Dodo6/Topic_Modelling_using_LDA
1
1{2 "cells": [3 {4 "cell_type": "code",5 "source": [6 "from google.colab import drive\n",7 "drive.mount('/content/drive')"8 ],9 "metadata": {10 "colab": {11 "base_uri": "https://localhost:8080/"12 },13 "id": "sliXNs8OcCTl",14 "outputId": "8a37481d-b159-4f1b-fd57-dd5021ae9b98"15 },16 "execution_count": 68,17 "outputs": [18 {19 "output_type": "stream",20 "name": "stdout",21 "text": [22 "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"23 ]24 }25 ]26 },27 {28 "cell_type": "markdown",29 "metadata": {30 "id": "VR1rvwwmkkLq"31 },32 "source": [33 "# 1) Importing Libraries and reading the data."34 ]35 },36 {37 "cell_type": "code",38 "source": [39 "!pip install nltk\n",40 "import os\n",41 "import numpy as np\n",42 "import pandas as pd\n",43 "import nltk\n",44 "from sklearn.feature_extraction.text import CountVectorizer\n",45 "from sklearn.decomposition import LatentDirichletAllocation\n",46 "import glob\n",47 "nltk.download('stopwords')\n",48 "nltk.download('wordnet')\n",49 "nltk.download('punkt')\n"50 ],51 "metadata": {52 "colab": {53 "base_uri": "https://localhost:8080/"54 },55 "id": "apElZsielWKM",56 "outputId": "4fa479f6-a59f-4fd2-d161-0f3edf73e37e"57 },58 "execution_count": 69,59 "outputs": [60 {61 "output_type": "stream",62 "name": "stdout",63 "text": [64 "Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (3.8.1)\n",65 "Requirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from nltk) (8.1.7)\n",66 "Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from nltk) (1.4.2)\n",67 "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.10/dist-packages (from nltk) (2024.9.11)\n",68 "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from nltk) (4.66.5)\n"69 ]70 },71 {72 "output_type": "stream",73 "name": "stderr",74 "text": [75 "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",76 "[nltk_data] Package stopwords is already up-to-date!\n",77 "[nltk_data] Downloading package wordnet to /root/nltk_data...\n",78 "[nltk_data] Package wordnet is already up-to-date!\n",79 "[nltk_data] Downloading package punkt to /root/nltk_data...\n",80 "[nltk_data] Package punkt is already up-to-date!\n"81 ]82 },83 {84 "output_type": "execute_result",85 "data": {86 "text/plain": [87 "True"88 ]89 },90 "metadata": {},91 "execution_count": 6992 }93 ]94 },95 {96 "cell_type": "code",97 "execution_count": 70,98 "metadata": {99 "scrolled": false,100 "colab": {101 "base_uri": "https://localhost:8080/"102 },103 "id": "RqeBx6-rkkLw",104 "outputId": "5a9ba9f9-97ad-4df5-e472-7c7fa416a7eb"105 },106 "outputs": [107 {108 "output_type": "stream",109 "name": "stdout",110 "text": [111 "['.ipynb_checkpoints', 'data04.txt', 'data05.txt', 'data01.txt', 'data03.txt', 'data02.txt', 'data06.txt', 'data07.txt', 'data08.txt', 'data10.txt', 'data09.txt', 'data11.txt', 'data12.txt', 'data13.txt', 'data14.txt', 'data15.txt', 'data17.txt', 'data16.txt', 'data18.txt', 'data19.txt', 'data20.txt']\n"112 ]113 }114 ],115 "source": [116 "DATA_PATH = \"/content/drive/MyDrive/train_txt\"\n",117 "print(os.listdir(DATA_PATH))"118 ]119 },120 {121 "cell_type": "markdown",122 "metadata": {123 "id": "SDNZc-RMkkLx"124 },125 "source": [126 "# 2) Preprocessing the data."127 ]128 },129 {130 "cell_type": "code",131 "execution_count": 71,132 "metadata": {133 "colab": {134 "base_uri": "https://localhost:8080/"135 },136 "id": "fUozx7x4kkLy",137 "outputId": "e875e323-7dd8-45ba-ea1d-0e8cb35fd795"138 },139 "outputs": [140 {141 "output_type": "execute_result",142 "data": {143 "text/plain": [144 "20"145 ]146 },147 "metadata": {},148 "execution_count": 71149 }150 ],151 "source": [152 "folders = [\"data{0:02}\".format(i) for i in range(1,2)]\n",153 "# Read all texts into a list.\n",154 "papers = []\n",155 "for folder in folders:\n",156 " file_names = os.listdir(DATA_PATH)\n",157 " for file_name in file_names:\n",158 " if os.path.isfile(os.path.join(DATA_PATH, file_name)):\n",159 " with open(DATA_PATH + '/' + file_name, encoding='utf-8', errors='ignore', mode='r+') as f:\n",160 " data = f.read()\n",161 " papers.append(data)\n",162 "len(papers)"163 ]164 },165 {166 "cell_type": "code",167 "execution_count": 72,168 "metadata": {169 "colab": {170 "base_uri": "https://localhost:8080/"171 },172 "id": "ndFikFFAkkLz",173 "outputId": "24140b53-e286-48f9-e711-d9d23c04cc84"174 },175 "outputs": [176 {177 "output_type": "stream",178 "name": "stdout",179 "text": [180 "Article\n",181 "\n",182 "Overcoming Barriers in Supply Chain Analytics—\n",183 "Investigating Measures in LSCM Organizations\n",184 "Tino T. Herden *, Benjamin Nitsche and Benno Gerlach\n",185 "Chair of Logistics, Technische Universität Berlin, Straße des 17. Juni 135, 10623 Berlin, Germany\n",186 "* Correspondence: herden@logistik.tu-berlin.de\n",187 "Received: 23 December 2019; Accepted: 17 February 2020; Published: 26 February 2020\n",188 "\n",189 "Abstract: While supply chain analytics shows promise regarding value, benefits, and increase in\n",190 "performance for logistics and supply chain management (LSCM) organizations, those organizations\n",191 "are often either reluctant to invest or unable to achieve the returns they aspire to. This article\n",192 "systematically explores the barriers LSCM organizations experience in employing supply chain\n",193 "analytics that contribute to such reluctance and unachieved returns and measures to overcome these\n",194 "barriers. This article therefore aims to systemize the barriers and measures and allocate measures to\n",195 "barriers in order to provide or\n"196 ]197 }198 ],199 "source": [200 "print(papers[19][:1000])"201 ]202 },203 {204 "cell_type": "code",205 "execution_count": 73,206 "metadata": {207 "colab": {208 "base_uri": "https://localhost:8080/"209 },210 "id": "nq6Jw6VqkkL0",211 "outputId": "a54b077d-1984-43a8-dc46-88ccec09d30c"212 },213 "outputs": [214 {215 "output_type": "stream",216 "name": "stdout",217 "text": [218 "20\n"219 ]220 }221 ],222 "source": [223 "#Performing tokenizaation, lemmatization, stemming and removing stop words\n",224 "\n",225 "stop_words = nltk.corpus.stopwords.words('english')\n",226 "wtk = nltk.tokenize.RegexpTokenizer(r'\\w+')\n",227 "wnl = nltk.stem.wordnet.WordNetLemmatizer()\n",228 "\n",229 "def normalize_corpus(papers):\n",230 " norm_papers = []\n",231 " for paper in papers:\n",232 " paper = paper.lower()\n",233 " paper_tokens = [token.strip() for token in wtk.tokenize(paper)]\n",234 " paper_tokens = [wnl.lemmatize(token) for token in paper_tokens if not token.isnumeric()]\n",235 " paper_tokens = [token for token in paper_tokens if len(token) > 1]\n",236 " paper_tokens = [token for token in paper_tokens if token not in stop_words]\n",237 " paper_tokens = list(filter(None, paper_tokens))\n",238 " if paper_tokens:\n",239 " norm_papers.append(paper_tokens)\n",240 "\n",241 " return norm_papers\n",242 "\n",243 "norm_papers = normalize_corpus(papers)\n",244 "print(len(norm_papers))"245 ]246 },247 {248 "cell_type": "code",249 "execution_count": 74,250 "metadata": {251 "colab": {252 "base_uri": "https://localhost:8080/"253 },254 "id": "8EQFrXYXkkL2",255 "outputId": "1b91238e-c009-4c20-f281-2cc1566c172f"256 },257 "outputs": [258 {259 "output_type": "stream",260 "name": "stdout",261 "text": [262 "['article', 'energy', 'economic', 'efficiency', 'maize', 'agroecosystem', 'three', 'management', 'strategy', 'frailesca', 'chiapas', 'mexico', 'franklin', 'martínez', 'francisco', 'guevara', 'carlos', 'aguilar', 'rené', 'pinto', 'manuel', 'la', 'luis', 'rodríguez', 'deb', 'aryal', 'estudiante', 'de', 'doctorado', 'en', 'ciencias', 'agropecuarias', 'sustentabilidad', 'universidad', 'autónoma', 'de', 'chiapas', 'unach', 'carretera', 'ocozocoautla', 'villaflores', 'km', 'villaflores', 'mexico', 'franklinmar7820', 'yahoo', 'com', 'mx', 'investigador', 'de']\n"263 ]264 }265 ],266 "source": [267 "print(norm_papers[0][:50])"268 ]269 },270 {271 "cell_type": "markdown",272 "metadata": {273 "id": "6-g6MV9WkkL3"274 },275 "source": [276 "# 3) Feature Engineering"277 ]278 },279 {280 "cell_type": "code",281 "execution_count": 75,282 "metadata": {283 "colab": {284 "base_uri": "https://localhost:8080/"285 },286 "id": "gtPTwACOkkL5",287 "outputId": "6ef73b8d-0830-49be-9a3c-7779d2500c68"288 },289 "outputs": [290 {291 "output_type": "execute_result",292 "data": {293 "text/plain": [294 "(20, 5479)"295 ]296 },297 "metadata": {},298 "execution_count": 75299 }300 ],301 "source": [302 "#Converting a collection of text documents to a matrix of token counts\n",303 "\n",304 "cv = CountVectorizer(min_df=0.1, max_df=0.7, ngram_range=(1,2),\n",305 " token_pattern=None, tokenizer=lambda doc: doc,\n",306 " preprocessor=lambda doc: doc)\n",307 "cv_features = cv.fit_transform(norm_papers)\n",308 "cv_features.shape"309 ]310 },311 {312 "cell_type": "code",313 "execution_count": 76,314 "metadata": {315 "colab": {316 "base_uri": "https://localhost:8080/"317 },318 "id": "tOsx6atFkkL6",319 "outputId": "0282d825-b214-4473-e107-e3bba65f9f1b"320 },321 "outputs": [322 {323 "output_type": "stream",324 "name": "stdout",325 "text": [326 "Total Vocabulary Size: 5479\n"327 ]328 }329 ],330 "source": [331 "\n",332 "vocabulary = np.array(cv.get_feature_names_out()) # Use get_feature_names_out() instead of get_feature_names()\n",333 "print('Total Vocabulary Size:', len(vocabulary))"334 ]335 },336 {337 "cell_type": "markdown",338 "metadata": {339 "id": "20chCNeekkL7"340 },341 "source": [342 "# 4) Topic modeling with Latent Dirichlet Allocation (LDA)"343 ]344 },345 {346 "cell_type": "code",347 "execution_count": 77,348 "metadata": {349 "colab": {350 "base_uri": "https://localhost:8080/"351 },352 "id": "Ih0s_lFxkkL7",353 "outputId": "69b40c5c-c766-4f70-87b9-dfcb00030d77"354 },355 "outputs": [356 {357 "output_type": "stream",358 "name": "stdout",359 "text": [360 "CPU times: user 29.8 s, sys: 10.9 s, total: 40.7 s\n",361 "Wall time: 2min 16s\n"362 ]363 }364 ],365 "source": [366 "%%time\n",367 "\n",368 "TOTAL_TOPICS = 20\n",369 "\n",370 "lda_model = LatentDirichletAllocation(n_components =TOTAL_TOPICS, max_iter=500, max_doc_update_iter=50,\n",371 " learning_method='online', batch_size=5479, learning_offset=50.,\n",372 " random_state=42, n_jobs=16)\n",373 "document_topics = lda_model.fit_transform(cv_features)"374 ]375 },376 {377 "cell_type": "code",378 "execution_count": 78,379 "metadata": {380 "id": "OZMp-LEtkkL8"381 },382 "outputs": [],383 "source": [384 "topic_terms = lda_model.components_"385 ]386 },387 {388 "cell_type": "markdown",389 "metadata": {390 "id": "80jobd1VkkL8"391 },392 "source": [393 "# 5) Terms per topic"394 ]395 },396 {397 "cell_type": "code",398 "execution_count": 79,399 "metadata": {400 "colab": {401 "base_uri": "https://localhost:8080/",402 "height": 676403 },404 "id": "1ZxpbHNIkkL8",405 "outputId": "0c8f1ccb-041e-4062-aebc-08ebc4e6a52c"406 },407 "outputs": [408 {409 "output_type": "execute_result",410 "data": {411 "text/plain": [412 " Terms per Topic\n",413 "Topic1 energy, pig, growing, diet, content, fed, fiber, nutrient, adult, greater, ge, corn, dm, animal, acid, protein, meal, crossref, matter, stage\n",414 "Topic2 inverter, apple, group, output, crossref, cost, power, management, welfare, animal, wild, feature, sd, transport, october, current, approach, controlled, error, logistics\n",415 "Topic3 analytics, measure, barrier, organization, blockchain, technical, chain, solution, fruit, supply, supply chain, business, technical efficiency, initiative, smart, efficiency, user, video, management, need\n",416 "Topic4 proposed, error, accuracy, power, input, part, energy, carry, output, design, th, performance, reduction, scheme, operation, electronics, measure, prediction, ieee, analytics\n",417 "Topic5 blockchain, group, crossref, efficiency, cost, score, animal, smart, measure, prediction, density, feature, higher, day, approach, ieee, analytics, application, design, welfare\n",418 "Topic6 image, bc, focus, group, fusion, crossref, proposed, treatment, mouse, image fusion, technique, region, map, il, animal, expression, score, intestinal, administration, multi\n",419 "Topic7 output, power, design, voltage, current, electronics, core, density, proposed, input, simulation, equation, efficiency, frequency, ieee, loss, dc, energy, equivalent, circuit\n",420 "Topic8 cost, broiler, crossref, density, inverter, feature, energy, area, current, frequency, controlled, animal, score, power, bird, output, distance, voltage, production, core\n",421 "Topic9 analytics, yield, energy, blockchain, barrier, crossref, feature, measure, approach, management, treatment, growing, solution, pig, prediction, organization, algorithm, biomass, technical efficiency, electronics\n",422 "Topic10 wild, west, italy, sample, antibody, crossref, positive, animal, serum, european, presence, region, adult, mammal, dis, dis crossref, human, surveillance, pcr, bird\n",423 "Topic11 inverter, management, efficiency, output, crossref, energy, current, yield, group, controlled, bc, technical, score, farmer, technical efficiency, maize, transport, two three, signal, like\n",424 "Topic12 inverter, controlled, transport, feature, apple, prediction, welfare, score, crossref, cost, group, criterion, logistics, preharvest, error, terminal, broiler, port, distance, experiment\n",425 "Topic13 analytics, logistics, image, technical, efficiency, business, criterion, application, allows, chem crossref, initiative, gene, chain, identified, sorting, mean sd, driver, last, study concludes, chicken\n",426 "Topic14 production, energy, crossref, welfare, cost, score, management, treatment, efficiency, economic, group, s1, animal, fruit, test, sci crossref, sd, input, apple, criterion\n",427 "Topic15 analytics, measure, barrier, crossref, supply chain, supply, blockchain, image, group, need, proposed, approach, organization, logistics, day, score, chain, section, business, energy\n",428 "Topic16 management, energy, production, maize, efficiency, chicken, animal, economic, cost, farmer, gene, ax, input, ii, farm, mexico, agriculture, labour, crop, iii\n",429 "Topic17 inverter, loop, current, crossref, new, power, advance, output, diagram, period, equation, change, image, ieee, colón, proposed, controlled, electronics, exception, column\n",430 "Topic18 yield, biomass, harvest, year, cutting, crossref, height, cm, treatment, mixture, mg, production, soil, july, agriculture, specie, temperature, plant, crop, grass\n",431 "Topic19 crossref, yield, biomass, group, fruit, treatment, preharvest, criterion, treated, apple, inverter, harvest, lower, smart, cost, cutting, blockchain, day, animal, specie\n",432 "Topic20 welfare, score, cost, production, broiler, analytics, measure, animal, profit, nc, china, crossref, management, economic, per, total cost, group, transport, higher, biomass"433 ],434 "text/html": [435 "\n",436 " <div id=\"df-c0d1b55f-3812-4f6c-9b54-c1ccebc6fc0e\" class=\"colab-df-container\">\n",437 " <div>\n",438 "<style scoped>\n",439 " .dataframe tbody tr th:only-of-type {\n",440 " vertical-align: middle;\n",441 " }\n",442 "\n",443 " .dataframe tbody tr th {\n",444 " vertical-align: top;\n",445 " }\n",446 "\n",447 " .dataframe thead th {\n",448 " text-align: right;\n",449 " }\n",450 "</style>\n",451 "<table border=\"1\" class=\"dataframe\">\n",452 " <thead>\n",453 " <tr style=\"text-align: right;\">\n",454 " <th></th>\n",455 " <th>Terms per Topic</th>\n",456 " </tr>\n",457 " </thead>\n",458 " <tbody>\n",459 " <tr>\n",460 " <th>Topic1</th>\n",461 " <td>energy, pig, growing, diet, content, fed, fiber, nutrient, adult, greater, ge, corn, dm, animal, acid, protein, meal, crossref, matter, stage</td>\n",462 " </tr>\n",463 " <tr>\n",464 " <th>Topic2</th>\n",465 " <td>inverter, apple, group, output, crossref, cost, power, management, welfare, animal, wild, feature, sd, transport, october, current, approach, controlled, error, logistics</td>\n",466 " </tr>\n",467 " <tr>\n",468 " <th>Topic3</th>\n",469 " <td>analytics, measure, barrier, organization, blockchain, technical, chain, solution, fruit, supply, supply chain, business, technical efficiency, initiative, smart, efficiency, user, video, management, need</td>\n",470 " </tr>\n",471 " <tr>\n",472 " <th>Topic4</th>\n",473 " <td>proposed, error, accuracy, power, input, part, energy, carry, output, design, th, performance, reduction, scheme, operation, electronics, measure, prediction, ieee, analytics</td>\n",474 " </tr>\n",475 " <tr>\n",476 " <th>Topic5</th>\n",477 " <td>blockchain, group, crossref, efficiency, cost, score, animal, smart, measure, prediction, density, feature, higher, day, approach, ieee, analytics, application, design, welfare</td>\n",478 " </tr>\n",479 " <tr>\n",480 " <th>Topic6</th>\n",481 " <td>image, bc, focus, group, fusion, crossref, proposed, treatment, mouse, image fusion, technique, region, map, il, animal, expression, score, intestinal, administration, multi</td>\n",482 " </tr>\n",483 " <tr>\n",484 " <th>Topic7</th>\n",485 " <td>output, power, design, voltage, current, electronics, core, density, proposed, input, simulation, equation, efficiency, frequency, ieee, loss, dc, energy, equivalent, circuit</td>\n",486 " </tr>\n",487 " <tr>\n",488 " <th>Topic8</th>\n",489 " <td>cost, broiler, crossref, density, inverter, feature, energy, area, current, frequency, controlled, animal, score, power, bird, output, distance, voltage, production, core</td>\n",490 " </tr>\n",491 " <tr>\n",492 " <th>Topic9</th>\n",493 " <td>analytics, yield, energy, blockchain, barrier, crossref, feature, measure, approach, management, treatment, growing, solution, pig, prediction, organization, algorithm, biomass, technical efficiency, electronics</td>\n",494 " </tr>\n",495 " <tr>\n",496 " <th>Topic10</th>\n",497 " <td>wild, west, italy, sample, antibody, crossref, positive, animal, serum, european, presence, region, adult, mammal, dis, dis crossref, human, surveillance, pcr, bird</td>\n",498 " </tr>\n",499 " <tr>\n",500 " <th>Topic11</th>\n",501 " <td>inverter, management, efficiency, output, crossref, energy, current, yield, group, controlled, bc, technical, score, farmer, technical efficiency, maize, transport, two three, signal, like</td>\n",502 " </tr>\n",503 " <tr>\n",504 " <th>Topic12</th>\n",505 " <td>inverter, controlled, transport, feature, apple, prediction, welfare, score, crossref, cost, group, criterion, logistics, preharvest, error, terminal, broiler, port, distance, experiment</td>\n",506 " </tr>\n",507 " <tr>\n",508 " <th>Topic13</th>\n",509 " <td>analytics, logistics, image, technical, efficiency, business, criterion, application, allows, chem crossref, initiative, gene, chain, identified, sorting, mean sd, driver, last, study concludes, chicken</td>\n",510 " </tr>\n",511 " <tr>\n",512 " <th>Topic14</th>\n",513 " <td>production, energy, crossref, welfare, cost, score, management, treatment, efficiency, economic, group, s1, animal, fruit, test, sci crossref, sd, input, apple, criterion</td>\n",514 " </tr>\n",515 " <tr>\n",516 " <th>Topic15</th>\n",517 " <td>analytics, measure, barrier, crossref, supply chain, supply, blockchain, image, group, need, proposed, approach, organization, logistics, day, score, chain, section, business, energy</td>\n",518 " </tr>\n",519 " <tr>\n",520 " <th>Topic16</th>\n",521 " <td>management, energy, production, maize, efficiency, chicken, animal, economic, cost, farmer, gene, ax, input, ii, farm, mexico, agriculture, labour, crop, iii</td>\n",522 " </tr>\n",523 " <tr>\n",524 " <th>Topic17</th>\n",525 " <td>inverter, loop, current, crossref, new, power, advance, output, diagram, period, equation, change, image, ieee, colón, proposed, controlled, electronics, exception, column</td>\n",526 " </tr>\n",527 " <tr>\n",528 " <th>Topic18</th>\n",529 " <td>yield, biomass, harvest, year, cutting, crossref, height, cm, treatment, mixture, mg, production, soil, july, agriculture, specie, temperature, plant, crop, grass</td>\n",530 " </tr>\n",531 " <tr>\n",532 " <th>Topic19</th>\n",533 " <td>crossref, yield, biomass, group, fruit, treatment, preharvest, criterion, treated, apple, inverter, harvest, lower, smart, cost, cutting, blockchain, day, animal, specie</td>\n",534 " </tr>\n",535 " <tr>\n",536 " <th>Topic20</th>\n",537 " <td>welfare, score, cost, production, broiler, analytics, measure, animal, profit, nc, china, crossref, management, economic, per, total cost, group, transport, higher, biomass</td>\n",538 " </tr>\n",539 " </tbody>\n",540 "</table>\n",541 "</div>\n",542 " <div class=\"colab-df-buttons\">\n",543 "\n",544 " <div class=\"colab-df-container\">\n",545 " <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c0d1b55f-3812-4f6c-9b54-c1ccebc6fc0e')\"\n",546 " title=\"Convert this dataframe to an interactive table.\"\n",547 " style=\"display:none;\">\n",548 "\n",549 " <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",550 " <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",551 " </svg>\n",552 " </button>\n",553 "\n",554 " <style>\n",555 " .colab-df-container {\n",556 " display:flex;\n",557 " gap: 12px;\n",558 " }\n",559 "\n",560 " .colab-df-convert {\n",561 " background-color: #E8F0FE;\n",562 " border: none;\n",563 " border-radius: 50%;\n",564 " cursor: pointer;\n",565 " display: none;\n",566 " fill: #1967D2;\n",567 " height: 32px;\n",568 " padding: 0 0 0 0;\n",569 " width: 32px;\n",570 " }\n",571 "\n",572 " .colab-df-convert:hover {\n",573 " background-color: #E2EBFA;\n",574 " box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",575 " fill: #174EA6;\n",576 " }\n",577 "\n",578 " .colab-df-buttons div {\n",579 " margin-bottom: 4px;\n",580 " }\n",581 "\n",582 " [theme=dark] .colab-df-convert {\n",583 " background-color: #3B4455;\n",584 " fill: #D2E3FC;\n",585 " }\n",586 "\n",587 " [theme=dark] .colab-df-convert:hover {\n",588 " background-color: #434B5C;\n",589 " box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",590 " filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",591 " fill: #FFFFFF;\n",592 " }\n",593 " </style>\n",594 "\n",595 " <script>\n",596 " const buttonEl =\n",597 " document.querySelector('#df-c0d1b55f-3812-4f6c-9b54-c1ccebc6fc0e button.colab-df-convert');\n",598 " buttonEl.style.display =\n",599 " google.colab.kernel.accessAllowed ? 'block' : 'none';\n",600 "\n",601 " async function convertToInteractive(key) {\n",602 " const element = document.querySelector('#df-c0d1b55f-3812-4f6c-9b54-c1ccebc6fc0e');\n",603 " const dataTable =\n",604 " await google.colab.kernel.invokeFunction('convertToInteractive',\n",605 " [key], {});\n",606 " if (!dataTable) return;\n",607 "\n",608 " const docLinkHtml = 'Like what you see? Visit the ' +\n",609 " '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",610 " + ' to learn more about interactive tables.';\n",611 " element.innerHTML = '';\n",612 " dataTable['output_type'] = 'display_data';\n",613 " await google.colab.output.renderOutput(dataTable, element);\n",614 " const docLink = document.createElement('div');\n",615 " docLink.innerHTML = docLinkHtml;\n",616 " element.appendChild(docLink);\n",617 " }\n",618 " </script>\n",619 " </div>\n",620 "\n",621 "\n",622 "<div id=\"df-ec090829-17f4-4495-8d33-34084489377e\">\n",623 " <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-ec090829-17f4-4495-8d33-34084489377e')\"\n",624 " title=\"Suggest charts\"\n",625 " style=\"display:none;\">\n",626 "\n",627 "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",628 " width=\"24px\">\n",629 " <g>\n",630 " <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",631 " </g>\n",632 "</svg>\n",633 " </button>\n",634 "\n",635 "<style>\n",636 " .colab-df-quickchart {\n",637 " --bg-color: #E8F0FE;\n",638 " --fill-color: #1967D2;\n",639 " --hover-bg-color: #E2EBFA;\n",640 " --hover-fill-color: #174EA6;\n",641 " --disabled-fill-color: #AAA;\n",642 " --disabled-bg-color: #DDD;\n",643 " }\n",644 "\n",645 " [theme=dark] .colab-df-quickchart {\n",646 " --bg-color: #3B4455;\n",647 " --fill-color: #D2E3FC;\n",648 " --hover-bg-color: #434B5C;\n",649 " --hover-fill-color: #FFFFFF;\n",650 " --disabled-bg-color: #3B4455;\n",651 " --disabled-fill-color: #666;\n",652 " }\n",653 "\n",654 " .colab-df-quickchart {\n",655 " background-color: var(--bg-color);\n",656 " border: none;\n",657 " border-radius: 50%;\n",658 " cursor: pointer;\n",659 " display: none;\n",660 " fill: var(--fill-color);\n",661 " height: 32px;\n",662 " padding: 0;\n",663 " width: 32px;\n",664 " }\n",665 "\n",666 " .colab-df-quickchart:hover {\n",667 " background-color: var(--hover-bg-color);\n",668 " box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",669 " fill: var(--button-hover-fill-color);\n",670 " }\n",671 "\n",672 " .colab-df-quickchart-complete:disabled,\n",673 " .colab-df-quickchart-complete:disabled:hover {\n",674 " background-color: var(--disabled-bg-color);\n",675 " fill: var(--disabled-fill-color);\n",676 " box-shadow: none;\n",677 " }\n",678 "\n",679 " .colab-df-spinner {\n",680 " border: 2px solid var(--fill-color);\n",681 " border-color: transparent;\n",682 " border-bottom-color: var(--fill-color);\n",683 " animation:\n",684 " spin 1s steps(1) infinite;\n",685 " }\n",686 "\n",687 " @keyframes spin {\n",688 " 0% {\n",689 " border-color: transparent;\n",690 " border-bottom-color: var(--fill-color);\n",691 " border-left-color: var(--fill-color);\n",692 " }\n",693 " 20% {\n",694 " border-color: transparent;\n",695 " border-left-color: var(--fill-color);\n",696 " border-top-color: var(--fill-color);\n",697 " }\n",698 " 30% {\n",699 " border-color: transparent;\n",700 " border-left-color: var(--fill-color);\n",701 " border-top-color: var(--fill-color);\n",702 " border-right-color: var(--fill-color);\n",703 " }\n",704 " 40% {\n",705 " border-color: transparent;\n",706 " border-right-color: var(--fill-color);\n",707 " border-top-color: var(--fill-color);\n",708 " }\n",709 " 60% {\n",710 " border-color: transparent;\n",711 " border-right-color: var(--fill-color);\n",712 " }\n",713 " 80% {\n",714 " border-color: transparent;\n",715 " border-right-color: var(--fill-color);\n",716 " border-bottom-color: var(--fill-color);\n",717 " }\n",718 " 90% {\n",719 " border-color: transparent;\n",720 " border-bottom-color: var(--fill-color);\n",721 " }\n",722 " }\n",723 "</style>\n",724 "\n",725 " <script>\n",726 " async function quickchart(key) {\n",727 " const quickchartButtonEl =\n",728 " document.querySelector('#' + key + ' button');\n",729 " quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",730 " quickchartButtonEl.classList.add('colab-df-spinner');\n",731 " try {\n",732 " const charts = await google.colab.kernel.invokeFunction(\n",733 " 'suggestCharts', [key], {});\n",734 " } catch (error) {\n",735 " console.error('Error during call to suggestCharts:', error);\n",736 " }\n",737 " quickchartButtonEl.classList.remove('colab-df-spinner');\n",738 " quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",739 " }\n",740 " (() => {\n",741 " let quickchartButtonEl =\n",742 " document.querySelector('#df-ec090829-17f4-4495-8d33-34084489377e button');\n",743 " quickchartButtonEl.style.display =\n",744 " google.colab.kernel.accessAllowed ? 'block' : 'none';\n",745 " })();\n",746 " </script>\n",747 "</div>\n",748 "\n",749 " <div id=\"id_dbe130b5-f8c2-4744-9003-996b003fc00d\">\n",750 " <style>\n",751 " .colab-df-generate {\n",752 " background-color: #E8F0FE;\n",753 " border: none;\n",754 " border-radius: 50%;\n",755 " cursor: pointer;\n",756 " display: none;\n",757 " fill: #1967D2;\n",758 " height: 32px;\n",759 " padding: 0 0 0 0;\n",760 " width: 32px;\n",761 " }\n",762 "\n",763 " .colab-df-generate:hover {\n",764 " background-color: #E2EBFA;\n",765 " box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",766 " fill: #174EA6;\n",767 " }\n",768 "\n",769 " [theme=dark] .colab-df-generate {\n",770 " background-color: #3B4455;\n",771 " fill: #D2E3FC;\n",772 " }\n",773 "\n",774 " [theme=dark] .colab-df-generate:hover {\n",775 " background-color: #434B5C;\n",776 " box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",777 " filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",778 " fill: #FFFFFF;\n",779 " }\n",780 " </style>\n",781 " <button class=\"colab-df-generate\" onclick=\"generateWithVariable('topics_df')\"\n",782 " title=\"Generate code using this dataframe.\"\n",783 " style=\"display:none;\">\n",784 "\n",785 " <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",786 " width=\"24px\">\n",787 " <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",788 " </svg>\n",789 " </button>\n",790 " <script>\n",791 " (() => {\n",792 " const buttonEl =\n",793 " document.querySelector('#id_dbe130b5-f8c2-4744-9003-996b003fc00d button.colab-df-generate');\n",794 " buttonEl.style.display =\n",795 " google.colab.kernel.accessAllowed ? 'block' : 'none';\n",796 "\n",797 " buttonEl.onclick = () => {\n",798 " google.colab.notebook.generateWithVariable('topics_df');\n",799 " }\n",800 " })();\n",801 " </script>\n",802 " </div>\n",803 "\n",804 " </div>\n",805 " </div>\n"806 ],807 "application/vnd.google.colaboratory.intrinsic+json": {808 "type": "dataframe",809 "variable_name": "topics_df",810 "summary": "{\n \"name\": \"topics_df\",\n \"rows\": 20,\n \"fields\": [\n {\n \"column\": \"Terms per Topic\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 20,\n \"samples\": [\n \"energy, pig, growing, diet, content, fed, fiber, nutrient, adult, greater, ge, corn, dm, animal, acid, protein, meal, crossref, matter, stage\",\n \"yield, biomass, harvest, year, cutting, crossref, height, cm, treatment, mixture, mg, production, soil, july, agriculture, specie, temperature, plant, crop, grass\",\n \"management, energy, production, maize, efficiency, chicken, animal, economic, cost, farmer, gene, ax, input, ii, farm, mexico, agriculture, labour, crop, iii\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"811 }812 },813 "metadata": {},814 "execution_count": 79815 }816 ],817 "source": [818 "#Keywords for the various topics\n",819 "top_terms = 20\n",820 "topic_key_term_idxs = np.argsort(-np.absolute(topic_terms), axis=1)[:, :top_terms]\n",821 "topic_keyterms = vocabulary[topic_key_term_idxs]\n",822 "topics = [', '.join(topic) for topic in topic_keyterms]\n",823 "pd.set_option('display.max_colwidth', None) # Change -1 to None to display entire column content\n",824 "topics_df = pd.DataFrame(topics,\n",825 " columns = ['Terms per Topic'],\n",826 " index=['Topic'+str(t) for t in range(1, TOTAL_TOPICS+1)])\n",827 "topics_df\n"828 ]829 },830 {831 "cell_type": "markdown",832 "metadata": {833 "id": "Y6Nsw2zSkkL8"834 },835 "source": [836 "# 6) Weight of each terms in a particular topic with respect to each document.\n"837 ]838 },839 {840 "cell_type": "code",841 "execution_count": 80,842 "metadata": {843 "scrolled": true,844 "colab": {845 "base_uri": "https://localhost:8080/",846 "height": 676847 },848 "id": "zwobvmZjkkL8",849 "outputId": "697efe89-4a24-435a-9b69-408c0706aeaf"850 },851 "outputs": [852 {853 "output_type": "execute_result",854 "data": {855 "text/plain": [856 " 0 1 2 3 4 5 6 7 8 \\\n",857 "T1 0.00002 0.09745 0.00001 0.00001 0.00002 0.03216 0.00002 0.00003 0.99971 \n",858 "T2 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",859 "T3 0.00002 0.77052 0.00001 0.00001 0.78923 0.00001 0.00002 0.00003 0.00002 \n",860 "T4 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",861 "T5 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",862 "T6 0.00002 0.02945 0.00001 0.00001 0.00002 0.00001 0.99971 0.00003 0.00002 \n",863 "T7 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",864 "T8 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",865 "T9 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",866 "T10 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",867 "T11 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",868 "T12 0.00002 0.02585 0.00001 0.93883 0.00002 0.80486 0.00002 0.00003 0.00002 \n",869 "T13 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",870 "T14 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",871 "T15 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",872 "T16 0.99971 0.00002 0.00001 0.00001 0.21049 0.16274 0.00002 0.99943 0.00002 \n",873 "T17 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",874 "T18 0.00002 0.07646 0.99973 0.06090 0.00002 0.00001 0.00002 0.00003 0.00002 \n",875 "T19 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",876 "T20 0.00002 0.00002 0.00001 0.00001 0.00002 0.00001 0.00002 0.00003 0.00002 \n",877 "\n",878 " 9 10 11 12 13 14 15 16 17 \\\n",879 "T1 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",880 "T2 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",881 "T3 0.00003 0.00001 0.00002 0.00002 0.00002 0.93596 0.00063 0.00001 0.31616 \n",882 "T4 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",883 "T5 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",884 "T6 0.00003 0.00001 0.00002 0.07722 0.99962 0.03571 0.00063 0.00001 0.00002 \n",885 "T7 0.00003 0.33138 0.99958 0.23868 0.00002 0.02809 0.00063 0.00001 0.00002 \n",886 "T8 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",887 "T9 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",888 "T10 0.99948 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",889 "T11 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",890 "T12 0.00003 0.66837 0.00002 0.68377 0.00002 0.00001 0.82269 0.99985 0.61179 \n",891 "T13 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",892 "T14 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",893 "T15 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",894 "T16 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.16592 0.00001 0.07169 \n",895 "T17 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",896 "T18 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",897 "T19 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",898 "T20 0.00003 0.00001 0.00002 0.00002 0.00002 0.00001 0.00063 0.00001 0.00002 \n",899 "\n",900 " 18 19 \n",901 "T1 0.00002 0.00001 \n",902 "T2 0.00002 0.00001 \n",903 "T3 0.02620 0.99987 \n",904 "T4 0.00002 0.00001 \n",905 "T5 0.00002 0.00001 \n",906 "T6 0.00002 0.00001 \n",907 "T7 0.00002 0.00001 \n",908 "T8 0.00002 0.00001 \n",909 "T9 0.00002 0.00001 \n",910 "T10 0.00002 0.00001 \n",911 "T11 0.00002 0.00001 \n",912 "T12 0.97349 0.00001 \n",913 "T13 0.00002 0.00001 \n",914 "T14 0.00002 0.00001 \n",915 "T15 0.00002 0.00001 \n",916 "T16 0.00002 0.00001 \n",917 "T17 0.00002 0.00001 \n",918 "T18 0.00002 0.00001 \n",919 "T19 0.00002 0.00001 \n",920 "T20 0.00002 0.00001 "921 ],922 "text/html": [923 "\n",924 " <div id=\"df-16b44a23-c186-4bec-9c6f-eba85300270b\" class=\"colab-df-container\">\n",925 " <div>\n",926 "<style scoped>\n",927 " .dataframe tbody tr th:only-of-type {\n",928 " vertical-align: middle;\n",929 " }\n",930 "\n",931 " .dataframe tbody tr th {\n",932 " vertical-align: top;\n",933 " }\n",934 "\n",935 " .dataframe thead th {\n",936 " text-align: right;\n",937 " }\n",938 "</style>\n",939 "<table border=\"1\" class=\"dataframe\">\n",940 " <thead>\n",941 " <tr style=\"text-align: right;\">\n",942 " <th></th>\n",943 " <th>0</th>\n",944 " <th>1</th>\n",945 " <th>2</th>\n",946 " <th>3</th>\n",947 " <th>4</th>\n",948 " <th>5</th>\n",949 " <th>6</th>\n",950 " <th>7</th>\n",951 " <th>8</th>\n",952 " <th>9</th>\n",953 " <th>10</th>\n",954 " <th>11</th>\n",955 " <th>12</th>\n",956 " <th>13</th>\n",957 " <th>14</th>\n",958 " <th>15</th>\n",959 " <th>16</th>\n",960 " <th>17</th>\n",961 " <th>18</th>\n",962 " <th>19</th>\n",963 " </tr>\n",964 " </thead>\n",965 " <tbody>\n",966 " <tr>\n",967 " <th>T1</th>\n",968 " <td>0.00002</td>\n",969 " <td>0.09745</td>\n",970 " <td>0.00001</td>\n",971 " <td>0.00001</td>\n",972 " <td>0.00002</td>\n",973 " <td>0.03216</td>\n",974 " <td>0.00002</td>\n",975 " <td>0.00003</td>\n",976 " <td>0.99971</td>\n",977 " <td>0.00003</td>\n",978 " <td>0.00001</td>\n",979 " <td>0.00002</td>\n",980 " <td>0.00002</td>\n",981 " <td>0.00002</td>\n",982 " <td>0.00001</td>\n",983 " <td>0.00063</td>\n",984 " <td>0.00001</td>\n",985 " <td>0.00002</td>\n",986 " <td>0.00002</td>\n",987 " <td>0.00001</td>\n",988 " </tr>\n",989 " <tr>\n",990 " <th>T2</th>\n",991 " <td>0.00002</td>\n",992 " <td>0.00002</td>\n",993 " <td>0.00001</td>\n",994 " <td>0.00001</td>\n",995 " <td>0.00002</td>\n",996 " <td>0.00001</td>\n",997 " <td>0.00002</td>\n",998 " <td>0.00003</td>\n",999 " <td>0.00002</td>\n",1000 " <td>0.00003</td>\n",1001 " <td>0.00001</td>\n",1002 " <td>0.00002</td>\n",1003 " <td>0.00002</td>\n",1004 " <td>0.00002</td>\n",1005 " <td>0.00001</td>\n",1006 " <td>0.00063</td>\n",1007 " <td>0.00001</td>\n",1008 " <td>0.00002</td>\n",1009 " <td>0.00002</td>\n",1010 " <td>0.00001</td>\n",1011 " </tr>\n",1012 " <tr>\n",1013 " <th>T3</th>\n",1014 " <td>0.00002</td>\n",1015 " <td>0.77052</td>\n",1016 " <td>0.00001</td>\n",1017 " <td>0.00001</td>\n",1018 " <td>0.78923</td>\n",1019 " <td>0.00001</td>\n",1020 " <td>0.00002</td>\n",1021 " <td>0.00003</td>\n",1022 " <td>0.00002</td>\n",1023 " <td>0.00003</td>\n",1024 " <td>0.00001</td>\n",1025 " <td>0.00002</td>\n",1026 " <td>0.00002</td>\n",1027 " <td>0.00002</td>\n",1028 " <td>0.93596</td>\n",1029 " <td>0.00063</td>\n",1030 " <td>0.00001</td>\n",1031 " <td>0.31616</td>\n",1032 " <td>0.02620</td>\n",1033 " <td>0.99987</td>\n",1034 " </tr>\n",1035 " <tr>\n",1036 " <th>T4</th>\n",1037 " <td>0.00002</td>\n",1038 " <td>0.00002</td>\n",1039 " <td>0.00001</td>\n",1040 " <td>0.00001</td>\n",1041 " <td>0.00002</td>\n",1042 " <td>0.00001</td>\n",1043 " <td>0.00002</td>\n",1044 " <td>0.00003</td>\n",1045 " <td>0.00002</td>\n",1046 " <td>0.00003</td>\n",1047 " <td>0.00001</td>\n",1048 " <td>0.00002</td>\n",1049 " <td>0.00002</td>\n",1050 " <td>0.00002</td>\n",1051 " <td>0.00001</td>\n",1052 " <td>0.00063</td>\n",1053 " <td>0.00001</td>\n",1054 " <td>0.00002</td>\n",1055 " <td>0.00002</td>\n",1056 " <td>0.00001</td>\n",1057 " </tr>\n",1058 " <tr>\n",1059 " <th>T5</th>\n",1060 " <td>0.00002</td>\n",1061 " <td>0.00002</td>\n",1062 " <td>0.00001</td>\n",1063 " <td>0.00001</td>\n",1064 " <td>0.00002</td>\n",1065 " <td>0.00001</td>\n",1066 " <td>0.00002</td>\n",1067 " <td>0.00003</td>\n",1068 " <td>0.00002</td>\n",1069 " <td>0.00003</td>\n",1070 " <td>0.00001</td>\n",1071 " <td>0.00002</td>\n",1072 " <td>0.00002</td>\n",1073 " <td>0.00002</td>\n",1074 " <td>0.00001</td>\n",1075 " <td>0.00063</td>\n",1076 " <td>0.00001</td>\n",1077 " <td>0.00002</td>\n",1078 " <td>0.00002</td>\n",1079 " <td>0.00001</td>\n",1080 " </tr>\n",1081 " <tr>\n",1082 " <th>T6</th>\n",1083 " <td>0.00002</td>\n",1084 " <td>0.02945</td>\n",1085 " <td>0.00001</td>\n",1086 " <td>0.00001</td>\n",1087 " <td>0.00002</td>\n",1088 " <td>0.00001</td>\n",1089 " <td>0.99971</td>\n",1090 " <td>0.00003</td>\n",1091 " <td>0.00002</td>\n",1092 " <td>0.00003</td>\n",1093 " <td>0.00001</td>\n",1094 " <td>0.00002</td>\n",1095 " <td>0.07722</td>\n",1096 " <td>0.99962</td>\n",1097 " <td>0.03571</td>\n",1098 " <td>0.00063</td>\n",1099 " <td>0.00001</td>\n",1100 " <td>0.00002</td>\n",1101 " <td>0.00002</td>\n",1102 " <td>0.00001</td>\n",1103 " </tr>\n",1104 " <tr>\n",1105 " <th>T7</th>\n",1106 " <td>0.00002</td>\n",1107 " <td>0.00002</td>\n",1108 " <td>0.00001</td>\n",1109 " <td>0.00001</td>\n",1110 " <td>0.00002</td>\n",1111 " <td>0.00001</td>\n",1112 " <td>0.00002</td>\n",1113 " <td>0.00003</td>\n",1114 " <td>0.00002</td>\n",1115 " <td>0.00003</td>\n",1116 " <td>0.33138</td>\n",1117 " <td>0.99958</td>\n",1118 " <td>0.23868</td>\n",1119 " <td>0.00002</td>\n",1120 " <td>0.02809</td>\n",1121 " <td>0.00063</td>\n",1122 " <td>0.00001</td>\n",1123 " <td>0.00002</td>\n",1124 " <td>0.00002</td>\n",1125 " <td>0.00001</td>\n",1126 " </tr>\n",1127 " <tr>\n",1128 " <th>T8</th>\n",1129 " <td>0.00002</td>\n",1130 " <td>0.00002</td>\n",1131 " <td>0.00001</td>\n",1132 " <td>0.00001</td>\n",1133 " <td>0.00002</td>\n",1134 " <td>0.00001</td>\n",1135 " <td>0.00002</td>\n",1136 " <td>0.00003</td>\n",1137 " <td>0.00002</td>\n",1138 " <td>0.00003</td>\n",1139 " <td>0.00001</td>\n",1140 " <td>0.00002</td>\n",1141 " <td>0.00002</td>\n",1142 " <td>0.00002</td>\n",1143 " <td>0.00001</td>\n",1144 " <td>0.00063</td>\n",1145 " <td>0.00001</td>\n",1146 " <td>0.00002</td>\n",1147 " <td>0.00002</td>\n",1148 " <td>0.00001</td>\n",1149 " </tr>\n",1150 " <tr>\n",1151 " <th>T9</th>\n",1152 " <td>0.00002</td>\n",1153 " <td>0.00002</td>\n",1154 " <td>0.00001</td>\n",1155 " <td>0.00001</td>\n",1156 " <td>0.00002</td>\n",1157 " <td>0.00001</td>\n",1158 " <td>0.00002</td>\n",1159 " <td>0.00003</td>\n",1160 " <td>0.00002</td>\n",1161 " <td>0.00003</td>\n",1162 " <td>0.00001</td>\n",1163 " <td>0.00002</td>\n",1164 " <td>0.00002</td>\n",1165 " <td>0.00002</td>\n",1166 " <td>0.00001</td>\n",1167 " <td>0.00063</td>\n",1168 " <td>0.00001</td>\n",1169 " <td>0.00002</td>\n",1170 " <td>0.00002</td>\n",1171 " <td>0.00001</td>\n",1172 " </tr>\n",1173 " <tr>\n",1174 " <th>T10</th>\n",1175 " <td>0.00002</td>\n",1176 " <td>0.00002</td>\n",1177 " <td>0.00001</td>\n",1178 " <td>0.00001</td>\n",1179 " <td>0.00002</td>\n",1180 " <td>0.00001</td>\n",1181 " <td>0.00002</td>\n",1182 " <td>0.00003</td>\n",1183 " <td>0.00002</td>\n",1184 " <td>0.99948</td>\n",1185 " <td>0.00001</td>\n",1186 " <td>0.00002</td>\n",1187 " <td>0.00002</td>\n",1188 " <td>0.00002</td>\n",1189 " <td>0.00001</td>\n",1190 " <td>0.00063</td>\n",1191 " <td>0.00001</td>\n",1192 " <td>0.00002</td>\n",1193 " <td>0.00002</td>\n",1194 " <td>0.00001</td>\n",1195 " </tr>\n",1196 " <tr>\n",1197 " <th>T11</th>\n",1198 " <td>0.00002</td>\n",1199 " <td>0.00002</td>\n",1200 " <td>0.00001</td>\n",