BMGLab_Python_Data_structure.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "s39SnnxrZxsx"
   },
   "source": [
    "# Python Data Structures\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "c_Id55m6Jsbu"
   },
   "source": [
    "> This notebook is largely based on the notebook \"Lesson 5: Python Data Structures\" from Pragmatic AI Labs.\n",
    "\n",
    "https://colab.research.google.com/github/paiml/python_for_datascience/blob/master/Lesson5_Python_For_Data_Science_Python_Data_structure.ipynb#scrollTo=aCBZvOZn3V6D\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Topics Covered\n",
    "##### 1-List\n",
    "##### 2-Tuple\n",
    "##### 3-Set\n",
    "##### 4-Dictionaries\n",
    "##### 5-Numpy Arrays\n",
    "##### 6-Pandas Dataframe"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0mnOHaZpZ1CU"
   },
   "source": [
    "## Lists\n",
    " "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MgQzM2FbzhpW"
   },
   "source": [
    "### Creating an empty list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "1gUdm3jfzlCB",
    "outputId": "a84844d5-a2f6-43f5-f587-8e00535ea56f"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "empty = []\n",
    "\n",
    "empty"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "empty= list()\n",
    "empty"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "fLx7Rtstz3Pn"
   },
   "source": [
    "### Using square brackets with initial values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "X6_VTC9moTAM",
    "outputId": "c218cea9-dbf7-4b5d-d8b2-4915070562a0"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1, 2, 3]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "numbers = [1, 2, 3]\n",
    "numbers\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a=list()\n",
    "a"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "m7FQdEVcAMJl"
   },
   "source": [
    "### Creating using multiplication"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "lanCHsNZATqK",
    "outputId": "afdc49d3-928d-4854-9ff4-4ef2709d10d7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]"
      ]
     },
     "execution_count": 7,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "num_players = 10\n",
    "scores = [0] * num_players\n",
    "scores"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "h9l7kUOC43iL"
   },
   "source": [
    "### Mixing data types\n",
    "Lists can contain multple data types"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "jBqfcq6Q4-Yl",
    "outputId": "38f14f53-4a84-4c4a-d56b-3254d72bd0a7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 1, 2.0, [13], {}]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mixed = ['a', 1, 2.0, [13], {}]\n",
    "mixed"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_rehYX145nEk"
   },
   "source": [
    "### Indexing\n",
    "Items in lists can be accessed using indices "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "PuGNKkIV5_64"
   },
   "source": [
    "#### Access first item"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1, 2, 3]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "numbers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "98QVzpN_ogFQ",
    "outputId": "93224fef-7b66-492e-851c-62c71a4d3eb5"
   },
   "outputs": [
    {
     "ename": "IndexError",
     "evalue": "list index out of range",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mIndexError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[13], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mnumbers\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m]\u001b[49m\n",
      "\u001b[0;31mIndexError\u001b[0m: list index out of range"
     ]
    }
   ],
   "source": [
    "numbers[3]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "wYljuMmX6FDo"
   },
   "source": [
    "#### Access last item"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "j5XB0hVZ6S5E",
    "outputId": "702efb97-d245-4b06-c028-fe8ae61288e6"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "numbers[-1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "tZJYdQW87vwk"
   },
   "source": [
    "#### Access any item"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "7EJZyQUl7y_5",
    "outputId": "433c5b3d-51f9-44ee-bb1b-d8d162c744bf"
   },
   "outputs": [
    {
     "ename": "IndexError",
     "evalue": "list index out of range",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mIndexError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[16], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mnumbers\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m4\u001b[39;49m\u001b[43m]\u001b[49m\n",
      "\u001b[0;31mIndexError\u001b[0m: list index out of range"
     ]
    }
   ],
   "source": [
    "numbers[4]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "g4-XjayC8KO7"
   },
   "source": [
    "### Adding to a list"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "VVoxc0Co81iD"
   },
   "source": [
    "#### Append to the end of a list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "7l9O1BOz89Sg",
    "outputId": "f5ed7734-afd3-4dcd-8311-ac809622b29b"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 19]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters = ['a']\n",
    "letters.append('c')\n",
    "letters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "GOWYij2p9bwL"
   },
   "source": [
    "#### Insert at beginning of list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "KgMcKp5W9fI7",
    "outputId": "5f5acb75-5715-456a-f63b-76d675676766"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['b', 'a', 19]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters.insert(0, 'b')\n",
    "letters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "z2pfGnq7-PHc"
   },
   "source": [
    "#### Insert at arbitrary position"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "SgovUUMS-TxT",
    "outputId": "2d639b6d-eaa7-4f91-b837-88136a2b403a"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['b', 'a', 'c', 'c']"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters.insert(2, 'c')\n",
    "letters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "W2WMgepZAjkO"
   },
   "source": [
    "#### Extending with another list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "UYn06yndAoNH",
    "outputId": "a1c34ae5-d500-44b0-98a3-c4db3b47c910"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 'b', 'c', 'e', 'f', 'g']"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "more_letters = ['e', 'f', 'g']\n",
    "letters.extend(more_letters)\n",
    "letters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 'b', 'c', 'e', 'f', 'g', ['e', 'f', 'g']]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "more_letters\n",
    "letters.append(more_letters)\n",
    "letters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "wzPgAr_s_CrC"
   },
   "source": [
    "### Change item at some position"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "BZGy8c8bov2q",
    "outputId": "4fc4fd41-0e1e-4324-8302-b0ce19558908"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['b', 'a', 'c', 'd', 'e', 'f', 'g']"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters[3] = 'd'\n",
    "letters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "PGcA5_5__RZm"
   },
   "source": [
    "### Swap two items"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('b', 'a')"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters[0], letters[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "egbXdmQ__UB4",
    "outputId": "439400af-99d2-4d6c-aaac-f16c822bf73e"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 'b', 19]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters[0], letters[1] = letters[1], letters[0]\n",
    "letters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "RNirVSMaHOp4"
   },
   "source": [
    "### Removing items from a list"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "K0ecop0OHXo_"
   },
   "source": [
    "#### Pop from the end"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "ZfFG3MZ7HdXa",
    "outputId": "fe842c28-5813-4286-df92-908864af1f53"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 'b', 'c', 'd', 'e']"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters = ['a', 'b', 'c', 'd', 'e', 'f']\n",
    "letters.pop()\n",
    "letters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 'b', 'c', 'd']"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters.pop()\n",
    "letters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 'b', 'c']"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters.pop()\n",
    "letters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "WSm1EhxBH8a2"
   },
   "source": [
    "#### Pop by index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "R62Fg9l4IAYV",
    "outputId": "a6bc87d5-46e8-4383-ced0-e53c67026e43"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 'b', 'd', 'e']"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters.pop(2)\n",
    "letters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "wDhR89qxIUEh"
   },
   "source": [
    "#### Remove specific item"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "cAyAJIeOpYrU",
    "outputId": "60762469-653a-4e89-8ffc-4082273b728e"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 'b', 'e']"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters.remove('d')\n",
    "letters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Tuples\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "D9_M_6cwUAaX"
   },
   "source": [
    "### Create tuple using brackets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "7Zqb_MU2UEJa",
    "outputId": "0b125537-00c5-4bd2-85d4-3dc130fcf6b7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 2, 3)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tup = (1, 2, 3)\n",
    "tup\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ep3XqjhqUIS1"
   },
   "source": [
    "### Create tuple with commas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "Oz8dkzlzUNEe",
    "outputId": "c8b25da2-8291-406f-b3e3-614cb7c06bba"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 2, 3)"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tup = 1, 2, 3\n",
    "tup"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "p5Ie15xNUvK-"
   },
   "source": [
    "### Create empty tuple"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "6M3eLXfXUxLX",
    "outputId": "83081a8c-9e5b-4a5a-bd3e-248f805e6da7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "()"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tup = ()\n",
    "tup"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0YKr2HU6UzgT"
   },
   "source": [
    "### Create tuple with single item"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "9ib336cLU3iu",
    "outputId": "1f47d8eb-ed90-4c0e-d759-e7aa76f4b11d"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1,)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tup = 1,\n",
    "tup"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "a_eqCY6XTy1x"
   },
   "source": [
    "## List ve Tuple arasindaki benzer ozellikler\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "HpNqX6QFLmdK"
   },
   "source": [
    "### Check item in sequence"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "NpIdl5Cfp7-f",
    "outputId": "1f78c614-29a9-42d7-d2da-300df5698dfc"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "3 in (1, 2, 3, 4, 5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Ms_bF8BjL79W"
   },
   "source": [
    "### Check item not in sequence"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "gLXaJE6EMGyb",
    "outputId": "786985a3-a630-4617-a4d3-babd7fca9e77"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'a' not in [1, 2, 3, 4, 5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UNKJxMb6Mipn"
   },
   "source": [
    "### Slicing"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "r_fLVxRhNWLA"
   },
   "source": [
    "#### Setting start, slice to the end"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "098SVCIvsibb",
    "outputId": "8a737bd9-05af-4f95-fdc4-aa882fef47c9"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('d',)"
      ]
     },
     "execution_count": 32,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters = 'a', 'b', 'c', 'd', 'e', 'f'\n",
    "letters[3:4]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "dsNvabgmNeqw"
   },
   "source": [
    "#### Set end, slice from beginning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "QVNJeYVtNh56",
    "outputId": "249d9c60-e20c-4d78-dc02-67b74b17fe17"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a']"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters[:1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Lrd7HuHnNvIi"
   },
   "source": [
    "#### Index from end of sequence"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "9XiynpN9M9V_",
    "outputId": "3b8497e3-1219-496f-ec24-6c99dbd3ff8c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('c', 'd', 'e', 'f')"
      ]
     },
     "execution_count": 34,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters[-4:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1, 1, 1, 1, 1]"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "liste= [1,1,1,1,1]\n",
    "liste"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[2, 9, 1]"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "numbers = [5, 2, 9, 1, 7]\n",
    "numbers[1:3]\n",
    "numbers[1:4]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Quiz - Lists\n",
    "\n",
    "#### 1- Can a list object have the same elements inside?\n",
    "#### 2- Given the list numbers = [5, 2, 9, 1, 7], what is the output of numbers[2]?\n",
    "#### 3- How would you append the number 10 to the end of the numbers list?\n",
    "#### 4- What is the difference in output between numbers[1:3] and numbers[1:4]?\n",
    "#### 5- If tuple_nums = (3, 8, 1, 6), can you modify the value at index 1 to be 5? Explain why or why not.\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "SxpzGoM_Z_RU"
   },
   "source": [
    "# Dictionaries"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "l9nWQuW1oLCE"
   },
   "source": [
    "### Create an empty dict "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "45C_FS-eoR-3",
    "outputId": "bd814a64-d7e0-4577-fbe0-46c721330ab1"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{}"
      ]
     },
     "execution_count": 46,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary = {}\n",
    "dictionary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{}"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary = dict()\n",
    "dictionary"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "yXNaZRMdpQoK"
   },
   "source": [
    "### Use curley braces to create a dictionary with initial key/values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "oRTWGBtvpYcb",
    "outputId": "922c363f-d506-4eb0-81bb-a7301155bdf7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'key-1': 'value-1', 'key-2': 'value-2'}"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary = {'key-1': 'value-1',\n",
    "              'key-2': 'value-2'}\n",
    "\n",
    "dictionary"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "vb9aP6o5pv_B"
   },
   "source": [
    "### Access value using key"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "3-jz1H8Apzgm",
    "outputId": "3970a9a3-a15c-4a80-a2fc-81ad55cc1717"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'value-1'"
      ]
     },
     "execution_count": 51,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary['key-1']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UBSLRWEeqE-W"
   },
   "source": [
    "### Add a key/value pair to an existing dictionary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "J98co3mWqJ5I",
    "outputId": "4ec4724f-aeca-48db-d6c9-84fef9a8c849"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'key-1': 'value-1', 'key-2': 'value-2', 'key-3': 'value-3', 'Yavuz': 'Cakir'}"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary['key-3'] = 'value-3'\n",
    "dictionary['Yavuz'] = 'Cakir'\n",
    "\n",
    "dictionary"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "xmHWK2hHq7c_"
   },
   "source": [
    "### Update value for existing key"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "VrV2r-vUq-JV",
    "outputId": "c7960849-de81-461f-eed5-1806f9a01ceb"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'new-value-2'"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary['key-2'] = 'new-value-2'\n",
    "dictionary['key-2']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_ot60Snlra6K"
   },
   "source": [
    "### Get keys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'key-1': 'value-1',\n",
       " 'key-2': 'new-value-2',\n",
       " 'key-3': 'value-3',\n",
       " 'Yavuz': 'Cakir'}"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_values(['value-1', 'new-value-2', 'value-3', 'Cakir'])"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary.values()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "Lv726tMhrYnh",
    "outputId": "23089819-c637-4e89-a48e-ee5507b4b550"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('key-1', 'key-2', 'key-3', 'Yavuz')"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(dictionary.keys())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "WGJyKhKgrf11"
   },
   "source": [
    "### Get values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "F7F-fNMMrhT5",
    "outputId": "f9ace37c-d4de-450d-b4e3-c6b06790fbd0"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_keys(['key-2', 'key-3', 'Yavuz'])"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary.keys()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "tCpdFg8JrqKM"
   },
   "source": [
    "### Get iterable keys and items"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "dictionary['Pinar_Ekici'] = ['Ekici',2003,\"Izmir\"]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "0dZRJamArlLg",
    "outputId": "1d43a628-2f5e-4d4e-c179-b7cbc2373c37"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_items([('key-2', 'new-value-2'), ('key-3', 'value-3'), ('Yavuz', 'Cakir'), ('Pinar', ['Ekici', 2003, 'Izmir']), ('Pinar_Ekici', ['Ekici', 2003, 'Izmir'])])"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary.items()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'key-2': 'new-value-2',\n",
       " 'key-3': 'value-3',\n",
       " 'Yavuz': 'Cakir',\n",
       " 'Pinar': ['Ekici', 2003, 'Izmir'],\n",
       " 'Pinar_Ekici': ['Ekici', 2003, 'Izmir']}"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dictionary"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Cvk5OCmQrvkd"
   },
   "source": [
    "### Use items in for loop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "id": "bzYEfTEWrxno",
    "outputId": "b8b1427b-7eb0-4f4c-c36c-3b526d9a09dd",
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "key-2: new-value-2\n",
      "key-3: value-3\n",
      "Yavuz: Cakir\n",
      "Pinar: ['Ekici', 2003, 'Izmir']\n",
      "Pinar_Ekici: ['Ekici', 2003, 'Izmir']\n"
     ]
    }
   ],
   "source": [
    "for yavuz, cakir in dictionary.items():\n",
    "  print(f\"{yavuz}: {cakir}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "9fqITS30sJC6"
   },
   "source": [
    "### Check if dictionary has key\n",
    "The 'in' syntax we used with sequences checks the dicts keys for membership."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "c1XdFLXNsWVq",
    "outputId": "fc5b766b-be93-4d8f-95e0-fd17f981bee0"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'Yavuz' in dictionary"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "YmWqelbJthVB"
   },
   "source": [
    "### Remove item"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "tOLuWnHEtkjT",
    "outputId": "e90cf788-09a9-4e0a-9231-b29f8c070fab"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'key-2': 'new-value-2',\n",
       " 'key-3': 'value-3',\n",
       " 'Pinar_Ekici': ['Ekici', 2003, 'Izmir']}"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "del(dictionary['Pinar'])\n",
    "dictionary"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "AnFGTgxCiZnk"
   },
   "source": [
    "### Keys must be immutable"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "rnKNsxuZinvy"
   },
   "source": [
    "#### List as key\n",
    "Lists are mutable and not hashable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 198
    },
    "id": "16t9F7PPipo4",
    "outputId": "ad113919-80cc-44cd-cc76-ad1d252dde27"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{('item-1', 'item-2', 'item-3'): 'some-value'}"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "items = ('item-1', 'item-2', 'item-3')\n",
    "\n",
    "map = {}\n",
    "\n",
    "map[items] = \"some-value\"\n",
    "map"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_9vXIamIjLER"
   },
   "source": [
    "#### Tuple as a key\n",
    "Tuples are immutable and hence hashable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "K2pFCFu3jNRM",
    "outputId": "5e1fc13f-b76f-45d5-9fff-359f6199972e"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{('item-1', 'item-2', 'item-3'): 'some-value'}"
      ]
     },
     "execution_count": 67,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "items = 'item-1', 'item-2', 'item-3'\n",
    "map = {}\n",
    "map[items] = \"some-value\"\n",
    "\n",
    "map"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#  QUIZ\n",
    "#### 1- Create a dictionary called student with keys 'name', 'age', and 'grade', and assign appropriate values.\n",
    "#### 2- How would you access the 'age' of the student from the student dictionary?\n",
    "#### 3- Add a new key-value pair 'major': 'Computer Science' to the student dictionary.\n",
    "#### 4- If you try to access a key that doesn't exist in a dictionary, what happens?\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Y1rOvrTSaCnA"
   },
   "source": [
    "# Sets"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_Bu_DUont1Ks"
   },
   "source": [
    "### Create set from tuple or list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "epPCLrckt4Zy",
    "outputId": "df768aae-5c29-492b-a444-d60735fb0f36"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'a', 'b', 'c'}"
      ]
     },
     "execution_count": 68,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters = 'a', 'a', 'a', 'b', 'c'\n",
    "unique_letters = set(letters)\n",
    "unique_letters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1, 2, 3, 3]"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letters = [1,2,3,3]\n",
    "letters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{1, 2, 3}"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "set(letters)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "qnQHMNCRuebg"
   },
   "source": [
    "### Create set from a string"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['m', 'i', 's', 's', 'i', 's', 's', 'i', 'p', 'p', 'i']"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "unique_chars_list = list('mississippi')\n",
    "unique_chars_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "IRsuJBVC_ORB",
    "outputId": "ffca987d-0534-4e4f-d660-24318b4c2795"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'i', 'm', 'p', 's'}"
      ]
     },
     "execution_count": 69,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "unique_chars = set('mississippi')\n",
    "unique_chars"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "LUJyjEh1uzrv"
   },
   "source": [
    "### Create set using curley braces"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "afYk3yfTu3Pt",
    "outputId": "8fc66ae0-c16c-45e0-d684-41757f68ee81"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{1, 2, 3, 4, 5}"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "unique_num = {1, 1, 2, 3, 4, 5, 5}\n",
    "#or set()\n",
    "unique_num"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "set_a = dict()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "jDMYvC0avu_C"
   },
   "source": [
    "### Adding to a set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "hoZ7hcrBvwtc",
    "outputId": "1585f6f0-3122-480e-a69a-022460b0fbc7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{1, 2, 3, 4, 5, 6}"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "unique_num.add(6)\n",
    "unique_num"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "o-UWnVB7v8yb"
   },
   "source": [
    "### Popping from a set\n",
    "Pop method removes and returns a random element of the set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "e9xWJPXnwF4s",
    "outputId": "3d0bc7f2-3dda-4738-975b-011d09f8ec7f"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "unique_num.pop()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "VJjl2Fv9vLOl"
   },
   "source": [
    "### Indexing\n",
    "Sets have no order, and hence cannot be accessed via indexing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 164
    },
    "id": "vxPCJWJOvShU",
    "outputId": "8bd70eb2-1c1d-4b64-f23b-dcf278c4a29f"
   },
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "'set' object is not subscriptable",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[97], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43munique_num\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m4\u001b[39;49m\u001b[43m]\u001b[49m\n",
      "\u001b[0;31mTypeError\u001b[0m: 'set' object is not subscriptable"
     ]
    }
   ],
   "source": [
    "unique_num[4]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "TQyoEjgivjA3"
   },
   "source": [
    "### Checking membership"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "3zOvkWX6vlf2",
    "outputId": "020d8aef-4a5a-45fc-da0c-8e5a74240487"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "3 in unique_num"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6ph_k8RUweYA"
   },
   "source": [
    "### Set operations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "id": "7EfN4R5xwmXM"
   },
   "outputs": [],
   "source": [
    "s1 = { 1 ,2 ,3 ,4, 5, 6, 7}\n",
    "s2 = { 0, 2, 4, 6, 8 }"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "RAG3ATbtwtwm"
   },
   "source": [
    "#### Items in first set, but not in the second"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "kCfxlj9Lwz1x",
    "outputId": "3c3b92ad-959b-46bf-ecb0-2513886923b9"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{1, 3, 5, 7}"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s1 - s2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "KDA6bO1Vw8Bk"
   },
   "source": [
    "#### Items in either or both sets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "a-1CBUnRw-y-",
    "outputId": "584219f7-80ba-4e24-f3ec-b833428bfc87"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{0, 1, 2, 3, 4, 5, 6, 7, 8}"
      ]
     },
     "execution_count": 79,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s1 | s2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ADEQBlFrxIN7"
   },
   "source": [
    "#### Items in both sets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "IIudbePtxRkR",
    "outputId": "ad5fcea8-8b15-467d-a895-c11e4caa8609"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{2, 4, 6}"
      ]
     },
     "execution_count": 80,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s1 & s2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "list()\n",
    "set()\n",
    "dict()\n",
    "list=[]\n",
    "set=\n",
    "tuple\n",
    "dict={}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Questions\n",
    "\n",
    "### How to add elemnts into list and set? \n",
    "### How to create List-set-Dict, with an alternative method?\n",
    "\n",
    "#### Create two sets: set1 = {1, 2, 3, 4} and set2 = {3, 4, 5, 6}. What is the output of set1.union(set2)?\n",
    "#### What is the output of set1.intersection(set2)?\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "y-xMLy31aHaZ"
   },
   "source": [
    "# Work with the numpy array\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0yTnd14-HasX"
   },
   "source": [
    "###### Numpy is an opened source numerical computing libary for python. \n",
    "###### As with many high performance Python libraries, significant parts of it are in fact written in C/C++"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "W7mqP9swyh5d"
   },
   "source": [
    "### Create a numpy array from a list of lists"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 85
    },
    "id": "NOAicBI_ynGz",
    "outputId": "188d1747-f144-47ea-b9d6-887b3b1e88d8"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4],\n",
       "       [ 5,  6,  7,  8],\n",
       "       [ 9, 10, 11, 12],\n",
       "       [13, 14, 15, 16]])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "list_of_lists = [[1, 2, 3, 4], [5, 6, 7, 8], [9, 10, 11, 12], [13, 14, 15, 16]]\n",
    "\n",
    "np_array = np.array(list_of_lists)\n",
    "\n",
    "np_array"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0eHeRfdAyzTY"
   },
   "source": [
    "### Initialize an array of zeros"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 85
    },
    "id": "1BoLJ2XYy2op",
    "outputId": "9945a4a2-28ed-4775-860d-999f4a1c4d54"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 0., 0., 0.],\n",
       "       [0., 0., 0., 0., 0.],\n",
       "       [0., 0., 0., 0., 0.],\n",
       "       [0., 0., 0., 0., 0.]])"
      ]
     },
     "execution_count": 83,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "zeros_array = np.zeros( (4, 5) )\n",
    "zeros_array"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "92DsgsVSzC2T"
   },
   "source": [
    "### Initialize and array of ones"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 119
    },
    "id": "F_TWC3z6zYA2",
    "outputId": "2d7317b1-5b89-44b5-844d-ceec8b50ff86"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1., 1., 1., 1., 1., 1.],\n",
       "       [1., 1., 1., 1., 1., 1.],\n",
       "       [1., 1., 1., 1., 1., 1.],\n",
       "       [1., 1., 1., 1., 1., 1.],\n",
       "       [1., 1., 1., 1., 1., 1.],\n",
       "       [1., 1., 1., 1., 1., 1.]])"
      ]
     },
     "execution_count": 84,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ones_array = np.ones( (6, 6) )\n",
    "ones_array"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Ejoa6qiszx-O"
   },
   "source": [
    "### Using reshape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "id": "RgJ6ZfVfOm6R",
    "outputId": "67f363e4-a9cd-477f-9ed1-6165d9fd3ac5"
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'nine' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mnine\u001b[49m\u001b[38;5;241m.\u001b[39mreshape(\u001b[38;5;241m3\u001b[39m,\u001b[38;5;241m3\u001b[39m)\n",
      "\u001b[0;31mNameError\u001b[0m: name 'nine' is not defined"
     ]
    }
   ],
   "source": [
    "nine.reshape(3,3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "lB_e_dbx03bL"
   },
   "source": [
    "### Introspection"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "___j8Jrc06k8"
   },
   "source": [
    "#### Get the data type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "IEDq1Hcu0-z_",
    "outputId": "45152487-40ba-4f23-d1c0-11bb969e21a4"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype('int64')"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array.dtype"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "OTREEzKu1CU1"
   },
   "source": [
    "#### Get the array's shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "JZ-1Vxj41GKC",
    "outputId": "54b58943-55aa-4b94-ee19-81cc036512ef"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4, 4)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4],\n",
       "       [ 5,  6,  7,  8],\n",
       "       [ 9, 10, 11, 12],\n",
       "       [13, 14, 15, 16]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "OeY1bxyJ1Idv"
   },
   "source": [
    "#### Get the number of items in the array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "9-MK_t881LVg",
    "outputId": "557d0f24-8814-4378-8926-144d8aacbe6e"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "16"
      ]
     },
     "execution_count": 89,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array.size"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "SifJ6bra1TQ0"
   },
   "source": [
    "#### Get the size of the array in bytes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "5YzTBEid1YsX",
    "outputId": "9b09f32c-a717-40c3-d048-8c7559f95a17"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "128"
      ]
     },
     "execution_count": 90,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array.nbytes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "toHDZHec1f9F"
   },
   "source": [
    "### Setting the data type"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "7bdGC31e1pxo"
   },
   "source": [
    "#### dtype parameter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 85
    },
    "id": "3quViOL01sy4",
    "outputId": "ea7f0ea3-7b16-4b23-fb7b-ea457ee8ea4b"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4],\n",
       "       [ 5,  6,  7,  8],\n",
       "       [ 9, 10, 11, 12],\n",
       "       [13, 14, 15, 16]], dtype=int8)"
      ]
     },
     "execution_count": 91,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array = np.array(list_of_lists, dtype=np.int8)\n",
    "np_array"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "xd-_Qgqo1yyu"
   },
   "source": [
    "#### Size reduction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "pFk4n7d312LH",
    "outputId": "7c84121e-c3b4-4145-8fd7-7cd065ee7240"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "16"
      ]
     },
     "execution_count": 92,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array.nbytes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "vvPhjEXoWYnT"
   },
   "source": [
    "### Array Slicing\n",
    "\n",
    "\n",
    "*   Slicing can be used to get a view reprsenting a sub-array.\n",
    "*   The slice is a view to the original array, the data is not copied to a new data structure\n",
    "*   The slice is taken in the form: array[ rows, columns ]\n",
    "\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 85
    },
    "id": "tDjuERnX2hUp",
    "outputId": "74052c3f-0c04-45e3-dc68-633903d0e939"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4],\n",
       "       [ 5,  6,  7,  8],\n",
       "       [ 9, 10, 11, 12],\n",
       "       [13, 14, 15, 16]], dtype=int8)"
      ]
     },
     "execution_count": 94,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 9, 10, 11],\n",
       "       [13, 14, 15]])"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array[2:, :3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[4]])"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array[:1, 3:]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "DZw_vVRta7q8"
   },
   "source": [
    "### Math operations\n",
    "\n",
    "\n",
    "*   Unlike a unlike nested lists, matrix operations perform mathimatical operations on data\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "DcuhDzog3k7b"
   },
   "source": [
    "#### Create two 3 x 3 arrays"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 2, 3, 4, 5, 6, 7, 8])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.arange(9)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "id": "Hk4TSZMp3ueg",
    "outputId": "f9c0a3be-9eaa-4d19-df19-53de928ffde4"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 1, 2],\n",
       "       [3, 4, 5],\n",
       "       [6, 7, 8]])"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array_1 = np.arange(9).reshape(3,3)\n",
    "np_array_1\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "id": "BGUAuzGW32MZ",
    "outputId": "f84c69d5-cf39-40f3-8716-1b2950a8200a"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[10, 11, 12],\n",
       "       [13, 14, 15],\n",
       "       [16, 17, 18]])"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array_2 = np.arange(10, 19).reshape(3,3)\n",
    "np_array_2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "JtgSgziO3-zG"
   },
   "source": [
    "#### Multiply the arrays"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "id": "DnsoTaV64B6s",
    "outputId": "1ff2e5fe-8c02-4a14-e447-489a91ae7dab"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[  0,  11,  24],\n",
       "       [ 39,  56,  75],\n",
       "       [ 96, 119, 144]])"
      ]
     },
     "execution_count": 98,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array_1 * np_array_2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bLZEFu6F4RZ9"
   },
   "source": [
    "#### Add the arrays"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "id": "gtImxWZW4TIK",
    "outputId": "0549bcbe-a4ec-4563-d8e3-a9b5faa12f1c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[10, 12, 14],\n",
       "       [16, 18, 20],\n",
       "       [22, 24, 26]])"
      ]
     },
     "execution_count": 99,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array_1 + np_array_2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "7R8mt4RU4yMz"
   },
   "source": [
    "### Matrix operations"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "1OU4oaWt40Jp"
   },
   "source": [
    "#### Transpose"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  2,  3,  4],\n",
       "       [ 5,  6,  7,  8],\n",
       "       [ 9, 10, 11, 12],\n",
       "       [13, 14, 15, 16]])"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 85
    },
    "id": "EXIwtxD942UO",
    "outputId": "ee5697f7-97bd-4b89-d053-771afa6fa69b"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1,  5,  9, 13],\n",
       "       [ 2,  6, 10, 14],\n",
       "       [ 3,  7, 11, 15],\n",
       "       [ 4,  8, 12, 16]], dtype=int8)"
      ]
     },
     "execution_count": 100,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np_array.T"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "z-hjI2NsaK4w"
   },
   "source": [
    "## Pandas DataFrame\n",
    "*   One of the most highly leveraged data structures for data science\n",
    "*   A table-like two dimensional data structure.\n",
    "*   A new and faster alternative- Polars\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "e8Dxdc4V6wlV"
   },
   "source": [
    "### Create a DataFrame- Who joined the class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 297
    },
    "id": "73JaHcb261eb",
    "outputId": "95ec9725-3f0e-472d-c9e1-6439bfeac6ff"
   },
   "outputs": [
    {
     "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>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Birsen</td>\n",
       "      <td>Yurtdas</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Musa</td>\n",
       "      <td>Kirgezen</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Duygu</td>\n",
       "      <td>Keremitci</td>\n",
       "      <td>21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Elif</td>\n",
       "      <td>Duymaz</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Ozlem</td>\n",
       "      <td>Tuna</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Ebru</td>\n",
       "      <td>Kocakaya</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Emir</td>\n",
       "      <td>Amiritabat</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Elyar</td>\n",
       "      <td>Bafandeh</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Yavuz</td>\n",
       "      <td>Cakir</td>\n",
       "      <td>80</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  first_name   last_name  age\n",
       "0     Birsen     Yurtdas   20\n",
       "1       Musa    Kirgezen   13\n",
       "2      Duygu   Keremitci   21\n",
       "3       Elif      Duymaz   15\n",
       "4      Ozlem        Tuna   23\n",
       "5       Ebru    Kocakaya   30\n",
       "6       Emir  Amiritabat   40\n",
       "7      Elyar    Bafandeh   50\n",
       "8      Yavuz       Cakir   80"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "first_names = ['Birsen', 'Musa', 'Duygu', 'Elif', 'Ozlem', 'Ebru', 'Emir', 'Elyar', 'Yavuz']\n",
    "last_names = ['Yurtdas', 'Kirgezen', 'Keremitci', 'Duymaz', 'Tuna', 'Kocakaya', 'Amiritabat', 'Bafandeh','Cakir']\n",
    "ages = [20, 13, 21, 15, 23, 30, 40, 50,80]\n",
    "\n",
    "df = pd.DataFrame({ 'first_name': first_names, 'last_name': last_names, 'age': ages})\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ut_QqgQi7CvX"
   },
   "source": [
    "### Head - looking at the top"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 297
    },
    "id": "FN7tXlFV7FiE",
    "outputId": "f48221e8-bcee-4d3c-e2e0-e3bd130b202d"
   },
   "outputs": [
    {
     "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>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Birsen</td>\n",
       "      <td>Yurtdas</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Musa</td>\n",
       "      <td>Kirgezen</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Duygu</td>\n",
       "      <td>Keremitci</td>\n",
       "      <td>21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Elif</td>\n",
       "      <td>Duymaz</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Ozlem</td>\n",
       "      <td>Tuna</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  first_name  last_name  age\n",
       "0     Birsen    Yurtdas   20\n",
       "1       Musa   Kirgezen   13\n",
       "2      Duygu  Keremitci   21\n",
       "3       Elif     Duymaz   15\n",
       "4      Ozlem       Tuna   23"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2lZEPhBd7PGN"
   },
   "source": [
    "### Setting number of rows returned with head"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "id": "mO583bRm7J9y"
   },
   "outputs": [
    {
     "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>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Birsen</td>\n",
       "      <td>Yurtdas</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Musa</td>\n",
       "      <td>Kirgezen</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Duygu</td>\n",
       "      <td>Keremitci</td>\n",
       "      <td>21</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  first_name  last_name  age\n",
       "0     Birsen    Yurtdas   20\n",
       "1       Musa   Kirgezen   13\n",
       "2      Duygu  Keremitci   21"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "fP0Szs_k7ZwM"
   },
   "source": [
    "### Tail - looking at the bottom"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 111
    },
    "id": "lWpCA6lh7dIZ",
    "outputId": "6ad75973-5eba-4e1f-e70f-709f20036be7"
   },
   "outputs": [
    {
     "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>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Elyar</td>\n",
       "      <td>Bafandeh</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Yavuz</td>\n",
       "      <td>Cakir</td>\n",
       "      <td>80</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  first_name last_name  age\n",
       "7      Elyar  Bafandeh   50\n",
       "8      Yavuz     Cakir   80"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "aMcpAbpW7sKB"
   },
   "source": [
    "### Describe - descriptive statistics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'summary' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[44], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43msummary\u001b[49m(df)\n",
      "\u001b[0;31mNameError\u001b[0m: name 'summary' is not defined"
     ]
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 297
    },
    "id": "c1SCEPeB7xIi",
    "outputId": "ad35757e-f072-4208-e853-1f25dc24614e"
   },
   "outputs": [
    {
     "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>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>9.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>32.444444</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>21.477378</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>13.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>20.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>23.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>40.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>80.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             age\n",
       "count   9.000000\n",
       "mean   32.444444\n",
       "std    21.477378\n",
       "min    13.000000\n",
       "25%    20.000000\n",
       "50%    23.000000\n",
       "75%    40.000000\n",
       "max    80.000000"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Of3owwjI71cr"
   },
   "source": [
    "### Access one column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "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>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Birsen</td>\n",
       "      <td>Yurtdas</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Musa</td>\n",
       "      <td>Kirgezen</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Duygu</td>\n",
       "      <td>Keremitci</td>\n",
       "      <td>21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Elif</td>\n",
       "      <td>Duymaz</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Ozlem</td>\n",
       "      <td>Tuna</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Ebru</td>\n",
       "      <td>Kocakaya</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Emir</td>\n",
       "      <td>Amiritabat</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Elyar</td>\n",
       "      <td>Bafandeh</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Yavuz</td>\n",
       "      <td>Cakir</td>\n",
       "      <td>80</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  first_name   last_name  age\n",
       "0     Birsen     Yurtdas   20\n",
       "1       Musa    Kirgezen   13\n",
       "2      Duygu   Keremitci   21\n",
       "3       Elif      Duymaz   15\n",
       "4      Ozlem        Tuna   23\n",
       "5       Ebru    Kocakaya   30\n",
       "6       Emir  Amiritabat   40\n",
       "7      Elyar    Bafandeh   50\n",
       "8      Yavuz       Cakir   80"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 170
    },
    "id": "siMCagaq74bO",
    "outputId": "99907925-afaf-459c-bb9f-63a7b9bf25e2"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    20\n",
       "1    13\n",
       "2    21\n",
       "3    15\n",
       "4    23\n",
       "5    30\n",
       "6    40\n",
       "7    50\n",
       "8    80\n",
       "Name: age, dtype: int64"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['age']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "KdOsmAk67-FA"
   },
   "source": [
    "### Slice a column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 102
    },
    "id": "dNl_CTuk8Bip",
    "outputId": "df4f7aa6-4457-4c77-f2cb-5c77c227d072"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4    Ozlem\n",
       "5     Ebru\n",
       "6     Emir\n",
       "7    Elyar\n",
       "8    Yavuz\n",
       "Name: first_name, dtype: object"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['first_name'][4:]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "H3iUwAI-8TFp"
   },
   "source": [
    "### Use conditions to filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    False\n",
       "1    False\n",
       "2    False\n",
       "3    False\n",
       "4    False\n",
       "5    False\n",
       "6    False\n",
       "7     True\n",
       "8     True\n",
       "Name: age, dtype: bool"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['age'] > 40"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 142
    },
    "id": "pjYmR1d0fbUh",
    "outputId": "0add25f2-e4c6-4a21-98d8-6c77cdacea4e"
   },
   "outputs": [
    {
     "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>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Emir</td>\n",
       "      <td>Amiritabat</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Elyar</td>\n",
       "      <td>Bafandeh</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Yavuz</td>\n",
       "      <td>Cakir</td>\n",
       "      <td>80</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  first_name   last_name  age\n",
       "6       Emir  Amiritabat   40\n",
       "7      Elyar    Bafandeh   50\n",
       "8      Yavuz       Cakir   80"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df['age'] > 30]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "mU_PWc0zaO0X"
   },
   "source": [
    "## 5.6 Use the pandas Series\n",
    "\n",
    "\n",
    "*   A one dimensional labeled array\n",
    "*   Contains data of only one type\n",
    "*   Similar to a column in a spreedsheet\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "8IJJSLsN8kAq"
   },
   "source": [
    "### Create a series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 85
    },
    "id": "cdGYE9LdnSwU",
    "outputId": "c4a7433b-e15c-4f27-d727-72cf26e9de70"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    1\n",
       "1    2\n",
       "2    3\n",
       "dtype: int64"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd_series = pd.Series( [1, 2, 3 ] )\n",
    "pd_series"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "GzZyCmanpu2p"
   },
   "source": [
    "### Series introspection methods"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "RlsP8h-KpxxE",
    "outputId": "5eb734b2-d44e-422c-c53b-fb0fdca4b1ba"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'This series is made up of 3 items whose data type is int64'"
      ]
     },
     "execution_count": 115,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f\"This series is made up of {pd_series.size} items whose data type is {pd_series.dtype}\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "OgKF9C9an8iB"
   },
   "source": [
    "### A Pandas DataFrame is composed of Pandas Series."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "wAmSud2ToHuh",
    "outputId": "9afc9fb8-bef8-4f3f-95ac-8d26f9375233"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.series.Series"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "age = df.age\n",
    "type( age )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "DooLFZH1ovCV"
   },
   "source": [
    "### Some useful helper methods of a Series"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "iyDtUDT3JRuY"
   },
   "source": [
    "#### mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "9gi2tOSTJTrI",
    "outputId": "1fbee477-4a35-422d-949b-1fe0b180af04"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4.888888888888889"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd_series = pd.Series([ 1, 2, 3, 5, 6, 6, 6, 7, 8])\n",
    "pd_series.mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bILvFviLJbok"
   },
   "source": [
    "#### Unique"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "azsZ0xzcJdN2",
    "outputId": "f8371eb1-959f-4726-acd1-e00729f9f2d6"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 2, 3, 5, 6, 7, 8])"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd_series.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[6]"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(set(pd_series[pd_series.duplicated()]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'numpy.ndarray' object has no attribute 'pop'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[62], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpd_series\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43munique\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpop\u001b[49m(np\u001b[38;5;241m.\u001b[39marray(\u001b[38;5;28mlist\u001b[39m(\u001b[38;5;28mset\u001b[39m(pd_series[pd_series\u001b[38;5;241m.\u001b[39mduplicated()]))))\n",
      "\u001b[0;31mAttributeError\u001b[0m: 'numpy.ndarray' object has no attribute 'pop'"
     ]
    }
   ],
   "source": [
    "np.array(pd_series.unique()).pop(np.array(list(set(pd_series[pd_series.duplicated()]))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([6])"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array(list(set(pd_series[pd_series.duplicated()])))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    False\n",
       "1    False\n",
       "2    False\n",
       "3    False\n",
       "4    False\n",
       "5     True\n",
       "6     True\n",
       "7    False\n",
       "8    False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd_series.duplicated()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    1\n",
       "1    2\n",
       "2    3\n",
       "3    5\n",
       "7    7\n",
       "8    8\n",
       "dtype: int64"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "uniq = pd_series[~pd_series.duplicated(keep=False)]\n",
    "uniq"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "GT2CGOucJgjz"
   },
   "source": [
    "#### Max"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "id": "s-PPBB7Co385",
    "outputId": "27c23504-0120-489f-b52b-0c6fbd49b8d9"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd_series.min()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [
    "_rehYX145nEk",
    "g4-XjayC8KO7"
   ],
   "name": "Lesson5-Python For Data Science-Python-Data-structure.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.12"
  },
  "vscode": {
   "interpreter": {
    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}