initial commit

data/faction-picker-bot/model-metrics/alchemists_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea1789786129fce45584c13a3397ee8cb7307db822a1da5fedafb12c18d5eed0
+size 1947

data/faction-picker-bot/model-metrics/auren_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708d7177e927fcf83b3d1f5b1555de2e0c61d3de85cfd8a9dc021ad1a428a01a
+size 1947

data/faction-picker-bot/model-metrics/chaosmagicians_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207ca43e5cba6224b4d5fa094938ad4ae5ddd95cc3d3f3c57e7d26ca9d923b63
+size 1947

data/faction-picker-bot/model-metrics/cultists_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccbe7b1e90ceafdf6b3be34b4fdcb8906e9611aa4d2f8499705994aa18a44641
+size 1947

data/faction-picker-bot/model-metrics/darklings_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e758e197cdda1240b7642bcf510dda63c7a995c1203df043cc87abeb20e4f531
+size 1947

data/faction-picker-bot/model-metrics/dwarves_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7713332a1d047d3429d706782a7273901234f7629e677f969456b9ddfb0255
+size 1947

data/faction-picker-bot/model-metrics/engineers_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d00887350427c6a07fc27bd6f154d7b5e4b804af43e1612bed7203315419b3
+size 1947

data/faction-picker-bot/model-metrics/fakirs_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d812b4bee5209db515f8cc632ff36bfa4edfe3b703f4637f34faadcc47b697fd
+size 1947

data/faction-picker-bot/model-metrics/giants_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c45ff7bcab64efbd907b48f58d180be20508c3e4c35a0a188360571d4c100e9
+size 1947

data/faction-picker-bot/model-metrics/halflings_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47587e688ae79c8054292cb9fc14e83fc0dcad4398e46b01e78329ac6585c1d
+size 1947

data/faction-picker-bot/model-metrics/mermaids_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626399cb4d6513172ca32c191b1ce9171db1ce140b387b3df71c17e42cd9943a
+size 1947

data/faction-picker-bot/model-metrics/nomads_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a15fb6da282e424483732eed52f4b26114ddd2cbe1a02e8576be720d255e36
+size 1947

data/faction-picker-bot/model-metrics/swarmlings_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c999ce2428d138573bc96498b01baed7e59c281e010f1b9bb461e3d0d0ec282
+size 1947

data/faction-picker-bot/model-metrics/witches_results.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2468e77c5d6ca041e56ea1d5dcc97a845f078b871c583b75fc415f0926dad511
+size 1947

data/faction-picker-bot/model_metrics.json

@@ -0,0 +1 @@
+{"alchemists": 17.675128486070648, "auren": 19.080928489227144, "chaosmagicians": 19.46938549474033, "cultists": 19.00761903403616, "darklings": 16.87301997476913, "dwarves": 18.991842395304392, "engineers": 21.028359645696742, "fakirs": 18.156050332057664, "giants": 18.29384343801704, "halflings": 18.85417082077842, "mermaids": 18.28377694840633, "nomads": 18.702529060243318, "swarmlings": 19.15995957442542, "witches": 20.259218473315254}

data/faction-picker-bot/model_plot_data.csv

@@ -0,0 +1,41 @@
+,alchemists,auren,chaosmagicians,cultists,darklings,dwarves,engineers,fakirs,giants,halflings,mermaids,nomads,swarmlings,witches,step
+0,648.7720708898261,669.4489452282111,762.2322533573642,687.0629980348449,639.7082456984546,654.1255021734601,769.6754181350328,642.6044298363403,624.2278894424893,686.3085860437354,678.9587843424483,694.1059542935128,720.396653187467,757.6125769177443,0
+1,637.3292141891817,663.0722057630607,751.8262780416434,679.7462433480741,636.3290969429851,647.3902454701415,760.5686757411795,632.1724146530397,617.2973738377747,679.1175676916363,671.570842531147,689.5701241575272,711.3169576845813,752.9446591114736,1
+2,628.2725551881837,658.9467961797883,746.0067724741028,673.9077085448572,632.8872637124164,639.2284663240579,748.6682432518876,621.8023103502233,612.6221518871562,673.2100309116455,664.3418032889064,684.0621989319749,702.0881635702716,749.853303732407,2
+3,617.711208531599,646.4433189780476,740.3258502240238,667.2427418009195,627.9442074499824,631.9188504209125,739.0720495875825,610.8283683277766,608.7998924897995,665.8745757986458,659.7401246038571,680.2066190896799,692.0503354107688,741.5615639922369,3
+4,610.8450755141429,642.3771791765287,736.3100062635818,662.2796368608252,625.8075722572539,627.5675574623299,731.9591435840516,603.1905874585583,606.4676802427515,661.2280437634356,654.6807792054955,676.7256378644045,686.6179160343556,738.4670791898939,4
+5,603.2528637141353,636.8104731996839,731.4892200411483,658.7132579901624,622.4489802248954,623.6582688298516,727.1503840691779,599.974867643471,602.0871063197523,657.7623058861408,648.9084795493441,674.3350935260501,679.1587907783195,733.4717951335231,5
+6,597.2692380967173,631.9945037573879,728.1821502572217,656.0241083978572,619.2344317589026,618.9268814268202,721.6159320866637,594.7282697176723,599.3486390835214,655.0895771177283,644.1741520099541,671.9830641377272,673.2080561593073,729.4665364366599,6
+7,600.8829869386568,633.5979332321201,730.2221420541675,657.6282171483334,620.3890238213779,620.6746693673872,723.9597810968279,597.7710464807687,601.0434993098472,656.7480858203904,646.257990129086,673.1090865771098,675.687360568262,730.9764432641963,7
+8,596.8236338296165,626.7278948542381,724.1061683489298,654.9736922516416,617.4892588199425,615.0074724890153,719.3601936180125,595.8389315820715,598.3805477827165,653.957173512589,641.9789113638342,671.671134606839,669.5467326719767,725.7868335443956,8
+9,592.3765927504709,620.8355893155724,718.6212922561575,651.1247835501217,614.7286188131098,610.3477911978836,715.5662498595609,590.564653781051,595.6339766951634,650.2205908515215,638.1506368353295,669.3612919664854,664.4636090797732,720.967248481557,9
+10,587.825149451334,617.3216778808569,715.3594046497202,649.3533468576242,612.4308904325915,606.5337985020511,712.215911972959,586.2241728062921,593.710211575739,648.2682138132438,636.1488357976593,667.6478279396249,660.8659426123893,718.1733077875534,10
+11,589.5182163368322,618.322599530766,716.24091343748,650.5309762552923,613.0528500856026,607.7446749208535,713.39385116429,588.1348913466418,593.8867112332022,649.284259099433,636.8567105969262,668.3597789175591,661.5142347432303,719.0651991721768,11
+12,584.9838210241215,615.3303238975622,712.3568357655938,648.3677867295952,611.5258642480559,605.1544918967002,711.3297522323834,584.7641911685396,592.0595044309526,646.5338786027611,634.9173361876275,667.0013329361564,656.4698965785147,716.6395087046192,12
+13,581.5220193508667,612.687737529571,709.2249188959175,647.2204519771175,609.9729586988227,603.4141396215696,709.7467399437463,583.8720383963625,590.0943116032118,644.8813143536664,633.4791594166866,665.7285397205048,652.3835464313739,714.7167386158347,13
+14,578.773183581451,608.9897442173759,706.0335707075503,645.0859489518062,608.4972325666221,600.5133865534436,707.4700605353008,579.7943918707982,589.310660868885,642.3168704457452,630.9613941686544,664.4086658676039,648.8874898647856,711.4844547667986,14
+15,577.2696903958636,607.4567549682497,705.045083412137,644.7757030837558,607.8796773405677,599.3406549700887,706.8446979348059,578.6843042444436,588.7597144196682,641.635309066003,629.251153792108,663.8157777881115,646.2890008235288,709.8728908477798,15
+16,575.664967537361,605.3268825842044,702.6655681486056,643.9843243091183,606.5870193320288,597.0590140880041,705.1798481251435,578.077331410402,588.2782627829613,640.7516781347916,627.6176111005921,663.1656074817056,644.0287351527754,708.1775700455779,16
+17,574.0591198996926,604.0177656683932,700.6290648076781,642.688511914822,605.7629105668955,595.48146235614,704.1845012748911,575.6680845466807,587.632420409432,639.2240420911392,626.51436028497,662.169688713374,642.3709589508904,706.5637306660359,17
+18,572.2630118446893,603.0693974069595,699.140769510253,641.5601613010398,605.1070245064401,594.7047958131006,702.6697533863651,574.0915918266344,586.8975741426962,638.3806205698611,626.0368856083089,661.6694028225465,639.7042418828519,706.0886798120923,18
+19,570.780511823943,601.9249360658484,697.7591876571412,640.254313651557,604.0687566973556,593.1513642279393,701.1905626546211,572.0192029136342,587.0589607140283,637.7367351395895,625.1543805560473,661.0715302527323,637.7178115754689,705.1099707979018,19
+20,571.5127623394145,602.2066149210393,698.177554507262,640.9174857257098,604.3994471059788,593.7178701283473,701.8342946981738,573.1926771402124,586.7743749845421,638.0151495705611,625.742447962035,661.4630435175633,638.2634707279194,705.4841185226455,20
+21,570.5852499511337,600.8043869448671,697.3334805095099,640.9128051119659,604.1749307281642,592.7136779254823,700.8511387823481,572.2458733972068,586.8268888699081,637.4616722160297,625.5606377537314,661.1835278633856,636.8972195601174,704.6122560924734,21
+22,569.7806208324092,599.90113742883,696.1551128032131,640.3206821468891,603.2714080052851,592.2593133905908,700.2874612862214,571.8350377442333,585.3989890912651,636.9061107230797,624.7618150636553,660.7893916430663,635.1917343113911,703.4895087171692,22
+23,568.7909755928669,599.5769911658084,695.31909078836,639.9638595086408,602.9701163283648,591.9984110163101,699.5755363242596,571.3809261055638,585.2410231839682,636.6429799519332,624.5148310562275,660.582051674323,633.9516866664687,703.060368612541,23
+24,567.6804267728196,598.9319716799558,694.2434277968888,639.4015832667063,602.2803937519755,590.6382148608167,698.8578639199657,569.976556868412,585.2237920012386,636.1369521682705,623.6928543633396,660.4643664996307,632.680233576771,702.160759855424,24
+25,566.3629961317681,598.4189891845375,693.3506617174979,639.025092447775,601.7839153317499,589.9435432819197,698.2100681697757,568.4089796785605,585.331743690273,635.6607969966682,623.050887521307,659.9122947686835,631.127273208597,701.4927116991628,25
+26,565.5527632859471,598.4429809352572,692.8788501870138,638.5435200617649,601.3685018755712,588.8884558720987,697.7384744685396,568.5339824835058,585.1429992363101,635.492594732926,622.4663870002253,659.8317848436752,630.0598024898521,701.0862636603699,26
+27,565.8397601754149,598.6968101121863,693.4354138772941,638.7817836988613,601.7114918787605,589.4658715537857,698.02945629981,569.262623788053,584.9416380884509,635.9056737222279,622.8207534306896,659.9385297722687,630.6975487220275,701.5495998951778,27
+28,565.7125477276957,598.3086206438642,692.6343643636384,638.8238784829543,601.7836507626503,589.1290141943938,697.3550263964914,569.6007422490479,584.9418243820081,636.1807172585213,622.2669848468437,659.6076880451526,629.8539466458425,700.959252952045,28
+29,565.3190631380744,598.2314982451803,691.7557767562414,639.0061571292919,601.5335736664177,588.774945489402,696.2776575888688,569.2962429577211,584.5950407561058,635.876114219732,621.9934382631757,659.4105459004777,628.7541217439046,700.2611060857353,29
+30,565.6607404962194,598.2078596172695,691.6410094235471,638.8057240492251,601.5040286971572,589.251040227096,696.5195437506239,569.5111426248332,584.674265011558,635.8254801920561,622.2356251789718,659.3198963600023,629.262750587241,700.4952454542739,30
+31,564.8352672658827,597.0438113858539,691.0833363745967,638.5162433282142,601.4076171335715,589.2415684021477,696.1649428429013,569.33532595307,585.1710120427615,635.5219407322602,621.9623219043755,659.1733542201614,628.7776204852973,700.2555239382336,31
+32,564.0038235848505,595.5834313312713,690.1674443634612,638.5932163281392,601.2296994115135,588.9645804376365,695.6881218774157,569.9177896704355,585.3951505114562,634.8565388862999,621.5750564610103,658.9430354766166,627.9720794623624,700.003036322642,32
+33,564.1186023243777,595.0613450878775,689.5778444314027,638.575201742338,600.955672683097,588.4558147207764,695.2182627139741,569.7066883122773,585.3831374510894,634.2217876174765,621.2938041134965,658.8866896876679,627.2813283021916,699.9300062068482,33
+34,564.4271932300455,595.4123065741094,690.0009873653669,638.5395460754002,601.1574847956921,588.8456443833736,695.4868017534175,569.8773521062257,585.203464159462,634.2892112815317,621.5125404535727,658.9474837616003,627.7048362642913,700.116184273579,34
+35,565.1593146419949,596.4280853428336,690.8691224089195,638.6927156788012,601.789199874673,589.4026992564604,696.0588573359586,570.3160057175952,585.4584624655465,634.7719918673711,621.9995476652037,659.2848590853157,628.871692374401,700.7662095248967,35
+36,565.287716135833,596.3308402460937,690.285698621844,638.441001852567,601.6010914740499,588.6132686431056,695.6184784934085,568.9838410869844,585.3101886566062,634.5754237861742,621.9302525772285,659.0008828880373,628.4542410695352,700.5373798012636,36
+37,564.9020004757136,596.7951775484757,689.7642741663126,638.1490016713188,601.5183423012853,589.0807475133544,694.9370008406274,568.1487237914284,585.4731081178237,634.1572564512918,621.5511189718871,658.5122502226754,628.1867011388488,700.4848173309434,37
+38,564.3730946403289,596.380842209301,689.6779632429117,638.673915659707,601.4216822373772,588.7591993987488,694.9385575981698,568.4993097766853,585.4846341287998,633.8621411462135,620.9935155072978,658.3784424586584,627.6251786254774,700.3609774992724,38
+39,564.574170070073,596.6677276635442,689.6999093078748,638.5724902737153,601.3295513248406,589.1362769648549,695.3030915046879,568.8856420645013,585.3970713823205,633.773920197131,621.0697922396822,658.4158001586013,627.6801250268218,700.5151817938748,39

faction-picker-bot/.ipynb_checkpoints/individual_faction_data-checkpoint.ipynb

@@ -0,0 +1,1087 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "id": "2f27067c-4b22-4f2e-b467-427467475fa6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import math\n",
+    "import time\n",
+    "import yaml\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "id": "df1442eb-fb81-43c5-9b22-2cff7b794da0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'D:\\\\PycharmProjects\\\\TerraBot\\\\faction-picker-bot'"
+      ]
+     },
+     "execution_count": 83,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "_dh[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "id": "708c5ce7-eed3-4449-9140-1f41e8865b66",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['In',\n",
+       " 'Out',\n",
+       " '_',\n",
+       " '_11',\n",
+       " '_12',\n",
+       " '_14',\n",
+       " '_15',\n",
+       " '_17',\n",
+       " '_19',\n",
+       " '_2',\n",
+       " '_20',\n",
+       " '_21',\n",
+       " '_33',\n",
+       " '_34',\n",
+       " '_35',\n",
+       " '_36',\n",
+       " '_37',\n",
+       " '_38',\n",
+       " '_39',\n",
+       " '_40',\n",
+       " '_42',\n",
+       " '_43',\n",
+       " '_44',\n",
+       " '_45',\n",
+       " '_46',\n",
+       " '_47',\n",
+       " '_48',\n",
+       " '_49',\n",
+       " '_50',\n",
+       " '_51',\n",
+       " '_52',\n",
+       " '_53',\n",
+       " '_54',\n",
+       " '_55',\n",
+       " '_56',\n",
+       " '_57',\n",
+       " '_58',\n",
+       " '_59',\n",
+       " '_6',\n",
+       " '_63',\n",
+       " '_64',\n",
+       " '_8',\n",
+       " '_9',\n",
+       " '__',\n",
+       " '___',\n",
+       " '__builtin__',\n",
+       " '__builtins__',\n",
+       " '__doc__',\n",
+       " '__loader__',\n",
+       " '__name__',\n",
+       " '__package__',\n",
+       " '__spec__',\n",
+       " '_dh',\n",
+       " '_i',\n",
+       " '_i1',\n",
+       " '_i10',\n",
+       " '_i11',\n",
+       " '_i12',\n",
+       " '_i13',\n",
+       " '_i14',\n",
+       " '_i15',\n",
+       " '_i16',\n",
+       " '_i17',\n",
+       " '_i18',\n",
+       " '_i19',\n",
+       " '_i2',\n",
+       " '_i20',\n",
+       " '_i21',\n",
+       " '_i22',\n",
+       " '_i23',\n",
+       " '_i24',\n",
+       " '_i25',\n",
+       " '_i26',\n",
+       " '_i27',\n",
+       " '_i28',\n",
+       " '_i29',\n",
+       " '_i3',\n",
+       " '_i30',\n",
+       " '_i31',\n",
+       " '_i32',\n",
+       " '_i33',\n",
+       " '_i34',\n",
+       " '_i35',\n",
+       " '_i36',\n",
+       " '_i37',\n",
+       " '_i38',\n",
+       " '_i39',\n",
+       " '_i4',\n",
+       " '_i40',\n",
+       " '_i41',\n",
+       " '_i42',\n",
+       " '_i43',\n",
+       " '_i44',\n",
+       " '_i45',\n",
+       " '_i46',\n",
+       " '_i47',\n",
+       " '_i48',\n",
+       " '_i49',\n",
+       " '_i5',\n",
+       " '_i50',\n",
+       " '_i51',\n",
+       " '_i52',\n",
+       " '_i53',\n",
+       " '_i54',\n",
+       " '_i55',\n",
+       " '_i56',\n",
+       " '_i57',\n",
+       " '_i58',\n",
+       " '_i59',\n",
+       " '_i6',\n",
+       " '_i60',\n",
+       " '_i61',\n",
+       " '_i62',\n",
+       " '_i63',\n",
+       " '_i64',\n",
+       " '_i65',\n",
+       " '_i66',\n",
+       " '_i67',\n",
+       " '_i68',\n",
+       " '_i69',\n",
+       " '_i7',\n",
+       " '_i70',\n",
+       " '_i71',\n",
+       " '_i72',\n",
+       " '_i73',\n",
+       " '_i74',\n",
+       " '_i75',\n",
+       " '_i76',\n",
+       " '_i8',\n",
+       " '_i9',\n",
+       " '_ih',\n",
+       " '_ii',\n",
+       " '_iii',\n",
+       " '_oh',\n",
+       " 'allmermaids',\n",
+       " 'colnames',\n",
+       " 'each_faction_dataset',\n",
+       " 'exit',\n",
+       " 'faction',\n",
+       " 'faction_dataset',\n",
+       " 'factions',\n",
+       " 'featdf',\n",
+       " 'get_ipython',\n",
+       " 'indexes',\n",
+       " 'indexs',\n",
+       " 'math',\n",
+       " 'np',\n",
+       " 'os',\n",
+       " 'pd',\n",
+       " 'quit',\n",
+       " 'time',\n",
+       " 'vpdf',\n",
+       " 'yaml']"
+      ]
+     },
+     "execution_count": 76,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dir()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 90,
+   "id": "b51ade6d-f3df-4c59-95bb-f1e1df99cf75",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "script_dir = os.path.dirname(_dh[0])\n",
+    "filename = os.path.join(script_dir, 'params.yaml')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 91,
+   "id": "7fdcd13e-011c-4349-86b1-f00098edc00c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'D:\\\\PycharmProjects\\\\TerraBot\\\\params.yaml'"
+      ]
+     },
+     "execution_count": 91,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "filename"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "abc42db1-fdda-48f9-ac22-73ab04e07658",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'yaml' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-2-6d8b02a8dfed>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"../params.yaml\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'r'\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mfd\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m     \u001b[0mparams\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0myaml\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msafe_load\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfd\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m: name 'yaml' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "with open(\"../params.yaml\", 'r') as fd:\n",
+    "    params = yaml.safe_load(fd)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "941150cc-5223-4984-8981-808021c5ce55",
+   "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>Unnamed: 0</th>\n",
+       "      <th>game</th>\n",
+       "      <th>witches</th>\n",
+       "      <th>auren</th>\n",
+       "      <th>swarmlings</th>\n",
+       "      <th>mermaids</th>\n",
+       "      <th>cultists</th>\n",
+       "      <th>halflings</th>\n",
+       "      <th>dwarves</th>\n",
+       "      <th>engineers</th>\n",
+       "      <th>chaosmagicians</th>\n",
+       "      <th>giants</th>\n",
+       "      <th>fakirs</th>\n",
+       "      <th>nomads</th>\n",
+       "      <th>darklings</th>\n",
+       "      <th>alchemists</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0000000001</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>118.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>62.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>050615</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>122.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>0512</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>124.0</td>\n",
+       "      <td>101.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>051501</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>84.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>77.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>72.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>54.0</td>\n",
+       "      <td>78.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>060303</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>108.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>121.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>78.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>128.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111541</th>\n",
+       "      <td>111541</td>\n",
+       "      <td>Youreacrookcaptianhook</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>126.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>105.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>37.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111542</th>\n",
+       "      <td>111542</td>\n",
+       "      <td>YourMomIsAChaosMagician</td>\n",
+       "      <td>112.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>114.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>120.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111543</th>\n",
+       "      <td>111543</td>\n",
+       "      <td>ytuwertqwtr</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>105.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>102.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111544</th>\n",
+       "      <td>111544</td>\n",
+       "      <td>yuertyqert</td>\n",
+       "      <td>128.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>141.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111545</th>\n",
+       "      <td>111545</td>\n",
+       "      <td>ZeicheMasZeuchnis</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>132.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>120.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>111546 rows × 16 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        Unnamed: 0                     game  witches  auren  swarmlings  \\\n",
+       "0                0               0000000001      NaN    NaN         NaN   \n",
+       "1                1                   050615      NaN    NaN         NaN   \n",
+       "2                2                     0512      NaN    NaN         NaN   \n",
+       "3                3                   051501      NaN   84.0         NaN   \n",
+       "4                4                   060303      NaN    NaN         NaN   \n",
+       "...            ...                      ...      ...    ...         ...   \n",
+       "111541      111541   Youreacrookcaptianhook      NaN    NaN       126.0   \n",
+       "111542      111542  YourMomIsAChaosMagician    112.0    NaN       114.0   \n",
+       "111543      111543              ytuwertqwtr      NaN    NaN       105.0   \n",
+       "111544      111544               yuertyqert    128.0    NaN         NaN   \n",
+       "111545      111545        ZeicheMasZeuchnis      NaN    NaN         NaN   \n",
+       "\n",
+       "        mermaids  cultists  halflings  dwarves  engineers  chaosmagicians  \\\n",
+       "0          118.0       NaN       62.0      NaN        NaN             NaN   \n",
+       "1            NaN       NaN        NaN      NaN        NaN             NaN   \n",
+       "2            NaN       NaN        NaN      NaN      124.0           101.0   \n",
+       "3            NaN       NaN       77.0      NaN        NaN            72.0   \n",
+       "4          108.0       NaN        NaN      NaN      121.0             NaN   \n",
+       "...          ...       ...        ...      ...        ...             ...   \n",
+       "111541       NaN       NaN      105.0      NaN        NaN             NaN   \n",
+       "111542       NaN       NaN        NaN      NaN        NaN             NaN   \n",
+       "111543       NaN       NaN        NaN    102.0        NaN             NaN   \n",
+       "111544       NaN       NaN        NaN      NaN        NaN           141.0   \n",
+       "111545       NaN       NaN        NaN    132.0        NaN             NaN   \n",
+       "\n",
+       "        giants  fakirs  nomads  darklings  alchemists  \n",
+       "0          NaN     NaN     NaN        NaN         NaN  \n",
+       "1          NaN     NaN     NaN      122.0         NaN  \n",
+       "2          NaN     NaN     NaN        NaN         NaN  \n",
+       "3          NaN     NaN    54.0       78.0         NaN  \n",
+       "4          NaN    78.0     NaN      128.0         NaN  \n",
+       "...        ...     ...     ...        ...         ...  \n",
+       "111541     NaN     NaN    37.0        NaN         NaN  \n",
+       "111542     NaN     NaN   120.0        NaN         NaN  \n",
+       "111543     NaN     NaN     NaN        NaN         NaN  \n",
+       "111544     NaN     NaN     NaN        NaN         NaN  \n",
+       "111545     NaN     NaN    88.0      120.0         NaN  \n",
+       "\n",
+       "[111546 rows x 16 columns]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vpdf = pd.read_csv('D://PycharmProjects/TerraBot/data/faction-picker-bot/vpdata.csv')\n",
+    "featdf = pd.read_csv('D://PycharmProjects/TerraBot/data/faction-picker-bot/featdata.csv')\n",
+    "\n",
+    "# split in 12 faction data\n",
+    "vpdf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "db0b961f-c751-439d-8583-da459db2d6d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "colnames = list(vpdf.columns)\n",
+    "factions = [x for x in colnames if x != 'game' and x != 'Unnamed: 0']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "657af1ef-3338-4c27-b7a2-dbfe7ab959ed",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0         False\n",
+       "1          True\n",
+       "2          True\n",
+       "3          True\n",
+       "4         False\n",
+       "          ...  \n",
+       "111541     True\n",
+       "111542     True\n",
+       "111543     True\n",
+       "111544     True\n",
+       "111545     True\n",
+       "Name: mermaids, Length: 111546, dtype: bool"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "indexs = pd.isnull(vpdf['mermaids'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "5ed90fe5-75b1-47db-957d-deeeaf750f02",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "allmermaids = vpdf['mermaids'][~indexs]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "788e7f43-8e25-4b53-b4be-98eefee1ae85",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0         118.0\n",
+       "4         108.0\n",
+       "6         104.0\n",
+       "9         106.0\n",
+       "21        140.0\n",
+       "          ...  \n",
+       "111522     98.0\n",
+       "111525     90.0\n",
+       "111535     68.0\n",
+       "111537     85.0\n",
+       "111538    136.0\n",
+       "Name: mermaids, Length: 33442, dtype: float64"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "allmermaids"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "282694f1-2c1a-4b55-920a-791d50ea7946",
+   "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>Unnamed: 0</th>\n",
+       "      <th>game</th>\n",
+       "      <th>r1_SCORE1</th>\n",
+       "      <th>r1_SCORE2</th>\n",
+       "      <th>r1_SCORE3</th>\n",
+       "      <th>r1_SCORE4</th>\n",
+       "      <th>r1_SCORE5</th>\n",
+       "      <th>r1_SCORE6</th>\n",
+       "      <th>r1_SCORE7</th>\n",
+       "      <th>r1_SCORE8</th>\n",
+       "      <th>...</th>\n",
+       "      <th>BON8</th>\n",
+       "      <th>BON9</th>\n",
+       "      <th>BON10</th>\n",
+       "      <th>2players</th>\n",
+       "      <th>3players</th>\n",
+       "      <th>4players</th>\n",
+       "      <th>5players</th>\n",
+       "      <th>map1</th>\n",
+       "      <th>map2</th>\n",
+       "      <th>map3</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0000000001</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>060303</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>6</td>\n",
+       "      <td>070315</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>9</td>\n",
+       "      <td>0pandoraravenclaw</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>21</td>\n",
+       "      <td>16JULY2015</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111522</th>\n",
+       "      <td>111522</td>\n",
+       "      <td>WelcomeFastPlayer</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111525</th>\n",
+       "      <td>111525</td>\n",
+       "      <td>WhatsForLunch</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111535</th>\n",
+       "      <td>111535</td>\n",
+       "      <td>XiangIsDumb</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111537</th>\n",
+       "      <td>111537</td>\n",
+       "      <td>XxxX01</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111538</th>\n",
+       "      <td>111538</td>\n",
+       "      <td>Yellowsubmarine</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>33442 rows × 73 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        Unnamed: 0               game  r1_SCORE1  r1_SCORE2  r1_SCORE3  \\\n",
+       "0                0         0000000001          0          0          0   \n",
+       "4                4             060303          0          1          0   \n",
+       "6                6             070315          0          1          0   \n",
+       "9                9  0pandoraravenclaw          0          1          0   \n",
+       "21              21         16JULY2015          0          0          0   \n",
+       "...            ...                ...        ...        ...        ...   \n",
+       "111522      111522  WelcomeFastPlayer          0          0          0   \n",
+       "111525      111525      WhatsForLunch          0          0          0   \n",
+       "111535      111535        XiangIsDumb          0          0          1   \n",
+       "111537      111537             XxxX01          1          0          0   \n",
+       "111538      111538    Yellowsubmarine          0          0          1   \n",
+       "\n",
+       "        r1_SCORE4  r1_SCORE5  r1_SCORE6  r1_SCORE7  r1_SCORE8  ...  BON8  \\\n",
+       "0               0          0          0          0          1  ...     0   \n",
+       "4               0          0          0          0          0  ...     1   \n",
+       "6               0          0          0          0          0  ...     1   \n",
+       "9               0          0          0          0          0  ...     0   \n",
+       "21              0          1          0          0          0  ...     0   \n",
+       "...           ...        ...        ...        ...        ...  ...   ...   \n",
+       "111522          0          1          0          0          0  ...     1   \n",
+       "111525          0          1          0          0          0  ...     1   \n",
+       "111535          0          0          0          0          0  ...     1   \n",
+       "111537          0          0          0          0          0  ...     1   \n",
+       "111538          0          0          0          0          0  ...     0   \n",
+       "\n",
+       "        BON9  BON10  2players  3players  4players  5players  map1  map2  map3  \n",
+       "0          1      1         1         0         0         0     1     0     0  \n",
+       "4          1      1         0         0         1         0     0     1     0  \n",
+       "6          1      1         0         0         1         0     1     0     0  \n",
+       "9          0      0         1         0         0         0     1     0     0  \n",
+       "21         1      0         0         0         1         0     1     0     0  \n",
+       "...      ...    ...       ...       ...       ...       ...   ...   ...   ...  \n",
+       "111522     1      0         0         0         1         0     1     0     0  \n",
+       "111525     0      0         1         0         0         0     1     0     0  \n",
+       "111535     1      0         0         1         0         0     1     0     0  \n",
+       "111537     0      1         0         1         0         0     1     0     0  \n",
+       "111538     1      1         0         1         0         0     1     0     0  \n",
+       "\n",
+       "[33442 rows x 73 columns]"
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "featdf[~indexs]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "a101ac03-1fe7-452f-a7b2-ad702136de81",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "each_faction_dataset = {}\n",
+    "for faction in factions:\n",
+    "    faction_dataset = {}\n",
+    "    indexes = pd.isnull(vpdf[faction])\n",
+    "    faction_dataset['vp'] = vpdf[faction][~indexes]\n",
+    "    faction_dataset['features'] = featdf[~indexs]\n",
+    "    each_faction_dataset[faction] = faction_dataset\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "60fd33be-c671-4112-9112-22b38df7fe08",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.7.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

faction-picker-bot/.ipynb_checkpoints/make_data-checkpoint.py

@@ -0,0 +1,178 @@
+import pandas as pd
+import numpy as np
+import math
+import time
+
+def main():
+    """This is the script version of creatingVPdata.ipynb for the dvc pipeline."""
+    # load data in
+    folderlocation = "D:/PycharmProjects/TerraBot/terra-mystica"
+    gameevents = pd.read_csv(f'{folderlocation}/game_events.csv')
+    games = pd.read_csv(f'{folderlocation}/games.csv')
+    gameslist = list(pd.unique(gameevents['game']))
+    allfactions = pd.unique(gameevents['faction'])
+    gamescoringtiles = pd.read_csv(f'{folderlocation}/game_scoring_tiles.csv')
+    gameoptions = pd.read_csv(f'{folderlocation}/game_options.csv')
+    stats = pd.read_csv(f'{folderlocation}/stats.csv')
+
+    # two vp dataset functions
+    def makenewdf():
+        """make an empty dataframe, organised in the way we want the target data, ready to be populated"""
+        validfactions = ['witches', 'auren', 'swarmlings', 'mermaids', 'cultists', 'halflings', 'dwarves', 'engineers', 'chaosmagicians', 'giants', 'fakirs', 'nomads', 'darklings', 'alchemists']
+        dfcols = ['game'] + validfactions
+        vpdf = pd.DataFrame(columns=dfcols)
+
+        return vpdf, dfcols, validfactions
+
+    vpdf, dfcols, validfactions = makenewdf()
+
+    def get_vp_from_game(singleGameEvents):
+        """Input game events for a single game. This is a pd.DataFrame.
+        Output a row where each faction in the game has its vp populated (the rest are nans)
+        """
+        newdf = pd.DataFrame([[np.nan] * 15], columns=dfcols)
+
+        # assign the game number
+        gameno = list(pd.unique(singleGameEvents['game']))
+
+        # assert len(gameno) == 1, 'More than 1 unique game was found'
+        try:
+            newdf['game'].replace({np.nan: gameno[0]}, inplace=True)
+        except:
+            print(f'DEBUGGING: len of table is {len(singleGameEvents)}')
+            print(f'DEBUGGING: gamnos list: {gameno}')
+            print(singleGameEvents)
+            raise
+
+        # find factions - there are some artifacts in the data. E.g. the "faction", "all". We need to filter them out.
+        rawfactions = list(pd.unique(singleGameEvents['faction']))
+        verifiedfactions = [rawfaction for rawfaction in rawfactions if rawfaction in validfactions]
+
+        for faction in verifiedfactions:
+            vpfaction = sum(singleGameEvents[(singleGameEvents['event'] == 'vp') & (singleGameEvents['faction'] == faction)]['num'])
+            newdf[faction].replace({np.nan: vpfaction}, inplace=True)
+
+        return newdf
+
+    # two features dataset functions
+    def emptyfeaturesdf():
+        """make an empty dataframe, organised in the way we want the feature data, ready to be populated"""
+        colnames = ['game']
+        uniqueScoreTiles = np.sort(pd.unique(gamescoringtiles['tile']))
+
+        # One-hot of round tiles, for each round
+        for gameround in range(1, 7):
+            roundstr = f'r{gameround}'
+            for tile in uniqueScoreTiles:
+                colnames.append(roundstr + '_' + tile)
+
+        # Boolean of bonus tiles
+        for bon in range(1, 11):
+            colnames.append(f'BON{bon}')
+
+        # One-hot player count (from 2, 3, 4 or 5 players)
+        for player in range(2, 6):
+            colnames.append(f'{player}players')
+
+        # one hot of the map used
+        """126fe960806d587c78546b30f1a90853b1ada468 - map1
+           95a66999127893f5925a5f591d54f8bcb9a670e6 - map2
+           be8f6ebf549404d015547152d5f2a1906ae8dd90 - map3
+        """
+        colnames = colnames + ['map1', 'map2', 'map3']
+
+        featuresdf = pd.DataFrame(columns=colnames)
+
+        return featuresdf, colnames
+
+    featuresdf, featcolnames = emptyfeaturesdf()
+
+    def get_features_from_game(singlegameevents, singlegamemeta, singlegameST, singleendplayers=None):
+        """
+        Inputs:
+            singlegameevents <pd.DataFrame>   - is game events for a single game
+            singlegamemeta   <pd.DataFrame>   - is a single row from `games` that gives map & player count
+            singlegameST     <pd.DataFrame>   - is a single row from `gamescoringtiles` that gives... score tile (suprisingly)
+            singleendplayers <pd.DataFrame>   - is a single row from `end players` that gives the amount of players at end of game, after dropouts
+        Return:          <pd.DataFrame>   - a row where features have been found (will be sparse)
+        """
+        newdf = pd.DataFrame([[0] * len(featcolnames)], columns=featcolnames)
+
+        # assign game string
+        singlegamemeta.iloc[0]['game']
+        newdf['game'].replace({0: singlegamemeta.iloc[0]['game']}, inplace=True)
+
+        # find the round tiles for each round
+        for gameround in range(1, 7):
+            roundstr = f'r{gameround}'
+            scoretile = roundstr + '_' + singlegameST[singlegameST['round'] == gameround]['tile'].values[0]
+            newdf[scoretile].replace({0: 1}, inplace=True)
+
+        # Boolean of bonus tiles
+        uniqueevents = list(pd.unique(singlegameevents['event']))
+        bonustiles = [event[5:] for event in uniqueevents if event.startswith('pass:BON')]
+        for bontile in bonustiles:
+            newdf[bontile].replace({0: 1}, inplace=True)
+
+        # One-hot player count (from 2, 3, 4 or 5 players)
+        if singleendplayers is None:
+            noplayers = singlegamemeta.iloc[0]['player_count']
+            print('gamemeta used for player count')
+        else:
+            noplayers = singleendplayers.iloc[0]['endplayers']
+
+        players = f'{noplayers}players'
+        newdf[players].replace({0: 1}, inplace=True)
+
+        # one hot of the map used
+        mapdict = {'126fe960806d587c78546b30f1a90853b1ada468': 'map1',
+                   '95a66999127893f5925a5f591d54f8bcb9a670e6': 'map2',
+                   'be8f6ebf549404d015547152d5f2a1906ae8dd90': 'map3'
+                   }
+        basemap = singlegamemeta.iloc[0]['base_map']
+        gamemap = mapdict[basemap]
+        newdf[gamemap].replace({0: 1}, inplace=True)
+
+        return newdf
+
+    # filtering
+    # making a dataset for ease
+    data = dict()
+    data['gameevents'] = gameevents
+    data['games'] = games
+    data['gamescoringtiles'] = gamescoringtiles
+
+    def filteringByBadgames(data, badgames):
+        """ Data is a dict containing gameevents, games, gamescoringtiles
+            badgames is a pd.dataframe that contains ['game'] to filter by
+        """
+        gameeventsfil = data['gameevents']
+        gamesfil = data['games']
+        gamescoringtilesfil = data['gamescoringtiles']
+
+        badgameslist = badgames['game']
+        gameeventsfilbefore = len(gameeventsfil)
+        gamesbefore = len(gamesfil)
+        gameSTbefore = len(gamescoringtilesfil)
+
+        gameeventsfil = gameeventsfil[~gameeventsfil['game'].isin(badgameslist)]
+        gamesfil = gamesfil[~gamesfil['game'].isin(badgameslist)]
+        gamescoringtilesfil = gamescoringtilesfil[~gamescoringtilesfil['game'].isin(badgameslist)]
+
+        print(f'game events before: {gameeventsfilbefore}, game events after: {len(gameeventsfil)}, game events removed: {gameeventsfilbefore-len(gameeventsfil)}')
+        print(f'games before: {gamesbefore}, games after: {len(gamesfil)}, games removed: {gamesbefore-len(gamesfil)}')
+        print(f'gameST before: {gameSTbefore}, gameST after: {len(gamescoringtilesfil)}, games removed: {gameSTbefore-len(gamescoringtilesfil)}')
+
+        data['gameevents'] = gameeventsfil
+        data['games'] = gamesfil
+        data['gamescoringtiles'] = gamescoringtilesfil
+
+        return data
+
+    # player count
+    badgames = games[games["player_count"].isin([1, 6, 7])]
+    data = filteringByBadgames(data, badgames)
+
+
+if __name__ == "__main__":
+    main()

faction-picker-bot/.ipynb_checkpoints/shap_metrics-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

faction-picker-bot/.ipynb_checkpoints/testdvc-checkpoint.ipynb

@@ -0,0 +1,44 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "test = pd.DataFrame([[1, 2]], columns=['col1', 'col2'])\n",
+    "test.to_csv('D://PycharmProjects/TerraBot/data/faction-picker-bot/testdvc.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.7.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}