atlas_of_worldstars
/
1_process_starbase_data.ipynb
501 строка · 15.3 Кб
1{2"cells": [3{4"cell_type": "code",5"execution_count": 1,6"metadata": {},7"outputs": [],8"source": [9"import pandas as pd"10]11},12{13"cell_type": "code",14"execution_count": 2,15"metadata": {},16"outputs": [17{18"name": "stdout",19"output_type": "stream",20"text": [21"watermark 1.8.1\n",22"pandas 0.23.4\n",23"ELEANOR LUTZ 2019-07-26 \n",24"\n",25"CPython 3.7.1\n",26"IPython 7.2.0\n",27"\n",28"compiler : MSC v.1900 64 bit (AMD64)\n",29"system : Windows\n",30"release : 10\n",31"machine : AMD64\n",32"processor : Intel64 Family 6 Model 63 Stepping 2, GenuineIntel\n",33"CPU cores : 12\n",34"interpreter: 64bit\n"35]36}37],38"source": [39"# Watermark is not required for this code, but is included for information. \n",40"import watermark\n",41"%load_ext watermark\n",42"%watermark -a \"ELEANOR LUTZ\" -d -v -iv -m"43]44},45{46"cell_type": "code",47"execution_count": 3,48"metadata": {},49"outputs": [50{51"data": {52"text/html": [53"<div>\n",54"<style scoped>\n",55" .dataframe tbody tr th:only-of-type {\n",56" vertical-align: middle;\n",57" }\n",58"\n",59" .dataframe tbody tr th {\n",60" vertical-align: top;\n",61" }\n",62"\n",63" .dataframe thead th {\n",64" text-align: right;\n",65" }\n",66"</style>\n",67"<table border=\"1\" class=\"dataframe\">\n",68" <thead>\n",69" <tr style=\"text-align: right;\">\n",70" <th></th>\n",71" <th>id</th>\n",72" <th>hip</th>\n",73" <th>hd</th>\n",74" <th>hr</th>\n",75" <th>gl</th>\n",76" <th>bf</th>\n",77" <th>proper</th>\n",78" <th>ra</th>\n",79" <th>dec</th>\n",80" <th>dist</th>\n",81" <th>...</th>\n",82" <th>bayer</th>\n",83" <th>flam</th>\n",84" <th>con</th>\n",85" <th>comp</th>\n",86" <th>comp_primary</th>\n",87" <th>base</th>\n",88" <th>lum</th>\n",89" <th>var</th>\n",90" <th>var_min</th>\n",91" <th>var_max</th>\n",92" </tr>\n",93" </thead>\n",94" <tbody>\n",95" <tr>\n",96" <th>0</th>\n",97" <td>0</td>\n",98" <td>NaN</td>\n",99" <td>NaN</td>\n",100" <td>NaN</td>\n",101" <td>NaN</td>\n",102" <td>NaN</td>\n",103" <td>Sol</td>\n",104" <td>0.000000</td>\n",105" <td>0.000000</td>\n",106" <td>0.0000</td>\n",107" <td>...</td>\n",108" <td>NaN</td>\n",109" <td>NaN</td>\n",110" <td>NaN</td>\n",111" <td>1</td>\n",112" <td>0</td>\n",113" <td>NaN</td>\n",114" <td>1.000000</td>\n",115" <td>NaN</td>\n",116" <td>NaN</td>\n",117" <td>NaN</td>\n",118" </tr>\n",119" <tr>\n",120" <th>1</th>\n",121" <td>1</td>\n",122" <td>1.0</td>\n",123" <td>224700.0</td>\n",124" <td>NaN</td>\n",125" <td>NaN</td>\n",126" <td>NaN</td>\n",127" <td>NaN</td>\n",128" <td>0.000060</td>\n",129" <td>1.089009</td>\n",130" <td>219.7802</td>\n",131" <td>...</td>\n",132" <td>NaN</td>\n",133" <td>NaN</td>\n",134" <td>Psc</td>\n",135" <td>1</td>\n",136" <td>1</td>\n",137" <td>NaN</td>\n",138" <td>9.638290</td>\n",139" <td>NaN</td>\n",140" <td>NaN</td>\n",141" <td>NaN</td>\n",142" </tr>\n",143" <tr>\n",144" <th>2</th>\n",145" <td>2</td>\n",146" <td>2.0</td>\n",147" <td>224690.0</td>\n",148" <td>NaN</td>\n",149" <td>NaN</td>\n",150" <td>NaN</td>\n",151" <td>NaN</td>\n",152" <td>0.000283</td>\n",153" <td>-19.498840</td>\n",154" <td>47.9616</td>\n",155" <td>...</td>\n",156" <td>NaN</td>\n",157" <td>NaN</td>\n",158" <td>Cet</td>\n",159" <td>1</td>\n",160" <td>2</td>\n",161" <td>NaN</td>\n",162" <td>0.392283</td>\n",163" <td>NaN</td>\n",164" <td>NaN</td>\n",165" <td>NaN</td>\n",166" </tr>\n",167" <tr>\n",168" <th>3</th>\n",169" <td>3</td>\n",170" <td>3.0</td>\n",171" <td>224699.0</td>\n",172" <td>NaN</td>\n",173" <td>NaN</td>\n",174" <td>NaN</td>\n",175" <td>NaN</td>\n",176" <td>0.000335</td>\n",177" <td>38.859279</td>\n",178" <td>442.4779</td>\n",179" <td>...</td>\n",180" <td>NaN</td>\n",181" <td>NaN</td>\n",182" <td>And</td>\n",183" <td>1</td>\n",184" <td>3</td>\n",185" <td>NaN</td>\n",186" <td>386.901132</td>\n",187" <td>NaN</td>\n",188" <td>NaN</td>\n",189" <td>NaN</td>\n",190" </tr>\n",191" <tr>\n",192" <th>4</th>\n",193" <td>4</td>\n",194" <td>4.0</td>\n",195" <td>224707.0</td>\n",196" <td>NaN</td>\n",197" <td>NaN</td>\n",198" <td>NaN</td>\n",199" <td>NaN</td>\n",200" <td>0.000569</td>\n",201" <td>-51.893546</td>\n",202" <td>134.2282</td>\n",203" <td>...</td>\n",204" <td>NaN</td>\n",205" <td>NaN</td>\n",206" <td>Phe</td>\n",207" <td>1</td>\n",208" <td>4</td>\n",209" <td>NaN</td>\n",210" <td>9.366989</td>\n",211" <td>NaN</td>\n",212" <td>NaN</td>\n",213" <td>NaN</td>\n",214" </tr>\n",215" </tbody>\n",216"</table>\n",217"<p>5 rows × 37 columns</p>\n",218"</div>"219],220"text/plain": [221" id hip hd hr gl bf proper ra dec dist \\\n",222"0 0 NaN NaN NaN NaN NaN Sol 0.000000 0.000000 0.0000 \n",223"1 1 1.0 224700.0 NaN NaN NaN NaN 0.000060 1.089009 219.7802 \n",224"2 2 2.0 224690.0 NaN NaN NaN NaN 0.000283 -19.498840 47.9616 \n",225"3 3 3.0 224699.0 NaN NaN NaN NaN 0.000335 38.859279 442.4779 \n",226"4 4 4.0 224707.0 NaN NaN NaN NaN 0.000569 -51.893546 134.2282 \n",227"\n",228" ... bayer flam con comp comp_primary base lum var \\\n",229"0 ... NaN NaN NaN 1 0 NaN 1.000000 NaN \n",230"1 ... NaN NaN Psc 1 1 NaN 9.638290 NaN \n",231"2 ... NaN NaN Cet 1 2 NaN 0.392283 NaN \n",232"3 ... NaN NaN And 1 3 NaN 386.901132 NaN \n",233"4 ... NaN NaN Phe 1 4 NaN 9.366989 NaN \n",234"\n",235" var_min var_max \n",236"0 NaN NaN \n",237"1 NaN NaN \n",238"2 NaN NaN \n",239"3 NaN NaN \n",240"4 NaN NaN \n",241"\n",242"[5 rows x 37 columns]"243]244},245"metadata": {},246"output_type": "display_data"247},248{249"data": {250"text/html": [251"<div>\n",252"<style scoped>\n",253" .dataframe tbody tr th:only-of-type {\n",254" vertical-align: middle;\n",255" }\n",256"\n",257" .dataframe tbody tr th {\n",258" vertical-align: top;\n",259" }\n",260"\n",261" .dataframe thead th {\n",262" text-align: right;\n",263" }\n",264"</style>\n",265"<table border=\"1\" class=\"dataframe\">\n",266" <thead>\n",267" <tr style=\"text-align: right;\">\n",268" <th></th>\n",269" <th>id</th>\n",270" <th>hip</th>\n",271" <th>hd</th>\n",272" <th>hr</th>\n",273" <th>gl</th>\n",274" <th>bf</th>\n",275" <th>proper</th>\n",276" <th>ra</th>\n",277" <th>dec</th>\n",278" <th>dist</th>\n",279" <th>...</th>\n",280" <th>bayer</th>\n",281" <th>flam</th>\n",282" <th>con</th>\n",283" <th>comp</th>\n",284" <th>comp_primary</th>\n",285" <th>base</th>\n",286" <th>lum</th>\n",287" <th>var</th>\n",288" <th>var_min</th>\n",289" <th>var_max</th>\n",290" </tr>\n",291" </thead>\n",292" <tbody>\n",293" <tr>\n",294" <th>1</th>\n",295" <td>1</td>\n",296" <td>1.0</td>\n",297" <td>224700.0</td>\n",298" <td>NaN</td>\n",299" <td>NaN</td>\n",300" <td>NaN</td>\n",301" <td>NaN</td>\n",302" <td>0.000060</td>\n",303" <td>1.089009</td>\n",304" <td>219.7802</td>\n",305" <td>...</td>\n",306" <td>NaN</td>\n",307" <td>NaN</td>\n",308" <td>Psc</td>\n",309" <td>1</td>\n",310" <td>1</td>\n",311" <td>NaN</td>\n",312" <td>9.638290</td>\n",313" <td>NaN</td>\n",314" <td>NaN</td>\n",315" <td>NaN</td>\n",316" </tr>\n",317" <tr>\n",318" <th>2</th>\n",319" <td>2</td>\n",320" <td>2.0</td>\n",321" <td>224690.0</td>\n",322" <td>NaN</td>\n",323" <td>NaN</td>\n",324" <td>NaN</td>\n",325" <td>NaN</td>\n",326" <td>0.000283</td>\n",327" <td>-19.498840</td>\n",328" <td>47.9616</td>\n",329" <td>...</td>\n",330" <td>NaN</td>\n",331" <td>NaN</td>\n",332" <td>Cet</td>\n",333" <td>1</td>\n",334" <td>2</td>\n",335" <td>NaN</td>\n",336" <td>0.392283</td>\n",337" <td>NaN</td>\n",338" <td>NaN</td>\n",339" <td>NaN</td>\n",340" </tr>\n",341" <tr>\n",342" <th>3</th>\n",343" <td>3</td>\n",344" <td>3.0</td>\n",345" <td>224699.0</td>\n",346" <td>NaN</td>\n",347" <td>NaN</td>\n",348" <td>NaN</td>\n",349" <td>NaN</td>\n",350" <td>0.000335</td>\n",351" <td>38.859279</td>\n",352" <td>442.4779</td>\n",353" <td>...</td>\n",354" <td>NaN</td>\n",355" <td>NaN</td>\n",356" <td>And</td>\n",357" <td>1</td>\n",358" <td>3</td>\n",359" <td>NaN</td>\n",360" <td>386.901132</td>\n",361" <td>NaN</td>\n",362" <td>NaN</td>\n",363" <td>NaN</td>\n",364" </tr>\n",365" <tr>\n",366" <th>4</th>\n",367" <td>4</td>\n",368" <td>4.0</td>\n",369" <td>224707.0</td>\n",370" <td>NaN</td>\n",371" <td>NaN</td>\n",372" <td>NaN</td>\n",373" <td>NaN</td>\n",374" <td>0.000569</td>\n",375" <td>-51.893546</td>\n",376" <td>134.2282</td>\n",377" <td>...</td>\n",378" <td>NaN</td>\n",379" <td>NaN</td>\n",380" <td>Phe</td>\n",381" <td>1</td>\n",382" <td>4</td>\n",383" <td>NaN</td>\n",384" <td>9.366989</td>\n",385" <td>NaN</td>\n",386" <td>NaN</td>\n",387" <td>NaN</td>\n",388" </tr>\n",389" <tr>\n",390" <th>5</th>\n",391" <td>5</td>\n",392" <td>5.0</td>\n",393" <td>224705.0</td>\n",394" <td>NaN</td>\n",395" <td>NaN</td>\n",396" <td>NaN</td>\n",397" <td>NaN</td>\n",398" <td>0.000665</td>\n",399" <td>-40.591202</td>\n",400" <td>257.7320</td>\n",401" <td>...</td>\n",402" <td>NaN</td>\n",403" <td>NaN</td>\n",404" <td>Phe</td>\n",405" <td>1</td>\n",406" <td>5</td>\n",407" <td>NaN</td>\n",408" <td>21.998851</td>\n",409" <td>NaN</td>\n",410" <td>NaN</td>\n",411" <td>NaN</td>\n",412" </tr>\n",413" </tbody>\n",414"</table>\n",415"<p>5 rows × 37 columns</p>\n",416"</div>"417],418"text/plain": [419" id hip hd hr gl bf proper ra dec dist \\\n",420"1 1 1.0 224700.0 NaN NaN NaN NaN 0.000060 1.089009 219.7802 \n",421"2 2 2.0 224690.0 NaN NaN NaN NaN 0.000283 -19.498840 47.9616 \n",422"3 3 3.0 224699.0 NaN NaN NaN NaN 0.000335 38.859279 442.4779 \n",423"4 4 4.0 224707.0 NaN NaN NaN NaN 0.000569 -51.893546 134.2282 \n",424"5 5 5.0 224705.0 NaN NaN NaN NaN 0.000665 -40.591202 257.7320 \n",425"\n",426" ... bayer flam con comp comp_primary base lum var \\\n",427"1 ... NaN NaN Psc 1 1 NaN 9.638290 NaN \n",428"2 ... NaN NaN Cet 1 2 NaN 0.392283 NaN \n",429"3 ... NaN NaN And 1 3 NaN 386.901132 NaN \n",430"4 ... NaN NaN Phe 1 4 NaN 9.366989 NaN \n",431"5 ... NaN NaN Phe 1 5 NaN 21.998851 NaN \n",432"\n",433" var_min var_max \n",434"1 NaN NaN \n",435"2 NaN NaN \n",436"3 NaN NaN \n",437"4 NaN NaN \n",438"5 NaN NaN \n",439"\n",440"[5 rows x 37 columns]"441]442},443"metadata": {},444"output_type": "display_data"445},446{447"name": "stdout",448"output_type": "stream",449"text": [450"119613 total stars available in database\n",451"8912 stars visible to the human eye\n"452]453}454],455"source": [456"# Clip the HYG Database to only include stars that are visible from Earth (magnitude <= 6.5)\n",457"\n",458"df = pd.read_csv('./data/hygdata_v3/hygdata_v3.csv', low_memory=False)\n",459"display(df.head())\n",460"\n",461"# Remove the sun because it doesn't make sense in a star chart\n",462"df = df[df['proper'] != 'Sol']\n",463"display(df.head())\n",464"df.to_csv('./data/processed/hygdata_processed.csv', index=False)\n",465"\n",466"print(len(df), 'total stars available in database')\n",467"df = df[df['mag'] <= 6.5]\n",468"print(len(df), 'stars visible to the human eye')\n",469"df.to_csv('./data/processed/hygdata_processed_mag65.csv', index=False)"470]471},472{473"cell_type": "code",474"execution_count": null,475"metadata": {},476"outputs": [],477"source": []478}479],480"metadata": {481"kernelspec": {482"display_name": "Python 3",483"language": "python",484"name": "python3"485},486"language_info": {487"codemirror_mode": {488"name": "ipython",489"version": 3490},491"file_extension": ".py",492"mimetype": "text/x-python",493"name": "python",494"nbconvert_exporter": "python",495"pygments_lexer": "ipython3",496"version": "3.7.1"497}498},499"nbformat": 4,500"nbformat_minor": 2501}502