talib-ai-ml/Email-Classification
0
1{2 "cells": [3 {4 "cell_type": "code",5 "execution_count": 1,6 "id": "2276651d",7 "metadata": {},8 "outputs": [],9 "source": [10 "import pandas as pd\n",11 "import sklearn\n",12 "from sklearn.ensemble import RandomForestClassifier\n",13 "from sklearn.feature_extraction.text import TfidfVectorizer\n",14 "from sklearn.model_selection import train_test_split\n",15 "from sklearn.metrics import classification_report\n",16 "import pickle"17 ]18 },19 {20 "cell_type": "code",21 "execution_count": 2,22 "id": "4b0793a5",23 "metadata": {},24 "outputs": [25 {26 "name": "stdout",27 "output_type": "stream",28 "text": [29 "scikit-learn version: 1.6.1\n"30 ]31 }32 ],33 "source": [34 "print(\"scikit-learn version:\", sklearn.__version__)"35 ]36 },37 {38 "cell_type": "code",39 "execution_count": 3,40 "id": "2d0a267a",41 "metadata": {},42 "outputs": [43 {44 "data": {45 "text/html": [46 "<div>\n",47 "<style scoped>\n",48 " .dataframe tbody tr th:only-of-type {\n",49 " vertical-align: middle;\n",50 " }\n",51 "\n",52 " .dataframe tbody tr th {\n",53 " vertical-align: top;\n",54 " }\n",55 "\n",56 " .dataframe thead th {\n",57 " text-align: right;\n",58 " }\n",59 "</style>\n",60 "<table border=\"1\" class=\"dataframe\">\n",61 " <thead>\n",62 " <tr style=\"text-align: right;\">\n",63 " <th></th>\n",64 " <th>email</th>\n",65 " <th>type</th>\n",66 " </tr>\n",67 " </thead>\n",68 " <tbody>\n",69 " <tr>\n",70 " <th>0</th>\n",71 " <td>Subject: Unvorhergesehener Absturz der Datenan...</td>\n",72 " <td>Incident</td>\n",73 " </tr>\n",74 " <tr>\n",75 " <th>1</th>\n",76 " <td>Subject: Customer Support Inquiry\\n\\nSeeking i...</td>\n",77 " <td>Request</td>\n",78 " </tr>\n",79 " <tr>\n",80 " <th>2</th>\n",81 " <td>Subject: Data Analytics for Investment\\n\\nI am...</td>\n",82 " <td>Request</td>\n",83 " </tr>\n",84 " <tr>\n",85 " <th>3</th>\n",86 " <td>Subject: Krankenhaus-Dienstleistung-Problem\\n\\...</td>\n",87 " <td>Incident</td>\n",88 " </tr>\n",89 " <tr>\n",90 " <th>4</th>\n",91 " <td>Subject: Security\\n\\nDear Customer Support, I ...</td>\n",92 " <td>Request</td>\n",93 " </tr>\n",94 " </tbody>\n",95 "</table>\n",96 "</div>"97 ],98 "text/plain": [99 " email type\n",100 "0 Subject: Unvorhergesehener Absturz der Datenan... Incident\n",101 "1 Subject: Customer Support Inquiry\\n\\nSeeking i... Request\n",102 "2 Subject: Data Analytics for Investment\\n\\nI am... Request\n",103 "3 Subject: Krankenhaus-Dienstleistung-Problem\\n\\... Incident\n",104 "4 Subject: Security\\n\\nDear Customer Support, I ... Request"105 ]106 },107 "execution_count": 3,108 "metadata": {},109 "output_type": "execute_result"110 }111 ],112 "source": [113 "df = pd.read_csv(\"combined_emails_with_natural_pii.csv\") # Replace with your actual dataset path\n",114 "\n",115 "# Check the first few rows of the dataset\n",116 "df.head()\n"117 ]118 },119 {120 "cell_type": "code",121 "execution_count": 4,122 "id": "8ed12426",123 "metadata": {},124 "outputs": [],125 "source": [126 "# Step 2: Preprocess and Vectorize the email text using TF-IDF\n",127 "vectorizer = TfidfVectorizer(stop_words=\"english\")\n",128 "X = vectorizer.fit_transform(df['email']) # Email text as feature\n",129 "\n",130 "# Step 3: Define target labels (categories)\n",131 "y = df['type'] # Categories: 'Incident', 'Request', 'Problem', 'Change'\n"132 ]133 },134 {135 "cell_type": "code",136 "execution_count": 5,137 "id": "b72d2e8e",138 "metadata": {},139 "outputs": [],140 "source": [141 "# Step 4: Split the dataset into training and testing sets\n",142 "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n"143 ]144 },145 {146 "cell_type": "code",147 "execution_count": 6,148 "id": "4f432786",149 "metadata": {},150 "outputs": [151 {152 "data": {153 "text/html": [154 "<style>#sk-container-id-1 {\n",155 " /* Definition of color scheme common for light and dark mode */\n",156 " --sklearn-color-text: #000;\n",157 " --sklearn-color-text-muted: #666;\n",158 " --sklearn-color-line: gray;\n",159 " /* Definition of color scheme for unfitted estimators */\n",160 " --sklearn-color-unfitted-level-0: #fff5e6;\n",161 " --sklearn-color-unfitted-level-1: #f6e4d2;\n",162 " --sklearn-color-unfitted-level-2: #ffe0b3;\n",163 " --sklearn-color-unfitted-level-3: chocolate;\n",164 " /* Definition of color scheme for fitted estimators */\n",165 " --sklearn-color-fitted-level-0: #f0f8ff;\n",166 " --sklearn-color-fitted-level-1: #d4ebff;\n",167 " --sklearn-color-fitted-level-2: #b3dbfd;\n",168 " --sklearn-color-fitted-level-3: cornflowerblue;\n",169 "\n",170 " /* Specific color for light theme */\n",171 " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",172 " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",173 " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",174 " --sklearn-color-icon: #696969;\n",175 "\n",176 " @media (prefers-color-scheme: dark) {\n",177 " /* Redefinition of color scheme for dark theme */\n",178 " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",179 " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",180 " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",181 " --sklearn-color-icon: #878787;\n",182 " }\n",183 "}\n",184 "\n",185 "#sk-container-id-1 {\n",186 " color: var(--sklearn-color-text);\n",187 "}\n",188 "\n",189 "#sk-container-id-1 pre {\n",190 " padding: 0;\n",191 "}\n",192 "\n",193 "#sk-container-id-1 input.sk-hidden--visually {\n",194 " border: 0;\n",195 " clip: rect(1px 1px 1px 1px);\n",196 " clip: rect(1px, 1px, 1px, 1px);\n",197 " height: 1px;\n",198 " margin: -1px;\n",199 " overflow: hidden;\n",200 " padding: 0;\n",201 " position: absolute;\n",202 " width: 1px;\n",203 "}\n",204 "\n",205 "#sk-container-id-1 div.sk-dashed-wrapped {\n",206 " border: 1px dashed var(--sklearn-color-line);\n",207 " margin: 0 0.4em 0.5em 0.4em;\n",208 " box-sizing: border-box;\n",209 " padding-bottom: 0.4em;\n",210 " background-color: var(--sklearn-color-background);\n",211 "}\n",212 "\n",213 "#sk-container-id-1 div.sk-container {\n",214 " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",215 " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",216 " so we also need the `!important` here to be able to override the\n",217 " default hidden behavior on the sphinx rendered scikit-learn.org.\n",218 " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",219 " display: inline-block !important;\n",220 " position: relative;\n",221 "}\n",222 "\n",223 "#sk-container-id-1 div.sk-text-repr-fallback {\n",224 " display: none;\n",225 "}\n",226 "\n",227 "div.sk-parallel-item,\n",228 "div.sk-serial,\n",229 "div.sk-item {\n",230 " /* draw centered vertical line to link estimators */\n",231 " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",232 " background-size: 2px 100%;\n",233 " background-repeat: no-repeat;\n",234 " background-position: center center;\n",235 "}\n",236 "\n",237 "/* Parallel-specific style estimator block */\n",238 "\n",239 "#sk-container-id-1 div.sk-parallel-item::after {\n",240 " content: \"\";\n",241 " width: 100%;\n",242 " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",243 " flex-grow: 1;\n",244 "}\n",245 "\n",246 "#sk-container-id-1 div.sk-parallel {\n",247 " display: flex;\n",248 " align-items: stretch;\n",249 " justify-content: center;\n",250 " background-color: var(--sklearn-color-background);\n",251 " position: relative;\n",252 "}\n",253 "\n",254 "#sk-container-id-1 div.sk-parallel-item {\n",255 " display: flex;\n",256 " flex-direction: column;\n",257 "}\n",258 "\n",259 "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",260 " align-self: flex-end;\n",261 " width: 50%;\n",262 "}\n",263 "\n",264 "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",265 " align-self: flex-start;\n",266 " width: 50%;\n",267 "}\n",268 "\n",269 "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",270 " width: 0;\n",271 "}\n",272 "\n",273 "/* Serial-specific style estimator block */\n",274 "\n",275 "#sk-container-id-1 div.sk-serial {\n",276 " display: flex;\n",277 " flex-direction: column;\n",278 " align-items: center;\n",279 " background-color: var(--sklearn-color-background);\n",280 " padding-right: 1em;\n",281 " padding-left: 1em;\n",282 "}\n",283 "\n",284 "\n",285 "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",286 "clickable and can be expanded/collapsed.\n",287 "- Pipeline and ColumnTransformer use this feature and define the default style\n",288 "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",289 "*/\n",290 "\n",291 "/* Pipeline and ColumnTransformer style (default) */\n",292 "\n",293 "#sk-container-id-1 div.sk-toggleable {\n",294 " /* Default theme specific background. It is overwritten whether we have a\n",295 " specific estimator or a Pipeline/ColumnTransformer */\n",296 " background-color: var(--sklearn-color-background);\n",297 "}\n",298 "\n",299 "/* Toggleable label */\n",300 "#sk-container-id-1 label.sk-toggleable__label {\n",301 " cursor: pointer;\n",302 " display: flex;\n",303 " width: 100%;\n",304 " margin-bottom: 0;\n",305 " padding: 0.5em;\n",306 " box-sizing: border-box;\n",307 " text-align: center;\n",308 " align-items: start;\n",309 " justify-content: space-between;\n",310 " gap: 0.5em;\n",311 "}\n",312 "\n",313 "#sk-container-id-1 label.sk-toggleable__label .caption {\n",314 " font-size: 0.6rem;\n",315 " font-weight: lighter;\n",316 " color: var(--sklearn-color-text-muted);\n",317 "}\n",318 "\n",319 "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",320 " /* Arrow on the left of the label */\n",321 " content: \"▸\";\n",322 " float: left;\n",323 " margin-right: 0.25em;\n",324 " color: var(--sklearn-color-icon);\n",325 "}\n",326 "\n",327 "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",328 " color: var(--sklearn-color-text);\n",329 "}\n",330 "\n",331 "/* Toggleable content - dropdown */\n",332 "\n",333 "#sk-container-id-1 div.sk-toggleable__content {\n",334 " max-height: 0;\n",335 " max-width: 0;\n",336 " overflow: hidden;\n",337 " text-align: left;\n",338 " /* unfitted */\n",339 " background-color: var(--sklearn-color-unfitted-level-0);\n",340 "}\n",341 "\n",342 "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",343 " /* fitted */\n",344 " background-color: var(--sklearn-color-fitted-level-0);\n",345 "}\n",346 "\n",347 "#sk-container-id-1 div.sk-toggleable__content pre {\n",348 " margin: 0.2em;\n",349 " border-radius: 0.25em;\n",350 " color: var(--sklearn-color-text);\n",351 " /* unfitted */\n",352 " background-color: var(--sklearn-color-unfitted-level-0);\n",353 "}\n",354 "\n",355 "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",356 " /* unfitted */\n",357 " background-color: var(--sklearn-color-fitted-level-0);\n",358 "}\n",359 "\n",360 "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",361 " /* Expand drop-down */\n",362 " max-height: 200px;\n",363 " max-width: 100%;\n",364 " overflow: auto;\n",365 "}\n",366 "\n",367 "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",368 " content: \"▾\";\n",369 "}\n",370 "\n",371 "/* Pipeline/ColumnTransformer-specific style */\n",372 "\n",373 "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",374 " color: var(--sklearn-color-text);\n",375 " background-color: var(--sklearn-color-unfitted-level-2);\n",376 "}\n",377 "\n",378 "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",379 " background-color: var(--sklearn-color-fitted-level-2);\n",380 "}\n",381 "\n",382 "/* Estimator-specific style */\n",383 "\n",384 "/* Colorize estimator box */\n",385 "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",386 " /* unfitted */\n",387 " background-color: var(--sklearn-color-unfitted-level-2);\n",388 "}\n",389 "\n",390 "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",391 " /* fitted */\n",392 " background-color: var(--sklearn-color-fitted-level-2);\n",393 "}\n",394 "\n",395 "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",396 "#sk-container-id-1 div.sk-label label {\n",397 " /* The background is the default theme color */\n",398 " color: var(--sklearn-color-text-on-default-background);\n",399 "}\n",400 "\n",401 "/* On hover, darken the color of the background */\n",402 "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",403 " color: var(--sklearn-color-text);\n",404 " background-color: var(--sklearn-color-unfitted-level-2);\n",405 "}\n",406 "\n",407 "/* Label box, darken color on hover, fitted */\n",408 "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",409 " color: var(--sklearn-color-text);\n",410 " background-color: var(--sklearn-color-fitted-level-2);\n",411 "}\n",412 "\n",413 "/* Estimator label */\n",414 "\n",415 "#sk-container-id-1 div.sk-label label {\n",416 " font-family: monospace;\n",417 " font-weight: bold;\n",418 " display: inline-block;\n",419 " line-height: 1.2em;\n",420 "}\n",421 "\n",422 "#sk-container-id-1 div.sk-label-container {\n",423 " text-align: center;\n",424 "}\n",425 "\n",426 "/* Estimator-specific */\n",427 "#sk-container-id-1 div.sk-estimator {\n",428 " font-family: monospace;\n",429 " border: 1px dotted var(--sklearn-color-border-box);\n",430 " border-radius: 0.25em;\n",431 " box-sizing: border-box;\n",432 " margin-bottom: 0.5em;\n",433 " /* unfitted */\n",434 " background-color: var(--sklearn-color-unfitted-level-0);\n",435 "}\n",436 "\n",437 "#sk-container-id-1 div.sk-estimator.fitted {\n",438 " /* fitted */\n",439 " background-color: var(--sklearn-color-fitted-level-0);\n",440 "}\n",441 "\n",442 "/* on hover */\n",443 "#sk-container-id-1 div.sk-estimator:hover {\n",444 " /* unfitted */\n",445 " background-color: var(--sklearn-color-unfitted-level-2);\n",446 "}\n",447 "\n",448 "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",449 " /* fitted */\n",450 " background-color: var(--sklearn-color-fitted-level-2);\n",451 "}\n",452 "\n",453 "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",454 "\n",455 "/* Common style for \"i\" and \"?\" */\n",456 "\n",457 ".sk-estimator-doc-link,\n",458 "a:link.sk-estimator-doc-link,\n",459 "a:visited.sk-estimator-doc-link {\n",460 " float: right;\n",461 " font-size: smaller;\n",462 " line-height: 1em;\n",463 " font-family: monospace;\n",464 " background-color: var(--sklearn-color-background);\n",465 " border-radius: 1em;\n",466 " height: 1em;\n",467 " width: 1em;\n",468 " text-decoration: none !important;\n",469 " margin-left: 0.5em;\n",470 " text-align: center;\n",471 " /* unfitted */\n",472 " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",473 " color: var(--sklearn-color-unfitted-level-1);\n",474 "}\n",475 "\n",476 ".sk-estimator-doc-link.fitted,\n",477 "a:link.sk-estimator-doc-link.fitted,\n",478 "a:visited.sk-estimator-doc-link.fitted {\n",479 " /* fitted */\n",480 " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",481 " color: var(--sklearn-color-fitted-level-1);\n",482 "}\n",483 "\n",484 "/* On hover */\n",485 "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",486 ".sk-estimator-doc-link:hover,\n",487 "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",488 ".sk-estimator-doc-link:hover {\n",489 " /* unfitted */\n",490 " background-color: var(--sklearn-color-unfitted-level-3);\n",491 " color: var(--sklearn-color-background);\n",492 " text-decoration: none;\n",493 "}\n",494 "\n",495 "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",496 ".sk-estimator-doc-link.fitted:hover,\n",497 "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",498 ".sk-estimator-doc-link.fitted:hover {\n",499 " /* fitted */\n",500 " background-color: var(--sklearn-color-fitted-level-3);\n",501 " color: var(--sklearn-color-background);\n",502 " text-decoration: none;\n",503 "}\n",504 "\n",505 "/* Span, style for the box shown on hovering the info icon */\n",506 ".sk-estimator-doc-link span {\n",507 " display: none;\n",508 " z-index: 9999;\n",509 " position: relative;\n",510 " font-weight: normal;\n",511 " right: .2ex;\n",512 " padding: .5ex;\n",513 " margin: .5ex;\n",514 " width: min-content;\n",515 " min-width: 20ex;\n",516 " max-width: 50ex;\n",517 " color: var(--sklearn-color-text);\n",518 " box-shadow: 2pt 2pt 4pt #999;\n",519 " /* unfitted */\n",520 " background: var(--sklearn-color-unfitted-level-0);\n",521 " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",522 "}\n",523 "\n",524 ".sk-estimator-doc-link.fitted span {\n",525 " /* fitted */\n",526 " background: var(--sklearn-color-fitted-level-0);\n",527 " border: var(--sklearn-color-fitted-level-3);\n",528 "}\n",529 "\n",530 ".sk-estimator-doc-link:hover span {\n",531 " display: block;\n",532 "}\n",533 "\n",534 "/* \"?\"-specific style due to the `<a>` HTML tag */\n",535 "\n",536 "#sk-container-id-1 a.estimator_doc_link {\n",537 " float: right;\n",538 " font-size: 1rem;\n",539 " line-height: 1em;\n",540 " font-family: monospace;\n",541 " background-color: var(--sklearn-color-background);\n",542 " border-radius: 1rem;\n",543 " height: 1rem;\n",544 " width: 1rem;\n",545 " text-decoration: none;\n",546 " /* unfitted */\n",547 " color: var(--sklearn-color-unfitted-level-1);\n",548 " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",549 "}\n",550 "\n",551 "#sk-container-id-1 a.estimator_doc_link.fitted {\n",552 " /* fitted */\n",553 " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",554 " color: var(--sklearn-color-fitted-level-1);\n",555 "}\n",556 "\n",557 "/* On hover */\n",558 "#sk-container-id-1 a.estimator_doc_link:hover {\n",559 " /* unfitted */\n",560 " background-color: var(--sklearn-color-unfitted-level-3);\n",561 " color: var(--sklearn-color-background);\n",562 " text-decoration: none;\n",563 "}\n",564 "\n",565 "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",566 " /* fitted */\n",567 " background-color: var(--sklearn-color-fitted-level-3);\n",568 "}\n",569 "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(random_state=42)</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\"><div><div>RandomForestClassifier</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier(random_state=42)</pre></div> </div></div></div></div>"570 ],571 "text/plain": [572 "RandomForestClassifier(random_state=42)"573 ]574 },575 "execution_count": 6,576 "metadata": {},577 "output_type": "execute_result"578 }579 ],580 "source": [581 "model = RandomForestClassifier(n_estimators=100, random_state=42)\n",582 "model.fit(X_train, y_train)"583 ]584 },585 {586 "cell_type": "code",587 "execution_count": 7,588 "id": "79735cfe",589 "metadata": {},590 "outputs": [591 {592 "name": "stdout",593 "output_type": "stream",594 "text": [595 "Classification Report:\n",596 " precision recall f1-score support\n",597 "\n",598 " Change 0.97 0.55 0.70 762\n",599 " Incident 0.65 0.98 0.78 2869\n",600 " Problem 0.80 0.10 0.18 1484\n",601 " Request 0.85 0.92 0.88 2085\n",602 "\n",603 " accuracy 0.73 7200\n",604 " macro avg 0.82 0.64 0.64 7200\n",605 "weighted avg 0.77 0.73 0.68 7200\n",606 "\n",607 "Model and Vectorizer have been save\n"608 ]609 }610 ],611 "source": [612 "# Step 6: Evaluate the model performance on the test set\n",613 "y_pred = model.predict(X_test)\n",614 "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n",615 "\n",616 "# Step 7: Save the trained model and vectorizer using pickle\n",617 "with open('email_classifier_model.pkl', 'wb') as model_file:\n",618 " pickle.dump(model, model_file)\n",619 "\n",620 "with open('vectorizer.pkl', 'wb') as vec_file:\n",621 " pickle.dump(vectorizer, vec_file)\n",622 "\n",623 "print(\"Model and Vectorizer have been save\")"624 ]625 },626 {627 "cell_type": "code",628 "execution_count": null,629 "id": "58b822fc",630 "metadata": {},631 "outputs": [],632 "source": []633 },634 {635 "cell_type": "code",636 "execution_count": null,637 "id": "b15eaad2",638 "metadata": {},639 "outputs": [],640 "source": []641 }642 ],643 "metadata": {644 "kernelspec": {645 "display_name": "Python 3",646 "language": "python",647 "name": "python3"648 },649 "language_info": {650 "codemirror_mode": {651 "name": "ipython",652 "version": 3653 },654 "file_extension": ".py",655 "mimetype": "text/x-python",656 "name": "python",657 "nbconvert_exporter": "python",658 "pygments_lexer": "ipython3",659 "version": "3.12.0"660 }661 },662 "nbformat": 4,663 "nbformat_minor": 5664}665