diff --git a/01_introduction.ipynb b/01_introduction.ipynb
index a766c3f2237073d4a9e2c9a930c076eb1c3bb2a3..f7a5f4f54ee222c0c85c6ccb929fff2e8af637a5 100644
--- a/01_introduction.ipynb
+++ b/01_introduction.ipynb
@@ -428,6 +428,268 @@
"print(vector)"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## One hot encoding \n",
+ "\n",
+ "The so called **one-hot-encoding** is a method to encode categorial features. \n",
+ "\n",
+ "Let's assume our beer data set has an extra column to encode the beer style:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>alcohol_content</th>\n",
+ " <th>bitterness</th>\n",
+ " <th>darkness</th>\n",
+ " <th>fruitiness</th>\n",
+ " <th>style</th>\n",
+ " <th>is_yummy</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>3.739295</td>\n",
+ " <td>0.422503</td>\n",
+ " <td>0.989463</td>\n",
+ " <td>0.215791</td>\n",
+ " <td>pilsener</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>4.207849</td>\n",
+ " <td>0.841668</td>\n",
+ " <td>0.928626</td>\n",
+ " <td>0.380420</td>\n",
+ " <td>ale</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>4.709494</td>\n",
+ " <td>0.322037</td>\n",
+ " <td>5.374682</td>\n",
+ " <td>0.145231</td>\n",
+ " <td>stout</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>4.684743</td>\n",
+ " <td>0.434315</td>\n",
+ " <td>4.072805</td>\n",
+ " <td>0.191321</td>\n",
+ " <td>pilsener</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>4.148710</td>\n",
+ " <td>0.570586</td>\n",
+ " <td>1.461568</td>\n",
+ " <td>0.260218</td>\n",
+ " <td>ale</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " alcohol_content bitterness darkness fruitiness style is_yummy\n",
+ "0 3.739295 0.422503 0.989463 0.215791 pilsener 0\n",
+ "1 4.207849 0.841668 0.928626 0.380420 ale 0\n",
+ "2 4.709494 0.322037 5.374682 0.145231 stout 1\n",
+ "3 4.684743 0.434315 4.072805 0.191321 pilsener 1\n",
+ "4 4.148710 0.570586 1.461568 0.260218 ale 0"
+ ]
+ },
+ "execution_count": 25,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.read_csv(\"data/beers_with_style.csv\").head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "The style column can take three different values: `pilsener`, `ale` and `stout`.\n",
+ "\n",
+ "To apply *one-hot-encoding* we replace the column `style` by three new columns `is_pilsener`, `is_ale` and `is_stout`:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>alcohol_content</th>\n",
+ " <th>bitterness</th>\n",
+ " <th>darkness</th>\n",
+ " <th>fruitiness</th>\n",
+ " <th>is_ale</th>\n",
+ " <th>is_pilsener</th>\n",
+ " <th>is_stout</th>\n",
+ " <th>is_yummy</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>3.739295</td>\n",
+ " <td>0.422503</td>\n",
+ " <td>0.989463</td>\n",
+ " <td>0.215791</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>4.207849</td>\n",
+ " <td>0.841668</td>\n",
+ " <td>0.928626</td>\n",
+ " <td>0.380420</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>4.709494</td>\n",
+ " <td>0.322037</td>\n",
+ " <td>5.374682</td>\n",
+ " <td>0.145231</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>4.684743</td>\n",
+ " <td>0.434315</td>\n",
+ " <td>4.072805</td>\n",
+ " <td>0.191321</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>4.148710</td>\n",
+ " <td>0.570586</td>\n",
+ " <td>1.461568</td>\n",
+ " <td>0.260218</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " alcohol_content bitterness darkness fruitiness is_ale is_pilsener \\\n",
+ "0 3.739295 0.422503 0.989463 0.215791 0 1 \n",
+ "1 4.207849 0.841668 0.928626 0.380420 1 0 \n",
+ "2 4.709494 0.322037 5.374682 0.145231 0 0 \n",
+ "3 4.684743 0.434315 4.072805 0.191321 0 1 \n",
+ "4 4.148710 0.570586 1.461568 0.260218 1 0 \n",
+ "\n",
+ " is_stout is_yummy \n",
+ "0 0 0 \n",
+ "1 0 0 \n",
+ "2 1 1 \n",
+ "3 0 1 \n",
+ "4 0 0 "
+ ]
+ },
+ "execution_count": 31,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.read_csv(\"data/beers_with_one_hot_encoding.csv\").head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "As you can see\n",
+ "- the new columns only have values `0` or `1`\n",
+ "- for each row exactly one entry of `is_pilsener`, `is_ale` and `is_stout` is `1`, all others are `0`."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "<div class=\"alert alert-block alert-info\">\n",
+ "<i class=\"fa fa-info-circle\"></i>\n",
+ "We will later see that <code>scikit-learn</code> has functions to transform categorical data into an appropriate one-hot-encoding.\n",
+ "</div>"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
diff --git a/data/beers_with_one_hot_encoding.csv b/data/beers_with_one_hot_encoding.csv
new file mode 100644
index 0000000000000000000000000000000000000000..161ee4d54b473975a5b4c65bf648995dbf1c407d
--- /dev/null
+++ b/data/beers_with_one_hot_encoding.csv
@@ -0,0 +1,226 @@
+alcohol_content,bitterness,darkness,fruitiness,is_ale,is_pilsener,is_stout,is_yummy
+3.7392953221603777,0.4225032988183505,0.989462508048864,0.2157910006100548,0,1,0,0
+4.207849022891722,0.8416677709351292,0.9286257771779024,0.3804200929756872,1,0,0,0
+4.709494110842424,0.3220369154718861,5.374681579916588,0.1452305306867214,0,0,1,1
+4.684742676618232,0.43431456529685997,4.072805148319574,0.19132082120196506,0,1,0,1
+4.1487095806832635,0.5705859977303992,1.4615680141969882,0.26021750111009473,1,0,0,0
+3.822707176067656,0.5442035671209013,0.9724141754104711,0.27567524761671885,0,0,1,0
+4.781677168686093,0.24494856501508375,6.654783144709145,0.0724059643417258,0,1,0,1
+5.283879238712101,0.2339010837446899,5.8626156965384935,0.08902128303364162,1,0,0,1
+4.289563172087767,0.6796344736526125,1.467328792654737,0.3347638616360541,0,0,1,0
+5.007389969791459,0.2880069162127078,4.543290590428586,0.11196570264909196,0,1,0,1
+4.885884733714292,0.40758041050450144,5.484282670613747,0.1809030292460357,1,0,0,1
+4.88699980108634,0.7593171332267783,2.2472813380462826,0.41517436348274095,0,0,1,1
+5.00516972754647,0.5866644352596934,0.8366476980348403,0.32648602956386275,0,1,0,1
+4.60938242559942,0.1119137875427797,4.012912182919277,0.06943379651708995,1,0,0,0
+4.797586724930365,0.5944243855219262,1.944308049016946,0.33821500286764794,0,0,1,1
+4.920402942767231,0.03793742812765255,3.0166941010688126,0.03182303123189086,0,1,0,0
+4.514646987132079,0.5180659040581066,0.7598715936195514,0.26425347612881017,1,0,0,0
+5.787968736703283,0.7615412972340481,4.4588448798621085,0.3541525492001101,0,0,1,1
+4.4843033410725806,0.6110943273309299,0.5182981529252185,0.2975460289364322,0,1,0,0
+4.667767508806038,0.08024571703059036,1.16315177747985,0.0343699881022153,1,0,0,0
+5.243665472674045,0.3711243140485669,5.45935964852258,0.17883069460768344,0,0,1,1
+5.097317931095987,0.5651738840803271,3.590548343329941,0.23930586001041385,0,1,0,1
+4.8989097894891005,0.2496723759465135,4.211756509313428,0.1196314370780298,1,0,0,1
+4.936540106165081,0.2686941896365934,5.465732865996512,0.09763172078958447,0,0,1,1
+5.560129359406711,0.5368023310400781,1.9386588433470389,0.32283860861177777,0,1,0,1
+4.086606839565337,0.6881737217045497,1.554424124324933,0.36638509027047145,1,0,0,0
+5.167219034791451,0.18339962166563198,3.496708765357939,0.035686099931214056,0,0,1,0
+4.805297479976446,0.4951075911938864,1.9868924105919743,0.2555292241478426,0,1,0,1
+5.251652775202468,0.6886639632433904,0.8523277929744486,0.3452927175979213,1,0,0,1
+4.6040584331979195,0.5411755544214232,2.418760168101697,0.26150260546792586,0,0,1,1
+5.320239937305652,0.3527392626087834,2.898092058558582,0.2230365037204423,0,1,0,1
+5.126808960337339,0.09039479782822037,3.4615683141975406,0.0191473906535776,1,0,0,0
+4.9172534781181465,0.8158955863868809,4.376087223704877,0.4149845803567057,0,0,1,1
+4.052013333376807,0.6214673607954408,2.071700636020688,0.2849198344873894,0,1,0,0
+3.7186286491469382,0.5651021685023335,1.4276238765165092,0.3262839838397662,1,0,0,0
+4.890790472939116,0.15471987603509305,4.094726876707195,0.06719844236076396,0,0,1,0
+4.951238272079908,0.2513551077335258,5.657894966224434,0.11912411570153952,0,1,0,1
+4.022490506787438,0.5496258428578215,2.455759859967517,0.21710802717473546,1,0,0,0
+4.435353937899214,0.6859305974434308,1.704486393840855,0.2925174842790473,0,0,1,1
+4.178505800309407,0.4927814215041726,1.6677783379833642,0.25294410687451563,0,1,0,0
+3.96220739994156,0.5994194608523018,1.1976404866318906,0.22773146828659135,1,0,0,0
+5.033468205084789,0.6702706124227704,3.4195005472342186,0.34105116451852097,0,0,1,1
+4.6720003913869235,0.563697143748036,0.960640156014422,0.3213611661494505,0,1,0,0
+4.085901182019937,0.4715894634026356,2.5902552391864693,0.1913502771728036,1,0,0,0
+5.1221635292722665,0.6208945112552599,2.054625738282005,0.2253092838276697,0,0,1,1
+4.620019159990127,0.1884865537616964,0.3847961052278246,0.12829831196697228,0,1,0,0
+4.228829934972972,1.059093559292834,1.7584039587611744,0.5036133276809346,1,0,0,1
+5.383462742685518,0.21165183845372051,5.586426798866984,0.07714601339596032,0,0,1,1
+4.429183362174499,0.6925156849146253,2.8484256568208814,0.3362417145923597,0,1,0,1
+4.840631547399172,0.613605471289796,5.025643848494268,0.32180540101466515,1,0,0,1
+5.307833319998519,0.04756896762684682,5.0687767548735465,0.0,0,0,1,0
+5.0078336210629235,0.5502594009477678,1.1865047940159248,0.22211365078130385,0,1,0,1
+5.072021362232559,0.2669862758693844,3.9927930229757456,0.0941511467103408,1,0,0,1
+4.566381874705192,0.6173075405169842,1.4875555950604906,0.3030195371932175,0,0,1,1
+4.757061332484208,0.3970832669397828,5.985756193183472,0.15898956770918315,0,1,0,1
+4.40738534829837,0.03318624353519134,0.8188670710876542,0.010531420985724009,1,0,0,0
+4.955681548047878,0.6415503043841695,1.6175381805961155,0.3301250932059537,0,0,1,1
+4.58482376813671,0.4219172266876728,0.2375684544848188,0.2440306230941965,0,1,0,0
+3.930921506975416,0.3270098092783109,0.971401251844598,0.19557843399924654,1,0,0,0
+4.590340912802551,0.2356715848303681,3.5433021824481505,0.11669653639590966,0,0,1,0
+4.191984205715052,0.284019561353523,0.0,0.15114772925632444,0,1,0,0
+5.1225546806970925,0.11342187629488547,5.488928311662474,0.06635560089486242,1,0,0,0
+4.721759494617157,0.16300725436328456,0.8420719432776125,0.05335121040347565,0,0,1,0
+4.622211029966211,0.41104223142501534,0.304561498446297,0.25426664729579085,0,1,0,0
+5.065190107335465,0.643053741073461,1.2454570695815042,0.2954764472105271,1,0,0,1
+5.462479282102972,0.7639267693097677,2.506357569734699,0.3572912202305075,0,0,1,1
+4.420849869481264,0.11420736197072845,1.8530627911594812,0.026367961343369918,0,1,0,0
+4.67544766651655,0.301723846240396,4.28169589280863,0.15094832048755016,1,0,0,1
+4.046559083647533,0.4776889516947808,1.095264775333837,0.2322798015856411,0,0,1,0
+4.617166000001592,0.337911159806104,1.578835966529656,0.16201429357107208,0,1,0,0
+5.172274119174623,0.3433863102613367,1.1217718948775388,0.13578271039596604,1,0,0,0
+4.679593704297321,0.7054348723639295,1.0034709856787551,0.2951007893633523,0,0,1,1
+4.6800922854829725,0.4282490135227799,1.2176055365079277,0.2007471808397608,0,1,0,0
+4.794710852704981,0.6703379430294519,1.4237510706970324,0.35774074373301723,1,0,0,1
+4.199465017172973,0.4087411785416169,0.5947782592829464,0.2204150993163528,0,0,1,0
+5.036475620760048,0.3828031166520064,3.7573747680006377,0.09897472345079156,0,1,0,1
+4.240815642975384,0.3795951052695677,1.5848878652671616,0.1996436559855703,1,0,0,0
+4.104266559005803,0.754832317621603,1.8646162932461017,0.3749272948041052,0,0,1,1
+5.955271950305143,0.47276004611348493,1.9991276011874115,0.1927970579618826,0,1,0,1
+4.98317523010529,0.8661370675955977,2.3706684447207085,0.4357466481490576,1,0,0,1
+4.509953778515362,0.4583230690382618,1.4851345330271808,0.2702080253452017,0,0,1,0
+4.191210697097752,0.7567853166583525,2.9236114339056494,0.3950996281152609,0,1,0,1
+5.3295591390555614,0.6619411759361196,2.0550563610527584,0.2923050543743978,1,0,0,1
+5.166125995203706,0.5364986608111579,2.2531317918537326,0.25318904485167365,0,0,1,1
+4.59438474272691,0.7616673852176574,1.486412446032617,0.4046063729708171,0,1,0,1
+4.730567376218069,0.5345209194180712,1.1911564886630863,0.2460573040507919,1,0,0,0
+4.762543146721715,0.0,4.043995028073375,0.0,0,0,1,0
+4.143057792497984,0.41156320481053205,0.9985628230735674,0.2396616691230564,0,1,0,0
+4.345766346534506,0.0,0.8024204648287228,0.0,1,0,0,0
+5.172993400965356,0.22218830113025712,5.748861822774688,0.09896961604538806,0,0,1,1
+4.469778556290719,0.6738095363428506,2.4590004632485933,0.416254569259542,0,1,0,1
+4.046520364556802,0.4000741149605301,1.8205203778237098,0.16088280718235612,1,0,0,0
+4.965806133711147,0.6625802599737914,2.0991413840373983,0.32000685164555664,0,0,1,1
+4.144977253167137,0.6210891841387731,0.5241747232890076,0.31874940024630416,0,1,0,0
+4.823315231814945,0.44887887283739536,6.015971140725851,0.1749183566103195,1,0,0,1
+4.906388587562084,0.6691350950342738,5.3110773111861596,0.32252667345812835,0,0,1,1
+4.726634398501472,0.572168101641073,0.7534170348024252,0.29659695973239697,0,1,0,0
+5.035716247239327,0.17253469401135466,0.4605954194893581,0.09354888110378162,1,0,0,0
+4.656122960907108,0.6650444778237858,1.2131017535977873,0.3323259309184993,0,0,1,1
+4.532253215388526,0.2430928539532585,1.1709900780105893,0.1706458553843593,0,1,0,0
+4.5481700270263286,0.35051282319248217,1.5200813270585067,0.16635694194128298,1,0,0,0
+4.544499673315782,0.5823111626250053,2.527342346549343,0.2783103914311418,0,0,1,1
+5.162578589631654,0.6148627877197309,1.477061055883044,0.2474304605213111,0,1,0,1
+4.833893948466684,0.4961369907583564,0.9995962008002728,0.22391460736794325,1,0,0,0
+5.201258407476644,0.15679491187635336,5.84583580728226,0.07296585562057499,0,0,1,1
+4.603930765210921,0.4728259087828541,0.970826344545684,0.21275381720720984,0,1,0,0
+4.603943096291582,0.09891530879189668,4.1528854641124,0.06608491797358101,1,0,0,0
+4.795552958702048,0.4436748439508389,0.6079313839173401,0.22375244606996847,0,0,1,0
+5.1593456412796765,0.6136975296529912,4.554829163314184,0.30534864943287343,0,1,0,1
+4.561281065512087,0.5933699020227752,0.49188481756350605,0.2831167545519204,1,0,0,0
+4.858803424114389,0.4169188244168133,0.07179097643198618,0.19309164353191527,0,0,1,0
+4.085811984189673,0.2446484787062544,0.6119697691812189,0.10146647587424222,0,1,0,0
+5.171840173189125,0.05280306940336196,4.450985392209264,0.0,1,0,0,0
+5.115758607885609,0.6961892798977378,4.043821057185001,0.32605536421884057,0,0,1,1
+5.0853504192882095,0.486853546336555,5.015973827326527,0.24679709938835026,0,1,0,1
+4.3198612462128505,0.2590047464223112,1.154713686918549,0.14532238128566194,1,0,0,0
+5.168156694425988,0.0,6.783746670214148,0.0,0,0,1,0
+4.9784050096812615,0.5037225973696902,1.280704335008831,0.23950347235929045,0,1,0,1
+3.8486282091608666,0.5526212249568543,1.8300476294328427,0.2076186617273654,1,0,0,0
+4.3080059825891714,0.7439184700173093,2.1805418626352737,0.33468264287662725,0,0,1,1
+4.3638145444539775,0.4573974281269594,2.5959150222700083,0.21934356321947365,0,1,0,1
+4.625553295316216,0.4529332325679191,1.2160535870940743,0.24649510626022306,1,0,0,0
+4.7078465178126745,0.9493856301576736,5.022760120545599,0.4361219247047203,0,0,1,1
+5.1126106922283165,0.4427692610767287,2.213164799520718,0.2175173321428012,0,1,0,1
+4.60928479903003,0.6376651795556787,1.0277183650041108,0.3276937878507505,1,0,0,0
+4.710526306181503,0.2710327631241003,5.383522540258733,0.11745721932861512,0,0,1,1
+4.0795300112706485,0.4336978380178236,2.487949151427727,0.19233745918230466,0,1,0,0
+4.605129058111356,0.7601899482475778,1.6059967765489758,0.37216610462853,1,0,0,1
+4.371416854212889,0.6226218192806234,1.85797988323771,0.29002244385015075,0,0,1,1
+5.434897537102555,0.47278142166659104,2.5246878138368154,0.2477352543763147,0,1,0,1
+3.0739927869088666,0.5852858802739863,1.3831206466392183,0.3340952590708193,1,0,0,0
+4.909845795201322,0.7665146563150838,4.010605026778202,0.351613397463848,0,0,1,1
+4.845131929090151,0.5816723103880109,1.842956749063554,0.2723736611732113,0,1,0,1
+4.900828313053719,0.6653422059874929,1.7455916185052236,0.32526151279694,1,0,0,1
+4.634559678927071,0.6672875756788887,1.2191607621866465,0.31106556672171504,0,0,1,1
+4.823549773751896,0.5032027034617681,4.297722594026217,0.2534546207985205,0,1,0,1
+4.474506146095889,0.5841120645799285,0.7604261637577064,0.3387673697858851,1,0,0,0
+4.892453851234189,0.6551675425119934,0.8599148014086141,0.3015660658618711,0,0,1,1
+4.8385087353524066,0.5901184463380091,1.2248343973170162,0.29919372001737354,0,1,0,1
+4.381397524835694,0.4406914509768374,0.8780128358335912,0.2258747735576792,1,0,0,0
+5.055874712104957,0.8386616196544887,4.97094334604903,0.4015155221891465,0,0,1,1
+4.770088117078503,0.6948718746783935,1.3880781978340129,0.2923041203859121,0,1,0,1
+4.7747093402817375,0.2645424543344852,5.168429257636191,0.08607468420271679,1,0,0,1
+4.191280620314243,0.7697354729181265,1.5780440658298238,0.3940464458074636,0,0,1,1
+4.853249202324078,0.6800569657440807,4.083833447063415,0.29297950054293903,0,1,0,1
+4.437962064064607,0.6288943759822643,0.8729770534803768,0.29020102015961524,1,0,0,0
+4.504904439526312,0.4726425725412575,0.6111727188374334,0.25717031431866155,0,0,1,0
+5.562901132616612,0.4405639757648828,4.630057186153164,0.2142173978546228,0,1,0,1
+4.37061279127637,0.4567571575150522,2.7737203212968105,0.19420161798633928,1,0,0,1
+4.719156751007689,0.5293899317968175,2.108490726296957,0.2845009597958012,0,0,1,1
+4.8425386630887095,0.6076025253085623,2.1090451829330648,0.3284034641632646,0,1,0,1
+4.494993896764447,0.3153933646261785,2.3684834523116383,0.13692811176282682,1,0,0,0
+4.498538989655988,0.2722753812273845,1.0664183839677048,0.14534888928495834,0,0,1,0
+5.0686657054176845,0.4882494401241486,4.323381343302478,0.2162727486173279,0,1,0,1
+4.86520848699937,0.1938215491306018,5.106044037270964,0.0732068319690718,1,0,0,0
+3.9726724014655717,0.7255428513391833,2.4894392808604544,0.3940302502214902,0,0,1,1
+4.901231668102691,0.07999736294548318,4.966178511756134,0.0,0,1,0,0
+4.56067954985581,0.5375683290763328,2.0265477783797627,0.3485345345547827,1,0,0,1
+4.603978447522283,0.6166512813874571,2.2102873385283703,0.2799316604659404,0,0,1,1
+4.339934550564419,0.4328051315133271,0.2221380962146917,0.2518510378435503,0,1,0,0
+3.702024296550728,0.6389595903795741,0.9351643596715498,0.34723438756983804,1,0,0,0
+4.89345561993195,0.1417888727685175,4.571465686065213,0.0,0,0,1,0
+5.1808768713522095,0.4836884737541486,2.8343889436467387,0.2423964126797811,0,1,0,1
+4.226749985901371,0.4964192508653471,1.6403129889417911,0.25267398283600895,1,0,0,0
+4.556431901580001,0.35005777018377504,1.387667879302526,0.16516465866368535,0,0,1,0
+4.626124655609613,0.5421125679086513,1.3968074399926442,0.2492380956502293,0,1,0,0
+5.0922248334636535,0.0,4.191398820258551,0.0,1,0,0,0
+4.899161690503445,0.06652174305298111,2.4166000367303986,0.03820906442831636,0,0,1,0
+4.6373683941628165,0.5321289055396973,1.8798898050732875,0.28113915432496656,0,1,0,1
+4.8181830768302625,0.4765695643174707,1.4128324252706563,0.19492621347795533,1,0,0,0
+5.012838107956776,0.631055749648945,1.7745121853110917,0.29032982541467794,0,0,1,1
+4.554763737504229,0.18602206486404396,3.8238218629564296,0.11818085254069625,0,1,0,0
+4.964769112948151,0.3709246362166373,1.4396690807525316,0.1687125166123709,1,0,0,0
+4.718207372012776,0.4868836646441811,0.7744738527949387,0.2651753723070033,0,0,1,0
+4.774682735043104,0.7221175297437538,6.038951894040884,0.33967037395810634,0,1,0,1
+5.000278495791396,0.9080130731524192,5.4310499028656265,0.4019055761771045,1,0,0,1
+4.889297359211636,0.2387601176878235,3.7546215325045913,0.11762273322277965,0,0,1,0
+4.810937613328119,0.3810033226801038,1.181885833126207,0.21623715341479488,0,1,0,0
+4.9924149023506175,0.5591369578682278,2.2259862755638298,0.2942212847540804,1,0,0,1
+5.367914710211371,0.12357486223202264,5.604502580379269,0.056792446768252375,0,0,1,0
+3.9949659373426516,0.5587634812053074,1.8403826747530576,0.2873699969411529,0,1,0,0
+5.378326999718162,0.4764212463533557,6.945111274463347,0.18975624847851,1,0,0,1
+5.861736899569883,0.5545087584614576,1.2503202867274583,0.24201488418423586,0,0,1,1
+4.614829612591472,0.3696172094283488,1.5431065162590059,0.14877686662777231,0,1,0,0
+5.2360940115732095,0.0,4.485126680342484,0.0,1,0,0,0
+4.970486555999896,0.2755490180517884,3.1029197403019912,0.16301556981305673,0,0,1,1
+4.838438710861518,0.2830581361303845,0.07443655867224641,0.1811510346305253,0,1,0,0
+5.035163956721139,0.6871975345655572,2.3390476693886395,0.3090767345536537,1,0,0,1
+4.8104211022238825,0.2812911297006149,6.044227396773093,0.11990680447427275,0,0,1,1
+5.198248613997872,0.4609744975324848,0.11584346696500615,0.2544099847227109,0,1,0,0
+4.9631903390156165,0.3604010481001159,4.515815714581629,0.1667319172121065,1,0,0,1
+4.909282109125602,0.6243517088496764,2.3511877609908653,0.3219190406857753,0,0,1,1
+4.568357036564035,0.6546260049224449,1.063442238215604,0.34143876546676705,0,1,0,0
+5.105198628130764,0.3439224253246719,3.4289867526500304,0.13561404366971222,1,0,0,1
+5.263433328468438,0.4478502824554645,5.015493883879213,0.1780178734826449,0,0,1,1
+4.758970880748969,0.557415284097465,1.3358428046209858,0.2672495100254132,0,1,0,1
+5.513982007981979,0.17004283678951662,4.093205422998805,0.09921637664659594,1,0,0,1
+4.845636289892032,0.6479722440790142,2.317108711651902,0.3118738071546832,0,0,1,1
+5.563767886924553,0.0,4.1861225213936,0.0,0,1,0,0
+5.067743257403525,0.7032498154561616,0.97813000108563,0.3120069748811195,1,0,0,1
+4.948453070151432,0.0,6.316242444294878,0.0,0,0,1,0
+4.74084596392849,0.2635240367311634,4.71345739338376,0.0609712737811886,0,1,0,1
+5.035461544615762,0.6058776943442449,1.8012594375973705,0.3217037835162609,1,0,0,1
+4.4229026867133285,0.1726710032400912,7.221284532316514,0.054750573754285985,0,0,1,0
+5.657109757110297,0.5721022713297903,3.5259449184102984,0.29474951437123503,0,1,0,1
+4.289039546501086,0.15252146459233518,1.3754041289935612,0.013465117317590205,1,0,0,0
+4.1597747512572685,0.7978215960527519,0.9163704549579376,0.4259705574231032,0,0,1,0
+4.299087895098071,0.6341034975312067,2.406091569614599,0.2548070096422226,0,1,0,1
+5.058898998436439,0.1053079901715316,4.3327005180293,0.08776585741923709,1,0,0,0
+4.639916190491344,0.0,0.6556991418389866,0.0,0,0,1,0
+4.99750861197712,0.2485074266624721,3.2841703994082008,0.07858500101380661,0,1,0,1
+4.1078737288819935,0.6994387358673055,2.25209918283752,0.29952091677912224,1,0,0,1
+4.059556896306028,0.15698590840532628,1.929391845756277,0.07147363426185585,0,0,1,0
+4.3820738648612245,0.5786039405321955,2.7204889653844395,0.21829954866951934,0,1,0,1
+4.587160266365657,0.6381790196024549,5.889957040926497,0.31272559116570514,1,0,0,1
+3.9329826512265056,0.6253760290712681,1.916115809819324,0.3078404367434497,0,0,1,0
+5.129053078389958,0.725591918749949,4.220478412365591,0.3605065284901468,0,1,0,1
+4.142898096352629,0.715511774814554,1.6154553665134486,0.28718912881369235,1,0,0,0
+4.311055333806913,0.1040636994710724,1.1383423597056943,0.009246826738128608,0,0,1,0
+4.2170069884183645,0.6123372486100588,0.653603679321312,0.3539533932567204,0,1,0,0
+4.284702598577564,1.0801696364991726,1.1929680418002442,0.5353145832327985,1,0,0,1
+4.850163438262958,0.6400127381084793,1.5543330429420243,0.36523001055142135,0,0,1,1
+4.638962265614757,0.1361812037670117,1.0664624096053654,0.044245900694067454,0,1,0,0
+4.178136247285695,0.6566818791299842,2.7480810469926924,0.3112970637465925,1,0,0,1
+4.039905740141564,0.7649263559531958,3.126262945032247,0.3783053447388735,0,0,1,1
diff --git a/data/beers_with_style.csv b/data/beers_with_style.csv
new file mode 100644
index 0000000000000000000000000000000000000000..9d99850bd1a024f8f33b0549793895140002cb09
--- /dev/null
+++ b/data/beers_with_style.csv
@@ -0,0 +1,226 @@
+alcohol_content,bitterness,darkness,fruitiness,style,is_yummy
+3.7392953221603777,0.4225032988183505,0.989462508048864,0.2157910006100548,pilsener,0
+4.207849022891722,0.8416677709351292,0.9286257771779024,0.3804200929756872,ale,0
+4.709494110842424,0.3220369154718861,5.374681579916588,0.1452305306867214,stout,1
+4.684742676618232,0.43431456529685997,4.072805148319574,0.19132082120196506,pilsener,1
+4.1487095806832635,0.5705859977303992,1.4615680141969882,0.26021750111009473,ale,0
+3.822707176067656,0.5442035671209013,0.9724141754104711,0.27567524761671885,stout,0
+4.781677168686093,0.24494856501508375,6.654783144709145,0.0724059643417258,pilsener,1
+5.283879238712101,0.2339010837446899,5.8626156965384935,0.08902128303364162,ale,1
+4.289563172087767,0.6796344736526125,1.467328792654737,0.3347638616360541,stout,0
+5.007389969791459,0.2880069162127078,4.543290590428586,0.11196570264909196,pilsener,1
+4.885884733714292,0.40758041050450144,5.484282670613747,0.1809030292460357,ale,1
+4.88699980108634,0.7593171332267783,2.2472813380462826,0.41517436348274095,stout,1
+5.00516972754647,0.5866644352596934,0.8366476980348403,0.32648602956386275,pilsener,1
+4.60938242559942,0.1119137875427797,4.012912182919277,0.06943379651708995,ale,0
+4.797586724930365,0.5944243855219262,1.944308049016946,0.33821500286764794,stout,1
+4.920402942767231,0.03793742812765255,3.0166941010688126,0.03182303123189086,pilsener,0
+4.514646987132079,0.5180659040581066,0.7598715936195514,0.26425347612881017,ale,0
+5.787968736703283,0.7615412972340481,4.4588448798621085,0.3541525492001101,stout,1
+4.4843033410725806,0.6110943273309299,0.5182981529252185,0.2975460289364322,pilsener,0
+4.667767508806038,0.08024571703059036,1.16315177747985,0.0343699881022153,ale,0
+5.243665472674045,0.3711243140485669,5.45935964852258,0.17883069460768344,stout,1
+5.097317931095987,0.5651738840803271,3.590548343329941,0.23930586001041385,pilsener,1
+4.8989097894891005,0.2496723759465135,4.211756509313428,0.1196314370780298,ale,1
+4.936540106165081,0.2686941896365934,5.465732865996512,0.09763172078958447,stout,1
+5.560129359406711,0.5368023310400781,1.9386588433470389,0.32283860861177777,pilsener,1
+4.086606839565337,0.6881737217045497,1.554424124324933,0.36638509027047145,ale,0
+5.167219034791451,0.18339962166563198,3.496708765357939,0.035686099931214056,stout,0
+4.805297479976446,0.4951075911938864,1.9868924105919743,0.2555292241478426,pilsener,1
+5.251652775202468,0.6886639632433904,0.8523277929744486,0.3452927175979213,ale,1
+4.6040584331979195,0.5411755544214232,2.418760168101697,0.26150260546792586,stout,1
+5.320239937305652,0.3527392626087834,2.898092058558582,0.2230365037204423,pilsener,1
+5.126808960337339,0.09039479782822037,3.4615683141975406,0.0191473906535776,ale,0
+4.9172534781181465,0.8158955863868809,4.376087223704877,0.4149845803567057,stout,1
+4.052013333376807,0.6214673607954408,2.071700636020688,0.2849198344873894,pilsener,0
+3.7186286491469382,0.5651021685023335,1.4276238765165092,0.3262839838397662,ale,0
+4.890790472939116,0.15471987603509305,4.094726876707195,0.06719844236076396,stout,0
+4.951238272079908,0.2513551077335258,5.657894966224434,0.11912411570153952,pilsener,1
+4.022490506787438,0.5496258428578215,2.455759859967517,0.21710802717473546,ale,0
+4.435353937899214,0.6859305974434308,1.704486393840855,0.2925174842790473,stout,1
+4.178505800309407,0.4927814215041726,1.6677783379833642,0.25294410687451563,pilsener,0
+3.96220739994156,0.5994194608523018,1.1976404866318906,0.22773146828659135,ale,0
+5.033468205084789,0.6702706124227704,3.4195005472342186,0.34105116451852097,stout,1
+4.6720003913869235,0.563697143748036,0.960640156014422,0.3213611661494505,pilsener,0
+4.085901182019937,0.4715894634026356,2.5902552391864693,0.1913502771728036,ale,0
+5.1221635292722665,0.6208945112552599,2.054625738282005,0.2253092838276697,stout,1
+4.620019159990127,0.1884865537616964,0.3847961052278246,0.12829831196697228,pilsener,0
+4.228829934972972,1.059093559292834,1.7584039587611744,0.5036133276809346,ale,1
+5.383462742685518,0.21165183845372051,5.586426798866984,0.07714601339596032,stout,1
+4.429183362174499,0.6925156849146253,2.8484256568208814,0.3362417145923597,pilsener,1
+4.840631547399172,0.613605471289796,5.025643848494268,0.32180540101466515,ale,1
+5.307833319998519,0.04756896762684682,5.0687767548735465,0.0,stout,0
+5.0078336210629235,0.5502594009477678,1.1865047940159248,0.22211365078130385,pilsener,1
+5.072021362232559,0.2669862758693844,3.9927930229757456,0.0941511467103408,ale,1
+4.566381874705192,0.6173075405169842,1.4875555950604906,0.3030195371932175,stout,1
+4.757061332484208,0.3970832669397828,5.985756193183472,0.15898956770918315,pilsener,1
+4.40738534829837,0.03318624353519134,0.8188670710876542,0.010531420985724009,ale,0
+4.955681548047878,0.6415503043841695,1.6175381805961155,0.3301250932059537,stout,1
+4.58482376813671,0.4219172266876728,0.2375684544848188,0.2440306230941965,pilsener,0
+3.930921506975416,0.3270098092783109,0.971401251844598,0.19557843399924654,ale,0
+4.590340912802551,0.2356715848303681,3.5433021824481505,0.11669653639590966,stout,0
+4.191984205715052,0.284019561353523,0.0,0.15114772925632444,pilsener,0
+5.1225546806970925,0.11342187629488547,5.488928311662474,0.06635560089486242,ale,0
+4.721759494617157,0.16300725436328456,0.8420719432776125,0.05335121040347565,stout,0
+4.622211029966211,0.41104223142501534,0.304561498446297,0.25426664729579085,pilsener,0
+5.065190107335465,0.643053741073461,1.2454570695815042,0.2954764472105271,ale,1
+5.462479282102972,0.7639267693097677,2.506357569734699,0.3572912202305075,stout,1
+4.420849869481264,0.11420736197072845,1.8530627911594812,0.026367961343369918,pilsener,0
+4.67544766651655,0.301723846240396,4.28169589280863,0.15094832048755016,ale,1
+4.046559083647533,0.4776889516947808,1.095264775333837,0.2322798015856411,stout,0
+4.617166000001592,0.337911159806104,1.578835966529656,0.16201429357107208,pilsener,0
+5.172274119174623,0.3433863102613367,1.1217718948775388,0.13578271039596604,ale,0
+4.679593704297321,0.7054348723639295,1.0034709856787551,0.2951007893633523,stout,1
+4.6800922854829725,0.4282490135227799,1.2176055365079277,0.2007471808397608,pilsener,0
+4.794710852704981,0.6703379430294519,1.4237510706970324,0.35774074373301723,ale,1
+4.199465017172973,0.4087411785416169,0.5947782592829464,0.2204150993163528,stout,0
+5.036475620760048,0.3828031166520064,3.7573747680006377,0.09897472345079156,pilsener,1
+4.240815642975384,0.3795951052695677,1.5848878652671616,0.1996436559855703,ale,0
+4.104266559005803,0.754832317621603,1.8646162932461017,0.3749272948041052,stout,1
+5.955271950305143,0.47276004611348493,1.9991276011874115,0.1927970579618826,pilsener,1
+4.98317523010529,0.8661370675955977,2.3706684447207085,0.4357466481490576,ale,1
+4.509953778515362,0.4583230690382618,1.4851345330271808,0.2702080253452017,stout,0
+4.191210697097752,0.7567853166583525,2.9236114339056494,0.3950996281152609,pilsener,1
+5.3295591390555614,0.6619411759361196,2.0550563610527584,0.2923050543743978,ale,1
+5.166125995203706,0.5364986608111579,2.2531317918537326,0.25318904485167365,stout,1
+4.59438474272691,0.7616673852176574,1.486412446032617,0.4046063729708171,pilsener,1
+4.730567376218069,0.5345209194180712,1.1911564886630863,0.2460573040507919,ale,0
+4.762543146721715,0.0,4.043995028073375,0.0,stout,0
+4.143057792497984,0.41156320481053205,0.9985628230735674,0.2396616691230564,pilsener,0
+4.345766346534506,0.0,0.8024204648287228,0.0,ale,0
+5.172993400965356,0.22218830113025712,5.748861822774688,0.09896961604538806,stout,1
+4.469778556290719,0.6738095363428506,2.4590004632485933,0.416254569259542,pilsener,1
+4.046520364556802,0.4000741149605301,1.8205203778237098,0.16088280718235612,ale,0
+4.965806133711147,0.6625802599737914,2.0991413840373983,0.32000685164555664,stout,1
+4.144977253167137,0.6210891841387731,0.5241747232890076,0.31874940024630416,pilsener,0
+4.823315231814945,0.44887887283739536,6.015971140725851,0.1749183566103195,ale,1
+4.906388587562084,0.6691350950342738,5.3110773111861596,0.32252667345812835,stout,1
+4.726634398501472,0.572168101641073,0.7534170348024252,0.29659695973239697,pilsener,0
+5.035716247239327,0.17253469401135466,0.4605954194893581,0.09354888110378162,ale,0
+4.656122960907108,0.6650444778237858,1.2131017535977873,0.3323259309184993,stout,1
+4.532253215388526,0.2430928539532585,1.1709900780105893,0.1706458553843593,pilsener,0
+4.5481700270263286,0.35051282319248217,1.5200813270585067,0.16635694194128298,ale,0
+4.544499673315782,0.5823111626250053,2.527342346549343,0.2783103914311418,stout,1
+5.162578589631654,0.6148627877197309,1.477061055883044,0.2474304605213111,pilsener,1
+4.833893948466684,0.4961369907583564,0.9995962008002728,0.22391460736794325,ale,0
+5.201258407476644,0.15679491187635336,5.84583580728226,0.07296585562057499,stout,1
+4.603930765210921,0.4728259087828541,0.970826344545684,0.21275381720720984,pilsener,0
+4.603943096291582,0.09891530879189668,4.1528854641124,0.06608491797358101,ale,0
+4.795552958702048,0.4436748439508389,0.6079313839173401,0.22375244606996847,stout,0
+5.1593456412796765,0.6136975296529912,4.554829163314184,0.30534864943287343,pilsener,1
+4.561281065512087,0.5933699020227752,0.49188481756350605,0.2831167545519204,ale,0
+4.858803424114389,0.4169188244168133,0.07179097643198618,0.19309164353191527,stout,0
+4.085811984189673,0.2446484787062544,0.6119697691812189,0.10146647587424222,pilsener,0
+5.171840173189125,0.05280306940336196,4.450985392209264,0.0,ale,0
+5.115758607885609,0.6961892798977378,4.043821057185001,0.32605536421884057,stout,1
+5.0853504192882095,0.486853546336555,5.015973827326527,0.24679709938835026,pilsener,1
+4.3198612462128505,0.2590047464223112,1.154713686918549,0.14532238128566194,ale,0
+5.168156694425988,0.0,6.783746670214148,0.0,stout,0
+4.9784050096812615,0.5037225973696902,1.280704335008831,0.23950347235929045,pilsener,1
+3.8486282091608666,0.5526212249568543,1.8300476294328427,0.2076186617273654,ale,0
+4.3080059825891714,0.7439184700173093,2.1805418626352737,0.33468264287662725,stout,1
+4.3638145444539775,0.4573974281269594,2.5959150222700083,0.21934356321947365,pilsener,1
+4.625553295316216,0.4529332325679191,1.2160535870940743,0.24649510626022306,ale,0
+4.7078465178126745,0.9493856301576736,5.022760120545599,0.4361219247047203,stout,1
+5.1126106922283165,0.4427692610767287,2.213164799520718,0.2175173321428012,pilsener,1
+4.60928479903003,0.6376651795556787,1.0277183650041108,0.3276937878507505,ale,0
+4.710526306181503,0.2710327631241003,5.383522540258733,0.11745721932861512,stout,1
+4.0795300112706485,0.4336978380178236,2.487949151427727,0.19233745918230466,pilsener,0
+4.605129058111356,0.7601899482475778,1.6059967765489758,0.37216610462853,ale,1
+4.371416854212889,0.6226218192806234,1.85797988323771,0.29002244385015075,stout,1
+5.434897537102555,0.47278142166659104,2.5246878138368154,0.2477352543763147,pilsener,1
+3.0739927869088666,0.5852858802739863,1.3831206466392183,0.3340952590708193,ale,0
+4.909845795201322,0.7665146563150838,4.010605026778202,0.351613397463848,stout,1
+4.845131929090151,0.5816723103880109,1.842956749063554,0.2723736611732113,pilsener,1
+4.900828313053719,0.6653422059874929,1.7455916185052236,0.32526151279694,ale,1
+4.634559678927071,0.6672875756788887,1.2191607621866465,0.31106556672171504,stout,1
+4.823549773751896,0.5032027034617681,4.297722594026217,0.2534546207985205,pilsener,1
+4.474506146095889,0.5841120645799285,0.7604261637577064,0.3387673697858851,ale,0
+4.892453851234189,0.6551675425119934,0.8599148014086141,0.3015660658618711,stout,1
+4.8385087353524066,0.5901184463380091,1.2248343973170162,0.29919372001737354,pilsener,1
+4.381397524835694,0.4406914509768374,0.8780128358335912,0.2258747735576792,ale,0
+5.055874712104957,0.8386616196544887,4.97094334604903,0.4015155221891465,stout,1
+4.770088117078503,0.6948718746783935,1.3880781978340129,0.2923041203859121,pilsener,1
+4.7747093402817375,0.2645424543344852,5.168429257636191,0.08607468420271679,ale,1
+4.191280620314243,0.7697354729181265,1.5780440658298238,0.3940464458074636,stout,1
+4.853249202324078,0.6800569657440807,4.083833447063415,0.29297950054293903,pilsener,1
+4.437962064064607,0.6288943759822643,0.8729770534803768,0.29020102015961524,ale,0
+4.504904439526312,0.4726425725412575,0.6111727188374334,0.25717031431866155,stout,0
+5.562901132616612,0.4405639757648828,4.630057186153164,0.2142173978546228,pilsener,1
+4.37061279127637,0.4567571575150522,2.7737203212968105,0.19420161798633928,ale,1
+4.719156751007689,0.5293899317968175,2.108490726296957,0.2845009597958012,stout,1
+4.8425386630887095,0.6076025253085623,2.1090451829330648,0.3284034641632646,pilsener,1
+4.494993896764447,0.3153933646261785,2.3684834523116383,0.13692811176282682,ale,0
+4.498538989655988,0.2722753812273845,1.0664183839677048,0.14534888928495834,stout,0
+5.0686657054176845,0.4882494401241486,4.323381343302478,0.2162727486173279,pilsener,1
+4.86520848699937,0.1938215491306018,5.106044037270964,0.0732068319690718,ale,0
+3.9726724014655717,0.7255428513391833,2.4894392808604544,0.3940302502214902,stout,1
+4.901231668102691,0.07999736294548318,4.966178511756134,0.0,pilsener,0
+4.56067954985581,0.5375683290763328,2.0265477783797627,0.3485345345547827,ale,1
+4.603978447522283,0.6166512813874571,2.2102873385283703,0.2799316604659404,stout,1
+4.339934550564419,0.4328051315133271,0.2221380962146917,0.2518510378435503,pilsener,0
+3.702024296550728,0.6389595903795741,0.9351643596715498,0.34723438756983804,ale,0
+4.89345561993195,0.1417888727685175,4.571465686065213,0.0,stout,0
+5.1808768713522095,0.4836884737541486,2.8343889436467387,0.2423964126797811,pilsener,1
+4.226749985901371,0.4964192508653471,1.6403129889417911,0.25267398283600895,ale,0
+4.556431901580001,0.35005777018377504,1.387667879302526,0.16516465866368535,stout,0
+4.626124655609613,0.5421125679086513,1.3968074399926442,0.2492380956502293,pilsener,0
+5.0922248334636535,0.0,4.191398820258551,0.0,ale,0
+4.899161690503445,0.06652174305298111,2.4166000367303986,0.03820906442831636,stout,0
+4.6373683941628165,0.5321289055396973,1.8798898050732875,0.28113915432496656,pilsener,1
+4.8181830768302625,0.4765695643174707,1.4128324252706563,0.19492621347795533,ale,0
+5.012838107956776,0.631055749648945,1.7745121853110917,0.29032982541467794,stout,1
+4.554763737504229,0.18602206486404396,3.8238218629564296,0.11818085254069625,pilsener,0
+4.964769112948151,0.3709246362166373,1.4396690807525316,0.1687125166123709,ale,0
+4.718207372012776,0.4868836646441811,0.7744738527949387,0.2651753723070033,stout,0
+4.774682735043104,0.7221175297437538,6.038951894040884,0.33967037395810634,pilsener,1
+5.000278495791396,0.9080130731524192,5.4310499028656265,0.4019055761771045,ale,1
+4.889297359211636,0.2387601176878235,3.7546215325045913,0.11762273322277965,stout,0
+4.810937613328119,0.3810033226801038,1.181885833126207,0.21623715341479488,pilsener,0
+4.9924149023506175,0.5591369578682278,2.2259862755638298,0.2942212847540804,ale,1
+5.367914710211371,0.12357486223202264,5.604502580379269,0.056792446768252375,stout,0
+3.9949659373426516,0.5587634812053074,1.8403826747530576,0.2873699969411529,pilsener,0
+5.378326999718162,0.4764212463533557,6.945111274463347,0.18975624847851,ale,1
+5.861736899569883,0.5545087584614576,1.2503202867274583,0.24201488418423586,stout,1
+4.614829612591472,0.3696172094283488,1.5431065162590059,0.14877686662777231,pilsener,0
+5.2360940115732095,0.0,4.485126680342484,0.0,ale,0
+4.970486555999896,0.2755490180517884,3.1029197403019912,0.16301556981305673,stout,1
+4.838438710861518,0.2830581361303845,0.07443655867224641,0.1811510346305253,pilsener,0
+5.035163956721139,0.6871975345655572,2.3390476693886395,0.3090767345536537,ale,1
+4.8104211022238825,0.2812911297006149,6.044227396773093,0.11990680447427275,stout,1
+5.198248613997872,0.4609744975324848,0.11584346696500615,0.2544099847227109,pilsener,0
+4.9631903390156165,0.3604010481001159,4.515815714581629,0.1667319172121065,ale,1
+4.909282109125602,0.6243517088496764,2.3511877609908653,0.3219190406857753,stout,1
+4.568357036564035,0.6546260049224449,1.063442238215604,0.34143876546676705,pilsener,0
+5.105198628130764,0.3439224253246719,3.4289867526500304,0.13561404366971222,ale,1
+5.263433328468438,0.4478502824554645,5.015493883879213,0.1780178734826449,stout,1
+4.758970880748969,0.557415284097465,1.3358428046209858,0.2672495100254132,pilsener,1
+5.513982007981979,0.17004283678951662,4.093205422998805,0.09921637664659594,ale,1
+4.845636289892032,0.6479722440790142,2.317108711651902,0.3118738071546832,stout,1
+5.563767886924553,0.0,4.1861225213936,0.0,pilsener,0
+5.067743257403525,0.7032498154561616,0.97813000108563,0.3120069748811195,ale,1
+4.948453070151432,0.0,6.316242444294878,0.0,stout,0
+4.74084596392849,0.2635240367311634,4.71345739338376,0.0609712737811886,pilsener,1
+5.035461544615762,0.6058776943442449,1.8012594375973705,0.3217037835162609,ale,1
+4.4229026867133285,0.1726710032400912,7.221284532316514,0.054750573754285985,stout,0
+5.657109757110297,0.5721022713297903,3.5259449184102984,0.29474951437123503,pilsener,1
+4.289039546501086,0.15252146459233518,1.3754041289935612,0.013465117317590205,ale,0
+4.1597747512572685,0.7978215960527519,0.9163704549579376,0.4259705574231032,stout,0
+4.299087895098071,0.6341034975312067,2.406091569614599,0.2548070096422226,pilsener,1
+5.058898998436439,0.1053079901715316,4.3327005180293,0.08776585741923709,ale,0
+4.639916190491344,0.0,0.6556991418389866,0.0,stout,0
+4.99750861197712,0.2485074266624721,3.2841703994082008,0.07858500101380661,pilsener,1
+4.1078737288819935,0.6994387358673055,2.25209918283752,0.29952091677912224,ale,1
+4.059556896306028,0.15698590840532628,1.929391845756277,0.07147363426185585,stout,0
+4.3820738648612245,0.5786039405321955,2.7204889653844395,0.21829954866951934,pilsener,1
+4.587160266365657,0.6381790196024549,5.889957040926497,0.31272559116570514,ale,1
+3.9329826512265056,0.6253760290712681,1.916115809819324,0.3078404367434497,stout,0
+5.129053078389958,0.725591918749949,4.220478412365591,0.3605065284901468,pilsener,1
+4.142898096352629,0.715511774814554,1.6154553665134486,0.28718912881369235,ale,0
+4.311055333806913,0.1040636994710724,1.1383423597056943,0.009246826738128608,stout,0
+4.2170069884183645,0.6123372486100588,0.653603679321312,0.3539533932567204,pilsener,0
+4.284702598577564,1.0801696364991726,1.1929680418002442,0.5353145832327985,ale,1
+4.850163438262958,0.6400127381084793,1.5543330429420243,0.36523001055142135,stout,1
+4.638962265614757,0.1361812037670117,1.0664624096053654,0.044245900694067454,pilsener,0
+4.178136247285695,0.6566818791299842,2.7480810469926924,0.3112970637465925,ale,1
+4.039905740141564,0.7649263559531958,3.126262945032247,0.3783053447388735,stout,1
diff --git a/extra_notebooks/create_datasets.py.ipynb b/extra_notebooks/create_datasets.py.ipynb
index 24c8999add7facd40f3d81b0662aaa00aa2f8b01..d31d7cfc09a9f9ea949c3d42ae3fbe12316ba210 100644
--- a/extra_notebooks/create_datasets.py.ipynb
+++ b/extra_notebooks/create_datasets.py.ipynb
@@ -1517,16 +1517,16 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "a,b,label\r\n",
- "-3.5917816146358463,3.6125988632537553,1\r\n",
- "6.5805856229887265,-2.1055567198515193,1\r\n",
- "-0.6709379386136889,-5.905073992793381,1\r\n",
- "-5.311555272572639,-3.791081462136176,1\r\n",
- "4.299831703773508,6.414946116559263,1\r\n",
- "3.2010167451214593,4.774052598321933,1\r\n",
- "5.820775108310813,2.2239136946409475,1\r\n",
- "4.845673615204521,-5.415136108888261,1\r\n",
- "-4.57686095669072,-3.374526063413908,1\r\n"
+ "a,b,label\n",
+ "-3.5917816146358463,3.6125988632537553,1\n",
+ "6.5805856229887265,-2.1055567198515193,1\n",
+ "-0.6709379386136889,-5.905073992793381,1\n",
+ "-5.311555272572639,-3.791081462136176,1\n",
+ "4.299831703773508,6.414946116559263,1\n",
+ "3.2010167451214593,4.774052598321933,1\n",
+ "5.820775108310813,2.2239136946409475,1\n",
+ "4.845673615204521,-5.415136108888261,1\n",
+ "-4.57686095669072,-3.374526063413908,1\n"
]
}
],
@@ -2141,6 +2141,43 @@
"df.columns"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# one hot encoding"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "features = pd.read_csv(\"../data/beers.csv\")\n",
+ "\n",
+ "style = [[\"pilsener\", \"ale\", \"stout\"][i%3] for i in range(len(features))]\n",
+ "features[\"style\"] = style\n",
+ "features = features[[\"alcohol_content\", \"bitterness\", \"darkness\", \"fruitiness\", \"style\", \"is_yummy\"]]\n",
+ "\n",
+ "\n",
+ "features.head()\n",
+ "\n",
+ "features.to_csv(\"../data/beers_with_style.csv\", index=False)\n",
+ "\n",
+ "y = pd.get_dummies(features[\"style\"], prefix='is')\n",
+ "features = features.drop(\"style\", axis=1)\n",
+ "\n",
+ "features = pd.concat([features, y], axis=1)\n",
+ "\n",
+ "features = features[[\"alcohol_content\", \"bitterness\", \"darkness\", \"fruitiness\", \"is_ale\", \"is_pilsener\", \"is_stout\", \"is_yummy\"]]\n",
+ "\n",
+ "features.to_csv(\"../data/beers_with_one_hot_encoding.csv\", index=False)"
+ ]
+ },
{
"cell_type": "code",
"execution_count": null,
@@ -2165,7 +2202,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.2"
+ "version": "3.7.4"
},
"latex_envs": {
"LaTeX_envs_menu_present": true,
@@ -2200,5 +2237,5 @@
}
},
"nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
}