commit 8c16b19eb6540df7023ee311d8a673ccd8f5c2e2
parent 5790628433062ffa03bd8d30a1f530ac644c5f50
Author: Andrew <andrewlaack1@gmail.com>
Date: Sat, 29 Jun 2024 13:14:42 -0500
MN NB
Diffstat:
2 files changed, 1324 insertions(+), 33 deletions(-)
diff --git a/phishingClassification/ClassificationTry2.ipynb b/phishingClassification/ClassificationTry2.ipynb
@@ -0,0 +1,650 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "First try was ugly.\n",
+ "\n",
+ "This uses count vectorizer instead which basically one hot encodes and checks how many times a given word is in a message.\n",
+ "\n",
+ "This is then passed into the multinomial nb for fitting and evaluation. \n",
+ "\n",
+ "This is 96.5% accurate."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "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>Unnamed: 0</th>\n",
+ " <th>Email Text</th>\n",
+ " <th>Email Type</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>0</td>\n",
+ " <td>re : 6 . 1100 , disc : uniformitarianism , re ...</td>\n",
+ " <td>Safe Email</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>the other side of * galicismos * * galicismo *...</td>\n",
+ " <td>Safe Email</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2</td>\n",
+ " <td>re : equistar deal tickets are you still avail...</td>\n",
+ " <td>Safe Email</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>3</td>\n",
+ " <td>\\nHello I am your hot lil horny toy.\\n I am...</td>\n",
+ " <td>Phishing Email</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>4</td>\n",
+ " <td>software at incredibly low prices ( 86 % lower...</td>\n",
+ " <td>Phishing Email</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18645</th>\n",
+ " <td>18646</td>\n",
+ " <td>date a lonely housewife always wanted to date ...</td>\n",
+ " <td>Phishing Email</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18646</th>\n",
+ " <td>18647</td>\n",
+ " <td>request submitted : access request for anita ....</td>\n",
+ " <td>Safe Email</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18647</th>\n",
+ " <td>18648</td>\n",
+ " <td>re : important - prc mtg hi dorn & john , as y...</td>\n",
+ " <td>Safe Email</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18648</th>\n",
+ " <td>18649</td>\n",
+ " <td>press clippings - letter on californian utilit...</td>\n",
+ " <td>Safe Email</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18649</th>\n",
+ " <td>18650</td>\n",
+ " <td>empty</td>\n",
+ " <td>Phishing Email</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>18634 rows × 3 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Unnamed: 0 Email Text \\\n",
+ "0 0 re : 6 . 1100 , disc : uniformitarianism , re ... \n",
+ "1 1 the other side of * galicismos * * galicismo *... \n",
+ "2 2 re : equistar deal tickets are you still avail... \n",
+ "3 3 \\nHello I am your hot lil horny toy.\\n I am... \n",
+ "4 4 software at incredibly low prices ( 86 % lower... \n",
+ "... ... ... \n",
+ "18645 18646 date a lonely housewife always wanted to date ... \n",
+ "18646 18647 request submitted : access request for anita .... \n",
+ "18647 18648 re : important - prc mtg hi dorn & john , as y... \n",
+ "18648 18649 press clippings - letter on californian utilit... \n",
+ "18649 18650 empty \n",
+ "\n",
+ " Email Type \n",
+ "0 Safe Email \n",
+ "1 Safe Email \n",
+ "2 Safe Email \n",
+ "3 Phishing Email \n",
+ "4 Phishing Email \n",
+ "... ... \n",
+ "18645 Phishing Email \n",
+ "18646 Safe Email \n",
+ "18647 Safe Email \n",
+ "18648 Safe Email \n",
+ "18649 Phishing Email \n",
+ "\n",
+ "[18634 rows x 3 columns]"
+ ]
+ },
+ "execution_count": 34,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import pandas as pd \n",
+ "\n",
+ "df = pd.read_csv('../datasets/phishing/Phishing_Email.csv')\n",
+ "df = df.dropna()\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-7 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: black;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-7 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: block;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-7 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-7 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-7 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-7 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 1ex;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-7 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-7 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-7 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[('vect', CountVectorizer()), ('clf', MultinomialNB())])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-19\" type=\"checkbox\" ><label for=\"sk-estimator-id-19\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> Pipeline<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.pipeline.Pipeline.html\">?<span>Documentation for Pipeline</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>Pipeline(steps=[('vect', CountVectorizer()), ('clf', MultinomialNB())])</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-20\" type=\"checkbox\" ><label for=\"sk-estimator-id-20\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> CountVectorizer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html\">?<span>Documentation for CountVectorizer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>CountVectorizer()</pre></div> </div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-21\" type=\"checkbox\" ><label for=\"sk-estimator-id-21\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> MultinomialNB<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.naive_bayes.MultinomialNB.html\">?<span>Documentation for MultinomialNB</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>MultinomialNB()</pre></div> </div></div></div></div></div></div>"
+ ],
+ "text/plain": [
+ "Pipeline(steps=[('vect', CountVectorizer()), ('clf', MultinomialNB())])"
+ ]
+ },
+ "execution_count": 35,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.naive_bayes import MultinomialNB\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "from sklearn.feature_extraction.text import CountVectorizer\n",
+ "\n",
+ "# First split for training and initial test split\n",
+ "X_train, X_test, y_train, y_test = train_test_split(df['Email Text'], df['Email Type'])\n",
+ "\n",
+ "\n",
+ "# Create pipeline\n",
+ "pipeline = Pipeline([\n",
+ " ('vect', CountVectorizer()), # Use CountVectorizer to convert text into token counts\n",
+ " ('clf', MultinomialNB()), # Naive Bayes classifier\n",
+ "])\n",
+ "\n",
+ "# Fit the model on the training data\n",
+ "pipeline.fit(X_train, y_train)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0.9654432281605495"
+ ]
+ },
+ "execution_count": 36,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from sklearn.metrics import accuracy_score\n",
+ "\n",
+ "pred = pipeline.predict(X_test)\n",
+ "accuracy_score(y_pred=pred, y_true=y_test)"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": ".venv",
+ "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": "3.11.2"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/phishingClassification/PhishingClassification.ipynb b/phishingClassification/PhishingClassification.ipynb
@@ -9,7 +9,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 33,
"metadata": {},
"outputs": [
{
@@ -140,7 +140,7 @@
"[18650 rows x 3 columns]"
]
},
- "execution_count": 1,
+ "execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
@@ -154,7 +154,27 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 34,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from sklearn.naive_bayes import CategoricalNB\n",
+ "import keras\n",
+ "import numpy as np\n",
+ "\n",
+ "def toStr(inp):\n",
+ " return str(inp)\n",
+ "\n",
+ "layer = keras.layers.TextVectorization()\n",
+ "\n",
+ "df['Email Text'] = df['Email Text'].apply(toStr)\n",
+ "arr = ' '.join(np.array(df['Email Text']).tolist())\n",
+ "layer.adapt(arr)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
@@ -166,86 +186,707 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 36,
"metadata": {},
"outputs": [
{
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "2024-06-28 15:01:02.519344: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",
- "2024-06-28 15:01:02.522426: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",
- "2024-06-28 15:01:02.563951: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
- "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
- "2024-06-28 15:01:03.357473: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
- "2024-06-28 15:01:03.896173: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
- "2024-06-28 15:01:03.896878: W tensorflow/core/common_runtime/gpu/gpu_device.cc:2251] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n",
- "Skipping registering GPU devices...\n"
+ "data": {
+ "text/plain": [
+ "191673"
+ ]
+ },
+ "execution_count": 36,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# All the words vectorized\n",
+ "len(layer.get_vocabulary())"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<tf.Tensor: shape=(1, 5), dtype=int64, numpy=array([[ 2, 12030, 9, 12, 10064]])>"
+ ]
+ },
+ "execution_count": 37,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "layer(['the fuck is that shit'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "KeyboardInterrupt",
+ "evalue": "",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[38], line 4\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapplyLayer\u001b[39m(text):\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m np\u001b[38;5;241m.\u001b[39marray(layer(text))\n\u001b[0;32m----> 4\u001b[0m X_train[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mEmail Text\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[43mX_train\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mEmail Text\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply\u001b[49m\u001b[43m(\u001b[49m\u001b[43mapplyLayer\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/pandas/core/series.py:4924\u001b[0m, in \u001b[0;36mSeries.apply\u001b[0;34m(self, func, convert_dtype, args, by_row, **kwargs)\u001b[0m\n\u001b[1;32m 4789\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapply\u001b[39m(\n\u001b[1;32m 4790\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 4791\u001b[0m func: AggFuncType,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 4796\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m 4797\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m DataFrame \u001b[38;5;241m|\u001b[39m Series:\n\u001b[1;32m 4798\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 4799\u001b[0m \u001b[38;5;124;03m Invoke function on values of Series.\u001b[39;00m\n\u001b[1;32m 4800\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 4915\u001b[0m \u001b[38;5;124;03m dtype: float64\u001b[39;00m\n\u001b[1;32m 4916\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m 4917\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mSeriesApply\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 4918\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4919\u001b[0m \u001b[43m \u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4920\u001b[0m \u001b[43m \u001b[49m\u001b[43mconvert_dtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert_dtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4921\u001b[0m \u001b[43m \u001b[49m\u001b[43mby_row\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mby_row\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4922\u001b[0m \u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4923\u001b[0m \u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m-> 4924\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/pandas/core/apply.py:1427\u001b[0m, in \u001b[0;36mSeriesApply.apply\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1424\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_compat()\n\u001b[1;32m 1426\u001b[0m \u001b[38;5;66;03m# self.func is Callable\u001b[39;00m\n\u001b[0;32m-> 1427\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply_standard\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/pandas/core/apply.py:1507\u001b[0m, in \u001b[0;36mSeriesApply.apply_standard\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1501\u001b[0m \u001b[38;5;66;03m# row-wise access\u001b[39;00m\n\u001b[1;32m 1502\u001b[0m \u001b[38;5;66;03m# apply doesn't have a `na_action` keyword and for backward compat reasons\u001b[39;00m\n\u001b[1;32m 1503\u001b[0m \u001b[38;5;66;03m# we need to give `na_action=\"ignore\"` for categorical data.\u001b[39;00m\n\u001b[1;32m 1504\u001b[0m \u001b[38;5;66;03m# TODO: remove the `na_action=\"ignore\"` when that default has been changed in\u001b[39;00m\n\u001b[1;32m 1505\u001b[0m \u001b[38;5;66;03m# Categorical (GH51645).\u001b[39;00m\n\u001b[1;32m 1506\u001b[0m action \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(obj\u001b[38;5;241m.\u001b[39mdtype, CategoricalDtype) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1507\u001b[0m mapped \u001b[38;5;241m=\u001b[39m \u001b[43mobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_map_values\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1508\u001b[0m \u001b[43m \u001b[49m\u001b[43mmapper\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcurried\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mna_action\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maction\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconvert\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconvert_dtype\u001b[49m\n\u001b[1;32m 1509\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1511\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(mapped) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(mapped[\u001b[38;5;241m0\u001b[39m], ABCSeries):\n\u001b[1;32m 1512\u001b[0m \u001b[38;5;66;03m# GH#43986 Need to do list(mapped) in order to get treated as nested\u001b[39;00m\n\u001b[1;32m 1513\u001b[0m \u001b[38;5;66;03m# See also GH#25959 regarding EA support\u001b[39;00m\n\u001b[1;32m 1514\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m obj\u001b[38;5;241m.\u001b[39m_constructor_expanddim(\u001b[38;5;28mlist\u001b[39m(mapped), index\u001b[38;5;241m=\u001b[39mobj\u001b[38;5;241m.\u001b[39mindex)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/pandas/core/base.py:921\u001b[0m, in \u001b[0;36mIndexOpsMixin._map_values\u001b[0;34m(self, mapper, na_action, convert)\u001b[0m\n\u001b[1;32m 918\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(arr, ExtensionArray):\n\u001b[1;32m 919\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m arr\u001b[38;5;241m.\u001b[39mmap(mapper, na_action\u001b[38;5;241m=\u001b[39mna_action)\n\u001b[0;32m--> 921\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43malgorithms\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmap_array\u001b[49m\u001b[43m(\u001b[49m\u001b[43marr\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmapper\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mna_action\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mna_action\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconvert\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/pandas/core/algorithms.py:1743\u001b[0m, in \u001b[0;36mmap_array\u001b[0;34m(arr, mapper, na_action, convert)\u001b[0m\n\u001b[1;32m 1741\u001b[0m values \u001b[38;5;241m=\u001b[39m arr\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mobject\u001b[39m, copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m 1742\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m na_action \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1743\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmap_infer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmapper\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconvert\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1744\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1745\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mmap_infer_mask(\n\u001b[1;32m 1746\u001b[0m values, mapper, mask\u001b[38;5;241m=\u001b[39misna(values)\u001b[38;5;241m.\u001b[39mview(np\u001b[38;5;241m.\u001b[39muint8), convert\u001b[38;5;241m=\u001b[39mconvert\n\u001b[1;32m 1747\u001b[0m )\n",
+ "File \u001b[0;32mlib.pyx:2972\u001b[0m, in \u001b[0;36mpandas._libs.lib.map_infer\u001b[0;34m()\u001b[0m\n",
+ "Cell \u001b[0;32mIn[38], line 2\u001b[0m, in \u001b[0;36mapplyLayer\u001b[0;34m(text)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapplyLayer\u001b[39m(text):\n\u001b[0;32m----> 2\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m np\u001b[38;5;241m.\u001b[39marray(\u001b[43mlayer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/keras/src/utils/traceback_utils.py:117\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 115\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 116\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 117\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 118\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 119\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/keras/src/layers/layer.py:846\u001b[0m, in \u001b[0;36mLayer.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 844\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 845\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 846\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 847\u001b[0m \u001b[38;5;66;03m# Change the layout for the layer output if needed.\u001b[39;00m\n\u001b[1;32m 848\u001b[0m \u001b[38;5;66;03m# This is useful for relayout intermediate tensor in the model\u001b[39;00m\n\u001b[1;32m 849\u001b[0m \u001b[38;5;66;03m# to achieve the optimal performance.\u001b[39;00m\n\u001b[1;32m 850\u001b[0m distribution \u001b[38;5;241m=\u001b[39m distribution_lib\u001b[38;5;241m.\u001b[39mdistribution()\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/keras/src/utils/traceback_utils.py:117\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 115\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 116\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 117\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 118\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 119\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/keras/src/ops/operation.py:48\u001b[0m, in \u001b[0;36mOperation.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 43\u001b[0m call_fn \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcall\n\u001b[1;32m 44\u001b[0m call_fn \u001b[38;5;241m=\u001b[39m traceback_utils\u001b[38;5;241m.\u001b[39minject_argument_info_in_traceback(\n\u001b[1;32m 45\u001b[0m call_fn,\n\u001b[1;32m 46\u001b[0m object_name\u001b[38;5;241m=\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.call()\u001b[39m\u001b[38;5;124m\"\u001b[39m),\n\u001b[1;32m 47\u001b[0m )\n\u001b[0;32m---> 48\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mcall_fn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 50\u001b[0m \u001b[38;5;66;03m# Plain flow.\u001b[39;00m\n\u001b[1;32m 51\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m any_symbolic_tensors(args, kwargs):\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/keras/src/utils/traceback_utils.py:156\u001b[0m, in \u001b[0;36minject_argument_info_in_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 154\u001b[0m bound_signature \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 155\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 156\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 157\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 158\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(e, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_keras_call_info_injected\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 159\u001b[0m \u001b[38;5;66;03m# Only inject info for the innermost failing call\u001b[39;00m\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/keras/src/layers/preprocessing/text_vectorization.py:574\u001b[0m, in \u001b[0;36mTextVectorization.call\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m 569\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\n\u001b[1;32m 570\u001b[0m inputs, (tf\u001b[38;5;241m.\u001b[39mTensor, tf\u001b[38;5;241m.\u001b[39mRaggedTensor, np\u001b[38;5;241m.\u001b[39mndarray, \u001b[38;5;28mlist\u001b[39m, \u001b[38;5;28mtuple\u001b[39m)\n\u001b[1;32m 571\u001b[0m ):\n\u001b[1;32m 572\u001b[0m inputs \u001b[38;5;241m=\u001b[39m tf\u001b[38;5;241m.\u001b[39mconvert_to_tensor(backend\u001b[38;5;241m.\u001b[39mconvert_to_numpy(inputs))\n\u001b[0;32m--> 574\u001b[0m inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_preprocess\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 576\u001b[0m \u001b[38;5;66;03m# If we're not doing any output processing, return right away.\u001b[39;00m\n\u001b[1;32m 577\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_output_mode \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/keras/src/layers/preprocessing/text_vectorization.py:553\u001b[0m, in \u001b[0;36mTextVectorization._preprocess\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m 549\u001b[0m inputs \u001b[38;5;241m=\u001b[39m tf\u001b[38;5;241m.\u001b[39msqueeze(inputs, axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m 550\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_split \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mwhitespace\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 551\u001b[0m \u001b[38;5;66;03m# This treats multiple whitespaces as one whitespace, and strips\u001b[39;00m\n\u001b[1;32m 552\u001b[0m \u001b[38;5;66;03m# leading and trailing whitespace.\u001b[39;00m\n\u001b[0;32m--> 553\u001b[0m inputs \u001b[38;5;241m=\u001b[39m \u001b[43mtf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstrings\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplit\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 554\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_split \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcharacter\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 555\u001b[0m inputs \u001b[38;5;241m=\u001b[39m tf\u001b[38;5;241m.\u001b[39mstrings\u001b[38;5;241m.\u001b[39municode_split(inputs, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUTF-8\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/tensorflow/python/util/traceback_utils.py:150\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 148\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 150\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 151\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 152\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/tensorflow/python/util/dispatch.py:1260\u001b[0m, in \u001b[0;36madd_dispatch_support.<locals>.decorator.<locals>.op_dispatch_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 1258\u001b[0m \u001b[38;5;66;03m# Fallback dispatch system (dispatch v1):\u001b[39;00m\n\u001b[1;32m 1259\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1260\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mdispatch_target\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1261\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mTypeError\u001b[39;00m, \u001b[38;5;167;01mValueError\u001b[39;00m):\n\u001b[1;32m 1262\u001b[0m \u001b[38;5;66;03m# Note: convert_to_eager_tensor currently raises a ValueError, not a\u001b[39;00m\n\u001b[1;32m 1263\u001b[0m \u001b[38;5;66;03m# TypeError, when given unexpected types. So we need to catch both.\u001b[39;00m\n\u001b[1;32m 1264\u001b[0m result \u001b[38;5;241m=\u001b[39m dispatch(op_dispatch_handler, args, kwargs)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/tensorflow/python/ops/ragged/ragged_string_ops.py:514\u001b[0m, in \u001b[0;36mstring_split_v2\u001b[0;34m(input, sep, maxsplit, name)\u001b[0m\n\u001b[1;32m 512\u001b[0m rank \u001b[38;5;241m=\u001b[39m \u001b[38;5;28minput\u001b[39m\u001b[38;5;241m.\u001b[39mshape\u001b[38;5;241m.\u001b[39mndims\n\u001b[1;32m 513\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m rank \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[0;32m--> 514\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mstring_split_v2\u001b[49m\u001b[43m(\u001b[49m\u001b[43marray_ops_stack\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstack\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmaxsplit\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m 515\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m rank \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m rank \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 516\u001b[0m sparse_result \u001b[38;5;241m=\u001b[39m string_ops\u001b[38;5;241m.\u001b[39mstring_split_v2(\n\u001b[1;32m 517\u001b[0m \u001b[38;5;28minput\u001b[39m, sep\u001b[38;5;241m=\u001b[39msep, maxsplit\u001b[38;5;241m=\u001b[39mmaxsplit)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/tensorflow/python/util/traceback_utils.py:150\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 148\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 150\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 151\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 152\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/tensorflow/python/util/dispatch.py:1260\u001b[0m, in \u001b[0;36madd_dispatch_support.<locals>.decorator.<locals>.op_dispatch_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 1258\u001b[0m \u001b[38;5;66;03m# Fallback dispatch system (dispatch v1):\u001b[39;00m\n\u001b[1;32m 1259\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1260\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mdispatch_target\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1261\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mTypeError\u001b[39;00m, \u001b[38;5;167;01mValueError\u001b[39;00m):\n\u001b[1;32m 1262\u001b[0m \u001b[38;5;66;03m# Note: convert_to_eager_tensor currently raises a ValueError, not a\u001b[39;00m\n\u001b[1;32m 1263\u001b[0m \u001b[38;5;66;03m# TypeError, when given unexpected types. So we need to catch both.\u001b[39;00m\n\u001b[1;32m 1264\u001b[0m result \u001b[38;5;241m=\u001b[39m dispatch(op_dispatch_handler, args, kwargs)\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/tensorflow/python/ops/ragged/ragged_string_ops.py:516\u001b[0m, in \u001b[0;36mstring_split_v2\u001b[0;34m(input, sep, maxsplit, name)\u001b[0m\n\u001b[1;32m 514\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m string_split_v2(array_ops_stack\u001b[38;5;241m.\u001b[39mstack([\u001b[38;5;28minput\u001b[39m]), sep, maxsplit)[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m 515\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m rank \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m rank \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 516\u001b[0m sparse_result \u001b[38;5;241m=\u001b[39m \u001b[43mstring_ops\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstring_split_v2\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 517\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msep\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmaxsplit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaxsplit\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 518\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ragged_tensor\u001b[38;5;241m.\u001b[39mRaggedTensor\u001b[38;5;241m.\u001b[39mfrom_value_rowids(\n\u001b[1;32m 519\u001b[0m values\u001b[38;5;241m=\u001b[39msparse_result\u001b[38;5;241m.\u001b[39mvalues,\n\u001b[1;32m 520\u001b[0m value_rowids\u001b[38;5;241m=\u001b[39msparse_result\u001b[38;5;241m.\u001b[39mindices[:, \u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 521\u001b[0m nrows\u001b[38;5;241m=\u001b[39msparse_result\u001b[38;5;241m.\u001b[39mdense_shape[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 522\u001b[0m validate\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m 523\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/tensorflow/python/ops/string_ops.py:283\u001b[0m, in \u001b[0;36mstring_split_v2\u001b[0;34m(source, sep, maxsplit)\u001b[0m\n\u001b[1;32m 280\u001b[0m sep \u001b[38;5;241m=\u001b[39m ops\u001b[38;5;241m.\u001b[39mconvert_to_tensor(sep, dtype\u001b[38;5;241m=\u001b[39mdtypes\u001b[38;5;241m.\u001b[39mstring)\n\u001b[1;32m 281\u001b[0m source \u001b[38;5;241m=\u001b[39m ops\u001b[38;5;241m.\u001b[39mconvert_to_tensor(source, dtype\u001b[38;5;241m=\u001b[39mdtypes\u001b[38;5;241m.\u001b[39mstring)\n\u001b[0;32m--> 283\u001b[0m indices, values, shape \u001b[38;5;241m=\u001b[39m \u001b[43mgen_string_ops\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstring_split_v2\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 284\u001b[0m \u001b[43m \u001b[49m\u001b[43msource\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msep\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmaxsplit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaxsplit\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 285\u001b[0m indices\u001b[38;5;241m.\u001b[39mset_shape([\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m2\u001b[39m])\n\u001b[1;32m 286\u001b[0m values\u001b[38;5;241m.\u001b[39mset_shape([\u001b[38;5;28;01mNone\u001b[39;00m])\n",
+ "File \u001b[0;32m~/gitRepos/machineLearning/.venv/lib/python3.11/site-packages/tensorflow/python/ops/gen_string_ops.py:1379\u001b[0m, in \u001b[0;36mstring_split_v2\u001b[0;34m(input, sep, maxsplit, name)\u001b[0m\n\u001b[1;32m 1377\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m tld\u001b[38;5;241m.\u001b[39mis_eager:\n\u001b[1;32m 1378\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1379\u001b[0m _result \u001b[38;5;241m=\u001b[39m \u001b[43mpywrap_tfe\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mTFE_Py_FastPathExecute\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1380\u001b[0m \u001b[43m \u001b[49m\u001b[43m_ctx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mStringSplitV2\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmaxsplit\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmaxsplit\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1381\u001b[0m _result \u001b[38;5;241m=\u001b[39m _StringSplitV2Output\u001b[38;5;241m.\u001b[39m_make(_result)\n\u001b[1;32m 1382\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _result\n",
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
+ "def applyLayer(text):\n",
+ " return np.array(layer(text))\n",
+ "\n",
+ "X_train['Email Text'] = X_train['Email Text'].apply(applyLayer)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "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>Unnamed: 0</th>\n",
+ " <th>Email Text</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>66</th>\n",
+ " <td>66</td>\n",
+ " <td>[1010, 1266, 922, 102, 188, 3053, 3093, 87, 6,...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13986</th>\n",
+ " <td>13987</td>\n",
+ " <td>[10171, 6568, 209, 54, 155, 5006, 6273, 11, 2,...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13711</th>\n",
+ " <td>13712</td>\n",
+ " <td>[132755, 243, 143884, 656, 186, 180977, 110, 2...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9031</th>\n",
+ " <td>9032</td>\n",
+ " <td>[2859, 177, 3753, 2, 545, 8, 303, 8, 2, 2859, ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8512</th>\n",
+ " <td>8513</td>\n",
+ " <td>[934, 934, 877, 13, 580, 129, 121, 65, 4, 336,...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Unnamed: 0 Email Text\n",
+ "66 66 [1010, 1266, 922, 102, 188, 3053, 3093, 87, 6,...\n",
+ "13986 13987 [10171, 6568, 209, 54, 155, 5006, 6273, 11, 2,...\n",
+ "13711 13712 [132755, 243, 143884, 656, 186, 180977, 110, 2...\n",
+ "9031 9032 [2859, 177, 3753, 2, 545, 8, 303, 8, 2, 2859, ...\n",
+ "8512 8513 [934, 934, 877, 13, 580, 129, 121, 65, 4, 336,..."
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X_train.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from keras.preprocessing.sequence import pad_sequences\n",
+ "X_train['Email Text'] = list(pad_sequences(X_train['Email Text'], maxlen=100, padding='post'))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "66 [1010, 1266, 922, 102, 188, 3053, 3093, 87, 6,...\n",
+ "13986 [10171, 6568, 209, 54, 155, 5006, 6273, 11, 2,...\n",
+ "13711 [132755, 243, 143884, 656, 186, 180977, 110, 2...\n",
+ "9031 [2859, 177, 3753, 2, 545, 8, 303, 8, 2, 2859, ...\n",
+ "8512 [934, 934, 877, 13, 580, 129, 121, 65, 4, 336,...\n",
+ " ... \n",
+ "682 [492, 816, 85, 753, 5, 492, 29, 370, 65, 57, 1...\n",
+ "10530 [1127, 21, 1804, 52, 13208, 12221, 84, 4, 417,...\n",
+ "17343 [14, 36, 1512, 127, 6643, 2, 18028, 12, 1303, ...\n",
+ "14529 [11, 38, 5, 8606, 11, 733, 17797, 18999, 15767...\n",
+ "6313 [148, 295, 12, 18, 70, 268, 8119, 621, 1001, 6...\n",
+ "Name: Email Text, Length: 13987, dtype: object"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X_train['Email Text']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
"from sklearn.naive_bayes import CategoricalNB\n",
- "import keras\n",
- "import numpy as np\n",
"\n",
- "def toStr(inp):\n",
- " return str(inp)\n",
+ "cat_nb = CategoricalNB()\n",
+ "X_train_padded_flat = np.array(X_train['Email Text'].tolist())\n",
"\n",
- "layer = keras.layers.TextVectorization()\n",
"\n",
- "X_train['Email Text'] = X_train['Email Text'].apply(toStr)\n",
- "arr = ' '.join(np.array(X_train['Email Text']).tolist())"
+ "def isPhish(txt):\n",
+ " if txt == 'Phishing Email':\n",
+ " return 1\n",
+ " else:\n",
+ " return 0\n",
+ "\n",
+ "y_train = y_train.apply(isPhish)"
]
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-1 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: black;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-1 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: block;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-1 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-1 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-1 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 1ex;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-1 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>CategoricalNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> CategoricalNB<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.naive_bayes.CategoricalNB.html\">?<span>Documentation for CategoricalNB</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>CategoricalNB()</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "CategoricalNB()"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "cat_nb.fit(X_train_padded_flat, y_train)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
- "layer.adapt(arr)"
+ "X_test['Email Text'] = X_test['Email Text'].apply(applyLayer)\n",
+ "X_test['Email Text'] = list(pad_sequences(X_test['Email Text'], maxlen=5000, padding='post'))\n",
+ "X_test = np.array(X_test['Email Text'].tolist())"
]
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "166954"
+ "array([0])"
]
},
- "execution_count": 8,
+ "execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "# All the words vectorized\n",
- "len(layer.get_vocabulary())"
+ "cat_nb.predict([X_test[1000]])"
]
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "<tf.Tensor: shape=(1, 5), dtype=int64, numpy=array([[ 2, 15274, 9, 12, 11579]])>"
+ "'Phishing Email'"
]
},
- "execution_count": 13,
+ "execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "layer(['the fuck is that shit'])"
+ "y_test.iloc[1000]"
]
}
],
