Imagine being hungry in an unfamiliar part of town and getting restaurant recommendations served up, based on your personal preferences, at just the right moment. The recommendation comes with an attached discount from your credit card provider for a local place around the corner!
Right now, Elo, one of the largest payment brands in Brazil, has built partnerships with merchants in order to offer promotions or discounts to cardholders. But do these promotions work for either the consumer or the merchant? Do customers enjoy their experience? Do merchants see repeat business? Personalization is key.
Elo has built machine learning models to understand the most important aspects and preferences in their customers’ lifecycle, from food to shopping. But so far none of them is specifically tailored for an individual or profile. This is where you come in.
In this competition, Kagglers will develop algorithms to identify and serve the most relevant opportunities to individuals, by uncovering signal in customer loyalty. Your input will improve customers’ lives and help Elo reduce unwanted campaigns, to create the right experience for customers.
train.csv
| Columns | Description |
|---|---|
| card_id | Unique card identifier |
| first_active_month | 'YYYY-MM', month of first purchase |
| feature_1 | Anonymized card categorical feature |
| feature_2 | Anonymized card categorical feature |
| feature_3 | Anonymized card categorical feature |
| target | Loyalty numerical score calculated 2 months after historical and evaluation period |
historical_transactions.csv and new_merchant_period.csv
these two files contain the same variable and the difference between the two tables only concern the position with respect to a reference date
| Columns | Description |
|---|---|
| card_id | Card identifier |
| month_lag | month lag to reference date |
| purchase_date | Purchase date |
| authorized_flag | Y' if approved, 'N' if denied |
| category_3 | anonymized category |
| installments | number of installments of purchase |
| category_1 | anonymized category |
| merchant_category_id | Merchant category identifier (anonymized) |
| subsector_id | Merchant category group identifier (anonymized) |
| merchant_id | Merchant identifier (anonymized) |
| purchase_amount | Normalized purchase amount |
| city_id | City identifier (anonymized) |
| state_id | State identifier (anonymized) |
| category_2 | anonymized category |
merchants.csv
| Columns | Description |
|---|---|
| merchant_id | Unique merchant identifier |
| merchant_group_id | Merchant group (anonymized ) |
| merchant_category_id | Unique identifier for merchant category (anonymized ) |
| subsector_id | Merchant category group (anonymized ) |
| numerical_1 | anonymized measure |
| numerical_2 | anonymized measure |
| category_1 | anonymized category |
| most_recent_sales_range | Range of revenue (monetary units) in last active month --> A > B > C > D > E |
| most_recent_purchases_range | Range of quantity of transactions in last active month --> A > B > C > D > E |
| avg_sales_lag3 | Monthly average of revenue in last 3 months divided by revenue in last active month |
| avg_purchases_lag3 | Monthly average of transactions in last 3 months divided by transactions in last active month |
| active_months_lag3 | Quantity of active months within last 3 months |
| avg_sales_lag6 | Monthly average of revenue in last 6 months divided by revenue in last active month |
| avg_purchases_lag6 | Monthly average of transactions in last 6 months divided by transactions in last active month |
| active_months_lag6 | Quantity of active months within last 6 months |
| avg_sales_lag12 | Monthly average of revenue in last 12 months divided by revenue in last active month |
| avg_purchases_lag12 | Monthly average of transactions in last 12 months divided by transactions in last active month |
| active_months_lag12 | Quantity of active months within last 12 months |
| category_4 | anonymized category |
| city_id | City identifier (anonymized ) |
| state_id | State identifier (anonymized ) |
| category_2 | anonymized category |
Root Mean Squared Error (RMSE)
raw_data/: data download from kaggledata/: preprocessed pickle datadeal/: filter/project part of the datafeat/: features we've mademodel/: LightGBM modelprediction/: prediction result
feature.py: building featurestrain_model.py: training model- online
- 0: 5-fold cross-validation
- 1: train model + predict result
- online
Put csv files into raw_data/
- historical_transactions.csv
- merchants.csv
- new_merchant_transactions.csv
- train.csv
- test.csv
python3 feature.pypython3 train_model.py- Elo world - Referenced
- LGB + FE (LB 3.707)
Parameters
seed = 333
EARLY_STOP = 300
OPT_ROUNDS = 691
MAX_ROUNDS = 3000
params = {
'boosting': 'gbdt',
'metric': 'rmse',
'objective': 'regression',
'learning_rate': 0.01,
'max_depth': -1,
'min_child_samples': 20,
'max_bin': 255,
'subsample': 0.85,
'subsample_freq': 10,
'colsample_bytree': 0.8,
'min_child_weight': 0.001,
'subsample_for_bin': 200000,
'min_split_gain': 0,
'reg_alpha': 0,
'reg_lambda': 0,
'num_leaves':63,
'seed': seed,
'nthread': 8
}Features
features: Index(['feature_1', 'feature_2', 'feature_3', 'elapsed_time',
'authorized_flag_mean', 'hist_transactions_count',
'hist_category_1_sum', 'hist_category_1_mean',
'hist_category_2_1.0_mean', 'hist_category_2_2.0_mean',
...
'installments_purchase_amount_max', 'installments_purchase_amount_std',
'city_id_purchase_amount_mean', 'city_id_purchase_amount_min',
'city_id_purchase_amount_max', 'city_id_purchase_amount_std',
'category_1_installments_mean', 'category_1_installments_min',
'category_1_installments_max', 'category_1_installments_std'],
dtype='object', length=161)Training Logs
online = 0: 5-fold cross-validation
[LightGBM] [Info] Total Bins 30298
[LightGBM] [Info] Number of data: 161532, number of used features: 161
[LightGBM] [Info] Total Bins 30298
[LightGBM] [Info] Number of data: 161532, number of used features: 161
[LightGBM] [Info] Total Bins 30298
[LightGBM] [Info] Number of data: 161532, number of used features: 161
[LightGBM] [Info] Total Bins 30298
[LightGBM] [Info] Number of data: 161532, number of used features: 161
[LightGBM] [Info] Total Bins 30298
[LightGBM] [Info] Number of data: 161532, number of used features: 161
[LightGBM] [Info] Start training from score -0.389536
[LightGBM] [Info] Start training from score -0.393868
[LightGBM] [Info] Start training from score -0.396439
[LightGBM] [Info] Start training from score -0.385136
[LightGBM] [Info] Start training from score -0.403205
[50] cv_agg's rmse: 3.75637 + 0.0747325
[100] cv_agg's rmse: 3.71579 + 0.0701915
[150] cv_agg's rmse: 3.69621 + 0.0671517
[200] cv_agg's rmse: 3.68714 + 0.0646511
[250] cv_agg's rmse: 3.6808 + 0.06396
[300] cv_agg's rmse: 3.67668 + 0.0634267
[350] cv_agg's rmse: 3.67342 + 0.0629173
[400] cv_agg's rmse: 3.67098 + 0.0623137
[450] cv_agg's rmse: 3.66922 + 0.061808
[500] cv_agg's rmse: 3.66794 + 0.0613145
[550] cv_agg's rmse: 3.66691 + 0.0611108
[600] cv_agg's rmse: 3.66639 + 0.0610175
[650] cv_agg's rmse: 3.66585 + 0.0606831
[700] cv_agg's rmse: 3.66518 + 0.0606471
[750] cv_agg's rmse: 3.66498 + 0.0604896
[800] cv_agg's rmse: 3.66496 + 0.0602144
[850] cv_agg's rmse: 3.66509 + 0.0600761
[900] cv_agg's rmse: 3.66529 + 0.0601632
[950] cv_agg's rmse: 3.66534 + 0.0602262
[1000] cv_agg's rmse: 3.66567 + 0.0601947
[1050] cv_agg's rmse: 3.66571 + 0.0601137
{'rmse-mean': [3.846791092658889, 3.8440041793576554, 3.841206089451326, 3.838599998200967, 3.836108047410305, 3.83356760403212, 3.8311344841068995, 3.828647541813279, 3.826211584740758, 3.8239014467412376, 3.8214886966966715, 3.8191241747716753, 3.8168672132497137, 3.8145346129526545, 3.8123020068864397, 3.8103104953380913, 3.808302594541594, 3.8062542942725366, 3.8043769729008448, 3.8024235732016756, 3.800384866205588, 3.798277383976221, 3.796379591316074, 3.7944272016538285, 3.792528929879373, 3.7907383124740965, 3.7888782375643637, 3.787122742601393, 3.7854343147544625, 3.783856277342686, 3.7822429141032976, 3.7806495142974774, 3.779084631330572, 3.777545166560324, 3.7759928217230616, 3.7743671542924795, 3.773061956030401, 3.7716766306102327, 3.770222466132619, 3.7688253652105246, 3.7674048476613984, 3.7660395538701814, 3.764810891308044, 3.763497466558255, 3.7622323691769353, 3.760979968339683, 3.759828202743139, 3.758701465007976, 3.757525443918742, 3.756371794380308, 3.7550902444119245, 3.7538963384692097, 3.7527234382489745, 3.7517143620681566, 3.750653218046254, 3.7495870046994533, 3.748457998231742, 3.747288808488112, 3.7462378503098757, 3.7452008013414257, 3.7441865725743897, 3.7431643282383065, 3.7421941091177073, 3.7411322598489867, 3.740195150342637, 3.7394186488420864, 3.7384101780767183, 3.7375047685315934, 3.7366126475995616, 3.735709776860099, 3.73491687685116, 3.734149652971552, 3.733350919753491, 3.7325911561599545, 3.7317258884961433, 3.7310303223092363, 3.7301513612548343, 3.7294408006620587, 3.728825719982139, 3.728086883625381, 3.7273319729526184, 3.726702388498567, 3.726039555397996, 3.725376567656208, 3.724688457114852, 3.7240599817301665, 3.723403287575818, 3.7227888949190318, 3.7220889801614154, 3.7214364374842654, 3.720781348995671, 3.7201529309986725, 3.7195292072273105, 3.7189165611780117, 3.718396101005991, 3.7178316560617213, 3.7173959942237964, 3.716881340699063, 3.7163321586033033, 3.71578956957715, 3.715266835215816, 3.7147712026090844, 3.714225730435367, 3.7136909120568817, 3.7130909136330112, 3.712539787047613, 3.712010950144645, 3.7115639729537113, 3.7110546985829087, 3.7106742013820826, 3.71015789907671, 3.709583867953031, 3.70910467439477, 3.7085966530710683, 3.7081746285164456, 3.707713614805219, 3.707271535590884, 3.7068561026375044, 3.7064356391097086, 3.70600713619078, 3.7056231324985935, 3.705197910338009, 3.704864091289005, 3.70451039897164, 3.704098637339105, 3.703693068090871, 3.7033500259601753, 3.703086072089146, 3.70266105009987, 3.702367538063455, 3.7019518730871317, 3.7015611696312285, 3.70121331759875, 3.7008724225126173, 3.7005491354861064, 3.7001369701667004, 3.6998190999513128, 3.6994286802994303, 3.699139587254327, 3.6988775185199785, 3.6985859132843784, 3.698306030902292, 3.698050706814661, 3.69780329167694, 3.697552324097819, 3.697251565975614, 3.6969763156644477, 3.696726144365038, 3.696491028588081, 3.696212267770862, 3.695944236759535, 3.6957009003030556, 3.69546827229638, 3.695250389315045, 3.695037451485072, 3.6948106539178687, 3.6945621081061146, 3.6943895613328506, 3.6941858114857866, 3.694013746090981, 3.6938448453824577, 3.6935988769929935, 3.693376540801606, 3.6932246421631816, 3.6931140592373692, 3.692893850759254, 3.6928013538121895, 3.6926666617252737, 3.6924518694846626, 3.6922446305407597, 3.692016802775825, 3.691783766796795, 3.691646678727352, 3.691506545060663, 3.6913071568151246, 3.6911337296361966, 3.6909556148719838, 3.6907281176357096, 3.690555994796528, 3.6903893245919677, 3.690171343560274, 3.6899704109320957, 3.6898281383552196, 3.6896106069370673, 3.6894055421682928, 3.689246591338423, 3.6890647401687566, 3.688881151782404, 3.6887101350053917, 3.6884989939409385, 3.6883860315095163, 3.688228410442023, 3.6880806157866717, 3.687924333009639, 3.6877421729022197, 3.6875947370390056, 3.6874915746042056, 3.6873520293232795, 3.6872236736420305, 3.687144832512066, 3.686948253251971, 3.6867676307233084, 3.6865975763215197, 3.686412286058117, 3.686266729987982, 3.6862095050108588, 3.6861139709165145, 3.6859704364679886, 3.685844688692756, 3.685687679524348, 3.68552085035146, 3.685443608545063, 3.6852489069574843, 3.6851013661428262, 3.684932388982496, 3.6848087382673307, 3.684675458279456, 3.684517155006433, 3.68437453464107, 3.684248451325002, 3.6840821390044787, 3.683948221498484, 3.6838074267329945, 3.683693517296085, 3.6834916413555163, 3.683415497158682, 3.6833101586289354, 3.6831314380027003, 3.6829765519786655, 3.6828287894889122, 3.682710985095293, 3.6825883436029736, 3.6825060825014, 3.682415200777619, 3.6823442905297434, 3.6822533591110025, 3.6821543252791242, 3.6820303443366895, 3.6819129124054286, 3.681813188493237, 3.681723428142611, 3.6816490499818997, 3.6815323361417027, 3.6814468313071567, 3.681339337607138, 3.681239147156254, 3.6810697014692657, 3.6809698208416273, 3.6808488869223637, 3.6808048205217636, 3.680735448905453, 3.6806788712226615, 3.6806363219682074, 3.6805047144306826, 3.6804641386363883, 3.6803814021113808, 3.6803127502078503, 3.6802632629518754, 3.680159625892503, 3.6800780478996318, 3.6799862776292436,3.6798809147447513, 3.679760870289857, 3.6796602453268648, 3.6796225653433496, 3.6795390162992554, 3.6794400847305866, 3.679373067695271,3.679311793603074, 3.6792368054084115, 3.679172522113446, 3.679034346433499, 3.678913544989065, 3.67880166370346, 3.6786591097640957, 3.6785747364767554, 3.6784519886088134, 3.678352694079996, 3.6783010619658527, 3.678206651014161, 3.678123695099437, 3.678004496488213, 3.677883006186291, 3.6777407005726688, 3.677684035091519, 3.6775425987997474, 3.6774274732824628, 3.677330623251651, 3.6772847432152758, 3.6772194078525, 3.677179200424534, 3.6771540012434016, 3.6771182769322204, 3.677013743638471, 3.6769573245080034, 3.6769386079276183, 3.67687851940374, 3.6767880549904133, 3.67672177967802, 3.6766750826309305, 3.6765833252543465, 3.676512540506038, 3.676454483771784, 3.6763712358240683, 3.6762988932784295, 3.6762184471998522, 3.676175677164461, 3.6761241343549598, 3.6760945979671398, 3.676032554589406, 3.675992161555226, 3.6759487385937106, 3.675883261634303, 3.67579507485019, 3.675746756947573, 3.6756465387838517, 3.675558563373477, 3.6754812534690586, 3.6754185791897123, 3.6753807889692496, 3.675275397789437, 3.675145160298561, 3.675030303795996, 3.6749793795178336, 3.6749285642213274, 3.6748922851506918, 3.674795133932266, 3.674685907723565, 3.674636101736982, 3.6745957655102273, 3.674470500160865, 3.6743992100734717, 3.6743824859696352, 3.674315861855316, 3.674263600908167, 3.6741708656253502, 3.674107555404683, 3.67405075324845, 3.6740025524880906, 3.673941097672695, 3.673879638350832, 3.6737678818789283, 3.673745761341413, 3.673658794583132, 3.6736011746493618, 3.6735563166893015, 3.67349910727546, 3.6734557441864446, 3.6734403181871813, 3.6734178569854876, 3.6733829310976516, 3.6732818646794656, 3.6732382978277736, 3.6731077778465306, 3.6730373077258704, 3.6729541275632736, 3.6728866265568967, 3.6728550919500713, 3.672830894068548, 3.672788966180024, 3.672744945663672, 3.6726886895544837, 3.672662534512095, 3.67259833685736, 3.672528104053319, 3.672477563191392, 3.6724528521232913, 3.672451953372336, 3.6723774625231456, 3.6723135110662604, 3.672294771891096, 3.672288583393395, 3.672238306060148, 3.6721624838581777, 3.6720955221783824, 3.6720434143235408, 3.6720478553745592, 3.672013255468413, 3.6719728984659605, 3.671896411388457, 3.67185492561904, 3.6717714099453937, 3.6717530616548024, 3.6717507225024333, 3.6717228108655418, 3.671649347993108, 3.6715777345951373, 3.6715586342726025, 3.6715065523120614, 3.6714634441715583, 3.6714259261037308, 3.6713685745873192, 3.67135419550175, 3.671287544757864, 3.67124569445883, 3.671193700100941, 3.6711522699061208, 3.671096291119465, 3.6710341670303395, 3.670983832556833, 3.670973369840142, 3.6709478492776193, 3.670895249961499, 3.6708476462771658, 3.670804229530688, 3.670744239242226, 3.67072994516325, 3.670693931172738, 3.670632994848019, 3.6706000280174265, 3.6705605033943316, 3.670530583311286, 3.670462688449961, 3.6704445731524906, 3.670410823599761, 3.6704105312789714, 3.670378156439333, 3.670332411405429, 3.6702912466672375, 3.6702734199699614, 3.670212987469223, 3.6701521173782874, 3.6701422135529937, 3.670153891227089, 3.6701296578050617, 3.6700752487949266, 3.6700529410885983, 3.670049505553301, 3.670005425944346, 3.669969362424747, 3.669928281008932, 3.6698880390116804, 3.6698535536650825, 3.6698168728484495, 3.669789195855955, 3.6697287520370723, 3.6696635770941426, 3.669601830729932, 3.66954760323989, 3.669511820417239, 3.669459277259667, 3.669442955464332, 3.6694294441339137, 3.6694491748324545, 3.6694245563099237, 3.6694085079387593, 3.669382544194776, 3.6693415242639973, 3.669290407572192, 3.6692189146234684, 3.669164511316312, 3.669104292242411, 3.6690854290220876, 3.66903617148619, 3.6690121197217733, 3.6689610352430213, 3.6689468250299315, 3.668928357618113, 3.6689264173404026, 3.668924521212334, 3.6688926995935427, 3.668873786227709, 3.6688267956415705, 3.668802686002922, 3.668769525287341, 3.668718434007425, 3.6687316308923386, 3.668714445823774, 3.668708052625702, 3.6686748807327922, 3.66865795258864, 3.668606420878067, 3.6685748578472337, 3.668553310280436, 3.668532612118316, 3.6685068534890624, 3.66847405784011, 3.668444724684001, 3.6683942345675256, 3.66838236915775, 3.668341772779393, 3.6683017296854543, 3.6682934361436326, 3.668261006467888, 3.668249696333681, 3.6682505195055035, 3.668231757636954, 3.668239750415195, 3.668187736549613, 3.6682104787368544, 3.6682040108383944, 3.668151968242958, 3.6681085802310562, 3.6680968376427083, 3.6680916257719374, 3.6680632459395013, 3.668013167506468, 3.6679920587276165, 3.667956825261706, 3.6679381713503125, 3.6678833117829965, 3.6678594130142828, 3.667808381035365, 3.6678161412715027, 3.667790239113804, 3.667789123991895, 3.6677876884690783, 3.6677671278240593, 3.6677759772137932, 3.667750317245923, 3.6677387029851287, 3.6677218157951073, 3.667698226231741, 3.6676731940841956, 3.6676300722226465, 3.667615953082496, 3.6676068596849043, 3.6675790012702043, 3.667569811370292, 3.667546032628781, 3.667520832336205, 3.6675185455589356, 3.6674958910679196, 3.667502617467604, 3.6674923381993048, 3.667471399064901, 3.6674314902622953, 3.6673900652705647, 3.667379546396939, 3.6673402897279863, 3.6673070836679784, 3.66727763242742, 3.6672977541019405, 3.667246714399554, 3.6671954677371934, 3.6671624693657123, 3.667110293181697, 3.667104211321162, 3.6670799416166466, 3.667033969648564, 3.6670262221513896, 3.6670030365973845, 3.667006434175454, 3.667001353994248, 3.666947531615507, 3.666952091585985, 3.6669387710255847, 3.666932861479208, 3.6669010254335754, 3.666913110091804, 3.666862701856556, 3.666903574576807,3.666937911897078, 3.66690840488681, 3.666898613805585, 3.666860049147931, 3.666824514449348, 3.666799446605405, 3.666805523590903, 3.6668142762160243, 3.6667861340274603, 3.666747361510262, 3.6667124244675704, 3.6666917671789627, 3.6666761804415025, 3.666666110562919, 3.6666340171049634, 3.6666420559943935, 3.6666372789427144, 3.6666224097147655, 3.6666249588256017, 3.666607654063718, 3.666621612287315, 3.6666348382264253, 3.6666105891623495, 3.6665993484532082, 3.6666052296743006, 3.6665845404495947, 3.66656255246061, 3.666587090861905, 3.666579707183943, 3.666563139950032, 3.666585192248527, 3.666598743375, 3.6666164297685184, 3.6665915452492484, 3.666563701071327, 3.66658961447916, 3.6665658529780374, 3.666567880615434, 3.6665431981537986, 3.6665146695174484, 3.6665168265383103, 3.666507166341127, 3.666495743157988, 3.666474102881692, 3.666460011264153, 3.6664377019152297, 3.6664100624192697, 3.66639038732283, 3.666359715840765, 3.666312606638231,3.6662856436282225, 3.666261156416348, 3.6662563436581435, 3.6662352271421197, 3.6662389242862745, 3.666199700965607, 3.6661592013698843,3.666162083358053, 3.666151192499663, 3.6661441116423914, 3.666156489272653, 3.666147230695303, 3.666160814307645, 3.666181875294769, 3.666165885751422, 3.6661479335344844, 3.6661750508546276, 3.666200232103436, 3.6661835199161317, 3.6661725869601574, 3.6661773740483192, 3.6661837954407517, 3.6661936443911536, 3.6661864082723334, 3.666185250975502, 3.6661895580115207, 3.6661753377064903, 3.6661525033661824, 3.6661001525432995, 3.6660885680308426, 3.6660628738332877, 3.6660365221951094, 3.6660246280154944, 3.666002741382448, 3.6659867554468106, 3.665959194333074, 3.6659158640371223, 3.6658853095689103, 3.6658560017402437, 3.6658405919000487, 3.6658505203094136, 3.6658237062961367, 3.6658253392252518, 3.6658207135886167, 3.66583078804006, 3.6658388777163182, 3.665829000809449, 3.665849970289888, 3.6658034987805808, 3.665760193816856, 3.6657371682704976, 3.6657072433731144, 3.665681988226305, 3.6656858945103736, 3.6656655144661867, 3.6656322739971423, 3.665614742841362, 3.665598126307791, 3.6655956147657234, 3.665586740167563, 3.66557503600309, 3.6655693715969777, 3.665558370477112, 3.6655320665898303, 3.665552877253488, 3.665534189235745, 3.665521974171353, 3.665527253614818, 3.6655054048626745, 3.665507222372214, 3.665465440051919, 3.6654469930180076, 3.6654346253551195, 3.665397564463705, 3.665377960076166, 3.6653807811956063, 3.6653633095123217, 3.665354480892783, 3.6653600612511674, 3.6653424011209017, 3.665309357746368, 3.6653408346199554, 3.6653401099991614, 3.6653092761493595, 3.665301330721676, 3.6652952425064513, 3.6652947904526543, 3.665293717260995, 3.665289403883604, 3.6652662206516586, 3.665272893119892, 3.665239651269812, 3.6652435447789236, 3.665206897389262, 3.665187741510196, 3.6651509151163695, 3.6651463291239907, 3.6651762632383673, 3.6651721996059328, 3.665177058868241, 3.6651522575993964, 3.665173974374844, 3.6651563322255525, 3.665134165569655, 3.6651345313402595, 3.66513593112368, 3.6651244767588294, 3.665065001698271, 3.66506298623053, 3.6650807880502847, 3.665076627439131, 3.6650900079694226, 3.665059540650946,3.665064060489115, 3.6650598651374304, 3.665064430760141, 3.6650463180429944, 3.6650168729340296, 3.6650476231661315, 3.6650439735142846,3.6650138012172357, 3.665020826286843, 3.665026255461787, 3.66503143572348, 3.665034062903035, 3.665053720526617, 3.665085138607465, 3.66510851306293, 3.665120066622799, 3.6651063286671013, 3.6650996930960416, 3.6650986831485626, 3.6651179116628425, 3.6650924586473757, 3.6650918146151232, 3.6651036723142005, 3.6650845357798283, 3.665051200615018, 3.6650437107534417, 3.665024652602719, 3.6650347407081805, 3.66499764324578, 3.6649878519573074, 3.664975026456318, 3.6649805312769623, 3.664965288181399, 3.66495804626265, 3.6649787462464274, 3.6650113550598973, 3.664998944477766, 3.6650316859789362, 3.6650542590272766, 3.6650570879864537, 3.6650763688374135, 3.6650838850272836, 3.6651036219127704, 3.6651058493189814, 3.665106418498161, 3.6650975908572834, 3.6650920516985197, 3.665121300749314, 3.6651139368219203, 3.665104768294244, 3.665121470650567, 3.6651447602756138, 3.665159849654471, 3.6651751804959063, 3.6651867467623567, 3.6651757380210555, 3.6651552991956238, 3.6651296909963804, 3.6650980759792597, 3.665068926108033, 3.6650681524667603, 3.6650289135491425, 3.6650247655607515, 3.6650139758670646, 3.6650226363136262, 3.6650408295559678, 3.665028958992136, 3.665050514055841, 3.665022472477981, 3.665037519263977, 3.664997980790494, 3.6649926703830618, 3.664977627008296, 3.6649791369278804, 3.6649473513551585], 'rmse-stdv': [0.07931041092630824, 0.07920690593281034, 0.07909851701638253, 0.07888677810824593, 0.07877046642777405, 0.07868026256901398, 0.07859517392364368, 0.07845560033084185, 0.07838260933262627, 0.07826933484232712, 0.078132355490509, 0.07802811022836982, 0.07799031240955123, 0.07775556012105743, 0.07773302457385509, 0.07766457338477921, 0.0776568426734956, 0.0775381861651184, 0.07747966009843012, 0.07742317860027784, 0.07729641391664734, 0.07721275040386988, 0.07713558172439063, 0.0770600898612606, 0.07693720839047885, 0.07692208171199723, 0.07691340839872497, 0.07686743980918471, 0.07675933341460986, 0.07668385648141647, 0.07670217366346385, 0.07652299922857692, 0.07647519252666982, 0.076308743557145, 0.07625123522162722, 0.07623163290638356, 0.07617608542404122, 0.07611712223947575, 0.07603423721028475, 0.07594518665433038, 0.07586384808443952, 0.07587690705099716, 0.07586940893593058, 0.07565737679482923, 0.07553549618590046, 0.07527214526697204, 0.07510008164902975, 0.07495366716976935, 0.07480766844252741, 0.07473245831548744, 0.07462370042042019, 0.0744295816436547, 0.07443930290900039, 0.07428770827957612, 0.07422458003036102, 0.07412112642510646, 0.07400039827958672, 0.07392062544172077, 0.07383919294920079, 0.07379132489969983, 0.07379623913313636, 0.07378178375058575, 0.07365114545838232, 0.07354977491284133, 0.07337983161713459, 0.0732433218261337, 0.07314170762418244, 0.07306905670320983, 0.07302330414741436, 0.07286395952592488, 0.07272923121687011, 0.0726459815583192, 0.07249650500297654, 0.07241288658308995, 0.07230648267533336, 0.07221778741677404, 0.07210614306503677, 0.0720028653794281, 0.07195093931448804, 0.07184894359472167, 0.07187651225008203, 0.07168295021528795, 0.0716206864682124, 0.07152084118621528, 0.07142267032507887, 0.07125533621320192, 0.07125333744376597, 0.07125045826796282, 0.07125512017016249, 0.07112203500080347, 0.07106646236286468, 0.07097255535136762, 0.07078849583858217, 0.0706597722982641, 0.07059553047144138, 0.07051634089880066, 0.07042384399496092, 0.07041234413082756, 0.07030454395251091, 0.07019154731260382, 0.07008312570955762, 0.07001091650313053, 0.06998099412812961, 0.06988153253135547, 0.06978075639748224, 0.06969949460368638, 0.06956250197421135, 0.06960394986643985, 0.06955995149385402, 0.06956736833696076, 0.06952211108768985, 0.06942407744520468, 0.069382251063055, 0.06939905631502909, 0.06929379527803091, 0.06915479858764932, 0.06910367700810793, 0.06909908430184493, 0.06905289715360996, 0.06891481165830368, 0.06884440643695236, 0.06876727397789142, 0.06881752268568779, 0.06879732872923182, 0.06880199545176403, 0.06876610832434965, 0.06876907543936855, 0.06873455617126792, 0.06881468092808771, 0.0687336586401322, 0.06871926343224302, 0.06866543884272376, 0.06847860088049885, 0.06847756794932869, 0.06844523420533298, 0.06832410650600919, 0.06822878727511805, 0.06807641035413928, 0.06803303569490404, 0.06796062713102549, 0.06785119238029429, 0.06777762216011593, 0.06772297857092577, 0.06763115815059798, 0.0675323243819175, 0.06746376568396895, 0.06744401600189744, 0.06740038379712293, 0.0672368246179285, 0.06715169045750874, 0.0670781542773098, 0.06699698975798508, 0.06687441376781758, 0.06685817809859353, 0.06682437590355254, 0.06673556775059555, 0.06666329054541746, 0.06656514955202622, 0.06651784831469382, 0.06638299529173491, 0.06628823953641805, 0.06624279935676242, 0.06614979581561099, 0.06607969899721995, 0.06603514904760625, 0.06597054978107579, 0.06592064146886713, 0.06581107863604695, 0.06581126620499755, 0.06573045572218618, 0.0656951964776434, 0.06568886203445141, 0.06562058394620872, 0.06562297782421185, 0.06561603730840998, 0.06554375268058199, 0.06545756094190822, 0.06544189275299367, 0.06535784188155051, 0.06533880901250395, 0.06526606266316998, 0.06525819832381281, 0.06520173502195079, 0.06516545166422316, 0.0651788456712322, 0.06511256188792325, 0.06508118688234649, 0.0650396148543542, 0.06503278763631688, 0.06508062883507168, 0.06504671518505395, 0.06492956822372398, 0.0648900745763215, 0.06481883523724609, 0.06481607760170972, 0.06477757179821661, 0.06471487702311587, 0.06468268876419225, 0.06464873183572374, 0.06465113403596394, 0.06459536408369539, 0.06457063463223843, 0.06448155187092561, 0.06451933064510643, 0.06451026812909774, 0.0644503087650833, 0.06443913109717662, 0.06435522956733684, 0.0642739781271579, 0.06422762355238716, 0.06420628003794294, 0.06417507684980704, 0.06414488378418592, 0.06411824147903988, 0.06413337606193312, 0.06411019210385656, 0.0641214793397865, 0.06417881606047637, 0.0641909835535811, 0.0641867797171103, 0.06417355231646793, 0.06409053134449964, 0.06409266234375141, 0.06403689414154426, 0.06405709466205672, 0.0640491885902071, 0.06404630914365947, 0.06401709869131175, 0.06403058368611271, 0.0639772068647033, 0.06397007118391625, 0.06398243759449752, 0.06396034914734301, 0.06394736015277949, 0.0639405283501696, 0.06396032287155357, 0.06399617375721411, 0.06397865790196307, 0.06395655116823713, 0.06396641137711864, 0.06392405951791637, 0.0639076415295798, 0.063963464294579, 0.06401022357962426, 0.06402564439447464, 0.06399279894801797, 0.06396605339508399, 0.06396798039375293, 0.06393752871220654, 0.06395999704840355, 0.06396405969842028, 0.06391594720946628, 0.06390127436428963, 0.0638841358303242, 0.06382420344293721, 0.06386092275901702, 0.06383769344222374, 0.06384233830174219, 0.0637995909767737, 0.0637695419750689, 0.06374108574727172, 0.06371938554124397, 0.06369584224832464, 0.06375509580496411, 0.06380904877440616, 0.06378225806023809, 0.0637494029268553, 0.0637599483303033, 0.06375043874254419, 0.06368442085241127, 0.06370045098770254, 0.0636664754300372, 0.06365088987194432, 0.06364979370656844, 0.06368542847278807, 0.06371707683786915, 0.06366305546979302, 0.06364344983667145, 0.06362497765460512, 0.06359227607046815, 0.06356449518793232, 0.06358451739068398, 0.06358819234781987, 0.06361218013000758, 0.06363795386334999, 0.06366473393099602, 0.06365789191840174, 0.06367500046636773, 0.0636946391324315, 0.06370247865254494, 0.06371667623337876, 0.06365932312268796, 0.06360467290563668, 0.06358864746988649, 0.06354738168679916, 0.06355220844737385, 0.06349378839544728, 0.06347153155694112, 0.06344565087925368, 0.06342674191555583, 0.06340195785930822, 0.0633821181959605, 0.06330527447543084, 0.06329543651552678, 0.0633050523150944, 0.06326052718817037, 0.06326321120430299, 0.0632059816495398, 0.06318020929975708, 0.0631882521942194, 0.06317059535998898, 0.06317505851231695, 0.06315734671958488, 0.06313738760827083, 0.06306916786014617, 0.06307813997963777, 0.06305750658847811, 0.06306050549329363, 0.06304850328342167, 0.06301404005298929, 0.06300106083573571, 0.06301346883478467, 0.06303125833676673, 0.06304652622002972, 0.0630155597516176, 0.06300987855905928, 0.06294605246738061, 0.06293383477419533, 0.0628783492078818, 0.06286770322289781, 0.06293282957641522, 0.06294199480506504, 0.06296140317216412, 0.06297124011259822, 0.0629384596622589, 0.06297694790563878, 0.06296325237934676, 0.06294133927678958, 0.0629193978665398, 0.06296325136645806, 0.06300220382172084, 0.06297200675788824, 0.06293551123393039, 0.06293197792613146, 0.0629147353713099, 0.06294428231334376, 0.06294925394267363, 0.06292003919956429, 0.06293104017095894, 0.06291728162681196, 0.06287220789693486, 0.06288106626386326, 0.06285260270661151, 0.062845104577393, 0.0628088570008898, 0.06274798568171104, 0.06273981271358757, 0.06269890597877051, 0.06270058906948506, 0.06265615393303305, 0.06265429872774955, 0.06266019778217018, 0.06261051344455697, 0.06263166647070637, 0.06270858009808533, 0.06269552362105897, 0.06267488455894897, 0.06267871968773148, 0.06264953751113898, 0.06267483344407679, 0.06269181631872411, 0.06274132379350603, 0.0627756241978542, 0.06278907042868852, 0.06273867561792829, 0.06273737897830009, 0.06273454828096922, 0.06271708424670483, 0.06272710319662499, 0.06273953027614637, 0.06271536523583075, 0.06266600148287822, 0.06268432083045086, 0.0626885635921372, 0.06268059479089856, 0.06262998137553989, 0.0625833946176769, 0.06257365142878622, 0.06256916689154494, 0.06255118590659442, 0.06256528705423635, 0.06253803126708432, 0.06253066713792547, 0.06251694022561766, 0.06251939065354627, 0.062469047648191486, 0.062462372188757255, 0.06244154490514718, 0.06238726285361589, 0.06231371494285115, 0.06229582109026003, 0.06229915522587306, 0.062321899614500076, 0.06233346548769044, 0.062300678543250464, 0.062302665701734955, 0.06229729299712619, 0.0622955690284105, 0.06227516474291276, 0.06228971332496101, 0.06229508334403869, 0.06232455515188602, 0.062317284522257294, 0.06231194649018429, 0.06229895249522079, 0.0622971348123528, 0.06231024708096255, 0.062320487098785834, 0.062331666633788925, 0.06236123198876739, 0.062328973856765425, 0.06229992551771514, 0.06233709460084829, 0.06230730802661221, 0.06231508298198461, 0.06232058960832423, 0.062274185787696425, 0.06222412079669852, 0.06217910500060761, 0.062176207122274355, 0.06216365250130667, 0.06213579605515021, 0.06211492765561657, 0.06209340054217239, 0.06210098780928776, 0.06206433029847696, 0.06204136494453992, 0.062020853917852586, 0.06202604994610573, 0.062008967156386895, 0.06198836280123066, 0.061970808909142985, 0.061954662425101906, 0.06195777185009929, 0.06194506590740291, 0.06189977281216914, 0.06186702999033739, 0.0618459226640462, 0.06182877355689507, 0.06180803316257944, 0.061796282434218426, 0.06179608313863866, 0.06178618351960974, 0.061796485347020334, 0.061737525178680495, 0.06174548126189098, 0.0617249893501992, 0.06174983393051202, 0.06175505698383936, 0.06174365155758735, 0.061751210896560674, 0.06172209184289181, 0.06173417567067261, 0.06174704867331639, 0.0617323714565574, 0.06169673590268312, 0.06168620472698347, 0.061664805373162705, 0.06167689072256763, 0.06168481093872368, 0.061640683109201594, 0.061613928532610364, 0.06158732498316064, 0.061551916736568395, 0.06153013966550687, 0.0615197904223706, 0.06151301456425142, 0.06148674236750895, 0.06148815398837537, 0.061450644079553585, 0.061460894982239465, 0.06146556102304928, 0.06148891486238816, 0.061465239853048914, 0.061474241512476935, 0.06148401139652955, 0.061498412067142565, 0.06146000077969304, 0.061419579794991574, 0.061386854324383906, 0.061352261723002864, 0.061315884695370956, 0.06127799430751481, 0.06129936524563021, 0.06131601884739799, 0.061286134930679824, 0.06132387263560751, 0.06132503946324379, 0.06133038690956843, 0.061314547785367934, 0.06128833589384549, 0.061244974125699285, 0.06122479246189142, 0.06123800099408173, 0.06124895501657323, 0.061264286696428374, 0.061262877731518686, 0.06123880139852852, 0.06124279943249819, 0.06120885742775494, 0.061163824258030644, 0.06119601824170859, 0.06121282443744989, 0.06123891718337786, 0.06124266765659468, 0.06125008169721782, 0.06124553812345482, 0.061315149173016406, 0.06130969302347866, 0.061297232864233914, 0.06130440270814449, 0.06129762689807777, 0.061304737912735455, 0.061329058135717415, 0.06135113856297154, 0.06134053837791483, 0.06136993945748697, 0.061397801918918735, 0.0613912919338384, 0.061395471017487074, 0.0613837895593469, 0.0613718638796695, 0.061329326444369524, 0.06130922221518882, 0.06131095058942261, 0.0613302255975771, 0.06128867763308319, 0.06124358891960497, 0.06124166993825233, 0.061215557267587734, 0.06121928787226501, 0.06121165368531067, 0.061185366522850754, 0.06116901579965842, 0.06112815057449232, 0.0611410860284327, 0.06111455935942073, 0.06113223361670805, 0.06113817317112277, 0.06111075775641813, 0.061094271411253516, 0.061105653243061664, 0.061117275658450404, 0.06107934050527011, 0.06107045300838932, 0.06105712653178953, 0.061054488536542925, 0.06104444906545307, 0.061042687509948006, 0.06105258061796575, 0.06106373102404292,0.06107697515755152, 0.061038880966672905, 0.061022844317926254, 0.06100156412048075, 0.06098562274384361, 0.060974304591601934, 0.060971472317740326, 0.06101161674557252, 0.06101566167174485, 0.06101169270304892, 0.06099212317884583, 0.06100107575214925, 0.06100982794949751, 0.061007597438213955, 0.0609951666969438, 0.061023501887482165, 0.0610432966662379, 0.06105300987545295, 0.06103041959547268, 0.06101949414233413, 0.06098579876995218, 0.06098371058172654, 0.060966865750357285, 0.06096140734728738, 0.060926095983351046, 0.06089655505687029,0.06088810890484515, 0.06090782604914856, 0.060911788877035085, 0.06091906806309084, 0.06092969206353124, 0.06095321309121441, 0.06092270613936314, 0.06093844716455778, 0.060934185576441466, 0.06095848564537609, 0.06096359396825747, 0.060977184093724685, 0.061017450784654294, 0.06101053069125206, 0.06097235329637615, 0.06099549274904125, 0.060960385168178796, 0.06097765628424448, 0.06096964410543264, 0.06094652238372381, 0.060972204652507266, 0.0609779009753731, 0.060983993301206726, 0.0609834098329587, 0.06096532812078977, 0.06098112685397411, 0.06096383436348536, 0.06094895851154943, 0.06099170998202262, 0.0609746653058523, 0.06098507628490904, 0.06094697418244816, 0.06086984513711718, 0.06086784302902802, 0.06083745849422474, 0.06081310995893908, 0.06083782755870717, 0.060846501090353784, 0.06084634676567408, 0.06085747280467526, 0.06084849069600456, 0.06085422812260339, 0.060859394320753255, 0.06083903280545984, 0.060863983365511264, 0.06081876228969147, 0.06083695985125946, 0.06082677144692669, 0.060795335138041744, 0.06077880041785745, 0.06076398520659111, 0.06077435040342423, 0.06074784676056305, 0.06075679567171416, 0.06072556896814232, 0.06075193588119813, 0.060759832725304, 0.06072837294538868, 0.06074006712569503, 0.06072439195952892, 0.06071239943046766, 0.06070662956942947, 0.06068311895815334, 0.060680240767792666, 0.060685430593611776, 0.060669357808261354, 0.060689021608511244, 0.06068741771698748, 0.060682282801688074, 0.06069442884812372, 0.06070572091229592, 0.06072336191543669, 0.060738359716835076, 0.06076584823387941, 0.0607644568726263, 0.06076052866962052, 0.06078140735858508, 0.060793202120871005, 0.06079430250289489, 0.060817050299927414, 0.060796568070700455, 0.06080727419010952, 0.060820341627604656, 0.060816098896227945, 0.06084269869540958, 0.06084902687070403, 0.060819035690068815, 0.06082554400595899, 0.06080810219507775, 0.060801459322100855, 0.060810185954512375, 0.060795312255858595, 0.060801261618240454, 0.06078190661234788, 0.06074375346709775, 0.06075512529174697, 0.06073753105650308, 0.060736309605306356, 0.060696478385595685, 0.060690940404088796, 0.06066962859014833, 0.06062008440952685, 0.0606307476882179, 0.06061358026930564, 0.06059439466207298, 0.06060751517528783, 0.06063815848646656, 0.060615230820537706, 0.060641259572885874, 0.06062863271111946, 0.06063168573328826, 0.06065022657126427, 0.0606470689591999, 0.0606265507352707, 0.06061748176074948, 0.06060409058513166, 0.06057602890861767, 0.06055892697155751, 0.060567290899493385, 0.060552041360019675, 0.06053995862742951, 0.060530473740840945, 0.06053840172368208, 0.0605406230919433, 0.06053797006915977, 0.06053406417327716, 0.06055717540792762, 0.06059701800287594, 0.060569731734045715, 0.06058487654352979, 0.06056322065840739, 0.06053911428622848, 0.06054930685786003, 0.060533340362870114, 0.06056726399745214, 0.06055354632800221, 0.060530027195155774, 0.06051744732453805, 0.06052703315621592, 0.0605510537907219, 0.06055440416310998, 0.060527163497347616, 0.06051135723048723, 0.06050895585232583, 0.06052307239578646, 0.06053755486699781, 0.060517268744579036, 0.06053265646751285, 0.06051813293528566, 0.06052544581459705, 0.060523201054944804, 0.06053618384172529, 0.06052749157185034, 0.06052845776752201, 0.0605162646426093, 0.0605014250795538, 0.060493779567637865, 0.06049011675783695, 0.06049093237578379, 0.06050625462660343, 0.06048494813172184, 0.06048108002245098, 0.06048961482014331, 0.06047476158344083, 0.060451639741426574, 0.060433860196174756, 0.06043849346881115, 0.060403880918533846, 0.060379767027471394, 0.06036702730801588, 0.06031528200064098, 0.06031569409177476, 0.060303674577549926, 0.06032691597420693, 0.06030762265322313, 0.060302190383396195, 0.06028916312996075, 0.060288341667752245, 0.0603008322636515, 0.060309317769401564, 0.06032147101556946, 0.0603215516468106, 0.06033352324589672, 0.06033075583154857, 0.060310175453628746, 0.06029677889297209, 0.06027829518676438, 0.06029917151280519, 0.060313224620580225, 0.06033630388731373, 0.06030636765265159, 0.060321420235596605, 0.060312791805371954, 0.06028624068771449, 0.06028255053154871, 0.0602517815450513, 0.06022873794017447, 0.06023939217293422, 0.06021451153790995, 0.060209163474974806, 0.060215834322063976, 0.06022739487192495, 0.06023233504456186]}
[LightGBM] [Info] Total Bins 30206
[LightGBM] [Info] Number of data: 151437, number of used features: 161
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/lightgbm/basic.py:752: UserWarning: categorical_feature in param dict is overridden.
warnings.warn('categorical_feature in param dict is overridden.')
[LightGBM] [Info] Start training from score -0.385543
Training until validation scores don't improve for 300 rounds.
[20] train's rmse: 3.73268 valid's rmse: 3.93332
[40] train's rmse: 3.67434 valid's rmse: 3.90038
[60] train's rmse: 3.62643 valid's rmse: 3.87638
[80] train's rmse: 3.5851 valid's rmse: 3.8586
[100] train's rmse: 3.54945 valid's rmse: 3.84536
[120] train's rmse: 3.51763 valid's rmse: 3.83526
[140] train's rmse: 3.48927 valid's rmse: 3.82804
[160] train's rmse: 3.46371 valid's rmse: 3.82288
[180] train's rmse: 3.44067 valid's rmse: 3.8179
[200] train's rmse: 3.41878 valid's rmse: 3.81444
[220] train's rmse: 3.4002 valid's rmse: 3.81142
[240] train's rmse: 3.38171 valid's rmse: 3.80832
[260] train's rmse: 3.36452 valid's rmse: 3.80626
[280] train's rmse: 3.34937 valid's rmse: 3.80481
[300] train's rmse: 3.33371 valid's rmse: 3.80289
[320] train's rmse: 3.31954 valid's rmse: 3.80129
[340] train's rmse: 3.30582 valid's rmse: 3.79949
[360] train's rmse: 3.29265 valid's rmse: 3.79876
[380] train's rmse: 3.28022 valid's rmse: 3.7971
[400] train's rmse: 3.26854 valid's rmse: 3.79627
[420] train's rmse: 3.25736 valid's rmse: 3.79522
[440] train's rmse: 3.24642 valid's rmse: 3.79481
[460] train's rmse: 3.23632 valid's rmse: 3.79442
[480] train's rmse: 3.22665 valid's rmse: 3.79349
[500] train's rmse: 3.21596 valid's rmse: 3.79271
[520] train's rmse: 3.20662 valid's rmse: 3.7924
[540] train's rmse: 3.19818 valid's rmse: 3.79214
[560] train's rmse: 3.1886 valid's rmse: 3.79188
[580] train's rmse: 3.17928 valid's rmse: 3.79179
[600] train's rmse: 3.17019 valid's rmse: 3.79153
[620] train's rmse: 3.16159 valid's rmse: 3.79093
[640] train's rmse: 3.15195 valid's rmse: 3.79108
[660] train's rmse: 3.14403 valid's rmse: 3.79087
[680] train's rmse: 3.13594 valid's rmse: 3.79066
[700] train's rmse: 3.12764 valid's rmse: 3.79058
[720] train's rmse: 3.1189 valid's rmse: 3.79098
[740] train's rmse: 3.11117 valid's rmse: 3.79109
[760] train's rmse: 3.10327 valid's rmse: 3.79106
[780] train's rmse: 3.09654 valid's rmse: 3.79144
[800] train's rmse: 3.0884 valid's rmse: 3.79145
[820] train's rmse: 3.08165 valid's rmse: 3.79141
[840] train's rmse: 3.07428 valid's rmse: 3.79161
[860] train's rmse: 3.06665 valid's rmse: 3.79141
[880] train's rmse: 3.05866 valid's rmse: 3.7914
[900] train's rmse: 3.0525 valid's rmse: 3.79157
[920] train's rmse: 3.04489 valid's rmse: 3.79182
[940] train's rmse: 3.03753 valid's rmse: 3.79218
[960] train's rmse: 3.03115 valid's rmse: 3.79213
[980] train's rmse: 3.02477 valid's rmse: 3.79201
Early stopping, best iteration is:
[691] train's rmse: 3.13174 valid's rmse: 3.79041
OPT_ROUNDS: 691online = 1: submission
- output
- model
- importance of feature
- submit csv
[LightGBM] [Info] Total Bins 30298
[LightGBM] [Info] Number of data: 201917, number of used features: 161
[LightGBM] [Info] Start training from score -0.393636
[100] train's rmse: 3.61348
[200] train's rmse: 3.49735
[300] train's rmse: 3.42535
[400] train's rmse: 3.365
[500] train's rmse: 3.31827
[600] train's rmse: 3.27806Score on Kaggle (root mean squared error): 3.702