 and Binary search 0.00010004044\n",
      "21 iteration 9 subiteration with 22000000 data -> Linear search 1.2423262596 and Binary search 0.00015013218\n",
      "22 iteration 9 subiteration with 23000000 data -> Linear search 1.58086092473 and Binary search 9.989739000000001e-05\n",
      "23 iteration 9 subiteration with 24000000 data -> Linear search 1.6064237117800002 and Binary search 5.002022e-05\n",
      "24 iteration 9 subiteration with 25000000 data -> Linear search 1.74678831102 and Binary search 0.0\n"
     ]
    }
   ],
   "source": [
    "# List for saving the result\n",
    "list_length = []\n",
    "list_algorithm = []\n",
    "list_time = []\n",
    "list_repetition = []\n",
    "\n",
    "# Length of data\n",
    "length = 1000000\n",
    "\n",
    "for i in range(25):\n",
    "    list_time_linear = []\n",
    "    list_time_binary = []\n",
    "    for j in range(10):\n",
    "        # Generate dummy data\n",
    "        list_random = []\n",
    "        for _ in range(length):\n",
    "            random = random_with_N_digits(16)\n",
    "            list_random.append(random)\n",
    "        # Get an index\n",
    "        index = randint(a = 0, b = length - 1)\n",
    "        # Linear search\n",
    "        start_linear = time.time()\n",
    "        output_linear = LinearSearch(\n",
    "            lys = list_random,\n",
    "            element = list_random[index]\n",
    "        )\n",
    "        end_linear = time.time()\n",
    "        dur_linear = round(end_linear - start_linear, ndigits = 10)\n",
    "        # Sort list\n",
    "        list_random.sort()\n",
    "        # Binary search\n",
    "        start_binary = time.time()\n",
    "        output_binary = BinarySearch(\n",
    "            lys = list_random,\n",
    "            val = list_random[index]\n",
    "        )\n",
    "        end_binary = time.time()\n",
    "        dur_binary = round(end_binary - start_binary, ndigits = 10)\n",
    "        # Append the result into list\n",
    "        list_length += [length, length]\n",
    "        list_algorithm += ['Linear Search', 'Binary Search']\n",
    "        list_time += [dur_linear, dur_binary]\n",
    "        list_repetition += [j, j]\n",
    "        list_time_linear.append(dur_linear)\n",
    "        list_time_binary.append(dur_binary)\n",
    "    # Status\n",
    "    avg_time_linear = np.mean(list_time_linear)\n",
    "    avg_time_binary = np.mean(list_time_binary)\n",
    "    print('{} iteration {} subiteration with {} data -> Linear search {} and Binary search {}'\n",
    "          .format(i, j, length, avg_time_linear, avg_time_binary))\n",
    "    length += 1000000"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "code_folding": []
   },
   "outputs": [],
   "source": [
    "# Create a dataframe\n",
    "df = pd.DataFrame(\n",
    "        {\n",
    "            'length': list_length,\n",
    "            'algorithm': list_algorithm,\n",
    "            'repetition': list_repetition,\n",
    "            'time': list_time\n",
    "        }\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dimension: 500 rows and 4 columns\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>length</th>\n",
       "      <th>algorithm</th>\n",
       "      <th>repetition</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1000000</td>\n",
       "      <td>Linear Search</td>\n",
       "      <td>0</td>\n",
       "      <td>0.012009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1000000</td>\n",
       "      <td>Binary Search</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1000000</td>\n",
       "      <td>Linear Search</td>\n",
       "      <td>1</td>\n",
       "      <td>0.030502</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1000000</td>\n",
       "      <td>Binary Search</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1000000</td>\n",
       "      <td>Linear Search</td>\n",
       "      <td>2</td>\n",
       "      <td>0.019513</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    length      algorithm  repetition      time\n",
       "0  1000000  Linear Search           0  0.012009\n",
       "1  1000000  Binary Search           0  0.000000\n",
       "2  1000000  Linear Search           1  0.030502\n",
       "3  1000000  Binary Search           1  0.000000\n",
       "4  1000000  Linear Search           2  0.019513"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print('Dimension: {} rows and {} columns'.format(len(df), len(df.columns)))\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data aggregation\n",
    "df_agg = df.groupby(['algorithm', 'length']).agg(\n",
    "    {\n",
    "        'time': ['mean', 'std']\n",
    "    }\n",
    ")\n",
    "# Multi index to single index\n",
    "df_agg.columns = df_agg.columns.droplevel(0)\n",
    "df_agg.reset_index(inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dimension: 50 rows and 4 columns\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>algorithm</th>\n",
       "      <th>length</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>Linear Search</td>\n",
       "      <td>21000000</td>\n",
       "      <td>1.175581</td>\n",
       "      <td>0.595206</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>Linear Search</td>\n",
       "      <td>22000000</td>\n",
       "      <td>1.242326</td>\n",
       "      <td>0.789555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>Linear Search</td>\n",
       "      <td>23000000</td>\n",
       "      <td>1.580861</td>\n",
       "      <td>1.184239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48</th>\n",
       "      <td>Linear Search</td>\n",
       "      <td>24000000</td>\n",
       "      <td>1.606424</td>\n",
       "      <td>0.963171</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49</th>\n",
       "      <td>Linear Search</td>\n",
       "      <td>25000000</td>\n",
       "      <td>1.746788</td>\n",
       "      <td>0.819139</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        algorithm    length      mean       std\n",
       "45  Linear Search  21000000  1.175581  0.595206\n",
       "46  Linear Search  22000000  1.242326  0.789555\n",
       "47  Linear Search  23000000  1.580861  1.184239\n",
       "48  Linear Search  24000000  1.606424  0.963171\n",
       "49  Linear Search  25000000  1.746788  0.819139"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print('Dimension: {} rows and {} columns'.format(len(df_agg), len(df_agg.columns)))\n",
    "df_agg.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x480 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<ggplot: (144906419767)>"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Time-series plot\n",
    "plotnine.options.figure_size = (8, 4.8)\n",
    "(\n",
    "    ggplot(data = df_agg)+\n",
    "    geom_line(aes(x = 'length',\n",
    "                  y = 'mean',\n",
    "                  color = 'algorithm',\n",
    "                  group = 'algorithm'),\n",
    "              size = 1.5)+\n",
    "    geom_point(aes(x = 'length',\n",
    "                   y = 'mean'),\n",
    "               size = 2)+\n",
    "    scale_color_manual(name = 'Algorithm', \n",
    "                      values = ['#80797c', '#981220'], \n",
    "                      labels = ['Binary search', 'Linear search'])+\n",
    "    labs(title = 'Searching Algorithm Performance')+\n",
    "    xlab('Number of Observations')+\n",
    "    ylab('Time (second)')+\n",
    "    theme_minimal()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['length'] = df['length'].astype('category')\n",
    "df['length'] = df['length'].cat.reorder_categories(list(map(str, df['length'].unique())))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x480 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<ggplot: (144922408533)>"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Box and whisker plot\n",
    "plotnine.options.figure_size = (8, 4.8)\n",
    "(\n",
    "    ggplot(data = df)+\n",
    "    geom_boxplot(aes(x = 'length',\n",
    "                     y = 'time',\n",
    "                     fill = 'algorithm'))+\n",
    "    labs(title = 'Standard Deviation of Searching Algorithm Performance')+\n",
    "    scale_fill_manual(name = 'Algorithm',\n",
    "                      values = ['#80797c', '#981220'],\n",
    "                      labels = ['Binary search', 'Linear search'])+\n",
    "    xlab('Number of Observations')+\n",
    "    ylab('Time (second)')+\n",
    "    coord_flip()+\n",
    "    theme_minimal()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Functions of searching algorithm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv('df_1.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Linear search\n",
    "def LinearSearch(lys, element):\n",
    "    for i in range (len(lys)):\n",
    "        if lys[i] == element:\n",
    "            return i\n",
    "    return -1\n",
    "\n",
    "# Binary search\n",
    "def BinarySearch(lys, val):\n",
    "    first = 0\n",
    "    last = len(lys) - 1\n",
    "    index = -1\n",
    "    while (first <= last) and (index == -1):\n",
    "        mid = (first+last) // 2\n",
    "        if lys[mid] == val:\n",
    "            index = mid\n",
    "        else:\n",
    "            if val<lys[mid]:\n",
    "                last = mid - 1\n",
    "            else:\n",
    "                first = mid + 1\n",
    "    return index\n",
    "\n",
    "# Jump search\n",
    "def JumpSearch (lys, val):\n",
    "    length = len(lys)\n",
    "    jump = int(math.sqrt(length))\n",
    "    left, right = 0, 0\n",
    "    while left < length and lys[left] <= val:\n",
    "        right = min(length - 1, left + jump)\n",
    "        if lys[left] <= val and lys[right] >= val:\n",
    "            break\n",
    "        left += jump;\n",
    "    if left >= length or lys[left] > val:\n",
    "        return -1\n",
    "    right = min(length - 1, right)\n",
    "    i = left\n",
    "    while i <= right and lys[i] <= val:\n",
    "        if lys[i] == val:\n",
    "            return i\n",
    "        i += 1\n",
    "    return -1\n",
    "\n",
    "# Fibonacci search\n",
    "def FibonacciSearch(lys, val):\n",
    "    fibM_minus_2 = 0\n",
    "    fibM_minus_1 = 1\n",
    "    fibM = fibM_minus_1 + fibM_minus_2\n",
    "    while (fibM < len(lys)):\n",
    "        fibM_minus_2 = fibM_minus_1\n",
    "        fibM_minus_1 = fibM\n",
    "        fibM = fibM_minus_1 + fibM_minus_2\n",
    "    index = -1;\n",
    "    while (fibM > 1):\n",
    "        i = min(index + fibM_minus_2, (len(lys)-1))\n",
    "        if (lys[i] < val):\n",
    "            fibM = fibM_minus_1\n",
    "            fibM_minus_1 = fibM_minus_2\n",
    "            fibM_minus_2 = fibM - fibM_minus_1\n",
    "            index = i\n",
    "        elif (lys[i] > val):\n",
    "            fibM = fibM_minus_2\n",
    "            fibM_minus_1 = fibM_minus_1 - fibM_minus_2\n",
    "            fibM_minus_2 = fibM - fibM_minus_1\n",
    "        else :\n",
    "            return i\n",
    "    if(fibM_minus_1 and index < (len(lys)-1) and lys[index+1] == val):\n",
    "        return index+1;\n",
    "    return -1\n",
    "\n",
    "# Exponential search\n",
    "def ExponentialSearch(lys, val):\n",
    "    if lys[0] == val:\n",
    "        return 0\n",
    "    index = 1\n",
    "    while index < len(lys) and lys[index] <= val:\n",
    "        index = index * 2\n",
    "    return BinarySearch( arr[:min(index, len(lys))], val)\n",
    "\n",
    "# Interpolation search\n",
    "def InterpolationSearch(lys, val):\n",
    "    low = 0\n",
    "    high = (len(lys) - 1)\n",
    "    while low <= high and val >= lys[low] and val <= lys[high]:\n",
    "        index = low + int(((float(high - low) / ( lys[high] - lys[low])) * ( val - lys[low])))\n",
    "        if lys[index] == val:\n",
    "            return index\n",
    "        if lys[index] < val:\n",
    "            low = index + 1;\n",
    "        else:\n",
    "            high = index - 1;\n",
    "    return -1"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}