From 9634997a661474ff02e250e197356c346c37639a Mon Sep 17 00:00:00 2001
From: Diwakar Gupta <39624018+Diwakar-Gupta@users.noreply.github.com>
Date: Sun, 14 Aug 2022 14:38:59 +0530
Subject: [PATCH] Spam_Ham_Classifier

---
 22-08-14-NLP/Spam_Ham_Classifier.ipynb | 728 +++++++++++++++++++++++++
 1 file changed, 728 insertions(+)
 create mode 100644 22-08-14-NLP/Spam_Ham_Classifier.ipynb

diff --git a/22-08-14-NLP/Spam_Ham_Classifier.ipynb b/22-08-14-NLP/Spam_Ham_Classifier.ipynb
new file mode 100644
index 0000000..1fb1b53
--- /dev/null
+++ b/22-08-14-NLP/Spam_Ham_Classifier.ipynb
@@ -0,0 +1,728 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "Spam_Ham_Classifier_April.ipynb",
+      "provenance": [],
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/Diwakar-Gupta/Data-Science-APRIL/blob/main/22-08-14-NLP/Spam_Ham_Classifier.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "871U7ZuiYLZw"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import pandas as pd"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "messages=pd.read_csv('https://raw.githubusercontent.com/Pepcoders/Data-Science-January/main/NLP/sms',sep='\\t',names=['label','message'])"
+      ],
+      "metadata": {
+        "id": "I7Msp7itYj2R"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "messages"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 424
+        },
+        "id": "pq4rXQk3Yk4q",
+        "outputId": "819647f5-e0d3-4dfa-e7dc-9dbe75588969"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "     label                                            message\n",
+              "0      ham  Go until jurong point, crazy.. Available only ...\n",
+              "1      ham                      Ok lar... Joking wif u oni...\n",
+              "2     spam  Free entry in 2 a wkly comp to win FA Cup fina...\n",
+              "3      ham  U dun say so early hor... U c already then say...\n",
+              "4      ham  Nah I don't think he goes to usf, he lives aro...\n",
+              "...    ...                                                ...\n",
+              "5567  spam  This is the 2nd time we have tried 2 contact u...\n",
+              "5568   ham               Will ü b going to esplanade fr home?\n",
+              "5569   ham  Pity, * was in mood for that. So...any other s...\n",
+              "5570   ham  The guy did some bitching but I acted like i'd...\n",
+              "5571   ham                         Rofl. Its true to its name\n",
+              "\n",
+              "[5572 rows x 2 columns]"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-68851dd4-ed16-4856-89ae-2f99da3a8613\">\n",
+              "    <div class=\"colab-df-container\">\n",
+              "      <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>label</th>\n",
+              "      <th>message</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>ham</td>\n",
+              "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>ham</td>\n",
+              "      <td>Ok lar... Joking wif u oni...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>spam</td>\n",
+              "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>ham</td>\n",
+              "      <td>U dun say so early hor... U c already then say...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>ham</td>\n",
+              "      <td>Nah I don't think he goes to usf, he lives aro...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>5567</th>\n",
+              "      <td>spam</td>\n",
+              "      <td>This is the 2nd time we have tried 2 contact u...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>5568</th>\n",
+              "      <td>ham</td>\n",
+              "      <td>Will ü b going to esplanade fr home?</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>5569</th>\n",
+              "      <td>ham</td>\n",
+              "      <td>Pity, * was in mood for that. So...any other s...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>5570</th>\n",
+              "      <td>ham</td>\n",
+              "      <td>The guy did some bitching but I acted like i'd...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>5571</th>\n",
+              "      <td>ham</td>\n",
+              "      <td>Rofl. Its true to its name</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>5572 rows × 2 columns</p>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-68851dd4-ed16-4856-89ae-2f99da3a8613')\"\n",
+              "              title=\"Convert this dataframe to an interactive table.\"\n",
+              "              style=\"display:none;\">\n",
+              "        \n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+              "       width=\"24px\">\n",
+              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
+              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
+              "  </svg>\n",
+              "      </button>\n",
+              "      \n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      flex-wrap:wrap;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "      <script>\n",
+              "        const buttonEl =\n",
+              "          document.querySelector('#df-68851dd4-ed16-4856-89ae-2f99da3a8613 button.colab-df-convert');\n",
+              "        buttonEl.style.display =\n",
+              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "        async function convertToInteractive(key) {\n",
+              "          const element = document.querySelector('#df-68851dd4-ed16-4856-89ae-2f99da3a8613');\n",
+              "          const dataTable =\n",
+              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                     [key], {});\n",
+              "          if (!dataTable) return;\n",
+              "\n",
+              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "            + ' to learn more about interactive tables.';\n",
+              "          element.innerHTML = '';\n",
+              "          dataTable['output_type'] = 'display_data';\n",
+              "          await google.colab.output.renderOutput(dataTable, element);\n",
+              "          const docLink = document.createElement('div');\n",
+              "          docLink.innerHTML = docLinkHtml;\n",
+              "          element.appendChild(docLink);\n",
+              "        }\n",
+              "      </script>\n",
+              "    </div>\n",
+              "  </div>\n",
+              "  "
+            ]
+          },
+          "metadata": {},
+          "execution_count": 3
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#Data Cleaning and Processing\n",
+        "import nltk\n",
+        "import re\n",
+        "nltk.download('stopwords')"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "0VMxeL37Yl3S",
+        "outputId": "7e136a17-47cf-489c-cd07-2d5ff4badc0a"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
+            "[nltk_data]   Unzipping corpora/stopwords.zip.\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "True"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 4
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from nltk.corpus import stopwords\n",
+        "from nltk.stem.porter import PorterStemmer\n"
+      ],
+      "metadata": {
+        "id": "9GuPp659Yo7F"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "ps=PorterStemmer()\n",
+        "corpus=[]"
+      ],
+      "metadata": {
+        "id": "KqkCObDMYqMR"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "for i in range(0,len(messages)):\n",
+        "  review = re.sub('[^a-zA-Z]', ' ', messages['message'][i])\n",
+        "  review=review.lower()\n",
+        "  review=review.split()\n",
+        "\n",
+        "  review=[ps.stem(word) for word in review if not word in stopwords.words('english')]\n",
+        "  review=\" \".join(review)\n",
+        "  corpus.append(review)\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "rxFW9nGaYt_K"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "## Create Bag Of Words Model\n",
+        "## Convert words to numeric form\n",
+        "\n",
+        "from sklearn.feature_extraction.text import CountVectorizer\n",
+        "cv=CountVectorizer(max_features=3000)\n",
+        "X=cv.fit_transform(corpus).toarray()"
+      ],
+      "metadata": {
+        "id": "qBoy9Zz1YvlC"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "messages['label']"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wJ7uRMHWY1QV",
+        "outputId": "e108b7e0-c192-4308-cd23-2a81efb50862"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "0        ham\n",
+              "1        ham\n",
+              "2       spam\n",
+              "3        ham\n",
+              "4        ham\n",
+              "        ... \n",
+              "5567    spam\n",
+              "5568     ham\n",
+              "5569     ham\n",
+              "5570     ham\n",
+              "5571     ham\n",
+              "Name: label, Length: 5572, dtype: object"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 9
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from sklearn.preprocessing import LabelEncoder\n",
+        "\n",
+        "lb=LabelEncoder()\n",
+        "y=lb.fit_transform(messages['label'])"
+      ],
+      "metadata": {
+        "id": "O0zFC_BvY3GJ"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "y"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "y0yDIIdVY5I5",
+        "outputId": "68b723c1-151a-4abb-da03-fc28e9c6b9b8"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "array([0, 0, 1, ..., 0, 0, 0])"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 11
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "IAIdHPTmY7sK",
+        "outputId": "d23d435a-742c-4d02-ef4b-fa05a5764df1"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "array([[0, 0, 0, ..., 0, 0, 0],\n",
+              "       [0, 0, 0, ..., 0, 0, 0],\n",
+              "       [0, 0, 0, ..., 0, 0, 0],\n",
+              "       ...,\n",
+              "       [0, 0, 0, ..., 0, 0, 0],\n",
+              "       [0, 0, 0, ..., 0, 0, 0],\n",
+              "       [0, 0, 0, ..., 0, 0, 0]])"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 12
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "## Model Building\n",
+        "\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "\n",
+        "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)"
+      ],
+      "metadata": {
+        "id": "_tGj9L80Y9Da"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from sklearn.naive_bayes import MultinomialNB,GaussianNB\n",
+        "\n",
+        "spam_detect_model_1=MultinomialNB()\n",
+        "\n",
+        "spam_detect_model_2=GaussianNB()\n"
+      ],
+      "metadata": {
+        "id": "f_57yerKY_VD"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "spam_detect_model_1.fit(X_train,y_train)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "AomcCaIAZSLJ",
+        "outputId": "a1b78ab3-087f-4928-fcf9-059cf6c616c4"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "MultinomialNB()"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 15
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "spam_detect_model_2.fit(X_train,y_train)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "tPrgljEDZTz_",
+        "outputId": "adec0210-377d-43ad-c533-8a9df765c95e"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "GaussianNB()"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 16
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "spam_detect_model_1.score(X_train,y_train)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "DunME4KgZU2C",
+        "outputId": "e8609db1-f633-48ae-f853-c125b5300802"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "0.989230424052053"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 17
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "spam_detect_model_2.score(X_train,y_train)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "HVcrLrKxZV52",
+        "outputId": "6f92f405-3ac0-4e31-f82d-9e90efd82db2"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "0.8873681848777204"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 18
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "spam_detect_model_1.score(X_test,y_test)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Tl0Op1wwZYxL",
+        "outputId": "c2045515-01c2-42f0-f75b-928811f78626"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "0.9838565022421525"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 19
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "spam_detect_model_2.score(X_test,y_test)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "FWWjotY3ZaLZ",
+        "outputId": "bda5673b-a874-4cfb-ce0d-f476205c787a"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "0.8600896860986547"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 20
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "###############CONCLUSION##################\n",
+        "#### MULTINOMIAL NB IS PERFORMING WELL ####"
+      ],
+      "metadata": {
+        "id": "mkmVgvEHZbYI"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "X_test"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "OEgI4b9fZkT9",
+        "outputId": "c4bcfec6-3b15-4979-80e9-2e5b800b4da1"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "array([[0, 0, 0, ..., 0, 0, 0],\n",
+              "       [0, 0, 0, ..., 0, 0, 0],\n",
+              "       [0, 0, 0, ..., 0, 0, 0],\n",
+              "       ...,\n",
+              "       [0, 0, 0, ..., 0, 0, 0],\n",
+              "       [0, 0, 0, ..., 0, 0, 0],\n",
+              "       [0, 0, 0, ..., 0, 0, 0]])"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 22
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "set(spam_detect_model_1.predict(X_test))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "sfJQayeaZoH8",
+        "outputId": "d22300ad-a956-457d-9f99-a10c38740658"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "{0, 1}"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 24
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        ""
+      ],
+      "metadata": {
+        "id": "Ivfr0OhLZpaN"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}
\ No newline at end of file