shujath000/stack_overflow
0
1{2 "cells": [3 {4 "cell_type": "markdown",5 "id": "704c8595-1f9b-4511-85d1-398a489721c6",6 "metadata": {},7 "source": [8 "### Data Collection"9 ]10 },11 {12 "cell_type": "code",13 "execution_count": 100,14 "id": "adac7be9-df90-4e81-a49a-28056ef18737",15 "metadata": {},16 "outputs": [],17 "source": [18 "import pandas as pd"19 ]20 },21 {22 "cell_type": "code",23 "execution_count": 101,24 "id": "ce25a764-8b1c-41c5-87db-4a68d8aad590",25 "metadata": {},26 "outputs": [],27 "source": [28 "df1=pd.read_csv(r\"C:\\Users\\sss\\Desktop\\datas_titles.csv\",usecols=[\"id\",\"title\"])"29 ]30 },31 {32 "cell_type": "code",33 "execution_count": 102,34 "id": "356af908-968c-45d6-86e7-5fd70154e80a",35 "metadata": {},36 "outputs": [],37 "source": [38 "df2=pd.read_csv(r\"C:\\Users\\sss\\Desktop\\datas_tags.csv\",usecols=[\"id\",\"tags\"])"39 ]40 },41 {42 "cell_type": "code",43 "execution_count": 103,44 "id": "196ecc83-1274-4769-ad5d-27997a5177bd",45 "metadata": {},46 "outputs": [],47 "source": [48 "df3=pd.read_csv(r\"C:\\Users\\sss\\Documents\\datas_urls_questions.csv\",usecols=[\"id\",\"questions_url\"])"49 ]50 },51 {52 "cell_type": "code",53 "execution_count": 104,54 "id": "f0b50f03-3c5b-45d2-b7d4-bc16dd1931cb",55 "metadata": {},56 "outputs": [],57 "source": [58 "df_merged=pd.merge(df1,df2,on=\"id\")"59 ]60 },61 {62 "cell_type": "code",63 "execution_count": 105,64 "id": "45b40742-759a-4a5f-9c45-748a79ac67e3",65 "metadata": {},66 "outputs": [],67 "source": [68 "final_merged=pd.merge(df_merged,df3,on=\"id\")"69 ]70 },71 {72 "cell_type": "code",73 "execution_count": 106,74 "id": "0b7b6646-04a2-439b-84f1-1ac34fa7c66b",75 "metadata": {},76 "outputs": [],77 "source": [78 "final_merged.to_csv(r\"C:\\Users\\sss\\Documents\\final_dataset.csv\")"79 ]80 },81 {82 "cell_type": "markdown",83 "id": "53974e55-90bf-4aee-a54e-784481332ba1",84 "metadata": {},85 "source": [86 "### Data Cleaning"87 ]88 },89 {90 "cell_type": "code",91 "execution_count": 107,92 "id": "bf6765e0-bea0-4491-a8c7-b29c3c00f0e2",93 "metadata": {},94 "outputs": [],95 "source": [96 "df=final_merged"97 ]98 },99 {100 "cell_type": "code",101 "execution_count": 447,102 "id": "ab026a7d-8628-4f05-8217-92033609e7e3",103 "metadata": {},104 "outputs": [],105 "source": [106 "import nltk\n",107 "import numpy as np\n",108 "from nltk.tokenize import sent_tokenize as s, word_tokenize as w\n",109 "from nltk.corpus import stopwords as stp\n",110 "import string as st\n",111 "import autocorrect\n",112 "from autocorrect import Speller as spp\n",113 "from nltk.stem import WordNetLemmatizer as wl\n",114 "from nltk.corpus import wordnet\n",115 "from nltk import pos_tag\n",116 "from sklearn.pipeline import Pipeline\n",117 "from sklearn.preprocessing import FunctionTransformer,MultiLabelBinarizer\n",118 "from sklearn.feature_extraction.text import TfidfVectorizer\n",119 "import ast\n",120 "from sklearn.multioutput import MultiOutputClassifier\n",121 "from sklearn.linear_model import LogisticRegression\n",122 "from sklearn.ensemble import BaggingClassifier\n",123 "from sklearn.metrics import accuracy_score,hamming_loss\n",124 "import joblib"125 ]126 },127 {128 "cell_type": "code",129 "execution_count": 109,130 "id": "b582c693-c536-4560-87c3-b1a89b7e842e",131 "metadata": {},132 "outputs": [],133 "source": [134 "df[\"tags\"]=df[\"tags\"].apply(ast.literal_eval)"135 ]136 },137 {138 "cell_type": "code",139 "execution_count": 110,140 "id": "4860d2f8-fa39-4b19-b1e6-b4010665851a",141 "metadata": {},142 "outputs": [143 {144 "name": "stderr",145 "output_type": "stream",146 "text": [147 "[nltk_data] Downloading package wordnet to\n",148 "[nltk_data] C:\\Users\\sss\\AppData\\Roaming\\nltk_data...\n",149 "[nltk_data] Package wordnet is already up-to-date!\n"150 ]151 },152 {153 "data": {154 "text/plain": [155 "True"156 ]157 },158 "execution_count": 110,159 "metadata": {},160 "output_type": "execute_result"161 }162 ],163 "source": [164 "nltk.download(\"wordnet\")"165 ]166 },167 {168 "cell_type": "code",169 "execution_count": 111,170 "id": "31960d58-4eba-4a4a-a22c-8537123161bc",171 "metadata": {},172 "outputs": [173 {174 "name": "stderr",175 "output_type": "stream",176 "text": [177 "[nltk_data] Downloading package punkt to\n",178 "[nltk_data] C:\\Users\\sss\\AppData\\Roaming\\nltk_data...\n",179 "[nltk_data] Package punkt is already up-to-date!\n",180 "[nltk_data] Downloading package stopwords to\n",181 "[nltk_data] C:\\Users\\sss\\AppData\\Roaming\\nltk_data...\n",182 "[nltk_data] Package stopwords is already up-to-date!\n",183 "[nltk_data] Downloading package wordnet to\n",184 "[nltk_data] C:\\Users\\sss\\AppData\\Roaming\\nltk_data...\n",185 "[nltk_data] Package wordnet is already up-to-date!\n",186 "[nltk_data] Downloading package averaged_perceptron_tagger to\n",187 "[nltk_data] C:\\Users\\sss\\AppData\\Roaming\\nltk_data...\n",188 "[nltk_data] Package averaged_perceptron_tagger is already up-to-\n",189 "[nltk_data] date!\n"190 ]191 },192 {193 "data": {194 "text/plain": [195 "True"196 ]197 },198 "execution_count": 111,199 "metadata": {},200 "output_type": "execute_result"201 }202 ],203 "source": [204 "nltk.download('punkt')\n",205 "nltk.download('stopwords')\n",206 "nltk.download(\"wordnet\")\n",207 "nltk.download('averaged_perceptron_tagger')"208 ]209 },210 {211 "cell_type": "code",212 "execution_count": 112,213 "id": "df4a80b5-d935-4653-a363-48a8f2b1fd9e",214 "metadata": {},215 "outputs": [],216 "source": [217 "def sahi_karneka_function(x):\n",218 " nouns=[]\n",219 " li=[]\n",220 " lem=wl()\n",221 " l=s(x) \n",222 " for i in l:\n",223 " d=w(i.lower())\n",224 " for k in d:\n",225 " li.append(k)\n",226 " lw=len(li)\n",227 " j=0\n",228 " while j<lw:\n",229 " if li[j] in st.punctuation:\n",230 " li.remove(li[j])\n",231 " lw=len(li)\n",232 " j=0\n",233 " elif li[j] in stp.words(\"english\"):\n",234 " li.remove(li[j])\n",235 " lw=len(li)\n",236 " j=0\n",237 " else:\n",238 " j=j+1\n",239 " tags=pos_tag(li)\n",240 " for word,tag in tags:\n",241 " if tag.startswith(\"NN\") or tag.startswith(\"V\"):\n",242 " nouns.append(word)\n",243 " semi_final_words=[lem.lemmatize(m,pos=\"n\") if tagg.startswith(\"NN\") else lem.lemmatize(m,pos=\"v\") for m,tagg in pos_tag(nouns)]\n",244 " final_sentence=\" \".join(semi_final_words)\n",245 " return final_sentence"246 ]247 },248 {249 "cell_type": "code",250 "execution_count": 113,251 "id": "96d278fa-3eb2-4751-909b-ed5a04fdd484",252 "metadata": {},253 "outputs": [],254 "source": [255 "df[\"title\"]=df[\"title\"].apply(sahi_karneka_function)"256 ]257 },258 {259 "cell_type": "code",260 "execution_count": 114,261 "id": "c493c122-f90f-47d1-98d2-508c3b061647",262 "metadata": {},263 "outputs": [],264 "source": [265 "def tag_mein_repeat_nikalna(x):\n",266 " row=x\n",267 " i=0\n",268 " l=len(row)\n",269 " while i<l:\n",270 " count=row.count(row[i])\n",271 " if count>1:\n",272 " rep=count-1\n",273 " j=0\n",274 " while j<rep:\n",275 " row.remove(row[i])\n",276 " j=j+1\n",277 " i=0\n",278 " l=len(row)\n",279 " else:\n",280 " i=i+1\n",281 " return row"282 ]283 },284 {285 "cell_type": "code",286 "execution_count": 115,287 "id": "e9e2aea9-4e0b-4c9a-a6f2-856f3b66221e",288 "metadata": {},289 "outputs": [],290 "source": [291 "df[\"tags\"]=df[\"tags\"].apply( tag_mein_repeat_nikalna)"292 ]293 },294 {295 "cell_type": "code",296 "execution_count": 164,297 "id": "7f870471-0ca1-457d-9363-622c20d7363b",298 "metadata": {},299 "outputs": [300 {301 "data": {302 "text/plain": [303 "'https://stackoverflow.com//questions/79689975/how-to-calculate-hierarchical-aggregates-of-a-dataframe-r'"304 ]305 },306 "execution_count": 164,307 "metadata": {},308 "output_type": "execute_result"309 }310 ],311 "source": [312 "df[\"questions_url\"][0]"313 ]314 },315 {316 "cell_type": "markdown",317 "id": "3d974fc3-3a35-4293-946d-6cdd95e61b54",318 "metadata": {},319 "source": [320 "### model selection and evaluation "321 ]322 },323 {324 "cell_type": "code",325 "execution_count": 371,326 "id": "d5eb6a6e-b39c-4a44-8166-871b75fdd5a8",327 "metadata": {},328 "outputs": [],329 "source": [330 "x=df[\"title\"]\n",331 "y1=df[\"tags\"]"332 ]333 },334 {335 "cell_type": "code",336 "execution_count": 372,337 "id": "ecef232d-80cb-432a-9093-bbba672576da",338 "metadata": {},339 "outputs": [],340 "source": [341 "ml=MultiLabelBinarizer()\n",342 "tfidf=TfidfVectorizer()\n",343 "x_train_tfidf=tfidf.fit_transform(x)\n",344 "x_test_tfidf=tfidf.transform(x[0:1])\n",345 "y_train_encoded=ml.fit_transform(y1)\n",346 "y_encoded_test=ml.transform(y1[0:1])"347 ]348 },349 {350 "cell_type": "code",351 "execution_count": 373,352 "id": "5e41ec78-9cec-4b9f-a490-c936f7c3d015",353 "metadata": {},354 "outputs": [],355 "source": [356 "log=LogisticRegression(max_iter=1000,class_weight='balanced')"357 ]358 },359 {360 "cell_type": "code",361 "execution_count": 374,362 "id": "3c97db28-a318-46bb-a8c6-e2a2843e4d94",363 "metadata": {},364 "outputs": [],365 "source": [366 "model=MultiOutputClassifier(log)"367 ]368 },369 {370 "cell_type": "code",371 "execution_count": 375,372 "id": "df6714e6-b38c-4eac-b068-e0bd50061fd5",373 "metadata": {},374 "outputs": [375 {376 "data": {377 "text/html": [378 "<style>#sk-container-id-9 {\n",379 " /* Definition of color scheme common for light and dark mode */\n",380 " --sklearn-color-text: #000;\n",381 " --sklearn-color-text-muted: #666;\n",382 " --sklearn-color-line: gray;\n",383 " /* Definition of color scheme for unfitted estimators */\n",384 " --sklearn-color-unfitted-level-0: #fff5e6;\n",385 " --sklearn-color-unfitted-level-1: #f6e4d2;\n",386 " --sklearn-color-unfitted-level-2: #ffe0b3;\n",387 " --sklearn-color-unfitted-level-3: chocolate;\n",388 " /* Definition of color scheme for fitted estimators */\n",389 " --sklearn-color-fitted-level-0: #f0f8ff;\n",390 " --sklearn-color-fitted-level-1: #d4ebff;\n",391 " --sklearn-color-fitted-level-2: #b3dbfd;\n",392 " --sklearn-color-fitted-level-3: cornflowerblue;\n",393 "\n",394 " /* Specific color for light theme */\n",395 " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",396 " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",397 " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",398 " --sklearn-color-icon: #696969;\n",399 "\n",400 " @media (prefers-color-scheme: dark) {\n",401 " /* Redefinition of color scheme for dark theme */\n",402 " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",403 " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",404 " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",405 " --sklearn-color-icon: #878787;\n",406 " }\n",407 "}\n",408 "\n",409 "#sk-container-id-9 {\n",410 " color: var(--sklearn-color-text);\n",411 "}\n",412 "\n",413 "#sk-container-id-9 pre {\n",414 " padding: 0;\n",415 "}\n",416 "\n",417 "#sk-container-id-9 input.sk-hidden--visually {\n",418 " border: 0;\n",419 " clip: rect(1px 1px 1px 1px);\n",420 " clip: rect(1px, 1px, 1px, 1px);\n",421 " height: 1px;\n",422 " margin: -1px;\n",423 " overflow: hidden;\n",424 " padding: 0;\n",425 " position: absolute;\n",426 " width: 1px;\n",427 "}\n",428 "\n",429 "#sk-container-id-9 div.sk-dashed-wrapped {\n",430 " border: 1px dashed var(--sklearn-color-line);\n",431 " margin: 0 0.4em 0.5em 0.4em;\n",432 " box-sizing: border-box;\n",433 " padding-bottom: 0.4em;\n",434 " background-color: var(--sklearn-color-background);\n",435 "}\n",436 "\n",437 "#sk-container-id-9 div.sk-container {\n",438 " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",439 " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",440 " so we also need the `!important` here to be able to override the\n",441 " default hidden behavior on the sphinx rendered scikit-learn.org.\n",442 " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",443 " display: inline-block !important;\n",444 " position: relative;\n",445 "}\n",446 "\n",447 "#sk-container-id-9 div.sk-text-repr-fallback {\n",448 " display: none;\n",449 "}\n",450 "\n",451 "div.sk-parallel-item,\n",452 "div.sk-serial,\n",453 "div.sk-item {\n",454 " /* draw centered vertical line to link estimators */\n",455 " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",456 " background-size: 2px 100%;\n",457 " background-repeat: no-repeat;\n",458 " background-position: center center;\n",459 "}\n",460 "\n",461 "/* Parallel-specific style estimator block */\n",462 "\n",463 "#sk-container-id-9 div.sk-parallel-item::after {\n",464 " content: \"\";\n",465 " width: 100%;\n",466 " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",467 " flex-grow: 1;\n",468 "}\n",469 "\n",470 "#sk-container-id-9 div.sk-parallel {\n",471 " display: flex;\n",472 " align-items: stretch;\n",473 " justify-content: center;\n",474 " background-color: var(--sklearn-color-background);\n",475 " position: relative;\n",476 "}\n",477 "\n",478 "#sk-container-id-9 div.sk-parallel-item {\n",479 " display: flex;\n",480 " flex-direction: column;\n",481 "}\n",482 "\n",483 "#sk-container-id-9 div.sk-parallel-item:first-child::after {\n",484 " align-self: flex-end;\n",485 " width: 50%;\n",486 "}\n",487 "\n",488 "#sk-container-id-9 div.sk-parallel-item:last-child::after {\n",489 " align-self: flex-start;\n",490 " width: 50%;\n",491 "}\n",492 "\n",493 "#sk-container-id-9 div.sk-parallel-item:only-child::after {\n",494 " width: 0;\n",495 "}\n",496 "\n",497 "/* Serial-specific style estimator block */\n",498 "\n",499 "#sk-container-id-9 div.sk-serial {\n",500 " display: flex;\n",501 " flex-direction: column;\n",502 " align-items: center;\n",503 " background-color: var(--sklearn-color-background);\n",504 " padding-right: 1em;\n",505 " padding-left: 1em;\n",506 "}\n",507 "\n",508 "\n",509 "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",510 "clickable and can be expanded/collapsed.\n",511 "- Pipeline and ColumnTransformer use this feature and define the default style\n",512 "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",513 "*/\n",514 "\n",515 "/* Pipeline and ColumnTransformer style (default) */\n",516 "\n",517 "#sk-container-id-9 div.sk-toggleable {\n",518 " /* Default theme specific background. It is overwritten whether we have a\n",519 " specific estimator or a Pipeline/ColumnTransformer */\n",520 " background-color: var(--sklearn-color-background);\n",521 "}\n",522 "\n",523 "/* Toggleable label */\n",524 "#sk-container-id-9 label.sk-toggleable__label {\n",525 " cursor: pointer;\n",526 " display: flex;\n",527 " width: 100%;\n",528 " margin-bottom: 0;\n",529 " padding: 0.5em;\n",530 " box-sizing: border-box;\n",531 " text-align: center;\n",532 " align-items: start;\n",533 " justify-content: space-between;\n",534 " gap: 0.5em;\n",535 "}\n",536 "\n",537 "#sk-container-id-9 label.sk-toggleable__label .caption {\n",538 " font-size: 0.6rem;\n",539 " font-weight: lighter;\n",540 " color: var(--sklearn-color-text-muted);\n",541 "}\n",542 "\n",543 "#sk-container-id-9 label.sk-toggleable__label-arrow:before {\n",544 " /* Arrow on the left of the label */\n",545 " content: \"▸\";\n",546 " float: left;\n",547 " margin-right: 0.25em;\n",548 " color: var(--sklearn-color-icon);\n",549 "}\n",550 "\n",551 "#sk-container-id-9 label.sk-toggleable__label-arrow:hover:before {\n",552 " color: var(--sklearn-color-text);\n",553 "}\n",554 "\n",555 "/* Toggleable content - dropdown */\n",556 "\n",557 "#sk-container-id-9 div.sk-toggleable__content {\n",558 " display: none;\n",559 " text-align: left;\n",560 " /* unfitted */\n",561 " background-color: var(--sklearn-color-unfitted-level-0);\n",562 "}\n",563 "\n",564 "#sk-container-id-9 div.sk-toggleable__content.fitted {\n",565 " /* fitted */\n",566 " background-color: var(--sklearn-color-fitted-level-0);\n",567 "}\n",568 "\n",569 "#sk-container-id-9 div.sk-toggleable__content pre {\n",570 " margin: 0.2em;\n",571 " border-radius: 0.25em;\n",572 " color: var(--sklearn-color-text);\n",573 " /* unfitted */\n",574 " background-color: var(--sklearn-color-unfitted-level-0);\n",575 "}\n",576 "\n",577 "#sk-container-id-9 div.sk-toggleable__content.fitted pre {\n",578 " /* unfitted */\n",579 " background-color: var(--sklearn-color-fitted-level-0);\n",580 "}\n",581 "\n",582 "#sk-container-id-9 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",583 " /* Expand drop-down */\n",584 " display: block;\n",585 " width: 100%;\n",586 " overflow: visible;\n",587 "}\n",588 "\n",589 "#sk-container-id-9 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",590 " content: \"▾\";\n",591 "}\n",592 "\n",593 "/* Pipeline/ColumnTransformer-specific style */\n",594 "\n",595 "#sk-container-id-9 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",596 " color: var(--sklearn-color-text);\n",597 " background-color: var(--sklearn-color-unfitted-level-2);\n",598 "}\n",599 "\n",600 "#sk-container-id-9 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",601 " background-color: var(--sklearn-color-fitted-level-2);\n",602 "}\n",603 "\n",604 "/* Estimator-specific style */\n",605 "\n",606 "/* Colorize estimator box */\n",607 "#sk-container-id-9 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",608 " /* unfitted */\n",609 " background-color: var(--sklearn-color-unfitted-level-2);\n",610 "}\n",611 "\n",612 "#sk-container-id-9 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",613 " /* fitted */\n",614 " background-color: var(--sklearn-color-fitted-level-2);\n",615 "}\n",616 "\n",617 "#sk-container-id-9 div.sk-label label.sk-toggleable__label,\n",618 "#sk-container-id-9 div.sk-label label {\n",619 " /* The background is the default theme color */\n",620 " color: var(--sklearn-color-text-on-default-background);\n",621 "}\n",622 "\n",623 "/* On hover, darken the color of the background */\n",624 "#sk-container-id-9 div.sk-label:hover label.sk-toggleable__label {\n",625 " color: var(--sklearn-color-text);\n",626 " background-color: var(--sklearn-color-unfitted-level-2);\n",627 "}\n",628 "\n",629 "/* Label box, darken color on hover, fitted */\n",630 "#sk-container-id-9 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",631 " color: var(--sklearn-color-text);\n",632 " background-color: var(--sklearn-color-fitted-level-2);\n",633 "}\n",634 "\n",635 "/* Estimator label */\n",636 "\n",637 "#sk-container-id-9 div.sk-label label {\n",638 " font-family: monospace;\n",639 " font-weight: bold;\n",640 " display: inline-block;\n",641 " line-height: 1.2em;\n",642 "}\n",643 "\n",644 "#sk-container-id-9 div.sk-label-container {\n",645 " text-align: center;\n",646 "}\n",647 "\n",648 "/* Estimator-specific */\n",649 "#sk-container-id-9 div.sk-estimator {\n",650 " font-family: monospace;\n",651 " border: 1px dotted var(--sklearn-color-border-box);\n",652 " border-radius: 0.25em;\n",653 " box-sizing: border-box;\n",654 " margin-bottom: 0.5em;\n",655 " /* unfitted */\n",656 " background-color: var(--sklearn-color-unfitted-level-0);\n",657 "}\n",658 "\n",659 "#sk-container-id-9 div.sk-estimator.fitted {\n",660 " /* fitted */\n",661 " background-color: var(--sklearn-color-fitted-level-0);\n",662 "}\n",663 "\n",664 "/* on hover */\n",665 "#sk-container-id-9 div.sk-estimator:hover {\n",666 " /* unfitted */\n",667 " background-color: var(--sklearn-color-unfitted-level-2);\n",668 "}\n",669 "\n",670 "#sk-container-id-9 div.sk-estimator.fitted:hover {\n",671 " /* fitted */\n",672 " background-color: var(--sklearn-color-fitted-level-2);\n",673 "}\n",674 "\n",675 "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",676 "\n",677 "/* Common style for \"i\" and \"?\" */\n",678 "\n",679 ".sk-estimator-doc-link,\n",680 "a:link.sk-estimator-doc-link,\n",681 "a:visited.sk-estimator-doc-link {\n",682 " float: right;\n",683 " font-size: smaller;\n",684 " line-height: 1em;\n",685 " font-family: monospace;\n",686 " background-color: var(--sklearn-color-background);\n",687 " border-radius: 1em;\n",688 " height: 1em;\n",689 " width: 1em;\n",690 " text-decoration: none !important;\n",691 " margin-left: 0.5em;\n",692 " text-align: center;\n",693 " /* unfitted */\n",694 " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",695 " color: var(--sklearn-color-unfitted-level-1);\n",696 "}\n",697 "\n",698 ".sk-estimator-doc-link.fitted,\n",699 "a:link.sk-estimator-doc-link.fitted,\n",700 "a:visited.sk-estimator-doc-link.fitted {\n",701 " /* fitted */\n",702 " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",703 " color: var(--sklearn-color-fitted-level-1);\n",704 "}\n",705 "\n",706 "/* On hover */\n",707 "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",708 ".sk-estimator-doc-link:hover,\n",709 "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",710 ".sk-estimator-doc-link:hover {\n",711 " /* unfitted */\n",712 " background-color: var(--sklearn-color-unfitted-level-3);\n",713 " color: var(--sklearn-color-background);\n",714 " text-decoration: none;\n",715 "}\n",716 "\n",717 "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",718 ".sk-estimator-doc-link.fitted:hover,\n",719 "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",720 ".sk-estimator-doc-link.fitted:hover {\n",721 " /* fitted */\n",722 " background-color: var(--sklearn-color-fitted-level-3);\n",723 " color: var(--sklearn-color-background);\n",724 " text-decoration: none;\n",725 "}\n",726 "\n",727 "/* Span, style for the box shown on hovering the info icon */\n",728 ".sk-estimator-doc-link span {\n",729 " display: none;\n",730 " z-index: 9999;\n",731 " position: relative;\n",732 " font-weight: normal;\n",733 " right: .2ex;\n",734 " padding: .5ex;\n",735 " margin: .5ex;\n",736 " width: min-content;\n",737 " min-width: 20ex;\n",738 " max-width: 50ex;\n",739 " color: var(--sklearn-color-text);\n",740 " box-shadow: 2pt 2pt 4pt #999;\n",741 " /* unfitted */\n",742 " background: var(--sklearn-color-unfitted-level-0);\n",743 " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",744 "}\n",745 "\n",746 ".sk-estimator-doc-link.fitted span {\n",747 " /* fitted */\n",748 " background: var(--sklearn-color-fitted-level-0);\n",749 " border: var(--sklearn-color-fitted-level-3);\n",750 "}\n",751 "\n",752 ".sk-estimator-doc-link:hover span {\n",753 " display: block;\n",754 "}\n",755 "\n",756 "/* \"?\"-specific style due to the `<a>` HTML tag */\n",757 "\n",758 "#sk-container-id-9 a.estimator_doc_link {\n",759 " float: right;\n",760 " font-size: 1rem;\n",761 " line-height: 1em;\n",762 " font-family: monospace;\n",763 " background-color: var(--sklearn-color-background);\n",764 " border-radius: 1rem;\n",765 " height: 1rem;\n",766 " width: 1rem;\n",767 " text-decoration: none;\n",768 " /* unfitted */\n",769 " color: var(--sklearn-color-unfitted-level-1);\n",770 " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",771 "}\n",772 "\n",773 "#sk-container-id-9 a.estimator_doc_link.fitted {\n",774 " /* fitted */\n",775 " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",776 " color: var(--sklearn-color-fitted-level-1);\n",777 "}\n",778 "\n",779 "/* On hover */\n",780 "#sk-container-id-9 a.estimator_doc_link:hover {\n",781 " /* unfitted */\n",782 " background-color: var(--sklearn-color-unfitted-level-3);\n",783 " color: var(--sklearn-color-background);\n",784 " text-decoration: none;\n",785 "}\n",786 "\n",787 "#sk-container-id-9 a.estimator_doc_link.fitted:hover {\n",788 " /* fitted */\n",789 " background-color: var(--sklearn-color-fitted-level-3);\n",790 "}\n",791 "\n",792 ".estimator-table summary {\n",793 " padding: .5rem;\n",794 " font-family: monospace;\n",795 " cursor: pointer;\n",796 "}\n",797 "\n",798 ".estimator-table details[open] {\n",799 " padding-left: 0.1rem;\n",800 " padding-right: 0.1rem;\n",801 " padding-bottom: 0.3rem;\n",802 "}\n",803 "\n",804 ".estimator-table .parameters-table {\n",805 " margin-left: auto !important;\n",806 " margin-right: auto !important;\n",807 "}\n",808 "\n",809 ".estimator-table .parameters-table tr:nth-child(odd) {\n",810 " background-color: #fff;\n",811 "}\n",812 "\n",813 ".estimator-table .parameters-table tr:nth-child(even) {\n",814 " background-color: #f6f6f6;\n",815 "}\n",816 "\n",817 ".estimator-table .parameters-table tr:hover {\n",818 " background-color: #e0e0e0;\n",819 "}\n",820 "\n",821 ".estimator-table table td {\n",822 " border: 1px solid rgba(106, 105, 104, 0.232);\n",823 "}\n",824 "\n",825 ".user-set td {\n",826 " color:rgb(255, 94, 0);\n",827 " text-align: left;\n",828 "}\n",829 "\n",830 ".user-set td.value pre {\n",831 " color:rgb(255, 94, 0) !important;\n",832 " background-color: transparent !important;\n",833 "}\n",834 "\n",835 ".default td {\n",836 " color: black;\n",837 " text-align: left;\n",838 "}\n",839 "\n",840 ".user-set td i,\n",841 ".default td i {\n",842 " color: black;\n",843 "}\n",844 "\n",845 ".copy-paste-icon {\n",846 " background-image: url(data:image/svg+xml;base64,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);\n",847 " background-repeat: no-repeat;\n",848 " background-size: 14px 14px;\n",849 " background-position: 0;\n",850 " display: inline-block;\n",851 " width: 14px;\n",852 " height: 14px;\n",853 " cursor: pointer;\n",854 "}\n",855 "</style><body><div id=\"sk-container-id-9\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultiOutputClassifier(estimator=LogisticRegression(class_weight='balanced',\n",856 " max_iter=1000))</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-25\" type=\"checkbox\" ><label for=\"sk-estimator-id-25\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>MultiOutputClassifier</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.multioutput.MultiOutputClassifier.html\">?<span>Documentation for MultiOutputClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",857 " <div class=\"estimator-table\">\n",858 " <details>\n",859 " <summary>Parameters</summary>\n",860 " <table class=\"parameters-table\">\n",861 " <tbody>\n",862 " \n",863 " <tr class=\"user-set\">\n",864 " <td><i class=\"copy-paste-icon\"\n",865 " onclick=\"copyToClipboard('estimator',\n",866 " this.parentElement.nextElementSibling)\"\n",867 " ></i></td>\n",868 " <td class=\"param\">estimator </td>\n",869 " <td class=\"value\">LogisticRegre...max_iter=1000)</td>\n",870 " </tr>\n",871 " \n",872 "\n",873 " <tr class=\"default\">\n",874 " <td><i class=\"copy-paste-icon\"\n",875 " onclick=\"copyToClipboard('n_jobs',\n",876 " this.parentElement.nextElementSibling)\"\n",877 " ></i></td>\n",878 " <td class=\"param\">n_jobs </td>\n",879 " <td class=\"value\">None</td>\n",880 " </tr>\n",881 " \n",882 " </tbody>\n",883 " </table>\n",884 " </details>\n",885 " </div>\n",886 " </div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-26\" type=\"checkbox\" ><label for=\"sk-estimator-id-26\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>estimator: LogisticRegression</div></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"estimator__\"><pre>LogisticRegression(class_weight='balanced', max_iter=1000)</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-27\" type=\"checkbox\" ><label for=\"sk-estimator-id-27\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LogisticRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"estimator__\">\n",887 " <div class=\"estimator-table\">\n",888 " <details>\n",889 " <summary>Parameters</summary>\n",890 " <table class=\"parameters-table\">\n",891 " <tbody>\n",892 " \n",893 " <tr class=\"default\">\n",894 " <td><i class=\"copy-paste-icon\"\n",895 " onclick=\"copyToClipboard('penalty',\n",896 " this.parentElement.nextElementSibling)\"\n",897 " ></i></td>\n",898 " <td class=\"param\">penalty </td>\n",899 " <td class=\"value\">'l2'</td>\n",900 " </tr>\n",901 " \n",902 "\n",903 " <tr class=\"default\">\n",904 " <td><i class=\"copy-paste-icon\"\n",905 " onclick=\"copyToClipboard('dual',\n",906 " this.parentElement.nextElementSibling)\"\n",907 " ></i></td>\n",908 " <td class=\"param\">dual </td>\n",909 " <td class=\"value\">False</td>\n",910 " </tr>\n",911 " \n",912 "\n",913 " <tr class=\"default\">\n",914 " <td><i class=\"copy-paste-icon\"\n",915 " onclick=\"copyToClipboard('tol',\n",916 " this.parentElement.nextElementSibling)\"\n",917 " ></i></td>\n",918 " <td class=\"param\">tol </td>\n",919 " <td class=\"value\">0.0001</td>\n",920 " </tr>\n",921 " \n",922 "\n",923 " <tr class=\"default\">\n",924 " <td><i class=\"copy-paste-icon\"\n",925 " onclick=\"copyToClipboard('C',\n",926 " this.parentElement.nextElementSibling)\"\n",927 " ></i></td>\n",928 " <td class=\"param\">C </td>\n",929 " <td class=\"value\">1.0</td>\n",930 " </tr>\n",931 " \n",932 "\n",933 " <tr class=\"default\">\n",934 " <td><i class=\"copy-paste-icon\"\n",935 " onclick=\"copyToClipboard('fit_intercept',\n",936 " this.parentElement.nextElementSibling)\"\n",937 " ></i></td>\n",938 " <td class=\"param\">fit_intercept </td>\n",939 " <td class=\"value\">True</td>\n",940 " </tr>\n",941 " \n",942 "\n",943 " <tr class=\"default\">\n",944 " <td><i class=\"copy-paste-icon\"\n",945 " onclick=\"copyToClipboard('intercept_scaling',\n",946 " this.parentElement.nextElementSibling)\"\n",947 " ></i></td>\n",948 " <td class=\"param\">intercept_scaling </td>\n",949 " <td class=\"value\">1</td>\n",950 " </tr>\n",951 " \n",952 "\n",953 " <tr class=\"user-set\">\n",954 " <td><i class=\"copy-paste-icon\"\n",955 " onclick=\"copyToClipboard('class_weight',\n",956 " this.parentElement.nextElementSibling)\"\n",957 " ></i></td>\n",958 " <td class=\"param\">class_weight </td>\n",959 " <td class=\"value\">'balanced'</td>\n",960 " </tr>\n",961 " \n",962 "\n",963 " <tr class=\"default\">\n",964 " <td><i class=\"copy-paste-icon\"\n",965 " onclick=\"copyToClipboard('random_state',\n",966 " this.parentElement.nextElementSibling)\"\n",967 " ></i></td>\n",968 " <td class=\"param\">random_state </td>\n",969 " <td class=\"value\">None</td>\n",970 " </tr>\n",971 " \n",972 "\n",973 " <tr class=\"default\">\n",974 " <td><i class=\"copy-paste-icon\"\n",975 " onclick=\"copyToClipboard('solver',\n",976 " this.parentElement.nextElementSibling)\"\n",977 " ></i></td>\n",978 " <td class=\"param\">solver </td>\n",979 " <td class=\"value\">'lbfgs'</td>\n",980 " </tr>\n",981 " \n",982 "\n",983 " <tr class=\"user-set\">\n",984 " <td><i class=\"copy-paste-icon\"\n",985 " onclick=\"copyToClipboard('max_iter',\n",986 " this.parentElement.nextElementSibling)\"\n",987 " ></i></td>\n",988 " <td class=\"param\">max_iter </td>\n",989 " <td class=\"value\">1000</td>\n",990 " </tr>\n",991 " \n",992 "\n",993 " <tr class=\"default\">\n",994 " <td><i class=\"copy-paste-icon\"\n",995 " onclick=\"copyToClipboard('multi_class',\n",996 " this.parentElement.nextElementSibling)\"\n",997 " ></i></td>\n",998 " <td class=\"param\">multi_class </td>\n",999 " <td class=\"value\">'deprecated'</td>\n",1000 " </tr>\n",1001 " \n",1002 "\n",1003 " <tr class=\"default\">\n",1004 " <td><i class=\"copy-paste-icon\"\n",1005 " onclick=\"copyToClipboard('verbose',\n",1006 " this.parentElement.nextElementSibling)\"\n",1007 " ></i></td>\n",1008 " <td class=\"param\">verbose </td>\n",1009 " <td class=\"value\">0</td>\n",1010 " </tr>\n",1011 " \n",1012 "\n",1013 " <tr class=\"default\">\n",1014 " <td><i class=\"copy-paste-icon\"\n",1015 " onclick=\"copyToClipboard('warm_start',\n",1016 " this.parentElement.nextElementSibling)\"\n",1017 " ></i></td>\n",1018 " <td class=\"param\">warm_start </td>\n",1019 " <td class=\"value\">False</td>\n",1020 " </tr>\n",1021 " \n",1022 "\n",1023 " <tr class=\"default\">\n",1024 " <td><i class=\"copy-paste-icon\"\n",1025 " onclick=\"copyToClipboard('n_jobs',\n",1026 " this.parentElement.nextElementSibling)\"\n",1027 " ></i></td>\n",1028 " <td class=\"param\">n_jobs </td>\n",1029 " <td class=\"value\">None</td>\n",1030 " </tr>\n",1031 " \n",1032 "\n",1033 " <tr class=\"default\">\n",1034 " <td><i class=\"copy-paste-icon\"\n",1035 " onclick=\"copyToClipboard('l1_ratio',\n",1036 " this.parentElement.nextElementSibling)\"\n",1037 " ></i></td>\n",1038 " <td class=\"param\">l1_ratio </td>\n",1039 " <td class=\"value\">None</td>\n",1040 " </tr>\n",1041 " \n",1042 " </tbody>\n",1043 " </table>\n",1044 " </details>\n",1045 " </div>\n",1046 " </div></div></div></div></div></div></div></div></div></div><script>function copyToClipboard(text, element) {\n",1047 " // Get the parameter prefix from the closest toggleable content\n",1048 " const toggleableContent = element.closest('.sk-toggleable__content');\n",1049 " const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",1050 " const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",1051 "\n",1052 " const originalStyle = element.style;\n",1053 " const computedStyle = window.getComputedStyle(element);\n",1054 " const originalWidth = computedStyle.width;\n",1055 " const originalHTML = element.innerHTML.replace('Copied!', '');\n",1056 "\n",1057 " navigator.clipboard.writeText(fullParamName)\n",1058 " .then(() => {\n",1059 " element.style.width = originalWidth;\n",1060 " element.style.color = 'green';\n",1061 " element.innerHTML = \"Copied!\";\n",1062 "\n",1063 " setTimeout(() => {\n",1064 " element.innerHTML = originalHTML;\n",1065 " element.style = originalStyle;\n",1066 " }, 2000);\n",1067 " })\n",1068 " .catch(err => {\n",1069 " console.error('Failed to copy:', err);\n",1070 " element.style.color = 'red';\n",1071 " element.innerHTML = \"Failed!\";\n",1072 " setTimeout(() => {\n",1073 " element.innerHTML = originalHTML;\n",1074 " element.style = originalStyle;\n",1075 " }, 2000);\n",1076 " });\n",1077 " return false;\n",1078 "}\n",1079 "\n",1080 "document.querySelectorAll('.fa-regular.fa-copy').forEach(function(element) {\n",1081 " const toggleableContent = element.closest('.sk-toggleable__content');\n",1082 " const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",1083 " const paramName = element.parentElement.nextElementSibling.textContent.trim();\n",1084 " const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",1085 "\n",1086 " element.setAttribute('title', fullParamName);\n",1087 "});\n",1088 "</script></body>"1089 ],1090 "text/plain": [1091 "MultiOutputClassifier(estimator=LogisticRegression(class_weight='balanced',\n",1092 " max_iter=1000))"1093 ]1094 },1095 "execution_count": 375,1096 "metadata": {},1097 "output_type": "execute_result"1098 }1099 ],1100 "source": [1101 "model.fit(x_train_tfidf,y_train_encoded)"1102 ]1103 },1104 {1105 "cell_type": "markdown",1106 "id": "266f92ec-f07f-42f3-a4fb-4ed84f59f453",1107 "metadata": {},1108 "source": [1109 "### default threshold of probability of label greater then 0.5 is predicted by logistic regression"1110 ]1111 },1112 {1113 "cell_type": "code",1114 "execution_count": 376,1115 "id": "e22f91a1-8e4c-454f-b43e-c2b9067749ff",1116 "metadata": {},1117 "outputs": [],1118 "source": [1119 "y_pred_default_prob=model.predict(x_test_tfidf)"1120 ]1121 },1122 {1123 "cell_type": "code",1124 "execution_count": 377,1125 "id": "4f51fa10-8b99-4473-9655-fb81b1c71b65",1126 "metadata": {},1127 "outputs": [1128 {1129 "data": {1130 "text/plain": [1131 "[('dataframe', 'pandas', 'python', 'r', 'spring-boot-2')]"1132 ]1133 },1134 "execution_count": 377,1135 "metadata": {},1136 "output_type": "execute_result"1137 }1138 ],1139 "source": [1140 "ml.inverse_transform(y_pred_default_prob)"1141 ]1142 },1143 {1144 "cell_type": "code",1145 "execution_count": 442,1146 "id": "6a92a35c-a678-41c3-bc67-9cbf4f56906f",1147 "metadata": {},1148 "outputs": [1149 {1150 "data": {1151 "text/plain": [1152 "[('r',)]"1153 ]1154 },1155 "execution_count": 442,1156 "metadata": {},1157 "output_type": "execute_result"1158 }1159 ],1160 "source": [1161 "ml.inverse_transform(y_encoded_test)"1162 ]1163 },1164 {1165 "cell_type": "code",1166 "execution_count": 378,1167 "id": "fe4ec6d6-17b6-4f4a-aab3-8a3fa7d86136",1168 "metadata": {},1169 "outputs": [1170 {1171 "name": "stdout",1172 "output_type": "stream",1173 "text": [1174 "Hamming Loss: 0.0009823182711198428\n",1175 "Accuracy Score: 0.0\n"1176 ]1177 }1178 ],1179 "source": [1180 "print(\"Hamming Loss:\",hamming_loss(y_encoded_test,y_pred_default_prob))\n",1181 "print(\"Accuracy Score:\",accuracy_score(y_encoded_test,y_pred_default_prob))"1182 ]1183 },1184 {1185 "cell_type": "code",1186 "execution_count": 379,1187 "id": "c114e272-e3a1-43cd-b638-025fc0286b46",1188 "metadata": {},1189 "outputs": [1190 {1191 "name": "stdout",1192 "output_type": "stream",1193 "text": [1194 "F1 Score (micro): 0.3333333333333333\n",1195 "F1 Score (macro): 0.0002455795677799607\n"1196 ]1197 }1198 ],1199 "source": [1200 "print(\"F1 Score (micro):\", f1_score(y_encoded_test,y_pred_default_prob, average='micro',zero_division=0))\n",