{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "pew = pd.read_csv('../data/pew.csv')" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
religion<$10k$10-20k$20-30k$30-40k$40-50k$50-75k$75-100k$100-150k>150kDon't know/refused
0Agnostic27346081761371221098496
1Atheist12273752357073597476
2Buddhist27213034335862395354
3Catholic41861773267063811169497926331489
4Don’t know/refused151415111035211718116
\n", "
" ], "text/plain": [ " religion <$10k $10-20k $20-30k $30-40k $40-50k $50-75k \\\n", "0 Agnostic 27 34 60 81 76 137 \n", "1 Atheist 12 27 37 52 35 70 \n", "2 Buddhist 27 21 30 34 33 58 \n", "3 Catholic 418 617 732 670 638 1116 \n", "4 Don’t know/refused 15 14 15 11 10 35 \n", "\n", " $75-100k $100-150k >150k Don't know/refused \n", "0 122 109 84 96 \n", "1 73 59 74 76 \n", "2 62 39 53 54 \n", "3 949 792 633 1489 \n", "4 21 17 18 116 " ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pew.head()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "pew_long = pd.melt(pew, id_vars='religion')" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
religionvariablevalue
0Agnostic<$10k27
1Atheist<$10k12
2Buddhist<$10k27
3Catholic<$10k418
4Don’t know/refused<$10k15
5Evangelical Prot<$10k575
6Hindu<$10k1
7Historically Black Prot<$10k228
8Jehovah's Witness<$10k20
9Jewish<$10k19
10Mainline Prot<$10k289
11Mormon<$10k29
12Muslim<$10k6
13Orthodox<$10k13
14Other Christian<$10k9
15Other Faiths<$10k20
16Other World Religions<$10k5
17Unaffiliated<$10k217
18Agnostic$10-20k34
19Atheist$10-20k27
20Buddhist$10-20k21
21Catholic$10-20k617
22Don’t know/refused$10-20k14
23Evangelical Prot$10-20k869
24Hindu$10-20k9
25Historically Black Prot$10-20k244
26Jehovah's Witness$10-20k27
27Jewish$10-20k19
28Mainline Prot$10-20k495
29Mormon$10-20k40
............
150Hindu>150k54
151Historically Black Prot>150k78
152Jehovah's Witness>150k6
153Jewish>150k151
154Mainline Prot>150k634
155Mormon>150k42
156Muslim>150k6
157Orthodox>150k46
158Other Christian>150k12
159Other Faiths>150k41
160Other World Religions>150k4
161Unaffiliated>150k258
162AgnosticDon't know/refused96
163AtheistDon't know/refused76
164BuddhistDon't know/refused54
165CatholicDon't know/refused1489
166Don’t know/refusedDon't know/refused116
167Evangelical ProtDon't know/refused1529
168HinduDon't know/refused37
169Historically Black ProtDon't know/refused339
170Jehovah's WitnessDon't know/refused37
171JewishDon't know/refused162
172Mainline ProtDon't know/refused1328
173MormonDon't know/refused69
174MuslimDon't know/refused22
175OrthodoxDon't know/refused73
176Other ChristianDon't know/refused18
177Other FaithsDon't know/refused71
178Other World ReligionsDon't know/refused8
179UnaffiliatedDon't know/refused597
\n", "

180 rows × 3 columns

\n", "
" ], "text/plain": [ " religion variable value\n", "0 Agnostic <$10k 27\n", "1 Atheist <$10k 12\n", "2 Buddhist <$10k 27\n", "3 Catholic <$10k 418\n", "4 Don’t know/refused <$10k 15\n", "5 Evangelical Prot <$10k 575\n", "6 Hindu <$10k 1\n", "7 Historically Black Prot <$10k 228\n", "8 Jehovah's Witness <$10k 20\n", "9 Jewish <$10k 19\n", "10 Mainline Prot <$10k 289\n", "11 Mormon <$10k 29\n", "12 Muslim <$10k 6\n", "13 Orthodox <$10k 13\n", "14 Other Christian <$10k 9\n", "15 Other Faiths <$10k 20\n", "16 Other World Religions <$10k 5\n", "17 Unaffiliated <$10k 217\n", "18 Agnostic $10-20k 34\n", "19 Atheist $10-20k 27\n", "20 Buddhist $10-20k 21\n", "21 Catholic $10-20k 617\n", "22 Don’t know/refused $10-20k 14\n", "23 Evangelical Prot $10-20k 869\n", "24 Hindu $10-20k 9\n", "25 Historically Black Prot $10-20k 244\n", "26 Jehovah's Witness $10-20k 27\n", "27 Jewish $10-20k 19\n", "28 Mainline Prot $10-20k 495\n", "29 Mormon $10-20k 40\n", ".. ... ... ...\n", "150 Hindu >150k 54\n", "151 Historically Black Prot >150k 78\n", "152 Jehovah's Witness >150k 6\n", "153 Jewish >150k 151\n", "154 Mainline Prot >150k 634\n", "155 Mormon >150k 42\n", "156 Muslim >150k 6\n", "157 Orthodox >150k 46\n", "158 Other Christian >150k 12\n", "159 Other Faiths >150k 41\n", "160 Other World Religions >150k 4\n", "161 Unaffiliated >150k 258\n", "162 Agnostic Don't know/refused 96\n", "163 Atheist Don't know/refused 76\n", "164 Buddhist Don't know/refused 54\n", "165 Catholic Don't know/refused 1489\n", "166 Don’t know/refused Don't know/refused 116\n", "167 Evangelical Prot Don't know/refused 1529\n", "168 Hindu Don't know/refused 37\n", "169 Historically Black Prot Don't know/refused 339\n", "170 Jehovah's Witness Don't know/refused 37\n", "171 Jewish Don't know/refused 162\n", "172 Mainline Prot Don't know/refused 1328\n", "173 Mormon Don't know/refused 69\n", "174 Muslim Don't know/refused 22\n", "175 Orthodox Don't know/refused 73\n", "176 Other Christian Don't know/refused 18\n", "177 Other Faiths Don't know/refused 71\n", "178 Other World Religions Don't know/refused 8\n", "179 Unaffiliated Don't know/refused 597\n", "\n", "[180 rows x 3 columns]" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pew_long" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
religionincomecount
0Agnostic<$10k27
1Atheist<$10k12
2Buddhist<$10k27
3Catholic<$10k418
4Don’t know/refused<$10k15
\n", "
" ], "text/plain": [ " religion income count\n", "0 Agnostic <$10k 27\n", "1 Atheist <$10k 12\n", "2 Buddhist <$10k 27\n", "3 Catholic <$10k 418\n", "4 Don’t know/refused <$10k 15" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pew_long = pd.melt(pew, id_vars='religion', var_name='income', value_name='count')\n", "pew_long.head()" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "billboard = pd.read_csv('../data/billboard.csv')" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearartisttracktimedate.enteredwk1wk2wk3wk4wk5...wk67wk68wk69wk70wk71wk72wk73wk74wk75wk76
020002 PacBaby Don't Cry (Keep...4:222000-02-268782.072.077.087.0...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
120002Ge+herThe Hardest Part Of ...3:152000-09-029187.092.0NaNNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
220003 Doors DownKryptonite3:532000-04-088170.068.067.066.0...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
320003 Doors DownLoser4:242000-10-217676.072.069.067.0...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
42000504 BoyzWobble Wobble3:352000-04-155734.025.017.017.0...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", "

5 rows × 81 columns

\n", "
" ], "text/plain": [ " year artist track time date.entered wk1 wk2 \\\n", "0 2000 2 Pac Baby Don't Cry (Keep... 4:22 2000-02-26 87 82.0 \n", "1 2000 2Ge+her The Hardest Part Of ... 3:15 2000-09-02 91 87.0 \n", "2 2000 3 Doors Down Kryptonite 3:53 2000-04-08 81 70.0 \n", "3 2000 3 Doors Down Loser 4:24 2000-10-21 76 76.0 \n", "4 2000 504 Boyz Wobble Wobble 3:35 2000-04-15 57 34.0 \n", "\n", " wk3 wk4 wk5 ... wk67 wk68 wk69 wk70 wk71 wk72 wk73 wk74 \\\n", "0 72.0 77.0 87.0 ... NaN NaN NaN NaN NaN NaN NaN NaN \n", "1 92.0 NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN \n", "2 68.0 67.0 66.0 ... NaN NaN NaN NaN NaN NaN NaN NaN \n", "3 72.0 69.0 67.0 ... NaN NaN NaN NaN NaN NaN NaN NaN \n", "4 25.0 17.0 17.0 ... NaN NaN NaN NaN NaN NaN NaN NaN \n", "\n", " wk75 wk76 \n", "0 NaN NaN \n", "1 NaN NaN \n", "2 NaN NaN \n", "3 NaN NaN \n", "4 NaN NaN \n", "\n", "[5 rows x 81 columns]" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard.head()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "billboard_long = pd.melt(\n", " billboard,\n", " id_vars=['year', 'artist', 'track', 'time', 'date.entered'],\n", " var_name='week',\n", " value_name='rating'\n", ")" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearartisttracktimedate.enteredweekrating
020002 PacBaby Don't Cry (Keep...4:222000-02-26wk187.0
120002Ge+herThe Hardest Part Of ...3:152000-09-02wk191.0
220003 Doors DownKryptonite3:532000-04-08wk181.0
320003 Doors DownLoser4:242000-10-21wk176.0
42000504 BoyzWobble Wobble3:352000-04-15wk157.0
\n", "
" ], "text/plain": [ " year artist track time date.entered week rating\n", "0 2000 2 Pac Baby Don't Cry (Keep... 4:22 2000-02-26 wk1 87.0\n", "1 2000 2Ge+her The Hardest Part Of ... 3:15 2000-09-02 wk1 91.0\n", "2 2000 3 Doors Down Kryptonite 3:53 2000-04-08 wk1 81.0\n", "3 2000 3 Doors Down Loser 4:24 2000-10-21 wk1 76.0\n", "4 2000 504 Boyz Wobble Wobble 3:35 2000-04-15 wk1 57.0" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_long.head()" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(24092, 7)" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_long.shape" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "ebola = pd.read_csv('../data/country_timeseries.csv')" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DateDayCases_GuineaCases_LiberiaCases_SierraLeoneCases_NigeriaCases_SenegalCases_UnitedStatesCases_SpainCases_MaliDeaths_GuineaDeaths_LiberiaDeaths_SierraLeoneDeaths_NigeriaDeaths_SenegalDeaths_UnitedStatesDeaths_SpainDeaths_Mali
01/5/20152892776.0NaN10030.0NaNNaNNaNNaNNaN1786.0NaN2977.0NaNNaNNaNNaNNaN
11/4/20152882775.0NaN9780.0NaNNaNNaNNaNNaN1781.0NaN2943.0NaNNaNNaNNaNNaN
21/3/20152872769.08166.09722.0NaNNaNNaNNaNNaN1767.03496.02915.0NaNNaNNaNNaNNaN
31/2/2015286NaN8157.0NaNNaNNaNNaNNaNNaNNaN3496.0NaNNaNNaNNaNNaNNaN
412/31/20142842730.08115.09633.0NaNNaNNaNNaNNaN1739.03471.02827.0NaNNaNNaNNaNNaN
\n", "
" ], "text/plain": [ " Date Day Cases_Guinea Cases_Liberia Cases_SierraLeone \\\n", "0 1/5/2015 289 2776.0 NaN 10030.0 \n", "1 1/4/2015 288 2775.0 NaN 9780.0 \n", "2 1/3/2015 287 2769.0 8166.0 9722.0 \n", "3 1/2/2015 286 NaN 8157.0 NaN \n", "4 12/31/2014 284 2730.0 8115.0 9633.0 \n", "\n", " Cases_Nigeria Cases_Senegal Cases_UnitedStates Cases_Spain Cases_Mali \\\n", "0 NaN NaN NaN NaN NaN \n", "1 NaN NaN NaN NaN NaN \n", "2 NaN NaN NaN NaN NaN \n", "3 NaN NaN NaN NaN NaN \n", "4 NaN NaN NaN NaN NaN \n", "\n", " Deaths_Guinea Deaths_Liberia Deaths_SierraLeone Deaths_Nigeria \\\n", "0 1786.0 NaN 2977.0 NaN \n", "1 1781.0 NaN 2943.0 NaN \n", "2 1767.0 3496.0 2915.0 NaN \n", "3 NaN 3496.0 NaN NaN \n", "4 1739.0 3471.0 2827.0 NaN \n", "\n", " Deaths_Senegal Deaths_UnitedStates Deaths_Spain Deaths_Mali \n", "0 NaN NaN NaN NaN \n", "1 NaN NaN NaN NaN \n", "2 NaN NaN NaN NaN \n", "3 NaN NaN NaN NaN \n", "4 NaN NaN NaN NaN " ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ebola.head()" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DateDayvariablevalue
01/5/2015289Cases_Guinea2776.0
11/4/2015288Cases_Guinea2775.0
21/3/2015287Cases_Guinea2769.0
31/2/2015286Cases_GuineaNaN
412/31/2014284Cases_Guinea2730.0
\n", "
" ], "text/plain": [ " Date Day variable value\n", "0 1/5/2015 289 Cases_Guinea 2776.0\n", "1 1/4/2015 288 Cases_Guinea 2775.0\n", "2 1/3/2015 287 Cases_Guinea 2769.0\n", "3 1/2/2015 286 Cases_Guinea NaN\n", "4 12/31/2014 284 Cases_Guinea 2730.0" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ebola_long = pd.melt(ebola, id_vars=['Date', 'Day'])\n", "ebola_long.head()" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Cases', 'Guinea']" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "'Cases_Guinea'.split('_')" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "# string accessor\n", "variable_split = ebola_long['variable'].str.split('_')" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "pandas.core.series.Series" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(variable_split)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 [Cases, Guinea]\n", "1 [Cases, Guinea]\n", "2 [Cases, Guinea]\n", "3 [Cases, Guinea]\n", "4 [Cases, Guinea]\n", "Name: variable, dtype: object" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "variable_split.head()" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "list" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(variable_split[0])" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Guinea'" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "variable_split[0][1]" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 Cases\n", "1 Cases\n", "2 Cases\n", "3 Cases\n", "4 Cases\n", "Name: variable, dtype: object" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "status_values = variable_split.str.get(0)\n", "status_values.head()" ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 Guinea\n", "1 Guinea\n", "2 Guinea\n", "3 Guinea\n", "4 Guinea\n", "Name: variable, dtype: object" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "country_values = variable_split.str.get(1)\n", "country_values.head()" ] }, { "cell_type": "code", "execution_count": 37, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "ebola_long['status'] = status_values\n", "ebola_long['country'] = country_values" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DateDayvariablevaluestatuscountry
01/5/2015289Cases_Guinea2776.0CasesGuinea
11/4/2015288Cases_Guinea2775.0CasesGuinea
21/3/2015287Cases_Guinea2769.0CasesGuinea
31/2/2015286Cases_GuineaNaNCasesGuinea
412/31/2014284Cases_Guinea2730.0CasesGuinea
\n", "
" ], "text/plain": [ " Date Day variable value status country\n", "0 1/5/2015 289 Cases_Guinea 2776.0 Cases Guinea\n", "1 1/4/2015 288 Cases_Guinea 2775.0 Cases Guinea\n", "2 1/3/2015 287 Cases_Guinea 2769.0 Cases Guinea\n", "3 1/2/2015 286 Cases_Guinea NaN Cases Guinea\n", "4 12/31/2014 284 Cases_Guinea 2730.0 Cases Guinea" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ebola_long.head()" ] }, { "cell_type": "code", "execution_count": 48, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "variable_split = ebola_long['variable'].str.split('_', expand=True)" ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "pandas.core.frame.DataFrame" ] }, "execution_count": 49, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(variable_split)" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
01
0CasesGuinea
1CasesGuinea
2CasesGuinea
3CasesGuinea
4CasesGuinea
\n", "
" ], "text/plain": [ " 0 1\n", "0 Cases Guinea\n", "1 Cases Guinea\n", "2 Cases Guinea\n", "3 Cases Guinea\n", "4 Cases Guinea" ] }, "execution_count": 50, "metadata": {}, "output_type": "execute_result" } ], "source": [ "variable_split.head()" ] }, { "cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [], "source": [ "variable_split.columns = ['status_expand', 'country_expand']" ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
status_expandcountry_expand
0CasesGuinea
1CasesGuinea
2CasesGuinea
3CasesGuinea
4CasesGuinea
\n", "
" ], "text/plain": [ " status_expand country_expand\n", "0 Cases Guinea\n", "1 Cases Guinea\n", "2 Cases Guinea\n", "3 Cases Guinea\n", "4 Cases Guinea" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "variable_split.head()" ] }, { "cell_type": "code", "execution_count": 46, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "ebola_long = pd.concat([ebola_long, variable_split], axis=1)" ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DateDayvariablevaluestatuscountrystatus_expandcountry_expand
01/5/2015289Cases_Guinea2776.0CasesGuineaCasesGuinea
11/4/2015288Cases_Guinea2775.0CasesGuineaCasesGuinea
21/3/2015287Cases_Guinea2769.0CasesGuineaCasesGuinea
31/2/2015286Cases_GuineaNaNCasesGuineaCasesGuinea
412/31/2014284Cases_Guinea2730.0CasesGuineaCasesGuinea
\n", "
" ], "text/plain": [ " Date Day variable value status country status_expand \\\n", "0 1/5/2015 289 Cases_Guinea 2776.0 Cases Guinea Cases \n", "1 1/4/2015 288 Cases_Guinea 2775.0 Cases Guinea Cases \n", "2 1/3/2015 287 Cases_Guinea 2769.0 Cases Guinea Cases \n", "3 1/2/2015 286 Cases_Guinea NaN Cases Guinea Cases \n", "4 12/31/2014 284 Cases_Guinea 2730.0 Cases Guinea Cases \n", "\n", " country_expand \n", "0 Guinea \n", "1 Guinea \n", "2 Guinea \n", "3 Guinea \n", "4 Guinea " ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ebola_long.head()" ] }, { "cell_type": "code", "execution_count": 51, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "weather = pd.read_csv('../data/weather.csv')" ] }, { "cell_type": "code", "execution_count": 53, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(22, 35)" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "weather.shape" ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idyearmonthelementd1d2d3d4d5d6d7
0MX1700420101tmaxNaNNaNNaNNaNNaNNaNNaN
1MX1700420101tminNaNNaNNaNNaNNaNNaNNaN
2MX1700420102tmaxNaN27.324.1NaNNaNNaNNaN
3MX1700420102tminNaN14.414.4NaNNaNNaNNaN
4MX1700420103tmaxNaNNaNNaNNaN32.1NaNNaN
\n", "
" ], "text/plain": [ " id year month element d1 d2 d3 d4 d5 d6 d7\n", "0 MX17004 2010 1 tmax NaN NaN NaN NaN NaN NaN NaN\n", "1 MX17004 2010 1 tmin NaN NaN NaN NaN NaN NaN NaN\n", "2 MX17004 2010 2 tmax NaN 27.3 24.1 NaN NaN NaN NaN\n", "3 MX17004 2010 2 tmin NaN 14.4 14.4 NaN NaN NaN NaN\n", "4 MX17004 2010 3 tmax NaN NaN NaN NaN 32.1 NaN NaN" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" } ], "source": [ "weather.iloc[:5, :11]" ] }, { "cell_type": "code", "execution_count": 54, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "weather_melt = pd.melt(\n", " weather,\n", " id_vars=['id', 'year', 'month', 'element'],\n", " var_name='day',\n", " value_name='temp'\n", ")" ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idyearmonthelementdaytemp
0MX1700420101tmaxd1NaN
1MX1700420101tmind1NaN
2MX1700420102tmaxd1NaN
3MX1700420102tmind1NaN
4MX1700420103tmaxd1NaN
\n", "
" ], "text/plain": [ " id year month element day temp\n", "0 MX17004 2010 1 tmax d1 NaN\n", "1 MX17004 2010 1 tmin d1 NaN\n", "2 MX17004 2010 2 tmax d1 NaN\n", "3 MX17004 2010 2 tmin d1 NaN\n", "4 MX17004 2010 3 tmax d1 NaN" ] }, "execution_count": 57, "metadata": {}, "output_type": "execute_result" } ], "source": [ "weather_melt.head()" ] }, { "cell_type": "code", "execution_count": 58, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "weather_tidy = weather_melt.pivot_table(\n", " index=['id', 'year', 'month', 'day'],\n", " columns='element',\n", " values='temp'\n", ")" ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "pandas.core.frame.DataFrame" ] }, "execution_count": 61, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(weather_tidy)" ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
elementidyearmonthdaytmaxtmin
0MX1700420101d1NaNNaN
1MX1700420101d10NaNNaN
2MX1700420101d11NaNNaN
3MX1700420101d12NaNNaN
4MX1700420101d13NaNNaN
\n", "
" ], "text/plain": [ "element id year month day tmax tmin\n", "0 MX17004 2010 1 d1 NaN NaN\n", "1 MX17004 2010 1 d10 NaN NaN\n", "2 MX17004 2010 1 d11 NaN NaN\n", "3 MX17004 2010 1 d12 NaN NaN\n", "4 MX17004 2010 1 d13 NaN NaN" ] }, "execution_count": 64, "metadata": {}, "output_type": "execute_result" } ], "source": [ "weather_tidy.reset_index().head()" ] }, { "cell_type": "code", "execution_count": 65, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "weather_tidy = (weather_melt\n", " .pivot_table(\n", " index=['id', 'year', 'month', 'day'],\n", " columns='element',\n", " values='temp')\n", " .reset_index()\n", ")" ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
elementidyearmonthdaytmaxtmin
0MX1700420101d1NaNNaN
1MX1700420101d10NaNNaN
2MX1700420101d11NaNNaN
3MX1700420101d12NaNNaN
4MX1700420101d13NaNNaN
\n", "
" ], "text/plain": [ "element id year month day tmax tmin\n", "0 MX17004 2010 1 d1 NaN NaN\n", "1 MX17004 2010 1 d10 NaN NaN\n", "2 MX17004 2010 1 d11 NaN NaN\n", "3 MX17004 2010 1 d12 NaN NaN\n", "4 MX17004 2010 1 d13 NaN NaN" ] }, "execution_count": 66, "metadata": {}, "output_type": "execute_result" } ], "source": [ "weather_tidy.head()" ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearartisttracktimedate.enteredweekrating
020002 PacBaby Don't Cry (Keep...4:222000-02-26wk187.0
120002Ge+herThe Hardest Part Of ...3:152000-09-02wk191.0
220003 Doors DownKryptonite3:532000-04-08wk181.0
320003 Doors DownLoser4:242000-10-21wk176.0
42000504 BoyzWobble Wobble3:352000-04-15wk157.0
\n", "
" ], "text/plain": [ " year artist track time date.entered week rating\n", "0 2000 2 Pac Baby Don't Cry (Keep... 4:22 2000-02-26 wk1 87.0\n", "1 2000 2Ge+her The Hardest Part Of ... 3:15 2000-09-02 wk1 91.0\n", "2 2000 3 Doors Down Kryptonite 3:53 2000-04-08 wk1 81.0\n", "3 2000 3 Doors Down Loser 4:24 2000-10-21 wk1 76.0\n", "4 2000 504 Boyz Wobble Wobble 3:35 2000-04-15 wk1 57.0" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_long.head()" ] }, { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearartisttracktimedate.enteredweekrating
320003 Doors DownLoser4:242000-10-21wk176.0
32020003 Doors DownLoser4:242000-10-21wk276.0
63720003 Doors DownLoser4:242000-10-21wk372.0
95420003 Doors DownLoser4:242000-10-21wk469.0
127120003 Doors DownLoser4:242000-10-21wk567.0
158820003 Doors DownLoser4:242000-10-21wk665.0
190520003 Doors DownLoser4:242000-10-21wk755.0
222220003 Doors DownLoser4:242000-10-21wk859.0
253920003 Doors DownLoser4:242000-10-21wk962.0
285620003 Doors DownLoser4:242000-10-21wk1061.0
317320003 Doors DownLoser4:242000-10-21wk1161.0
349020003 Doors DownLoser4:242000-10-21wk1259.0
380720003 Doors DownLoser4:242000-10-21wk1361.0
412420003 Doors DownLoser4:242000-10-21wk1466.0
444120003 Doors DownLoser4:242000-10-21wk1572.0
475820003 Doors DownLoser4:242000-10-21wk1676.0
507520003 Doors DownLoser4:242000-10-21wk1775.0
539220003 Doors DownLoser4:242000-10-21wk1867.0
570920003 Doors DownLoser4:242000-10-21wk1973.0
602620003 Doors DownLoser4:242000-10-21wk2070.0
634320003 Doors DownLoser4:242000-10-21wk21NaN
666020003 Doors DownLoser4:242000-10-21wk22NaN
697720003 Doors DownLoser4:242000-10-21wk23NaN
729420003 Doors DownLoser4:242000-10-21wk24NaN
761120003 Doors DownLoser4:242000-10-21wk25NaN
792820003 Doors DownLoser4:242000-10-21wk26NaN
824520003 Doors DownLoser4:242000-10-21wk27NaN
856220003 Doors DownLoser4:242000-10-21wk28NaN
887920003 Doors DownLoser4:242000-10-21wk29NaN
919620003 Doors DownLoser4:242000-10-21wk30NaN
........................
1458520003 Doors DownLoser4:242000-10-21wk47NaN
1490220003 Doors DownLoser4:242000-10-21wk48NaN
1521920003 Doors DownLoser4:242000-10-21wk49NaN
1553620003 Doors DownLoser4:242000-10-21wk50NaN
1585320003 Doors DownLoser4:242000-10-21wk51NaN
1617020003 Doors DownLoser4:242000-10-21wk52NaN
1648720003 Doors DownLoser4:242000-10-21wk53NaN
1680420003 Doors DownLoser4:242000-10-21wk54NaN
1712120003 Doors DownLoser4:242000-10-21wk55NaN
1743820003 Doors DownLoser4:242000-10-21wk56NaN
1775520003 Doors DownLoser4:242000-10-21wk57NaN
1807220003 Doors DownLoser4:242000-10-21wk58NaN
1838920003 Doors DownLoser4:242000-10-21wk59NaN
1870620003 Doors DownLoser4:242000-10-21wk60NaN
1902320003 Doors DownLoser4:242000-10-21wk61NaN
1934020003 Doors DownLoser4:242000-10-21wk62NaN
1965720003 Doors DownLoser4:242000-10-21wk63NaN
1997420003 Doors DownLoser4:242000-10-21wk64NaN
2029120003 Doors DownLoser4:242000-10-21wk65NaN
2060820003 Doors DownLoser4:242000-10-21wk66NaN
2092520003 Doors DownLoser4:242000-10-21wk67NaN
2124220003 Doors DownLoser4:242000-10-21wk68NaN
2155920003 Doors DownLoser4:242000-10-21wk69NaN
2187620003 Doors DownLoser4:242000-10-21wk70NaN
2219320003 Doors DownLoser4:242000-10-21wk71NaN
2251020003 Doors DownLoser4:242000-10-21wk72NaN
2282720003 Doors DownLoser4:242000-10-21wk73NaN
2314420003 Doors DownLoser4:242000-10-21wk74NaN
2346120003 Doors DownLoser4:242000-10-21wk75NaN
2377820003 Doors DownLoser4:242000-10-21wk76NaN
\n", "

76 rows × 7 columns

\n", "
" ], "text/plain": [ " year artist track time date.entered week rating\n", "3 2000 3 Doors Down Loser 4:24 2000-10-21 wk1 76.0\n", "320 2000 3 Doors Down Loser 4:24 2000-10-21 wk2 76.0\n", "637 2000 3 Doors Down Loser 4:24 2000-10-21 wk3 72.0\n", "954 2000 3 Doors Down Loser 4:24 2000-10-21 wk4 69.0\n", "1271 2000 3 Doors Down Loser 4:24 2000-10-21 wk5 67.0\n", "1588 2000 3 Doors Down Loser 4:24 2000-10-21 wk6 65.0\n", "1905 2000 3 Doors Down Loser 4:24 2000-10-21 wk7 55.0\n", "2222 2000 3 Doors Down Loser 4:24 2000-10-21 wk8 59.0\n", "2539 2000 3 Doors Down Loser 4:24 2000-10-21 wk9 62.0\n", "2856 2000 3 Doors Down Loser 4:24 2000-10-21 wk10 61.0\n", "3173 2000 3 Doors Down Loser 4:24 2000-10-21 wk11 61.0\n", "3490 2000 3 Doors Down Loser 4:24 2000-10-21 wk12 59.0\n", "3807 2000 3 Doors Down Loser 4:24 2000-10-21 wk13 61.0\n", "4124 2000 3 Doors Down Loser 4:24 2000-10-21 wk14 66.0\n", "4441 2000 3 Doors Down Loser 4:24 2000-10-21 wk15 72.0\n", "4758 2000 3 Doors Down Loser 4:24 2000-10-21 wk16 76.0\n", "5075 2000 3 Doors Down Loser 4:24 2000-10-21 wk17 75.0\n", "5392 2000 3 Doors Down Loser 4:24 2000-10-21 wk18 67.0\n", "5709 2000 3 Doors Down Loser 4:24 2000-10-21 wk19 73.0\n", "6026 2000 3 Doors Down Loser 4:24 2000-10-21 wk20 70.0\n", "6343 2000 3 Doors Down Loser 4:24 2000-10-21 wk21 NaN\n", "6660 2000 3 Doors Down Loser 4:24 2000-10-21 wk22 NaN\n", "6977 2000 3 Doors Down Loser 4:24 2000-10-21 wk23 NaN\n", "7294 2000 3 Doors Down Loser 4:24 2000-10-21 wk24 NaN\n", "7611 2000 3 Doors Down Loser 4:24 2000-10-21 wk25 NaN\n", "7928 2000 3 Doors Down Loser 4:24 2000-10-21 wk26 NaN\n", "8245 2000 3 Doors Down Loser 4:24 2000-10-21 wk27 NaN\n", "8562 2000 3 Doors Down Loser 4:24 2000-10-21 wk28 NaN\n", "8879 2000 3 Doors Down Loser 4:24 2000-10-21 wk29 NaN\n", "9196 2000 3 Doors Down Loser 4:24 2000-10-21 wk30 NaN\n", "... ... ... ... ... ... ... ...\n", "14585 2000 3 Doors Down Loser 4:24 2000-10-21 wk47 NaN\n", "14902 2000 3 Doors Down Loser 4:24 2000-10-21 wk48 NaN\n", "15219 2000 3 Doors Down Loser 4:24 2000-10-21 wk49 NaN\n", "15536 2000 3 Doors Down Loser 4:24 2000-10-21 wk50 NaN\n", "15853 2000 3 Doors Down Loser 4:24 2000-10-21 wk51 NaN\n", "16170 2000 3 Doors Down Loser 4:24 2000-10-21 wk52 NaN\n", "16487 2000 3 Doors Down Loser 4:24 2000-10-21 wk53 NaN\n", "16804 2000 3 Doors Down Loser 4:24 2000-10-21 wk54 NaN\n", "17121 2000 3 Doors Down Loser 4:24 2000-10-21 wk55 NaN\n", "17438 2000 3 Doors Down Loser 4:24 2000-10-21 wk56 NaN\n", "17755 2000 3 Doors Down Loser 4:24 2000-10-21 wk57 NaN\n", "18072 2000 3 Doors Down Loser 4:24 2000-10-21 wk58 NaN\n", "18389 2000 3 Doors Down Loser 4:24 2000-10-21 wk59 NaN\n", "18706 2000 3 Doors Down Loser 4:24 2000-10-21 wk60 NaN\n", "19023 2000 3 Doors Down Loser 4:24 2000-10-21 wk61 NaN\n", "19340 2000 3 Doors Down Loser 4:24 2000-10-21 wk62 NaN\n", "19657 2000 3 Doors Down Loser 4:24 2000-10-21 wk63 NaN\n", "19974 2000 3 Doors Down Loser 4:24 2000-10-21 wk64 NaN\n", "20291 2000 3 Doors Down Loser 4:24 2000-10-21 wk65 NaN\n", "20608 2000 3 Doors Down Loser 4:24 2000-10-21 wk66 NaN\n", "20925 2000 3 Doors Down Loser 4:24 2000-10-21 wk67 NaN\n", "21242 2000 3 Doors Down Loser 4:24 2000-10-21 wk68 NaN\n", "21559 2000 3 Doors Down Loser 4:24 2000-10-21 wk69 NaN\n", "21876 2000 3 Doors Down Loser 4:24 2000-10-21 wk70 NaN\n", "22193 2000 3 Doors Down Loser 4:24 2000-10-21 wk71 NaN\n", "22510 2000 3 Doors Down Loser 4:24 2000-10-21 wk72 NaN\n", "22827 2000 3 Doors Down Loser 4:24 2000-10-21 wk73 NaN\n", "23144 2000 3 Doors Down Loser 4:24 2000-10-21 wk74 NaN\n", "23461 2000 3 Doors Down Loser 4:24 2000-10-21 wk75 NaN\n", "23778 2000 3 Doors Down Loser 4:24 2000-10-21 wk76 NaN\n", "\n", "[76 rows x 7 columns]" ] }, "execution_count": 68, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_long[billboard_long['track'] == 'Loser']" ] }, { "cell_type": "code", "execution_count": 69, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "billboard_songs = billboard_long[['year', 'artist', 'track', 'time']]" ] }, { "cell_type": "code", "execution_count": 70, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearartisttracktime
020002 PacBaby Don't Cry (Keep...4:22
120002Ge+herThe Hardest Part Of ...3:15
220003 Doors DownKryptonite3:53
320003 Doors DownLoser4:24
42000504 BoyzWobble Wobble3:35
\n", "
" ], "text/plain": [ " year artist track time\n", "0 2000 2 Pac Baby Don't Cry (Keep... 4:22\n", "1 2000 2Ge+her The Hardest Part Of ... 3:15\n", "2 2000 3 Doors Down Kryptonite 3:53\n", "3 2000 3 Doors Down Loser 4:24\n", "4 2000 504 Boyz Wobble Wobble 3:35" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_songs.head()" ] }, { "cell_type": "code", "execution_count": 71, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(24092, 4)" ] }, "execution_count": 71, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_songs.shape" ] }, { "cell_type": "code", "execution_count": 72, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "billboard_songs = billboard_songs.drop_duplicates()" ] }, { "cell_type": "code", "execution_count": 73, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(317, 4)" ] }, "execution_count": 73, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_songs.shape" ] }, { "cell_type": "code", "execution_count": 76, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "range(0, 10)" ] }, "execution_count": 76, "metadata": {}, "output_type": "execute_result" } ], "source": [ "range(10)" ] }, { "cell_type": "code", "execution_count": 77, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "317" ] }, "execution_count": 77, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_songs.shape[0]" ] }, { "cell_type": "code", "execution_count": 78, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "317" ] }, "execution_count": 78, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(billboard_songs)" ] }, { "cell_type": "code", "execution_count": 79, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "billboard_songs['id'] = range(len(billboard_songs))" ] }, { "cell_type": "code", "execution_count": 81, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearartisttracktimeid
020002 PacBaby Don't Cry (Keep...4:220
120002Ge+herThe Hardest Part Of ...3:151
220003 Doors DownKryptonite3:532
320003 Doors DownLoser4:243
42000504 BoyzWobble Wobble3:354
5200098^0Give Me Just One Nig...3:245
62000A*TeensDancing Queen3:446
72000AaliyahI Don't Wanna4:157
82000AaliyahTry Again4:038
92000Adams, YolandaOpen My Heart5:309
\n", "
" ], "text/plain": [ " year artist track time id\n", "0 2000 2 Pac Baby Don't Cry (Keep... 4:22 0\n", "1 2000 2Ge+her The Hardest Part Of ... 3:15 1\n", "2 2000 3 Doors Down Kryptonite 3:53 2\n", "3 2000 3 Doors Down Loser 4:24 3\n", "4 2000 504 Boyz Wobble Wobble 3:35 4\n", "5 2000 98^0 Give Me Just One Nig... 3:24 5\n", "6 2000 A*Teens Dancing Queen 3:44 6\n", "7 2000 Aaliyah I Don't Wanna 4:15 7\n", "8 2000 Aaliyah Try Again 4:03 8\n", "9 2000 Adams, Yolanda Open My Heart 5:30 9" ] }, "execution_count": 81, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_songs.head(10)" ] }, { "cell_type": "code", "execution_count": 82, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "billboard_ratings = billboard_long.merge(\n", " billboard_songs, on=['year', 'artist', 'track', 'time']\n", ")" ] }, { "cell_type": "code", "execution_count": 83, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearartisttracktimedate.enteredweekratingid
020002 PacBaby Don't Cry (Keep...4:222000-02-26wk187.00
120002 PacBaby Don't Cry (Keep...4:222000-02-26wk282.00
220002 PacBaby Don't Cry (Keep...4:222000-02-26wk372.00
320002 PacBaby Don't Cry (Keep...4:222000-02-26wk477.00
420002 PacBaby Don't Cry (Keep...4:222000-02-26wk587.00
\n", "
" ], "text/plain": [ " year artist track time date.entered week rating id\n", "0 2000 2 Pac Baby Don't Cry (Keep... 4:22 2000-02-26 wk1 87.0 0\n", "1 2000 2 Pac Baby Don't Cry (Keep... 4:22 2000-02-26 wk2 82.0 0\n", "2 2000 2 Pac Baby Don't Cry (Keep... 4:22 2000-02-26 wk3 72.0 0\n", "3 2000 2 Pac Baby Don't Cry (Keep... 4:22 2000-02-26 wk4 77.0 0\n", "4 2000 2 Pac Baby Don't Cry (Keep... 4:22 2000-02-26 wk5 87.0 0" ] }, "execution_count": 83, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_ratings.head()" ] }, { "cell_type": "code", "execution_count": 84, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "billboard_ratings = billboard_ratings[['id', 'date.entered', 'week', 'rating']]" ] }, { "cell_type": "code", "execution_count": 85, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
iddate.enteredweekrating
002000-02-26wk187.0
102000-02-26wk282.0
202000-02-26wk372.0
302000-02-26wk477.0
402000-02-26wk587.0
\n", "
" ], "text/plain": [ " id date.entered week rating\n", "0 0 2000-02-26 wk1 87.0\n", "1 0 2000-02-26 wk2 82.0\n", "2 0 2000-02-26 wk3 72.0\n", "3 0 2000-02-26 wk4 77.0\n", "4 0 2000-02-26 wk5 87.0" ] }, "execution_count": 85, "metadata": {}, "output_type": "execute_result" } ], "source": [ "billboard_ratings.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.12" } }, "nbformat": 4, "nbformat_minor": 4 }