NLP_Password_Strength_Prediction.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "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": "3.7.4"
    },
    "colab": {
      "name": "NLP_Password_Strength_classifier.ipynb",
      "provenance": [],
      "collapsed_sections": []
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "4-jyY-wQQKa1"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import seaborn as sns\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore')"
      ],
      "execution_count": 45,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BFRTgNmulTOC",
        "outputId": "50d9c7aa-4caf-427c-c600-378f0a24662c"
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "r_JLIJOiQKa3"
      },
      "source": [
        "#### **reading dataset**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eokg_SNrQKa4",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 275
        },
        "outputId": "bfce9b3f-c7ea-438b-bff5-b2f8726b3afd"
      },
      "source": [
        "data=pd.read_csv('/content/drive/MyDrive/PASSWORD/data.csv',error_bad_lines=False)\n",
        "data.head()"
      ],
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "b'Skipping line 2810: expected 2 fields, saw 5\\nSkipping line 4641: expected 2 fields, saw 5\\nSkipping line 7171: expected 2 fields, saw 5\\nSkipping line 11220: expected 2 fields, saw 5\\nSkipping line 13809: expected 2 fields, saw 5\\nSkipping line 14132: expected 2 fields, saw 5\\nSkipping line 14293: expected 2 fields, saw 5\\nSkipping line 14865: expected 2 fields, saw 5\\nSkipping line 17419: expected 2 fields, saw 5\\nSkipping line 22801: expected 2 fields, saw 5\\nSkipping line 25001: expected 2 fields, saw 5\\nSkipping line 26603: expected 2 fields, saw 5\\nSkipping line 26742: expected 2 fields, saw 5\\nSkipping line 29702: expected 2 fields, saw 5\\nSkipping line 32767: expected 2 fields, saw 5\\nSkipping line 32878: expected 2 fields, saw 5\\nSkipping line 35643: expected 2 fields, saw 5\\nSkipping line 36550: expected 2 fields, saw 5\\nSkipping line 38732: expected 2 fields, saw 5\\nSkipping line 40567: expected 2 fields, saw 5\\nSkipping line 40576: expected 2 fields, saw 5\\nSkipping line 41864: expected 2 fields, saw 5\\nSkipping line 46861: expected 2 fields, saw 5\\nSkipping line 47939: expected 2 fields, saw 5\\nSkipping line 48628: expected 2 fields, saw 5\\nSkipping line 48908: expected 2 fields, saw 5\\nSkipping line 57582: expected 2 fields, saw 5\\nSkipping line 58782: expected 2 fields, saw 5\\nSkipping line 58984: expected 2 fields, saw 5\\nSkipping line 61518: expected 2 fields, saw 5\\nSkipping line 63451: expected 2 fields, saw 5\\nSkipping line 68141: expected 2 fields, saw 5\\nSkipping line 72083: expected 2 fields, saw 5\\nSkipping line 74027: expected 2 fields, saw 5\\nSkipping line 77811: expected 2 fields, saw 5\\nSkipping line 83958: expected 2 fields, saw 5\\nSkipping line 85295: expected 2 fields, saw 5\\nSkipping line 88665: expected 2 fields, saw 5\\nSkipping line 89198: expected 2 fields, saw 5\\nSkipping line 92499: expected 2 fields, saw 5\\nSkipping line 92751: expected 2 fields, saw 5\\nSkipping line 93689: expected 2 fields, saw 5\\nSkipping line 94776: expected 2 fields, saw 5\\nSkipping line 97334: expected 2 fields, saw 5\\nSkipping line 102316: expected 2 fields, saw 5\\nSkipping line 103421: expected 2 fields, saw 5\\nSkipping line 106872: expected 2 fields, saw 5\\nSkipping line 109363: expected 2 fields, saw 5\\nSkipping line 110117: expected 2 fields, saw 5\\nSkipping line 110465: expected 2 fields, saw 5\\nSkipping line 113843: expected 2 fields, saw 5\\nSkipping line 115634: expected 2 fields, saw 5\\nSkipping line 121518: expected 2 fields, saw 5\\nSkipping line 123692: expected 2 fields, saw 5\\nSkipping line 124708: expected 2 fields, saw 5\\nSkipping line 129608: expected 2 fields, saw 5\\nSkipping line 133176: expected 2 fields, saw 5\\nSkipping line 135532: expected 2 fields, saw 5\\nSkipping line 138042: expected 2 fields, saw 5\\nSkipping line 139485: expected 2 fields, saw 5\\nSkipping line 140401: expected 2 fields, saw 5\\nSkipping line 144093: expected 2 fields, saw 5\\nSkipping line 149850: expected 2 fields, saw 5\\nSkipping line 151831: expected 2 fields, saw 5\\nSkipping line 158014: expected 2 fields, saw 5\\nSkipping line 162047: expected 2 fields, saw 5\\nSkipping line 164515: expected 2 fields, saw 5\\nSkipping line 170313: expected 2 fields, saw 5\\nSkipping line 171325: expected 2 fields, saw 5\\nSkipping line 171424: expected 2 fields, saw 5\\nSkipping line 175920: expected 2 fields, saw 5\\nSkipping line 176210: expected 2 fields, saw 5\\nSkipping line 183603: expected 2 fields, saw 5\\nSkipping line 190264: expected 2 fields, saw 5\\nSkipping line 191683: expected 2 fields, saw 5\\nSkipping line 191988: expected 2 fields, saw 5\\nSkipping line 195450: expected 2 fields, saw 5\\nSkipping line 195754: expected 2 fields, saw 5\\nSkipping line 197124: expected 2 fields, saw 5\\nSkipping line 199263: expected 2 fields, saw 5\\nSkipping line 202603: expected 2 fields, saw 5\\nSkipping line 209960: expected 2 fields, saw 5\\nSkipping line 213218: expected 2 fields, saw 5\\nSkipping line 217060: expected 2 fields, saw 5\\nSkipping line 220121: expected 2 fields, saw 5\\nSkipping line 223518: expected 2 fields, saw 5\\nSkipping line 226293: expected 2 fields, saw 5\\nSkipping line 227035: expected 2 fields, saw 7\\nSkipping line 227341: expected 2 fields, saw 5\\nSkipping line 227808: expected 2 fields, saw 5\\nSkipping line 228516: expected 2 fields, saw 5\\nSkipping line 228733: expected 2 fields, saw 5\\nSkipping line 232043: expected 2 fields, saw 5\\nSkipping line 232426: expected 2 fields, saw 5\\nSkipping line 234490: expected 2 fields, saw 5\\nSkipping line 239626: expected 2 fields, saw 5\\nSkipping line 240461: expected 2 fields, saw 5\\nSkipping line 244518: expected 2 fields, saw 5\\nSkipping line 245395: expected 2 fields, saw 5\\nSkipping line 246168: expected 2 fields, saw 5\\nSkipping line 246655: expected 2 fields, saw 5\\nSkipping line 246752: expected 2 fields, saw 5\\nSkipping line 247189: expected 2 fields, saw 5\\nSkipping line 250276: expected 2 fields, saw 5\\nSkipping line 255327: expected 2 fields, saw 5\\nSkipping line 257094: expected 2 fields, saw 5\\n'\n",
            "b'Skipping line 264626: expected 2 fields, saw 5\\nSkipping line 265028: expected 2 fields, saw 5\\nSkipping line 269150: expected 2 fields, saw 5\\nSkipping line 271360: expected 2 fields, saw 5\\nSkipping line 273975: expected 2 fields, saw 5\\nSkipping line 274742: expected 2 fields, saw 5\\nSkipping line 276227: expected 2 fields, saw 5\\nSkipping line 279807: expected 2 fields, saw 5\\nSkipping line 283425: expected 2 fields, saw 5\\nSkipping line 287468: expected 2 fields, saw 5\\nSkipping line 292995: expected 2 fields, saw 5\\nSkipping line 293496: expected 2 fields, saw 5\\nSkipping line 293735: expected 2 fields, saw 5\\nSkipping line 295060: expected 2 fields, saw 5\\nSkipping line 296643: expected 2 fields, saw 5\\nSkipping line 296848: expected 2 fields, saw 5\\nSkipping line 308926: expected 2 fields, saw 5\\nSkipping line 310360: expected 2 fields, saw 5\\nSkipping line 317004: expected 2 fields, saw 5\\nSkipping line 318207: expected 2 fields, saw 5\\nSkipping line 331783: expected 2 fields, saw 5\\nSkipping line 333864: expected 2 fields, saw 5\\nSkipping line 335958: expected 2 fields, saw 5\\nSkipping line 336290: expected 2 fields, saw 5\\nSkipping line 343526: expected 2 fields, saw 5\\nSkipping line 343857: expected 2 fields, saw 5\\nSkipping line 344059: expected 2 fields, saw 5\\nSkipping line 348691: expected 2 fields, saw 5\\nSkipping line 353446: expected 2 fields, saw 5\\nSkipping line 357073: expected 2 fields, saw 5\\nSkipping line 359753: expected 2 fields, saw 5\\nSkipping line 359974: expected 2 fields, saw 5\\nSkipping line 366534: expected 2 fields, saw 5\\nSkipping line 369514: expected 2 fields, saw 5\\nSkipping line 377759: expected 2 fields, saw 5\\nSkipping line 379327: expected 2 fields, saw 5\\nSkipping line 380769: expected 2 fields, saw 5\\nSkipping line 381073: expected 2 fields, saw 5\\nSkipping line 381489: expected 2 fields, saw 5\\nSkipping line 386304: expected 2 fields, saw 5\\nSkipping line 387635: expected 2 fields, saw 5\\nSkipping line 389613: expected 2 fields, saw 5\\nSkipping line 392604: expected 2 fields, saw 5\\nSkipping line 393184: expected 2 fields, saw 5\\nSkipping line 395530: expected 2 fields, saw 5\\nSkipping line 396939: expected 2 fields, saw 5\\nSkipping line 397385: expected 2 fields, saw 5\\nSkipping line 397509: expected 2 fields, saw 5\\nSkipping line 402902: expected 2 fields, saw 5\\nSkipping line 405187: expected 2 fields, saw 5\\nSkipping line 408412: expected 2 fields, saw 5\\nSkipping line 419423: expected 2 fields, saw 5\\nSkipping line 420962: expected 2 fields, saw 5\\nSkipping line 425965: expected 2 fields, saw 5\\nSkipping line 427496: expected 2 fields, saw 5\\nSkipping line 438881: expected 2 fields, saw 5\\nSkipping line 439776: expected 2 fields, saw 5\\nSkipping line 440345: expected 2 fields, saw 5\\nSkipping line 445507: expected 2 fields, saw 5\\nSkipping line 445548: expected 2 fields, saw 5\\nSkipping line 447184: expected 2 fields, saw 5\\nSkipping line 448603: expected 2 fields, saw 5\\nSkipping line 451732: expected 2 fields, saw 5\\nSkipping line 458249: expected 2 fields, saw 5\\nSkipping line 460274: expected 2 fields, saw 5\\nSkipping line 467630: expected 2 fields, saw 5\\nSkipping line 473961: expected 2 fields, saw 5\\nSkipping line 476281: expected 2 fields, saw 5\\nSkipping line 478010: expected 2 fields, saw 5\\nSkipping line 478322: expected 2 fields, saw 5\\nSkipping line 479999: expected 2 fields, saw 5\\nSkipping line 480898: expected 2 fields, saw 5\\nSkipping line 481688: expected 2 fields, saw 5\\nSkipping line 485193: expected 2 fields, saw 5\\nSkipping line 485519: expected 2 fields, saw 5\\nSkipping line 486000: expected 2 fields, saw 5\\nSkipping line 489063: expected 2 fields, saw 5\\nSkipping line 494525: expected 2 fields, saw 5\\nSkipping line 495009: expected 2 fields, saw 5\\nSkipping line 501954: expected 2 fields, saw 5\\nSkipping line 508035: expected 2 fields, saw 5\\nSkipping line 508828: expected 2 fields, saw 5\\nSkipping line 509833: expected 2 fields, saw 5\\nSkipping line 510410: expected 2 fields, saw 5\\nSkipping line 518229: expected 2 fields, saw 5\\nSkipping line 520302: expected 2 fields, saw 5\\nSkipping line 520340: expected 2 fields, saw 5\\n'\n",
            "b'Skipping line 525174: expected 2 fields, saw 5\\nSkipping line 526251: expected 2 fields, saw 5\\nSkipping line 529611: expected 2 fields, saw 5\\nSkipping line 531398: expected 2 fields, saw 5\\nSkipping line 534146: expected 2 fields, saw 5\\nSkipping line 544954: expected 2 fields, saw 5\\nSkipping line 553002: expected 2 fields, saw 5\\nSkipping line 553883: expected 2 fields, saw 5\\nSkipping line 553887: expected 2 fields, saw 5\\nSkipping line 553915: expected 2 fields, saw 5\\nSkipping line 554172: expected 2 fields, saw 5\\nSkipping line 563534: expected 2 fields, saw 5\\nSkipping line 565191: expected 2 fields, saw 5\\nSkipping line 574108: expected 2 fields, saw 5\\nSkipping line 574412: expected 2 fields, saw 5\\nSkipping line 575985: expected 2 fields, saw 5\\nSkipping line 580091: expected 2 fields, saw 5\\nSkipping line 582682: expected 2 fields, saw 5\\nSkipping line 585885: expected 2 fields, saw 5\\nSkipping line 590171: expected 2 fields, saw 5\\nSkipping line 591924: expected 2 fields, saw 5\\nSkipping line 592515: expected 2 fields, saw 5\\nSkipping line 593888: expected 2 fields, saw 5\\nSkipping line 596245: expected 2 fields, saw 5\\nSkipping line 607344: expected 2 fields, saw 5\\nSkipping line 607633: expected 2 fields, saw 5\\nSkipping line 610939: expected 2 fields, saw 5\\nSkipping line 613638: expected 2 fields, saw 5\\nSkipping line 615643: expected 2 fields, saw 5\\nSkipping line 615901: expected 2 fields, saw 5\\nSkipping line 617389: expected 2 fields, saw 5\\nSkipping line 634641: expected 2 fields, saw 5\\nSkipping line 635755: expected 2 fields, saw 5\\nSkipping line 646243: expected 2 fields, saw 5\\nSkipping line 647165: expected 2 fields, saw 5\\nSkipping line 648610: expected 2 fields, saw 5\\nSkipping line 648772: expected 2 fields, saw 5\\nSkipping line 651833: expected 2 fields, saw 5\\nSkipping line 653663: expected 2 fields, saw 5\\nSkipping line 656233: expected 2 fields, saw 5\\nSkipping line 656694: expected 2 fields, saw 5\\nSkipping line 659783: expected 2 fields, saw 5\\nSkipping line 660478: expected 2 fields, saw 5\\nSkipping line 661133: expected 2 fields, saw 5\\nSkipping line 661736: expected 2 fields, saw 5\\nSkipping line 669827: expected 2 fields, saw 5\\n'\n"
          ]
        },
        {
          "output_type": "execute_result",
          "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>password</th>\n",
              "      <th>strength</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>kzde5577</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>kino3434</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>visi7k1yr</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>megzy123</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>lamborghin1</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "      password  strength\n",
              "0     kzde5577         1\n",
              "1     kino3434         1\n",
              "2    visi7k1yr         1\n",
              "3     megzy123         1\n",
              "4  lamborghin1         1"
            ]
          },
          "metadata": {},
          "execution_count": 47
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "63E-BopuQKa5",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "988ab917-f4f9-484e-8f9c-c92dc0c9f1c0"
      },
      "source": [
        "data['strength'].unique()"
      ],
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 2, 0])"
            ]
          },
          "metadata": {},
          "execution_count": 48
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ztLoaxPUQKa6"
      },
      "source": [
        "#### code to check all the missing values in my dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mVVIydRAQKa6",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "022c59b4-ec71-43aa-d4d7-cd2024b20526"
      },
      "source": [
        "data.isna().sum()"
      ],
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "password    1\n",
              "strength    0\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "80grTBhpQKa7",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 80
        },
        "outputId": "53ca1712-34ac-45cf-937c-5c3f2e72a568"
      },
      "source": [
        "data[data['password'].isnull()]"
      ],
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>password</th>\n",
              "      <th>strength</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>367579</th>\n",
              "      <td>NaN</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "       password  strength\n",
              "367579      NaN         0"
            ]
          },
          "metadata": {},
          "execution_count": 50
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LMvsv2YLQKa7"
      },
      "source": [
        "data.dropna(inplace=True)"
      ],
      "execution_count": 51,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "92C693gCQKa7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f81dd8f3-ea26-4b55-ed42-c48815fd3cd9"
      },
      "source": [
        "data.isnull().sum()"
      ],
      "execution_count": 52,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "password    0\n",
              "strength    0\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 52
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "YNIgl6MEQKa8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 296
        },
        "outputId": "4074fced-a2d5-4a2f-f127-7b0fb14b414a"
      },
      "source": [
        "sns.countplot(data['strength'])"
      ],
      "execution_count": 53,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f3d601f59d0>"
            ]
          },
          "metadata": {},
          "execution_count": 53
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MAOpXMnKQKa8"
      },
      "source": [
        "password_tuple=np.array(data)"
      ],
      "execution_count": 54,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Z8LgBJCbQKa9",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ad00bcd5-c379-43f5-edc8-199ed30decaa"
      },
      "source": [
        "password_tuple"
      ],
      "execution_count": 55,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([['kzde5577', 1],\n",
              "       ['kino3434', 1],\n",
              "       ['visi7k1yr', 1],\n",
              "       ...,\n",
              "       ['184520socram', 1],\n",
              "       ['marken22a', 1],\n",
              "       ['fxx4pw4g', 1]], dtype=object)"
            ]
          },
          "metadata": {},
          "execution_count": 55
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IiDCozNZQKa-"
      },
      "source": [
        "#### **shuffling randomly for robustness**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yWw3v4XVQKa-"
      },
      "source": [
        "import random\n",
        "random.shuffle(password_tuple)"
      ],
      "execution_count": 56,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-d2zb9bzQKa_"
      },
      "source": [
        "x=[labels[0] for labels in password_tuple]\n",
        "y=[labels[1] for labels in password_tuple]\n"
      ],
      "execution_count": 57,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "X77pVcI6QKbA"
      },
      "source": [
        "#### **create a custom function to split input into characters of list**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-L7RaUSSQKbA"
      },
      "source": [
        "def word_divide_char(inputs):\n",
        "    character=[]\n",
        "    for i in inputs:\n",
        "        character.append(i)\n",
        "    return character"
      ],
      "execution_count": 59,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rbDlR9hBQKbB",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b659e464-3b51-446d-a19e-76d60e0f6888"
      },
      "source": [
        "word_divide_char('kzde5577')"
      ],
      "execution_count": 60,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['k', 'z', 'd', 'e', '5', '5', '7', '7']"
            ]
          },
          "metadata": {},
          "execution_count": 60
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qpr8G6fKQKbB"
      },
      "source": [
        "#### **import TF-IDF vectorizer to convert String data into numerical data**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GjDynX8hQKbC"
      },
      "source": [
        "from sklearn.feature_extraction.text import TfidfVectorizer"
      ],
      "execution_count": 61,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ww_RFM9DQKbC"
      },
      "source": [
        "vectorizer=TfidfVectorizer(tokenizer=word_divide_char)"
      ],
      "execution_count": 62,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SNRIQThNQKbC"
      },
      "source": [
        "#### **apply TF-IDF vectorizer on data**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w9ISj0nUQKbD"
      },
      "source": [
        "X=vectorizer.fit_transform(x)"
      ],
      "execution_count": 63,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yf4Kxd91QKbD",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b60d01cd-4eed-4b9d-cb4a-3ae9bfe04fd5"
      },
      "source": [
        "X.shape"
      ],
      "execution_count": 64,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(669639, 131)"
            ]
          },
          "metadata": {},
          "execution_count": 64
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DlI812HfQKbD",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "423fea08-aafd-4222-830b-6f28723136c1"
      },
      "source": [
        "vectorizer.get_feature_names()"
      ],
      "execution_count": 65,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['\\x01',\n",
              " '\\x02',\n",
              " '\\x05',\n",
              " '\\x06',\n",
              " '\\x08',\n",
              " '\\x10',\n",
              " '\\x11',\n",
              " '\\x16',\n",
              " '\\x17',\n",
              " '\\x19',\n",
              " '\\x1b',\n",
              " '\\x1c',\n",
              " '\\x1e',\n",
              " ' ',\n",
              " '!',\n",
              " '\"',\n",
              " '#',\n",
              " '$',\n",
              " '%',\n",
              " '&',\n",
              " '(',\n",
              " ')',\n",
              " '*',\n",
              " '+',\n",
              " '-',\n",
              " '.',\n",
              " '/',\n",
              " '0',\n",
              " '1',\n",
              " '2',\n",
              " '3',\n",
              " '4',\n",
              " '5',\n",
              " '6',\n",
              " '7',\n",
              " '8',\n",
              " '9',\n",
              " ';',\n",
              " '<',\n",
              " '=',\n",
              " '>',\n",
              " '?',\n",
              " '@',\n",
              " '[',\n",
              " '\\\\',\n",
              " ']',\n",
              " '^',\n",
              " '_',\n",
              " '`',\n",
              " 'a',\n",
              " 'b',\n",
              " 'c',\n",
              " 'd',\n",
              " 'e',\n",
              " 'f',\n",
              " 'g',\n",
              " 'h',\n",
              " 'i',\n",
              " 'j',\n",
              " 'k',\n",
              " 'l',\n",
              " 'm',\n",
              " 'n',\n",
              " 'o',\n",
              " 'p',\n",
              " 'q',\n",
              " 'r',\n",
              " 's',\n",
              " 't',\n",
              " 'u',\n",
              " 'v',\n",
              " 'w',\n",
              " 'x',\n",
              " 'y',\n",
              " 'z',\n",
              " '{',\n",
              " '|',\n",
              " '}',\n",
              " '~',\n",
              " '\\x7f',\n",
              " '\\x81',\n",
              " '\\x8d',\n",
              " '\\xa0',\n",
              " '¡',\n",
              " '¢',\n",
              " '¨',\n",
              " '¯',\n",
              " '°',\n",
              " '±',\n",
              " '²',\n",
              " '³',\n",
              " '´',\n",
              " 'µ',\n",
              " '¶',\n",
              " '·',\n",
              " '¹',\n",
              " 'º',\n",
              " '¼',\n",
              " '¾',\n",
              " '¿',\n",
              " '×',\n",
              " 'ß',\n",
              " 'à',\n",
              " 'á',\n",
              " 'â',\n",
              " 'ä',\n",
              " 'å',\n",
              " 'æ',\n",
              " 'ç',\n",
              " 'è',\n",
              " 'ê',\n",
              " 'ï',\n",
              " 'ð',\n",
              " 'ñ',\n",
              " 'ò',\n",
              " 'ó',\n",
              " 'ô',\n",
              " 'õ',\n",
              " 'ö',\n",
              " '÷',\n",
              " 'ù',\n",
              " 'ú',\n",
              " 'û',\n",
              " 'ü',\n",
              " 'ý',\n",
              " 'þ',\n",
              " 'ÿ',\n",
              " 'œ',\n",
              " '‚',\n",
              " '‹',\n",
              " '›']"
            ]
          },
          "metadata": {},
          "execution_count": 65
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "oNkgtzO-QKbE",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "421bedf2-7512-4d87-bf4c-b428d8612399"
      },
      "source": [
        "first_document_vector=X[0]\n",
        "first_document_vector"
      ],
      "execution_count": 66,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<1x131 sparse matrix of type '<class 'numpy.float64'>'\n",
              "\twith 6 stored elements in Compressed Sparse Row format>"
            ]
          },
          "metadata": {},
          "execution_count": 66
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1Uw_9O7-QKbE",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1b4bdec8-2a5a-4b41-a148-fbbb8da5c171"
      },
      "source": [
        "first_document_vector.T.todense()"
      ],
      "execution_count": 67,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "matrix([[0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.56668533],\n",
              "        [0.        ],\n",
              "        [0.5918464 ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.28571868],\n",
              "        [0.2213052 ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.29131744],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.33631618],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ],\n",
              "        [0.        ]])"
            ]
          },
          "metadata": {},
          "execution_count": 67
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "o9qMdP7-QKbF",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 419
        },
        "outputId": "e1862316-42ca-46fa-d665-fad470ae19e3"
      },
      "source": [
        "df=pd.DataFrame(first_document_vector.T.todense(),index=vectorizer.get_feature_names(),columns=['TF-IDF'])\n",
        "df.sort_values(by=['TF-IDF'],ascending=False)"
      ],
      "execution_count": 68,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>TF-IDF</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>0.591846</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>0.566685</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>z</th>\n",
              "      <td>0.336316</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>k</th>\n",
              "      <td>0.291317</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>d</th>\n",
              "      <td>0.285719</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>=</th>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>&lt;</th>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>;</th>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>›</th>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>131 rows × 1 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "      TF-IDF\n",
              "7   0.591846\n",
              "5   0.566685\n",
              "z   0.336316\n",
              "k   0.291317\n",
              "d   0.285719\n",
              "..       ...\n",
              "=   0.000000\n",
              "<   0.000000\n",
              ";   0.000000\n",
              "9   0.000000\n",
              "›   0.000000\n",
              "\n",
              "[131 rows x 1 columns]"
            ]
          },
          "metadata": {},
          "execution_count": 68
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6DuJ3P0OQKbF"
      },
      "source": [
        "#### **split data into train & test**\n",
        "    train---> To learn the relationship within data, \n",
        "    test-->  To do predictions, and this testing data will be unseen to my model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kCXBHeGXQKbG"
      },
      "source": [
        "from sklearn.model_selection import train_test_split"
      ],
      "execution_count": 69,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gqLcq0dhQKbG"
      },
      "source": [
        "X_train, X_test, y_train, y_test=train_test_split(X,y,test_size=0.2)"
      ],
      "execution_count": 70,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FUMqyAuQQKbG",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "392f04a4-2578-4a68-847c-ba270a57a47b"
      },
      "source": [
        "X_train.shape"
      ],
      "execution_count": 71,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(535711, 131)"
            ]
          },
          "metadata": {},
          "execution_count": 71
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9SEdsZMYQKbG"
      },
      "source": [
        "from sklearn.linear_model import LogisticRegression"
      ],
      "execution_count": 72,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Cpgbo5fmQKbH"
      },
      "source": [
        "#### **apply Logistic on data as use-cas is Classification**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "C-TpGyW3QKbH"
      },
      "source": [
        "clf=LogisticRegression(random_state=0,multi_class='multinomial')"
      ],
      "execution_count": 73,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4oEk2iTRQKbH",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "00fe1734-13d2-4242-e136-2f35df49410c"
      },
      "source": [
        "clf.fit(X_train,y_train)"
      ],
      "execution_count": 74,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
              "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
              "                   multi_class='multinomial', n_jobs=None, penalty='l2',\n",
              "                   random_state=0, solver='lbfgs', tol=0.0001, verbose=0,\n",
              "                   warm_start=False)"
            ]
          },
          "metadata": {},
          "execution_count": 74
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "t4RgDH_HQKbI"
      },
      "source": [
        "#### **doing prediction for specific custom data**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MdAcsvo9QKbI",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "2da947f9-adc6-464b-e092-d12f9b2e21a5"
      },
      "source": [
        "passwordCheck = input(\"Enter Password to check Strength: \")\n",
        "\n",
        "dt=np.array([passwordCheck])\n",
        "pred=vectorizer.transform(dt)\n",
        "x = clf.predict(pred)\n",
        "if x[0] == 0:\n",
        "  print(\"Your Password is Weak.\")\n",
        "elif x[0] == 1:\n",
        "  print(\"Your Password is Strong.\")\n",
        "else:\n",
        "  print(\"Your Password is Very Strong.\")"
      ],
      "execution_count": 83,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Enter Password to check Strength: @%12ABCXYZ$\n",
            "Your Password is Very Strong.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "g9l4WA0mQKbJ"
      },
      "source": [
        "#### **doing prediction on X-Test data**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cpiPZDAXQKbJ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "163ee3fc-7c0e-4941-abff-14ed37592f0b"
      },
      "source": [
        "y_pred=clf.predict(X_test)\n",
        "y_pred"
      ],
      "execution_count": 76,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 1, 2, ..., 1, 1, 1])"
            ]
          },
          "metadata": {},
          "execution_count": 76
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "THiXhjDjQKbK"
      },
      "source": [
        "#### **check Accuracy of your model using confusion_matrix,accuracy_score**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MG4wAL6LQKbK"
      },
      "source": [
        "from sklearn.metrics import confusion_matrix,accuracy_score"
      ],
      "execution_count": 77,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "KgbB6UwSQKbK",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c2d2e28d-017c-4d8a-fb5f-d9674b39bc62"
      },
      "source": [
        "cm=confusion_matrix(y_test,y_pred)\n",
        "print(cm)\n",
        "print(accuracy_score(y_test,y_pred))"
      ],
      "execution_count": 78,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[[ 5071 12733    12]\n",
            " [ 3608 93462  2568]\n",
            " [   28  5024 11422]]\n",
            "0.8210008362702348\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fSHZDKw5QKbL"
      },
      "source": [
        "##### **create report of your model**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EyAyudQ0QKbL",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d4349dca-7811-4a6f-b567-3cde6b77ac57"
      },
      "source": [
        "from sklearn.metrics import classification_report\n",
        "print(classification_report(y_test,y_pred))"
      ],
      "execution_count": 79,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.58      0.28      0.38     17816\n",
            "           1       0.84      0.94      0.89     99638\n",
            "           2       0.82      0.69      0.75     16474\n",
            "\n",
            "    accuracy                           0.82    133928\n",
            "   macro avg       0.75      0.64      0.67    133928\n",
            "weighted avg       0.80      0.82      0.80    133928\n",
            "\n"
          ]
        }
      ]
    }
  ]
}