Skip to content

Commit

Permalink
ML Lab Assignments
Browse files Browse the repository at this point in the history
  • Loading branch information
@hunter-619
hunter-619 committed Oct 18, 2023
1 parent 7c8087c commit d888826
Show file tree
Hide file tree
Showing 10 changed files with 219,640 additions and 0 deletions.
634 changes: 634 additions & 0 deletions ML/Assignment-1.ipynb
View file

Large diffs are not rendered by default.

345 changes: 345 additions & 0 deletions ML/Assignment-2.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,345 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Assignment 2\n",
"Classify the email using the binary classification method. Email Spam detection has two states:\n",
"a) Normal State – Not Spam,\n",
"b) Abnormal State – Spam.\n",
"Use K-Nearest Neighbors and Support Vector Machine for classification.\n",
"Analyze their performance.\n",
"Dataset link: The emails.csv dataset on the Kaggle https://www.kaggle.com/datasets/balaka18/email-spam-classification-dataset-csv"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.svm import SVC\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.neighbors import KNeighborsClassifier"
]
},
{
"cell_type": "code",
"execution_count": 4,
"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>Email No.</th>\n",
" <th>the</th>\n",
" <th>to</th>\n",
" <th>ect</th>\n",
" <th>and</th>\n",
" <th>for</th>\n",
" <th>of</th>\n",
" <th>a</th>\n",
" <th>you</th>\n",
" <th>hou</th>\n",
" <th>...</th>\n",
" <th>connevey</th>\n",
" <th>jay</th>\n",
" <th>valued</th>\n",
" <th>lay</th>\n",
" <th>infrastructure</th>\n",
" <th>military</th>\n",
" <th>allowing</th>\n",
" <th>ff</th>\n",
" <th>dry</th>\n",
" <th>Prediction</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Email 1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Email 2</td>\n",
" <td>8</td>\n",
" <td>13</td>\n",
" <td>24</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>2</td>\n",
" <td>102</td>\n",
" <td>1</td>\n",
" <td>27</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Email 3</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>8</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Email 4</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>22</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>51</td>\n",
" <td>2</td>\n",
" <td>10</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Email 5</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>17</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>57</td>\n",
" <td>0</td>\n",
" <td>9</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 3002 columns</p>\n",
"</div>"
],
"text/plain": [
" 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]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\"./datasets/emails.csv\", nrows=5000)\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Email No. 0\n",
"the 0\n",
"to 0\n",
"ect 0\n",
"and 0\n",
" ..\n",
"military 0\n",
"allowing 0\n",
"ff 0\n",
"dry 0\n",
"Prediction 0\n",
"Length: 3002, dtype: int64"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.isnull().sum()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"X = df.drop([\"Email No.\", \"Prediction\"], axis=1)\n",
"Y = df[\"Prediction\"]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"train_x, test_x, train_y, test_y = train_test_split(X, Y, test_size = 0.25, random_state = 1)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy Score for KNN: 0.8728\n"
]
}
],
"source": [
"knn = KNeighborsClassifier(n_neighbors=7)\n",
"knn.fit(train_x, train_y)\n",
"print(\"Accuracy Score for KNN:\", knn.score(test_x, test_y))"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy Score for SVC: 0.9168\n"
]
}
],
"source": [
"svc = SVC(C=1.0, kernel='rbf', gamma='auto')\n",
"svc.fit(train_x, train_y)\n",
"y_pred2 = svc.predict(test_x)\n",
"print(\"Accuracy Score for SVC:\", accuracy_score(y_pred2, test_y))"
]
}
],
"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": "3.10.7"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
Loading

0 comments on commit d888826

Please sign in to comment.