atlas_of_asteroids
/
2_merge_TNO_diameter_data.ipynb
1009 строк · 32.5 Кб
1{2"cells": [3{4"cell_type": "code",5"execution_count": null,6"metadata": {},7"outputs": [8{9"name": "stdout",10"output_type": "stream",11"text": [12"numpy 1.15.4\n",13"pandas 0.23.4\n",14"watermark 1.8.1\n",15"ELEANOR LUTZ 2019-06-03 \n",16"\n",17"CPython 3.7.1\n",18"IPython 7.2.0\n",19"\n",20"compiler : MSC v.1900 64 bit (AMD64)\n",21"system : Windows\n",22"release : 10\n",23"machine : AMD64\n",24"processor : Intel64 Family 6 Model 63 Stepping 2, GenuineIntel\n",25"CPU cores : 12\n",26"interpreter: 64bit\n"27]28}29],30"source": [31"# Watermark is not required for this code, but is included for information. \n",32"import watermark\n",33"%load_ext watermark\n",34"%watermark -a \"ELEANOR LUTZ\" -d -v -iv -m"35]36},37{38"cell_type": "code",39"execution_count": null,40"metadata": {},41"outputs": [],42"source": [43"import numpy as np\n",44"import pandas as pd\n",45"import os.path"46]47},48{49"cell_type": "code",50"execution_count": null,51"metadata": {},52"outputs": [53{54"data": {55"text/html": [56"<div>\n",57"<style scoped>\n",58" .dataframe tbody tr th:only-of-type {\n",59" vertical-align: middle;\n",60" }\n",61"\n",62" .dataframe tbody tr th {\n",63" vertical-align: top;\n",64" }\n",65"\n",66" .dataframe thead th {\n",67" text-align: right;\n",68" }\n",69"</style>\n",70"<table border=\"1\" class=\"dataframe\">\n",71" <thead>\n",72" <tr style=\"text-align: right;\">\n",73" <th></th>\n",74" <th>0</th>\n",75" </tr>\n",76" </thead>\n",77" <tbody>\n",78" <tr>\n",79" <th>0</th>\n",80" <td>2060 Chiron 1977 UB 13.7 0...</td>\n",81" </tr>\n",82" <tr>\n",83" <th>1</th>\n",84" <td>2060 Chiron 1977 UB 13.7 0...</td>\n",85" </tr>\n",86" <tr>\n",87" <th>2</th>\n",88" <td>2060 Chiron 1977 UB 13.7 0...</td>\n",89" </tr>\n",90" <tr>\n",91" <th>3</th>\n",92" <td>2060 Chiron 1977 UB 13.7 0...</td>\n",93" </tr>\n",94" <tr>\n",95" <th>4</th>\n",96" <td>2060 Chiron 1977 UB 13.7 0...</td>\n",97" </tr>\n",98" </tbody>\n",99"</table>\n",100"</div>"101],102"text/plain": [103" 0\n",104"0 2060 Chiron 1977 UB 13.7 0...\n",105"1 2060 Chiron 1977 UB 13.7 0...\n",106"2 2060 Chiron 1977 UB 13.7 0...\n",107"3 2060 Chiron 1977 UB 13.7 0...\n",108"4 2060 Chiron 1977 UB 13.7 0..."109]110},111"metadata": {},112"output_type": "display_data"113},114{115"data": {116"text/html": [117"<div>\n",118"<style scoped>\n",119" .dataframe tbody tr th:only-of-type {\n",120" vertical-align: middle;\n",121" }\n",122"\n",123" .dataframe tbody tr th {\n",124" vertical-align: top;\n",125" }\n",126"\n",127" .dataframe thead th {\n",128" text-align: right;\n",129" }\n",130"</style>\n",131"<table border=\"1\" class=\"dataframe\">\n",132" <thead>\n",133" <tr style=\"text-align: right;\">\n",134" <th></th>\n",135" <th>number</th>\n",136" <th>name</th>\n",137" <th>full_name</th>\n",138" <th>axis_AU</th>\n",139" <th>eccentricity</th>\n",140" <th>inclination</th>\n",141" <th>type</th>\n",142" <th>companions</th>\n",143" <th>magnitude</th>\n",144" <th>abs_magnitude</th>\n",145" <th>...</th>\n",146" <th>albedo_err2</th>\n",147" <th>albedo_notecode</th>\n",148" <th>albedo_colorcode</th>\n",149" <th>density</th>\n",150" <th>density_err1</th>\n",151" <th>density_err2</th>\n",152" <th>density_notecode</th>\n",153" <th>methods_da</th>\n",154" <th>methods_density</th>\n",155" <th>reference</th>\n",156" </tr>\n",157" </thead>\n",158" <tbody>\n",159" <tr>\n",160" <th>0</th>\n",161" <td>2060</td>\n",162" <td>Chiron</td>\n",163" <td>1977UB</td>\n",164" <td>13.7</td>\n",165" <td>0.38</td>\n",166" <td>7.</td>\n",167" <td>CEN</td>\n",168" <td>0</td>\n",169" <td>5.8</td>\n",170" <td>6.900</td>\n",171" <td>...</td>\n",172" <td>0.035</td>\n",173" <td>*</td>\n",174" <td>-</td>\n",175" <td>-9.999</td>\n",176" <td>-9.999</td>\n",177" <td>-9.999</td>\n",178" <td>-</td>\n",179" <td>T</td>\n",180" <td>-</td>\n",181" <td>L84a</td>\n",182" </tr>\n",183" <tr>\n",184" <th>1</th>\n",185" <td>2060</td>\n",186" <td>Chiron</td>\n",187" <td>1977UB</td>\n",188" <td>13.7</td>\n",189" <td>0.38</td>\n",190" <td>7.</td>\n",191" <td>CEN</td>\n",192" <td>0</td>\n",193" <td>5.8</td>\n",194" <td>-99.999</td>\n",195" <td>...</td>\n",196" <td>-9.999</td>\n",197" <td>-</td>\n",198" <td>G</td>\n",199" <td>-9.999</td>\n",200" <td>-9.999</td>\n",201" <td>-9.999</td>\n",202" <td>-</td>\n",203" <td>T</td>\n",204" <td>-</td>\n",205" <td>S91a</td>\n",206" </tr>\n",207" <tr>\n",208" <th>2</th>\n",209" <td>2060</td>\n",210" <td>Chiron</td>\n",211" <td>1977UB</td>\n",212" <td>13.7</td>\n",213" <td>0.38</td>\n",214" <td>7.</td>\n",215" <td>CEN</td>\n",216" <td>0</td>\n",217" <td>5.8</td>\n",218" <td>6.800</td>\n",219" <td>...</td>\n",220" <td>-9.999</td>\n",221" <td>*</td>\n",222" <td>G</td>\n",223" <td>-9.999</td>\n",224" <td>-9.999</td>\n",225" <td>-9.999</td>\n",226" <td>-</td>\n",227" <td>T</td>\n",228" <td>-</td>\n",229" <td>J92a</td>\n",230" </tr>\n",231" <tr>\n",232" <th>3</th>\n",233" <td>2060</td>\n",234" <td>Chiron</td>\n",235" <td>1977UB</td>\n",236" <td>13.7</td>\n",237" <td>0.38</td>\n",238" <td>7.</td>\n",239" <td>CEN</td>\n",240" <td>0</td>\n",241" <td>5.8</td>\n",242" <td>-99.999</td>\n",243" <td>...</td>\n",244" <td>-9.999</td>\n",245" <td>-</td>\n",246" <td>-</td>\n",247" <td>-9.999</td>\n",248" <td>-9.999</td>\n",249" <td>-9.999</td>\n",250" <td>-</td>\n",251" <td>O</td>\n",252" <td>-</td>\n",253" <td>B93a</td>\n",254" </tr>\n",255" <tr>\n",256" <th>4</th>\n",257" <td>2060</td>\n",258" <td>Chiron</td>\n",259" <td>1977UB</td>\n",260" <td>13.7</td>\n",261" <td>0.38</td>\n",262" <td>7.</td>\n",263" <td>CEN</td>\n",264" <td>0</td>\n",265" <td>5.8</td>\n",266" <td>6.900</td>\n",267" <td>...</td>\n",268" <td>0.030</td>\n",269" <td>*</td>\n",270" <td>-</td>\n",271" <td>-9.999</td>\n",272" <td>-9.999</td>\n",273" <td>-9.999</td>\n",274" <td>-</td>\n",275" <td>T</td>\n",276" <td>-</td>\n",277" <td>C94a</td>\n",278" </tr>\n",279" </tbody>\n",280"</table>\n",281"<p>5 rows × 35 columns</p>\n",282"</div>"283],284"text/plain": [285" number name full_name axis_AU eccentricity inclination type companions \\\n",286"0 2060 Chiron 1977UB 13.7 0.38 7. CEN 0 \n",287"1 2060 Chiron 1977UB 13.7 0.38 7. CEN 0 \n",288"2 2060 Chiron 1977UB 13.7 0.38 7. CEN 0 \n",289"3 2060 Chiron 1977UB 13.7 0.38 7. CEN 0 \n",290"4 2060 Chiron 1977UB 13.7 0.38 7. CEN 0 \n",291"\n",292" magnitude abs_magnitude ... albedo_err2 albedo_notecode \\\n",293"0 5.8 6.900 ... 0.035 * \n",294"1 5.8 -99.999 ... -9.999 - \n",295"2 5.8 6.800 ... -9.999 * \n",296"3 5.8 -99.999 ... -9.999 - \n",297"4 5.8 6.900 ... 0.030 * \n",298"\n",299" albedo_colorcode density density_err1 density_err2 density_notecode \\\n",300"0 - -9.999 -9.999 -9.999 - \n",301"1 G -9.999 -9.999 -9.999 - \n",302"2 G -9.999 -9.999 -9.999 - \n",303"3 - -9.999 -9.999 -9.999 - \n",304"4 - -9.999 -9.999 -9.999 - \n",305"\n",306" methods_da methods_density reference \n",307"0 T - L84a \n",308"1 T - S91a \n",309"2 T - J92a \n",310"3 O - B93a \n",311"4 T - C94a \n",312"\n",313"[5 rows x 35 columns]"314]315},316"metadata": {},317"output_type": "display_data"318},319{320"data": {321"text/html": [322"<div>\n",323"<style scoped>\n",324" .dataframe tbody tr th:only-of-type {\n",325" vertical-align: middle;\n",326" }\n",327"\n",328" .dataframe tbody tr th {\n",329" vertical-align: top;\n",330" }\n",331"\n",332" .dataframe thead th {\n",333" text-align: right;\n",334" }\n",335"</style>\n",336"<table border=\"1\" class=\"dataframe\">\n",337" <thead>\n",338" <tr style=\"text-align: right;\">\n",339" <th></th>\n",340" <th>number</th>\n",341" <th>name</th>\n",342" <th>full_name</th>\n",343" <th>type</th>\n",344" <th>diameter_km</th>\n",345" </tr>\n",346" </thead>\n",347" <tbody>\n",348" <tr>\n",349" <th>0</th>\n",350" <td>0</td>\n",351" <td></td>\n",352" <td>1996TS66</td>\n",353" <td>CUB</td>\n",354" <td>163.00</td>\n",355" </tr>\n",356" <tr>\n",357" <th>1</th>\n",358" <td>0</td>\n",359" <td></td>\n",360" <td>1998WW31</td>\n",361" <td>CUB</td>\n",362" <td>170.30</td>\n",363" </tr>\n",364" <tr>\n",365" <th>2</th>\n",366" <td>0</td>\n",367" <td></td>\n",368" <td>1999OJ4</td>\n",369" <td>CUB</td>\n",370" <td>103.95</td>\n",371" </tr>\n",372" <tr>\n",373" <th>3</th>\n",374" <td>0</td>\n",375" <td></td>\n",376" <td>2000CF105</td>\n",377" <td>CUB</td>\n",378" <td>78.30</td>\n",379" </tr>\n",380" <tr>\n",381" <th>4</th>\n",382" <td>0</td>\n",383" <td></td>\n",384" <td>2000GM137</td>\n",385" <td>CEN</td>\n",386" <td>8.80</td>\n",387" </tr>\n",388" </tbody>\n",389"</table>\n",390"</div>"391],392"text/plain": [393" number name full_name type diameter_km\n",394"0 0 1996TS66 CUB 163.00\n",395"1 0 1998WW31 CUB 170.30\n",396"2 0 1999OJ4 CUB 103.95\n",397"3 0 2000CF105 CUB 78.30\n",398"4 0 2000GM137 CEN 8.80"399]400},401"metadata": {},402"output_type": "display_data"403},404{405"name": "stdout",406"output_type": "stream",407"text": [408"179 unique asteroids\n"409]410}411],412"source": [413"# Manually assign column names from bundle_description.txt file\n",414"colnames = ['number', 'name', 'full_name', 'axis_AU', 'eccentricity', 'inclination',\n",415" 'type', 'companions', 'magnitude', 'abs_magnitude', 'abs_magnitude_err', \n",416" 'diameter_km', 'e_diameter_err1', 'e_diameter_err2', 'e_diameter_notecode', \n",417" 'p_diameter', 'p_diameter_err1', 'p_diameter_err2', 'p_diameter_notecode',\n",418" 'c_diameter', 'c_diameter_err1', 'c_diameter_err2', 'c_diameter_notecode',\n",419" 'albedo', 'albedo_err1', 'albedo_err2', 'albedo_notecode', 'albedo_colorcode', \n",420" 'density', 'density_err1', 'density_err2', 'density_notecode', \n",421" 'methods_da', 'methods_density', 'reference'\n",422" ]\n",423"\n",424"diams = pd.read_csv('./data/diameters/tno-centaur_diam-albedo-density/data/tno_centaur_diam_alb_dens.tab', \n",425" header=None, sep='\\t', encoding='latin-1')\n",426"\n",427"display(diams.head())\n",428"diams = diams[0].str.split(expand=True)\n",429"diams[2] = diams[2] + diams[3]\n",430"diams.drop([3], inplace=True, axis=1)\n",431"\n",432"diams.columns = colnames\n",433"display(diams.head())\n",434"\n",435"diams = diams[['number', 'name', 'full_name', 'type', 'diameter_km', 'p_diameter']]\n",436"diams['diameter_km'] = diams['diameter_km'].astype(float)\n",437"diams['p_diameter'] = diams['p_diameter'].astype(float)\n",438"diams.loc[~(diams['diameter_km'] > 0), 'diameter_km']=np.nan\n",439"diams.loc[~(diams['p_diameter'] > 0), 'p_diameter']=np.nan\n",440"diams['diameter_km'] = diams['diameter_km'].fillna(diams['p_diameter'])\n",441"diams = diams[~pd.isnull(diams['diameter_km'])]\n",442"\n",443"diams.set_index(['number', 'name', 'full_name', 'type'], inplace=True)\n",444"diams = diams.groupby(['number', 'name', 'full_name', 'type']).median()\n",445"diams = diams.reset_index()\n",446"diams['name'] = diams['name'].str.replace('-', '')\n",447"diams.loc[diams['name'] == 'Pluto', 'full_name'] = '134340Pluto'\n",448"diams.drop(['p_diameter'], axis=1, inplace=True)\n",449"\n",450"display(diams.head())\n",451"savename = './data/diameters/TNO_Centaurs.csv'\n",452"if not os.path.isfile(savename):\n",453" diams.to_csv(savename, index=False)\n",454"\n",455"print(len(diams), 'unique asteroids')"456]457},458{459"cell_type": "code",460"execution_count": null,461"metadata": {},462"outputs": [463{464"data": {465"text/html": [466"<div>\n",467"<style scoped>\n",468" .dataframe tbody tr th:only-of-type {\n",469" vertical-align: middle;\n",470" }\n",471"\n",472" .dataframe tbody tr th {\n",473" vertical-align: top;\n",474" }\n",475"\n",476" .dataframe thead th {\n",477" text-align: right;\n",478" }\n",479"</style>\n",480"<table border=\"1\" class=\"dataframe\">\n",481" <thead>\n",482" <tr style=\"text-align: right;\">\n",483" <th></th>\n",484" <th>id</th>\n",485" <th>spkid</th>\n",486" <th>full_name</th>\n",487" <th>pdes</th>\n",488" <th>name</th>\n",489" <th>neo</th>\n",490" <th>pha</th>\n",491" <th>diameter</th>\n",492" <th>prefix</th>\n",493" <th>q</th>\n",494" <th>per</th>\n",495" <th>class</th>\n",496" </tr>\n",497" </thead>\n",498" <tbody>\n",499" <tr>\n",500" <th>794557</th>\n",501" <td>bT3S3411</td>\n",502" <td>3246664</td>\n",503" <td>3411T3</td>\n",504" <td>3411 T-3</td>\n",505" <td>NaN</td>\n",506" <td>N</td>\n",507" <td>N</td>\n",508" <td>NaN</td>\n",509" <td>NaN</td>\n",510" <td>2.073221</td>\n",511" <td>1428.185418</td>\n",512" <td>MBA</td>\n",513" </tr>\n",514" <tr>\n",515" <th>794558</th>\n",516" <td>bT3S3521</td>\n",517" <td>3246672</td>\n",518" <td>3521T3</td>\n",519" <td>3521 T-3</td>\n",520" <td>NaN</td>\n",521" <td>N</td>\n",522" <td>N</td>\n",523" <td>NaN</td>\n",524" <td>NaN</td>\n",525" <td>1.546423</td>\n",526" <td>1386.029296</td>\n",527" <td>MCA</td>\n",528" </tr>\n",529" <tr>\n",530" <th>794559</th>\n",531" <td>bT3S4571</td>\n",532" <td>3248621</td>\n",533" <td>4571T3</td>\n",534" <td>4571 T-3</td>\n",535" <td>NaN</td>\n",536" <td>N</td>\n",537" <td>N</td>\n",538" <td>NaN</td>\n",539" <td>NaN</td>\n",540" <td>1.813901</td>\n",541" <td>1484.222588</td>\n",542" <td>MBA</td>\n",543" </tr>\n",544" <tr>\n",545" <th>794560</th>\n",546" <td>bT3S4658</td>\n",547" <td>3248624</td>\n",548" <td>4658T3</td>\n",549" <td>4658 T-3</td>\n",550" <td>NaN</td>\n",551" <td>N</td>\n",552" <td>N</td>\n",553" <td>NaN</td>\n",554" <td>NaN</td>\n",555" <td>1.718022</td>\n",556" <td>1138.438109</td>\n",557" <td>MBA</td>\n",558" </tr>\n",559" <tr>\n",560" <th>794561</th>\n",561" <td>bT3S5154</td>\n",562" <td>3248651</td>\n",563" <td>5154T3</td>\n",564" <td>5154 T-3</td>\n",565" <td>NaN</td>\n",566" <td>N</td>\n",567" <td>N</td>\n",568" <td>NaN</td>\n",569" <td>NaN</td>\n",570" <td>2.239464</td>\n",571" <td>1985.374056</td>\n",572" <td>MBA</td>\n",573" </tr>\n",574" </tbody>\n",575"</table>\n",576"</div>"577],578"text/plain": [579" id spkid full_name pdes name neo pha diameter prefix \\\n",580"794557 bT3S3411 3246664 3411T3 3411 T-3 NaN N N NaN NaN \n",581"794558 bT3S3521 3246672 3521T3 3521 T-3 NaN N N NaN NaN \n",582"794559 bT3S4571 3248621 4571T3 4571 T-3 NaN N N NaN NaN \n",583"794560 bT3S4658 3248624 4658T3 4658 T-3 NaN N N NaN NaN \n",584"794561 bT3S5154 3248651 5154T3 5154 T-3 NaN N N NaN NaN \n",585"\n",586" q per class \n",587"794557 2.073221 1428.185418 MBA \n",588"794558 1.546423 1386.029296 MCA \n",589"794559 1.813901 1484.222588 MBA \n",590"794560 1.718022 1138.438109 MBA \n",591"794561 2.239464 1985.374056 MBA "592]593},594"metadata": {},595"output_type": "display_data"596},597{598"data": {599"text/html": [600"<div>\n",601"<style scoped>\n",602" .dataframe tbody tr th:only-of-type {\n",603" vertical-align: middle;\n",604" }\n",605"\n",606" .dataframe tbody tr th {\n",607" vertical-align: top;\n",608" }\n",609"\n",610" .dataframe thead th {\n",611" text-align: right;\n",612" }\n",613"</style>\n",614"<table border=\"1\" class=\"dataframe\">\n",615" <thead>\n",616" <tr style=\"text-align: right;\">\n",617" <th></th>\n",618" <th>id</th>\n",619" <th>spkid</th>\n",620" <th>full_name</th>\n",621" <th>pdes</th>\n",622" <th>name</th>\n",623" <th>neo</th>\n",624" <th>pha</th>\n",625" <th>diameter</th>\n",626" <th>prefix</th>\n",627" <th>q</th>\n",628" <th>per</th>\n",629" <th>class</th>\n",630" <th>diameter_km</th>\n",631" </tr>\n",632" </thead>\n",633" <tbody>\n",634" <tr>\n",635" <th>794557</th>\n",636" <td>bT3S3411</td>\n",637" <td>3246664</td>\n",638" <td>3411T3</td>\n",639" <td>3411 T-3</td>\n",640" <td>NaN</td>\n",641" <td>N</td>\n",642" <td>N</td>\n",643" <td>NaN</td>\n",644" <td>NaN</td>\n",645" <td>2.073221</td>\n",646" <td>1428.185418</td>\n",647" <td>MBA</td>\n",648" <td>NaN</td>\n",649" </tr>\n",650" <tr>\n",651" <th>794558</th>\n",652" <td>bT3S3521</td>\n",653" <td>3246672</td>\n",654" <td>3521T3</td>\n",655" <td>3521 T-3</td>\n",656" <td>NaN</td>\n",657" <td>N</td>\n",658" <td>N</td>\n",659" <td>NaN</td>\n",660" <td>NaN</td>\n",661" <td>1.546423</td>\n",662" <td>1386.029296</td>\n",663" <td>MCA</td>\n",664" <td>NaN</td>\n",665" </tr>\n",666" <tr>\n",667" <th>794559</th>\n",668" <td>bT3S4571</td>\n",669" <td>3248621</td>\n",670" <td>4571T3</td>\n",671" <td>4571 T-3</td>\n",672" <td>NaN</td>\n",673" <td>N</td>\n",674" <td>N</td>\n",675" <td>NaN</td>\n",676" <td>NaN</td>\n",677" <td>1.813901</td>\n",678" <td>1484.222588</td>\n",679" <td>MBA</td>\n",680" <td>NaN</td>\n",681" </tr>\n",682" <tr>\n",683" <th>794560</th>\n",684" <td>bT3S4658</td>\n",685" <td>3248624</td>\n",686" <td>4658T3</td>\n",687" <td>4658 T-3</td>\n",688" <td>NaN</td>\n",689" <td>N</td>\n",690" <td>N</td>\n",691" <td>NaN</td>\n",692" <td>NaN</td>\n",693" <td>1.718022</td>\n",694" <td>1138.438109</td>\n",695" <td>MBA</td>\n",696" <td>NaN</td>\n",697" </tr>\n",698" <tr>\n",699" <th>794561</th>\n",700" <td>bT3S5154</td>\n",701" <td>3248651</td>\n",702" <td>5154T3</td>\n",703" <td>5154 T-3</td>\n",704" <td>NaN</td>\n",705" <td>N</td>\n",706" <td>N</td>\n",707" <td>NaN</td>\n",708" <td>NaN</td>\n",709" <td>2.239464</td>\n",710" <td>1985.374056</td>\n",711" <td>MBA</td>\n",712" <td>NaN</td>\n",713" </tr>\n",714" </tbody>\n",715"</table>\n",716"</div>"717],718"text/plain": [719" id spkid full_name pdes name neo pha diameter prefix \\\n",720"794557 bT3S3411 3246664 3411T3 3411 T-3 NaN N N NaN NaN \n",721"794558 bT3S3521 3246672 3521T3 3521 T-3 NaN N N NaN NaN \n",722"794559 bT3S4571 3248621 4571T3 4571 T-3 NaN N N NaN NaN \n",723"794560 bT3S4658 3248624 4658T3 4658 T-3 NaN N N NaN NaN \n",724"794561 bT3S5154 3248651 5154T3 5154 T-3 NaN N N NaN NaN \n",725"\n",726" q per class diameter_km \n",727"794557 2.073221 1428.185418 MBA NaN \n",728"794558 1.546423 1386.029296 MCA NaN \n",729"794559 1.813901 1484.222588 MBA NaN \n",730"794560 1.718022 1138.438109 MBA NaN \n",731"794561 2.239464 1985.374056 MBA NaN "732]733},734"metadata": {},735"output_type": "display_data"736},737{738"name": "stdout",739"output_type": "stream",740"text": [741"44 diameter values that can be joined\n",742"35 new diameter values added\n"743]744},745{746"data": {747"text/html": [748"<div>\n",749"<style scoped>\n",750" .dataframe tbody tr th:only-of-type {\n",751" vertical-align: middle;\n",752" }\n",753"\n",754" .dataframe tbody tr th {\n",755" vertical-align: top;\n",756" }\n",757"\n",758" .dataframe thead th {\n",759" text-align: right;\n",760" }\n",761"</style>\n",762"<table border=\"1\" class=\"dataframe\">\n",763" <thead>\n",764" <tr style=\"text-align: right;\">\n",765" <th></th>\n",766" <th>id</th>\n",767" <th>spkid</th>\n",768" <th>full_name</th>\n",769" <th>pdes</th>\n",770" <th>name</th>\n",771" <th>neo</th>\n",772" <th>pha</th>\n",773" <th>diameter</th>\n",774" <th>prefix</th>\n",775" <th>q</th>\n",776" <th>per</th>\n",777" <th>class</th>\n",778" </tr>\n",779" </thead>\n",780" <tbody>\n",781" <tr>\n",782" <th>794557</th>\n",783" <td>bT3S3411</td>\n",784" <td>3246664</td>\n",785" <td>3411T3</td>\n",786" <td>3411 T-3</td>\n",787" <td>NaN</td>\n",788" <td>N</td>\n",789" <td>N</td>\n",790" <td>NaN</td>\n",791" <td>NaN</td>\n",792" <td>2.073221</td>\n",793" <td>1428.185418</td>\n",794" <td>MBA</td>\n",795" </tr>\n",796" <tr>\n",797" <th>794558</th>\n",798" <td>bT3S3521</td>\n",799" <td>3246672</td>\n",800" <td>3521T3</td>\n",801" <td>3521 T-3</td>\n",802" <td>NaN</td>\n",803" <td>N</td>\n",804" <td>N</td>\n",805" <td>NaN</td>\n",806" <td>NaN</td>\n",807" <td>1.546423</td>\n",808" <td>1386.029296</td>\n",809" <td>MCA</td>\n",810" </tr>\n",811" <tr>\n",812" <th>794559</th>\n",813" <td>bT3S4571</td>\n",814" <td>3248621</td>\n",815" <td>4571T3</td>\n",816" <td>4571 T-3</td>\n",817" <td>NaN</td>\n",818" <td>N</td>\n",819" <td>N</td>\n",820" <td>NaN</td>\n",821" <td>NaN</td>\n",822" <td>1.813901</td>\n",823" <td>1484.222588</td>\n",824" <td>MBA</td>\n",825" </tr>\n",826" <tr>\n",827" <th>794560</th>\n",828" <td>bT3S4658</td>\n",829" <td>3248624</td>\n",830" <td>4658T3</td>\n",831" <td>4658 T-3</td>\n",832" <td>NaN</td>\n",833" <td>N</td>\n",834" <td>N</td>\n",835" <td>NaN</td>\n",836" <td>NaN</td>\n",837" <td>1.718022</td>\n",838" <td>1138.438109</td>\n",839" <td>MBA</td>\n",840" </tr>\n",841" <tr>\n",842" <th>794561</th>\n",843" <td>bT3S5154</td>\n",844" <td>3248651</td>\n",845" <td>5154T3</td>\n",846" <td>5154 T-3</td>\n",847" <td>NaN</td>\n",848" <td>N</td>\n",849" <td>N</td>\n",850" <td>NaN</td>\n",851" <td>NaN</td>\n",852" <td>2.239464</td>\n",853" <td>1985.374056</td>\n",854" <td>MBA</td>\n",855" </tr>\n",856" </tbody>\n",857"</table>\n",858"</div>"859],860"text/plain": [861" id spkid full_name pdes name neo pha diameter prefix \\\n",862"794557 bT3S3411 3246664 3411T3 3411 T-3 NaN N N NaN NaN \n",863"794558 bT3S3521 3246672 3521T3 3521 T-3 NaN N N NaN NaN \n",864"794559 bT3S4571 3248621 4571T3 4571 T-3 NaN N N NaN NaN \n",865"794560 bT3S4658 3248624 4658T3 4658 T-3 NaN N N NaN NaN \n",866"794561 bT3S5154 3248651 5154T3 5154 T-3 NaN N N NaN NaN \n",867"\n",868" q per class \n",869"794557 2.073221 1428.185418 MBA \n",870"794558 1.546423 1386.029296 MCA \n",871"794559 1.813901 1484.222588 MBA \n",872"794560 1.718022 1138.438109 MBA \n",873"794561 2.239464 1985.374056 MBA "874]875},876"metadata": {},877"output_type": "display_data"878}879],880"source": [881"df = pd.read_csv('./data/all_asteroids.csv', low_memory=False)\n",882"df['full_name'] = df['full_name'].str.replace(' ', '').str.replace('(', '').str.replace(')', '').str.replace('-', '')\n",883"display(df.tail())\n",884"\n",885"diams = pd.read_csv('./data/diameters/TNO_Centaurs.csv', low_memory=False)\n",886"diams.drop(['number', 'name', 'type'], axis=1, inplace=True)\n",887"df = pd.merge(df, diams, on='full_name', how='left')\n",888"display(df.tail())\n",889"\n",890"print(len(df[~pd.isnull(df['diameter_km'])]), 'diameter values that can be joined')\n",891"original = len(df[~pd.isnull(df['diameter'])])\n",892"df['diameter'] = df['diameter'].fillna(df['diameter_km'])\n",893"print(len(df[~pd.isnull(df['diameter'])])-original, 'new diameter values added')\n",894"df.drop(['diameter_km'], inplace=True, axis=1)\n",895"\n",896"savename = './data/all_asteroids_wrangled.csv'\n",897"if not os.path.isfile(savename):\n",898" df.to_csv(savename, index=False)\n",899"display(df.tail())"900]901},902{903"cell_type": "code",904"execution_count": null,905"metadata": {},906"outputs": [907{908"data": {909"text/html": [910"<div>\n",911"<style scoped>\n",912" .dataframe tbody tr th:only-of-type {\n",913" vertical-align: middle;\n",914" }\n",915"\n",916" .dataframe tbody tr th {\n",917" vertical-align: top;\n",918" }\n",919"\n",920" .dataframe thead th {\n",921" text-align: right;\n",922" }\n",923"</style>\n",924"<table border=\"1\" class=\"dataframe\">\n",925" <thead>\n",926" <tr style=\"text-align: right;\">\n",927" <th></th>\n",928" <th>id</th>\n",929" <th>spkid</th>\n",930" <th>full_name</th>\n",931" <th>pdes</th>\n",932" <th>name</th>\n",933" <th>neo</th>\n",934" <th>pha</th>\n",935" <th>diameter</th>\n",936" <th>prefix</th>\n",937" <th>q</th>\n",938" <th>per</th>\n",939" <th>class</th>\n",940" </tr>\n",941" </thead>\n",942" <tbody>\n",943" <tr>\n",944" <th>134339</th>\n",945" <td>a0134340</td>\n",946" <td>2134340</td>\n",947" <td>134340Pluto</td>\n",948" <td>134340</td>\n",949" <td>Pluto</td>\n",950" <td>N</td>\n",951" <td>N</td>\n",952" <td>2361</td>\n",953" <td>NaN</td>\n",954" <td>29.573992</td>\n",955" <td>90487.276927</td>\n",956" <td>TNO</td>\n",957" </tr>\n",958" </tbody>\n",959"</table>\n",960"</div>"961],962"text/plain": [963" id spkid full_name pdes name neo pha diameter prefix \\\n",964"134339 a0134340 2134340 134340Pluto 134340 Pluto N N 2361 NaN \n",965"\n",966" q per class \n",967"134339 29.573992 90487.276927 TNO "968]969},970"execution_count": null,971"metadata": {},972"output_type": "execute_result"973}974],975"source": [976"# Check that Pluto has been added appropriately\n",977"df[df['full_name'] == '134340Pluto']"978]979},980{981"cell_type": "code",982"execution_count": null,983"metadata": {},984"outputs": [],985"source": []986}987],988"metadata": {989"kernelspec": {990"display_name": "Python 3",991"language": "python",992"name": "python3"993},994"language_info": {995"codemirror_mode": {996"name": "ipython",997"version": 3998},999"file_extension": ".py",1000"mimetype": "text/x-python",1001"name": "python",1002"nbconvert_exporter": "python",1003"pygments_lexer": "ipython3",1004"version": "3.7.3"1005}1006},1007"nbformat": 4,1008"nbformat_minor": 21009}1010