Created
September 29, 2023 19:24
-
-
Save ShahStavan/b9796007943a71a60bdd2a8e31b97d35 to your computer and use it in GitHub Desktop.
22bce539_Practical_5.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"nbformat": 4, | |
"nbformat_minor": 0, | |
"metadata": { | |
"colab": { | |
"provenance": [], | |
"authorship_tag": "ABX9TyP8jfPENwh78S9kTzOjASEA", | |
"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/gist/ShahStavan/b9796007943a71a60bdd2a8e31b97d35/22bce539_practical_5.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"source": [ | |
"Name & Roll no. :- Shah Stavan, 22bce539\n", | |
"\n", | |
"Subject & Course code :- ML, 2CS501\n", | |
"\n", | |
"Date : 29/09/2023" | |
], | |
"metadata": { | |
"id": "_sFJmwl1QBOR" | |
} | |
}, | |
{ | |
"cell_type": "markdown", | |
"source": [ | |
"# Practical 5 Naive Bayes\n", | |
"Naïve-Bayes – Multivariate Bernoulli, Multinomial and Gaussian using sklearn" | |
], | |
"metadata": { | |
"id": "Z6p8pDGdQK9w" | |
} | |
}, | |
{ | |
"cell_type": "markdown", | |
"source": [ | |
"Text Feature Extraction using Common Vectorizer" | |
], | |
"metadata": { | |
"id": "X7eA9V3tQUxj" | |
} | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": { | |
"colab": { | |
"base_uri": "https://localhost:8080/" | |
}, | |
"id": "zv1FHGGnP2gI", | |
"outputId": "b37e893f-9827-46ea-c25d-5f67920ad4af" | |
}, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"name": "stdout", | |
"text": [ | |
"List of unique words : ['and' 'documentation' 'first' 'is' 'library' 'of' 'one' 'paper'\n", | |
" 'research' 'second' 'the' 'third' 'this']\n", | |
"Document Term Matrix : \n", | |
"[[1 1 1 1 1 1 0 1 1 0 1 0 1]\n", | |
" [1 1 0 1 0 0 0 1 1 2 1 0 1]\n", | |
" [1 0 0 0 0 0 1 0 0 0 1 1 0]\n", | |
" [0 0 1 1 0 0 0 1 1 0 1 0 1]]\n" | |
] | |
} | |
], | |
"source": [ | |
"from sklearn.feature_extraction.text import CountVectorizer\n", | |
"\n", | |
"# Create a CountVectorizer instance\n", | |
"vectorizer = CountVectorizer()\n", | |
"\n", | |
"# Define the corpus (collection of documents)\n", | |
"corpus = [\n", | |
" 'This is the first Research Paper and Documentation of Library.',\n", | |
" 'This is the second second Research Paper and Documentation.',\n", | |
" 'And the third one.',\n", | |
" 'Is this the first Research Paper?'\n", | |
"]\n", | |
"\n", | |
"# Transform the text data into a Document-Term Matrix (DTM)\n", | |
"X = vectorizer.fit_transform(corpus)\n", | |
"\n", | |
"# Get the list of unique words (features)\n", | |
"unique_words = vectorizer.get_feature_names_out()\n", | |
"\n", | |
"# Print the unique words\n", | |
"print(\"List of unique words : \", unique_words)\n", | |
"\n", | |
"# Print the Document-Term Matrix (DTM)\n", | |
"print(\"Document Term Matrix : \")\n", | |
"print(X.toarray())\n" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"source": [ | |
"1. Importing Python Libraries and Dependencies\n" | |
], | |
"metadata": { | |
"id": "jk4OBVk5QwHI" | |
} | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"import numpy as np\n", | |
"import pandas as pd\n", | |
"from sklearn.pipeline import Pipeline\n", | |
"from sklearn.model_selection import train_test_split\n", | |
"from sklearn.metrics import confusion_matrix\n", | |
"from sklearn.naive_bayes import MultinomialNB\n", | |
"from sklearn.naive_bayes import BernoulliNB\n", | |
"from sklearn.naive_bayes import GaussianNB" | |
], | |
"metadata": { | |
"id": "i7CusTIOQvwP" | |
}, | |
"execution_count": 6, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "markdown", | |
"source": [ | |
"2. Upload the Dataset" | |
], | |
"metadata": { | |
"id": "GqQCUz63RGZ4" | |
} | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"from google.colab import files\n", | |
"uploaded = files.upload()" | |
], | |
"metadata": { | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 73 | |
}, | |
"id": "Sq6QkzGlQ8WR", | |
"outputId": "3936c5cd-b08a-48bf-f18c-2e9b2e0f35d1" | |
}, | |
"execution_count": 3, | |
"outputs": [ | |
{ | |
"output_type": "display_data", | |
"data": { | |
"text/plain": [ | |
"<IPython.core.display.HTML object>" | |
], | |
"text/html": [ | |
"\n", | |
" <input type=\"file\" id=\"files-404040ae-d7be-4d65-99b6-dff1c6c94cca\" name=\"files[]\" multiple disabled\n", | |
" style=\"border:none\" />\n", | |
" <output id=\"result-404040ae-d7be-4d65-99b6-dff1c6c94cca\">\n", | |
" Upload widget is only available when the cell has been executed in the\n", | |
" current browser session. Please rerun this cell to enable.\n", | |
" </output>\n", | |
" <script>// Copyright 2017 Google LLC\n", | |
"//\n", | |
"// Licensed under the Apache License, Version 2.0 (the \"License\");\n", | |
"// you may not use this file except in compliance with the License.\n", | |
"// You may obtain a copy of the License at\n", | |
"//\n", | |
"// http://www.apache.org/licenses/LICENSE-2.0\n", | |
"//\n", | |
"// Unless required by applicable law or agreed to in writing, software\n", | |
"// distributed under the License is distributed on an \"AS IS\" BASIS,\n", | |
"// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", | |
"// See the License for the specific language governing permissions and\n", | |
"// limitations under the License.\n", | |
"\n", | |
"/**\n", | |
" * @fileoverview Helpers for google.colab Python module.\n", | |
" */\n", | |
"(function(scope) {\n", | |
"function span(text, styleAttributes = {}) {\n", | |
" const element = document.createElement('span');\n", | |
" element.textContent = text;\n", | |
" for (const key of Object.keys(styleAttributes)) {\n", | |
" element.style[key] = styleAttributes[key];\n", | |
" }\n", | |
" return element;\n", | |
"}\n", | |
"\n", | |
"// Max number of bytes which will be uploaded at a time.\n", | |
"const MAX_PAYLOAD_SIZE = 100 * 1024;\n", | |
"\n", | |
"function _uploadFiles(inputId, outputId) {\n", | |
" const steps = uploadFilesStep(inputId, outputId);\n", | |
" const outputElement = document.getElementById(outputId);\n", | |
" // Cache steps on the outputElement to make it available for the next call\n", | |
" // to uploadFilesContinue from Python.\n", | |
" outputElement.steps = steps;\n", | |
"\n", | |
" return _uploadFilesContinue(outputId);\n", | |
"}\n", | |
"\n", | |
"// This is roughly an async generator (not supported in the browser yet),\n", | |
"// where there are multiple asynchronous steps and the Python side is going\n", | |
"// to poll for completion of each step.\n", | |
"// This uses a Promise to block the python side on completion of each step,\n", | |
"// then passes the result of the previous step as the input to the next step.\n", | |
"function _uploadFilesContinue(outputId) {\n", | |
" const outputElement = document.getElementById(outputId);\n", | |
" const steps = outputElement.steps;\n", | |
"\n", | |
" const next = steps.next(outputElement.lastPromiseValue);\n", | |
" return Promise.resolve(next.value.promise).then((value) => {\n", | |
" // Cache the last promise value to make it available to the next\n", | |
" // step of the generator.\n", | |
" outputElement.lastPromiseValue = value;\n", | |
" return next.value.response;\n", | |
" });\n", | |
"}\n", | |
"\n", | |
"/**\n", | |
" * Generator function which is called between each async step of the upload\n", | |
" * process.\n", | |
" * @param {string} inputId Element ID of the input file picker element.\n", | |
" * @param {string} outputId Element ID of the output display.\n", | |
" * @return {!Iterable<!Object>} Iterable of next steps.\n", | |
" */\n", | |
"function* uploadFilesStep(inputId, outputId) {\n", | |
" const inputElement = document.getElementById(inputId);\n", | |
" inputElement.disabled = false;\n", | |
"\n", | |
" const outputElement = document.getElementById(outputId);\n", | |
" outputElement.innerHTML = '';\n", | |
"\n", | |
" const pickedPromise = new Promise((resolve) => {\n", | |
" inputElement.addEventListener('change', (e) => {\n", | |
" resolve(e.target.files);\n", | |
" });\n", | |
" });\n", | |
"\n", | |
" const cancel = document.createElement('button');\n", | |
" inputElement.parentElement.appendChild(cancel);\n", | |
" cancel.textContent = 'Cancel upload';\n", | |
" const cancelPromise = new Promise((resolve) => {\n", | |
" cancel.onclick = () => {\n", | |
" resolve(null);\n", | |
" };\n", | |
" });\n", | |
"\n", | |
" // Wait for the user to pick the files.\n", | |
" const files = yield {\n", | |
" promise: Promise.race([pickedPromise, cancelPromise]),\n", | |
" response: {\n", | |
" action: 'starting',\n", | |
" }\n", | |
" };\n", | |
"\n", | |
" cancel.remove();\n", | |
"\n", | |
" // Disable the input element since further picks are not allowed.\n", | |
" inputElement.disabled = true;\n", | |
"\n", | |
" if (!files) {\n", | |
" return {\n", | |
" response: {\n", | |
" action: 'complete',\n", | |
" }\n", | |
" };\n", | |
" }\n", | |
"\n", | |
" for (const file of files) {\n", | |
" const li = document.createElement('li');\n", | |
" li.append(span(file.name, {fontWeight: 'bold'}));\n", | |
" li.append(span(\n", | |
" `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n", | |
" `last modified: ${\n", | |
" file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n", | |
" 'n/a'} - `));\n", | |
" const percent = span('0% done');\n", | |
" li.appendChild(percent);\n", | |
"\n", | |
" outputElement.appendChild(li);\n", | |
"\n", | |
" const fileDataPromise = new Promise((resolve) => {\n", | |
" const reader = new FileReader();\n", | |
" reader.onload = (e) => {\n", | |
" resolve(e.target.result);\n", | |
" };\n", | |
" reader.readAsArrayBuffer(file);\n", | |
" });\n", | |
" // Wait for the data to be ready.\n", | |
" let fileData = yield {\n", | |
" promise: fileDataPromise,\n", | |
" response: {\n", | |
" action: 'continue',\n", | |
" }\n", | |
" };\n", | |
"\n", | |
" // Use a chunked sending to avoid message size limits. See b/62115660.\n", | |
" let position = 0;\n", | |
" do {\n", | |
" const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n", | |
" const chunk = new Uint8Array(fileData, position, length);\n", | |
" position += length;\n", | |
"\n", | |
" const base64 = btoa(String.fromCharCode.apply(null, chunk));\n", | |
" yield {\n", | |
" response: {\n", | |
" action: 'append',\n", | |
" file: file.name,\n", | |
" data: base64,\n", | |
" },\n", | |
" };\n", | |
"\n", | |
" let percentDone = fileData.byteLength === 0 ?\n", | |
" 100 :\n", | |
" Math.round((position / fileData.byteLength) * 100);\n", | |
" percent.textContent = `${percentDone}% done`;\n", | |
"\n", | |
" } while (position < fileData.byteLength);\n", | |
" }\n", | |
"\n", | |
" // All done.\n", | |
" yield {\n", | |
" response: {\n", | |
" action: 'complete',\n", | |
" }\n", | |
" };\n", | |
"}\n", | |
"\n", | |
"scope.google = scope.google || {};\n", | |
"scope.google.colab = scope.google.colab || {};\n", | |
"scope.google.colab._files = {\n", | |
" _uploadFiles,\n", | |
" _uploadFilesContinue,\n", | |
"};\n", | |
"})(self);\n", | |
"</script> " | |
] | |
}, | |
"metadata": {} | |
}, | |
{ | |
"output_type": "stream", | |
"name": "stdout", | |
"text": [ | |
"Saving emails.csv to emails.csv\n" | |
] | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"import pandas as pd\n", | |
"\n", | |
"# Load the dataset\n", | |
"data_file_path = 'emails.csv'\n", | |
"df = pd.read_csv(data_file_path)\n", | |
"\n", | |
"# Display the first few rows of the dataset\n", | |
"print(df.head())\n", | |
"\n", | |
"# Split the data into features (X) and target (y)\n", | |
"y = df['Prediction']\n", | |
"X = df.drop(['Prediction', 'Email No.'], axis=1)\n", | |
"\n", | |
"# Split the data into training and testing sets\n", | |
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=10)" | |
], | |
"metadata": { | |
"colab": { | |
"base_uri": "https://localhost:8080/" | |
}, | |
"id": "zJM_wznNRL6p", | |
"outputId": "5b017cf3-a031-4560-8534-06a4ab1f5b9e" | |
}, | |
"execution_count": 7, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"name": "stdout", | |
"text": [ | |
" Email No. the to ect and for of a you hou ... connevey jay \\\n", | |
"0 Email 1 0 0 1 0 0 0 2 0 0 ... 0 0 \n", | |
"1 Email 2 8 13 24 6 6 2 102 1 27 ... 0 0 \n", | |
"2 Email 3 0 0 1 0 0 0 8 0 0 ... 0 0 \n", | |
"3 Email 4 0 5 22 0 5 1 51 2 10 ... 0 0 \n", | |
"4 Email 5 7 6 17 1 5 2 57 0 9 ... 0 0 \n", | |
"\n", | |
" valued lay infrastructure military allowing ff dry Prediction \n", | |
"0 0 0 0 0 0 0 0 0 \n", | |
"1 0 0 0 0 0 1 0 0 \n", | |
"2 0 0 0 0 0 0 0 0 \n", | |
"3 0 0 0 0 0 0 0 0 \n", | |
"4 0 0 0 0 0 1 0 0 \n", | |
"\n", | |
"[5 rows x 3002 columns]\n" | |
] | |
} | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"source": [ | |
"Practical 5 A : Multivariate Bernoulli NB" | |
], | |
"metadata": { | |
"id": "BXoEX9QfSSSc" | |
} | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"# Create and train the Bernoulli Naive Bayes model\n", | |
"model = BernoulliNB()\n", | |
"model.fit(X_train, y_train)\n", | |
"\n", | |
"# Make predictions on the test data\n", | |
"y_pred = model.predict(X_test)\n", | |
"\n", | |
"# Calculate and print the accuracy\n", | |
"accuracy_score = model.score(X_test, y_test)\n", | |
"print(\"Accuracy: {:.2f}%\".format(accuracy_score * 100))\n", | |
"\n", | |
"# Calculate and print the confusion matrix\n", | |
"confusion = confusion_matrix(y_test, y_pred)\n", | |
"print(\"Confusion Matrix:\")\n", | |
"print(confusion)" | |
], | |
"metadata": { | |
"colab": { | |
"base_uri": "https://localhost:8080/" | |
}, | |
"id": "ftRIJhYZSVKr", | |
"outputId": "67f84f4f-802f-4c5c-d9fb-598f1de80992" | |
}, | |
"execution_count": 8, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"name": "stdout", | |
"text": [ | |
"Accuracy: 87.34%\n", | |
"Confusion Matrix:\n", | |
"[[680 57]\n", | |
" [ 74 224]]\n" | |
] | |
} | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"source": [ | |
"Practical 5 B : Multinomial NB" | |
], | |
"metadata": { | |
"id": "7VtTcmFmSeYx" | |
} | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"# Create and train the Multinomial Naive Bayes model\n", | |
"model = MultinomialNB()\n", | |
"model.fit(X_train, y_train)\n", | |
"\n", | |
"# Predict the labels for the test dataset\n", | |
"y_pred = model.predict(X_test)\n", | |
"\n", | |
"# Calculate and print the accuracy\n", | |
"accuracy_score = model.score(X_test, y_test)\n", | |
"print(\"Accuracy: {:.2f}%\".format(accuracy_score * 100))\n", | |
"\n", | |
"# Calculate and print the confusion matrix\n", | |
"confusion = confusion_matrix(y_test, y_pred)\n", | |
"print(\"Confusion Matrix:\")\n", | |
"print(confusion)" | |
], | |
"metadata": { | |
"colab": { | |
"base_uri": "https://localhost:8080/" | |
}, | |
"id": "d2dREuZISgs4", | |
"outputId": "749737cc-ac72-48fc-93c7-b041bd1f89b3" | |
}, | |
"execution_count": 9, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"name": "stdout", | |
"text": [ | |
"Accuracy: 94.20%\n", | |
"Confusion Matrix:\n", | |
"[[693 44]\n", | |
" [ 16 282]]\n" | |
] | |
} | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"source": [ | |
"Practical 5 C : Gaussian NB" | |
], | |
"metadata": { | |
"id": "Wn22wKr-TanR" | |
} | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"# Initialize and train the Gaussian Naive Bayes model\n", | |
"model = GaussianNB()\n", | |
"model.fit(X_train, y_train)\n", | |
"\n", | |
"# Make predictions on the test data\n", | |
"y_pred = model.predict(X_test)\n", | |
"\n", | |
"# Calculate and print the accuracy\n", | |
"accuracy_score = model.score(X_test, y_test)\n", | |
"print(\"Accuracy: {:.2f}%\".format(accuracy_score * 100))\n", | |
"\n", | |
"\n", | |
"# Print the confusion matrix\n", | |
"confusion = confusion_matrix(y_test, y_pred)\n", | |
"print(\"Confusion Matrix:\")\n", | |
"print(confusion)" | |
], | |
"metadata": { | |
"colab": { | |
"base_uri": "https://localhost:8080/" | |
}, | |
"id": "0MnwEfu7TbYz", | |
"outputId": "36ca289f-ac50-4bea-dcc2-cb27afabdc20" | |
}, | |
"execution_count": 11, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"name": "stdout", | |
"text": [ | |
"Accuracy: 93.82%\n", | |
"Confusion Matrix:\n", | |
"[[692 45]\n", | |
" [ 19 279]]\n" | |
] | |
} | |
] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment