IIS/assets/mlflow/research.ipynb

import os


from sklearn.model_selection import train_test_split
import pandas as pd
import numpy

from sklearn.preprocessing import StandardScaler, OrdinalEncoder, OneHotEncoder

from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression
from catboost import CatBoostRegressor

from sklearn.metrics import mean_absolute_percentage_error, mean_absolute_error, mean_squared_error

df = pd.read_pickle('data/clean_data.pkl').sample(frac=0.1, random_state = 2) # Уменьшаем размер чтобы модель быстрее обучалась на лекции
df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 547701 entries, 313199 to 690900
Data columns (total 13 columns):
 #   Column         Non-Null Count   Dtype   
---  ------         --------------   -----   
 0   price          547701 non-null  int64   
 1   date           547701 non-null  object  
 2   time           547701 non-null  object  
 3   geo_lat        547701 non-null  float32 
 4   geo_lon        547701 non-null  float32 
 5   region         547701 non-null  category
 6   building_type  547701 non-null  category
 7   level          547701 non-null  int8    
 8   levels         547701 non-null  int8    
 9   rooms          547701 non-null  int8    
 10  area           547701 non-null  float16 
 11  kitchen_area   547701 non-null  float16 
 12  object_type    547701 non-null  category
dtypes: category(3), float16(2), float32(2), int64(1), int8(3), object(2)
memory usage: 26.1+ MB

df = df.rename(columns={'price': 'target'})
df = df.drop(columns=['date', 'time'])

df

	target	geo_lat	geo_lon	region	building_type	level	levels	rooms	area	kitchen_area	object_type
313199	4999999	59.958458	30.215530	2661	3	8	13	1	36.00000	7.199219	1
2437764	2150000	45.072674	41.936996	2900	3	5	5	1	52.00000	15.000000	1
4949072	8600000	59.939358	30.437069	2661	2	11	22	1	37.09375	9.796875	1
4109465	5100000	59.740479	30.569540	2661	1	2	9	3	74.50000	9.500000	1
2187702	3470000	56.324062	44.005390	2871	2	11	26	2	54.00000	8.000000	11
...	...	...	...	...	...	...	...	...	...	...	...
5188085	2300000	57.750603	40.866467	4189	3	2	3	1	38.00000	11.000000	1
4542014	6700000	55.911720	37.737419	81	3	2	5	2	66.37500	8.000000	1
3306731	3850000	51.704510	39.273037	2072	2	10	18	3	89.50000	14.203125	1
520293	1878885	54.943577	82.958862	9654	1	1	10	3	87.75000	12.921875	11
690900	4097350	59.882702	30.451246	2661	2	6	23	1	36.09375	16.203125	11

547701 rows × 11 columns

X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df['target'], test_size=0.25, random_state=2)

X_train.iloc[0]

geo_lat            56.327686
geo_lon            43.928062
region           2871.000000
building_type       1.000000
level               8.000000
levels             10.000000
rooms               2.000000
area               56.000000
kitchen_area        8.500000
object_type         1.000000
Name: 879487, dtype: float64

cat_features = X_train.select_dtypes(include=['category','object']).columns.to_list()
cat_features

['region', 'building_type', 'object_type']

num_features = X_train.select_dtypes(include=['number']).columns.to_list()
num_features

['geo_lat', 'geo_lon', 'level', 'levels', 'rooms', 'area', 'kitchen_area']

https://scikit-learn.org/stable/api/sklearn.preprocessing.html - разные способы кодирования и скалирования

s_scaler = StandardScaler()
l_encoder = OrdinalEncoder(handle_unknown='use_encoded_value', unknown_value=99999999) # unknown_value нужно выбирать с умом
regressor = CatBoostRegressor()

Column transformer

# Для удобной работы со столбцами
preprocessor = ColumnTransformer(
    transformers=[
        ('num', s_scaler, num_features),  # преобразования для числовых признаков
        ('cat', l_encoder, cat_features), # преобразования для категориальных признаков
    ],
    remainder='drop' ) # Удаляем столбцы, которые не затронуты преобразования

pipeline = Pipeline(steps=[('preprocessor', preprocessor), 
                           ('model', regressor)])

pipeline.fit(X_train, y_train)

Learning rate set to 0.105957
0:	learn: 22102085.4544239	total: 67.8ms	remaining: 1m 7s
1:	learn: 21994630.3403412	total: 87.1ms	remaining: 43.4s
2:	learn: 21906687.8196027	total: 105ms	remaining: 34.8s
3:	learn: 21834890.5050552	total: 124ms	remaining: 30.9s
4:	learn: 21770820.6751194	total: 143ms	remaining: 28.5s
5:	learn: 21719543.9330108	total: 163ms	remaining: 27s
6:	learn: 21676510.1666598	total: 183ms	remaining: 25.9s
7:	learn: 21641355.8079016	total: 202ms	remaining: 25.1s
8:	learn: 21612289.0494648	total: 223ms	remaining: 24.5s
9:	learn: 21583808.7061085	total: 242ms	remaining: 24s
10:	learn: 21559288.9618040	total: 266ms	remaining: 23.9s
11:	learn: 21537048.9920531	total: 286ms	remaining: 23.5s
12:	learn: 21444526.1629239	total: 306ms	remaining: 23.3s
13:	learn: 21426349.3370315	total: 324ms	remaining: 22.8s
14:	learn: 21411901.2338278	total: 344ms	remaining: 22.6s
15:	learn: 21399279.8023459	total: 360ms	remaining: 22.1s
16:	learn: 21299421.1434822	total: 382ms	remaining: 22.1s
17:	learn: 21288560.2595435	total: 400ms	remaining: 21.8s
18:	learn: 21277368.8876877	total: 421ms	remaining: 21.8s
19:	learn: 21229205.2938305	total: 441ms	remaining: 21.6s
20:	learn: 21220238.4828158	total: 462ms	remaining: 21.5s
21:	learn: 21212849.7885410	total: 485ms	remaining: 21.6s
22:	learn: 21205304.4132821	total: 507ms	remaining: 21.5s
23:	learn: 21198813.8508479	total: 534ms	remaining: 21.7s
24:	learn: 21184627.2326983	total: 550ms	remaining: 21.4s
25:	learn: 21172748.3410688	total: 569ms	remaining: 21.3s
26:	learn: 21103305.4766520	total: 582ms	remaining: 21s
27:	learn: 21096636.4037750	total: 594ms	remaining: 20.6s
28:	learn: 21082202.2892557	total: 607ms	remaining: 20.3s
29:	learn: 21077185.5274954	total: 619ms	remaining: 20s
30:	learn: 21071613.1691098	total: 632ms	remaining: 19.7s
31:	learn: 21067654.8502386	total: 644ms	remaining: 19.5s
32:	learn: 21053425.8947843	total: 659ms	remaining: 19.3s
33:	learn: 21038024.0563140	total: 670ms	remaining: 19s
34:	learn: 20961357.9814339	total: 682ms	remaining: 18.8s
35:	learn: 20946027.4479676	total: 695ms	remaining: 18.6s
36:	learn: 20866676.4104322	total: 707ms	remaining: 18.4s
37:	learn: 20863078.3182449	total: 717ms	remaining: 18.1s
38:	learn: 20859910.3609500	total: 728ms	remaining: 17.9s
39:	learn: 20853462.2703730	total: 739ms	remaining: 17.7s
40:	learn: 20851610.3209036	total: 749ms	remaining: 17.5s
41:	learn: 20847674.0809285	total: 760ms	remaining: 17.3s
42:	learn: 20845384.9263391	total: 772ms	remaining: 17.2s
43:	learn: 20843256.7428906	total: 784ms	remaining: 17s
44:	learn: 20841580.8594834	total: 797ms	remaining: 16.9s
45:	learn: 20819301.2718345	total: 810ms	remaining: 16.8s
46:	learn: 20812094.5913582	total: 823ms	remaining: 16.7s
47:	learn: 20808932.0866915	total: 834ms	remaining: 16.5s
48:	learn: 20763172.9200413	total: 851ms	remaining: 16.5s
49:	learn: 20729084.6574594	total: 863ms	remaining: 16.4s
50:	learn: 20721820.5403996	total: 876ms	remaining: 16.3s
51:	learn: 20715664.3732084	total: 887ms	remaining: 16.2s
52:	learn: 20712658.7025295	total: 897ms	remaining: 16s
53:	learn: 20704254.1704930	total: 908ms	remaining: 15.9s
54:	learn: 20690967.9220470	total: 919ms	remaining: 15.8s
55:	learn: 20686546.8978473	total: 929ms	remaining: 15.7s
56:	learn: 20682362.4255777	total: 941ms	remaining: 15.6s
57:	learn: 20680744.8113421	total: 951ms	remaining: 15.4s
58:	learn: 20677926.0871267	total: 962ms	remaining: 15.3s
59:	learn: 20658478.3098789	total: 974ms	remaining: 15.3s
60:	learn: 20641964.4472246	total: 987ms	remaining: 15.2s
61:	learn: 20639551.4216654	total: 999ms	remaining: 15.1s
62:	learn: 20638344.8919341	total: 1.01s	remaining: 15s
63:	learn: 20635991.3894815	total: 1.02s	remaining: 15s
64:	learn: 20595846.8116432	total: 1.03s	remaining: 14.9s
65:	learn: 20592198.9483046	total: 1.05s	remaining: 14.8s
66:	learn: 20565316.0060422	total: 1.06s	remaining: 14.8s
67:	learn: 20563073.6783517	total: 1.07s	remaining: 14.7s
68:	learn: 20553650.4649650	total: 1.08s	remaining: 14.6s
69:	learn: 20545510.8230653	total: 1.09s	remaining: 14.5s
70:	learn: 20544114.9272186	total: 1.1s	remaining: 14.5s
71:	learn: 20541689.8802451	total: 1.11s	remaining: 14.4s
72:	learn: 20538792.7074671	total: 1.13s	remaining: 14.3s
73:	learn: 20517134.0713648	total: 1.14s	remaining: 14.3s
74:	learn: 20510477.9089445	total: 1.15s	remaining: 14.2s
75:	learn: 20494649.9067257	total: 1.17s	remaining: 14.2s
76:	learn: 20490851.9879851	total: 1.18s	remaining: 14.1s
77:	learn: 20488939.9621874	total: 1.19s	remaining: 14.1s
78:	learn: 20432532.8171644	total: 1.2s	remaining: 14s
79:	learn: 20428397.7107150	total: 1.22s	remaining: 14s
80:	learn: 20421638.7734419	total: 1.23s	remaining: 13.9s
81:	learn: 20421021.7388457	total: 1.24s	remaining: 13.9s
82:	learn: 20406404.2376730	total: 1.26s	remaining: 13.9s
83:	learn: 20021682.5008511	total: 1.28s	remaining: 13.9s
84:	learn: 20018322.6048631	total: 1.3s	remaining: 14s
85:	learn: 20004841.3476490	total: 1.31s	remaining: 14s
86:	learn: 19985666.0092745	total: 1.33s	remaining: 13.9s
87:	learn: 19983778.1947243	total: 1.34s	remaining: 13.9s
88:	learn: 19982460.1107908	total: 1.36s	remaining: 13.9s
89:	learn: 19979128.5494690	total: 1.37s	remaining: 13.8s
90:	learn: 19974094.9707357	total: 1.38s	remaining: 13.8s
91:	learn: 19972006.9431031	total: 1.4s	remaining: 13.8s
92:	learn: 19970846.2845466	total: 1.41s	remaining: 13.7s
93:	learn: 19968858.0073042	total: 1.42s	remaining: 13.7s
94:	learn: 19921720.6252972	total: 1.44s	remaining: 13.7s
95:	learn: 19916568.5707839	total: 1.45s	remaining: 13.6s
96:	learn: 19913228.5247508	total: 1.46s	remaining: 13.6s
97:	learn: 19901982.4625895	total: 1.48s	remaining: 13.6s
98:	learn: 19836107.7247888	total: 1.49s	remaining: 13.6s
99:	learn: 19834724.7455166	total: 1.5s	remaining: 13.5s
100:	learn: 19832811.9745741	total: 1.52s	remaining: 13.5s
101:	learn: 19818491.2851567	total: 1.53s	remaining: 13.5s
102:	learn: 19815779.3719026	total: 1.55s	remaining: 13.5s
103:	learn: 19814215.0962787	total: 1.56s	remaining: 13.5s
104:	learn: 19782274.6892663	total: 1.57s	remaining: 13.4s
105:	learn: 19777945.6507456	total: 1.59s	remaining: 13.4s
106:	learn: 19770488.9772154	total: 1.6s	remaining: 13.4s
107:	learn: 19769758.0023174	total: 1.61s	remaining: 13.3s
108:	learn: 19767541.9303017	total: 1.63s	remaining: 13.3s
109:	learn: 19766992.0126300	total: 1.64s	remaining: 13.2s
110:	learn: 19765032.8837298	total: 1.65s	remaining: 13.2s
111:	learn: 19705204.6771073	total: 1.66s	remaining: 13.2s
112:	learn: 19703649.0394020	total: 1.68s	remaining: 13.2s
113:	learn: 19693038.0415419	total: 1.69s	remaining: 13.1s
114:	learn: 19690294.4304072	total: 1.7s	remaining: 13.1s
115:	learn: 19686529.4709294	total: 1.71s	remaining: 13.1s
116:	learn: 19684887.8267152	total: 1.72s	remaining: 13s
117:	learn: 19369465.6970761	total: 1.74s	remaining: 13s
118:	learn: 19368868.0416380	total: 1.75s	remaining: 13s
119:	learn: 19334590.5868513	total: 1.77s	remaining: 13s
120:	learn: 19332200.0832597	total: 1.78s	remaining: 12.9s
121:	learn: 19320130.9244745	total: 1.79s	remaining: 12.9s
122:	learn: 19318220.9448337	total: 1.81s	remaining: 12.9s
123:	learn: 18941546.2095714	total: 1.82s	remaining: 12.9s
124:	learn: 18941056.2836883	total: 1.84s	remaining: 12.9s
125:	learn: 18939637.9662976	total: 1.85s	remaining: 12.8s
126:	learn: 18938172.4621610	total: 1.86s	remaining: 12.8s
127:	learn: 18935889.3619752	total: 1.88s	remaining: 12.8s
128:	learn: 18928784.7025346	total: 1.9s	remaining: 12.8s
129:	learn: 18926981.6933453	total: 1.91s	remaining: 12.8s
130:	learn: 18830178.3173696	total: 1.93s	remaining: 12.8s
131:	learn: 18828102.3918672	total: 1.94s	remaining: 12.8s
132:	learn: 18825755.9987015	total: 1.95s	remaining: 12.7s
133:	learn: 18793049.5462155	total: 1.97s	remaining: 12.7s
134:	learn: 18791452.8400128	total: 1.98s	remaining: 12.7s
135:	learn: 18484591.4924421	total: 1.99s	remaining: 12.7s
136:	learn: 18482373.1605741	total: 2s	remaining: 12.6s
137:	learn: 18414571.2543321	total: 2.02s	remaining: 12.6s
138:	learn: 18412913.4160574	total: 2.03s	remaining: 12.6s
139:	learn: 18409214.1141794	total: 2.04s	remaining: 12.6s
140:	learn: 18395140.1008086	total: 2.06s	remaining: 12.5s
141:	learn: 18390939.2248151	total: 2.07s	remaining: 12.5s
142:	learn: 18377925.8298573	total: 2.08s	remaining: 12.5s
143:	learn: 18371775.1291009	total: 2.09s	remaining: 12.4s
144:	learn: 18370251.1042623	total: 2.1s	remaining: 12.4s
145:	learn: 18332707.1499911	total: 2.12s	remaining: 12.4s
146:	learn: 18330693.2665230	total: 2.13s	remaining: 12.3s
147:	learn: 18329408.2952767	total: 2.14s	remaining: 12.3s
148:	learn: 18321783.9892793	total: 2.15s	remaining: 12.3s
149:	learn: 18321270.4958267	total: 2.16s	remaining: 12.2s
150:	learn: 18310325.1681801	total: 2.17s	remaining: 12.2s
151:	learn: 18299986.9413893	total: 2.18s	remaining: 12.2s
152:	learn: 18290217.7479708	total: 2.2s	remaining: 12.2s
153:	learn: 18280975.8537910	total: 2.21s	remaining: 12.1s

154:	learn: 18272215.6509019	total: 2.22s	remaining: 12.1s
155:	learn: 18263878.2178516	total: 2.23s	remaining: 12.1s
156:	learn: 18256009.4859248	total: 2.25s	remaining: 12.1s
157:	learn: 18248529.7799856	total: 2.26s	remaining: 12.1s
158:	learn: 18241388.0845094	total: 2.28s	remaining: 12s
159:	learn: 18234700.5127085	total: 2.29s	remaining: 12s
160:	learn: 18228095.5839778	total: 2.3s	remaining: 12s
161:	learn: 18222087.5153066	total: 2.31s	remaining: 12s
162:	learn: 18215963.2971261	total: 2.33s	remaining: 12s
163:	learn: 18210272.5545163	total: 2.34s	remaining: 11.9s
164:	learn: 18208920.7703569	total: 2.35s	remaining: 11.9s
165:	learn: 18204704.7145239	total: 2.37s	remaining: 11.9s
166:	learn: 18187135.8260335	total: 2.38s	remaining: 11.9s
167:	learn: 18183064.7135734	total: 2.39s	remaining: 11.9s
168:	learn: 18177887.1670860	total: 2.41s	remaining: 11.8s
169:	learn: 18173022.2110313	total: 2.42s	remaining: 11.8s
170:	learn: 18168573.4167384	total: 2.44s	remaining: 11.8s
171:	learn: 18165036.1971623	total: 2.45s	remaining: 11.8s
172:	learn: 18161841.9822954	total: 2.46s	remaining: 11.8s
173:	learn: 18129860.2061383	total: 2.48s	remaining: 11.8s
174:	learn: 18127931.5161091	total: 2.49s	remaining: 11.7s
175:	learn: 18124997.7778403	total: 2.5s	remaining: 11.7s
176:	learn: 18122975.2084322	total: 2.51s	remaining: 11.7s
177:	learn: 18120855.5325733	total: 2.53s	remaining: 11.7s
178:	learn: 18117907.6019994	total: 2.54s	remaining: 11.7s
179:	learn: 18116674.0864027	total: 2.56s	remaining: 11.7s
180:	learn: 18114086.9287957	total: 2.57s	remaining: 11.6s
181:	learn: 18087100.0827926	total: 2.59s	remaining: 11.6s
182:	learn: 18071944.2213105	total: 2.6s	remaining: 11.6s
183:	learn: 17952691.4261792	total: 2.61s	remaining: 11.6s
184:	learn: 17950298.6715866	total: 2.63s	remaining: 11.6s
185:	learn: 17949031.8169417	total: 2.64s	remaining: 11.6s
186:	learn: 17937943.5186847	total: 2.66s	remaining: 11.5s
187:	learn: 17937014.8027177	total: 2.67s	remaining: 11.5s
188:	learn: 17936493.5945773	total: 2.68s	remaining: 11.5s
189:	learn: 17935386.0093649	total: 2.69s	remaining: 11.5s
190:	learn: 17934203.8644718	total: 2.7s	remaining: 11.5s
191:	learn: 17928336.5184065	total: 2.72s	remaining: 11.4s
192:	learn: 17925443.1940046	total: 2.73s	remaining: 11.4s
193:	learn: 17924535.5533845	total: 2.75s	remaining: 11.4s
194:	learn: 17917225.8802206	total: 2.76s	remaining: 11.4s
195:	learn: 17904437.4148190	total: 2.77s	remaining: 11.4s
196:	learn: 17902915.3467923	total: 2.79s	remaining: 11.4s
197:	learn: 17900924.7512305	total: 2.8s	remaining: 11.3s
198:	learn: 17899976.2262471	total: 2.81s	remaining: 11.3s
199:	learn: 17896573.5977064	total: 2.83s	remaining: 11.3s
200:	learn: 17894480.1301072	total: 2.84s	remaining: 11.3s
201:	learn: 17891369.5414483	total: 2.85s	remaining: 11.3s
202:	learn: 17853776.3679239	total: 2.86s	remaining: 11.2s
203:	learn: 17851457.0828592	total: 2.88s	remaining: 11.2s
204:	learn: 17849621.6767992	total: 2.89s	remaining: 11.2s
205:	learn: 17848392.5509482	total: 2.9s	remaining: 11.2s
206:	learn: 17845597.2428619	total: 2.91s	remaining: 11.1s
207:	learn: 17841951.2763157	total: 2.92s	remaining: 11.1s
208:	learn: 17829332.8912371	total: 2.93s	remaining: 11.1s
209:	learn: 17825984.1152963	total: 2.95s	remaining: 11.1s
210:	learn: 17821360.2498463	total: 2.96s	remaining: 11.1s
211:	learn: 17816041.9633158	total: 2.97s	remaining: 11s
212:	learn: 17815089.0154101	total: 2.98s	remaining: 11s
213:	learn: 17812260.4222221	total: 2.99s	remaining: 11s
214:	learn: 17811642.1796060	total: 3s	remaining: 11s
215:	learn: 17811104.8656724	total: 3.01s	remaining: 10.9s
216:	learn: 17810456.2984828	total: 3.02s	remaining: 10.9s
217:	learn: 17809982.4909707	total: 3.04s	remaining: 10.9s
218:	learn: 17809543.7803178	total: 3.05s	remaining: 10.9s
219:	learn: 17809136.8325569	total: 3.06s	remaining: 10.9s
220:	learn: 17808758.7315278	total: 3.07s	remaining: 10.8s
221:	learn: 17808406.9145618	total: 3.09s	remaining: 10.8s
222:	learn: 17806754.0179687	total: 3.1s	remaining: 10.8s
223:	learn: 17806262.4885592	total: 3.11s	remaining: 10.8s
224:	learn: 17805319.3776209	total: 3.13s	remaining: 10.8s
225:	learn: 17805011.6013482	total: 3.14s	remaining: 10.7s
226:	learn: 17804724.0362310	total: 3.15s	remaining: 10.7s
227:	learn: 17793961.7547867	total: 3.16s	remaining: 10.7s
228:	learn: 17793044.3976904	total: 3.18s	remaining: 10.7s
229:	learn: 17791876.3449986	total: 3.19s	remaining: 10.7s
230:	learn: 17770039.2877531	total: 3.21s	remaining: 10.7s
231:	learn: 17769759.3423197	total: 3.22s	remaining: 10.7s
232:	learn: 17769498.1846872	total: 3.23s	remaining: 10.6s
233:	learn: 17769106.6516586	total: 3.24s	remaining: 10.6s
234:	learn: 17765866.7512613	total: 3.25s	remaining: 10.6s
235:	learn: 17763818.0836765	total: 3.27s	remaining: 10.6s
236:	learn: 17761637.5687877	total: 3.29s	remaining: 10.6s
237:	learn: 17755293.6166299	total: 3.3s	remaining: 10.6s
238:	learn: 17749597.6285121	total: 3.32s	remaining: 10.6s
239:	learn: 17731193.4780969	total: 3.33s	remaining: 10.6s
240:	learn: 17730941.1840209	total: 3.35s	remaining: 10.5s
241:	learn: 17730651.4109866	total: 3.36s	remaining: 10.5s
242:	learn: 17729951.1772204	total: 3.38s	remaining: 10.5s
243:	learn: 17725674.6169533	total: 3.39s	remaining: 10.5s
244:	learn: 17724397.3837970	total: 3.41s	remaining: 10.5s
245:	learn: 17723085.9667878	total: 3.42s	remaining: 10.5s
246:	learn: 17716068.0643361	total: 3.44s	remaining: 10.5s
247:	learn: 17685621.7941613	total: 3.45s	remaining: 10.5s
248:	learn: 17684272.6716694	total: 3.46s	remaining: 10.4s
249:	learn: 17683390.0888279	total: 3.48s	remaining: 10.4s
250:	learn: 17683052.4845925	total: 3.49s	remaining: 10.4s
251:	learn: 17678624.0868252	total: 3.51s	remaining: 10.4s
252:	learn: 17665657.9640584	total: 3.52s	remaining: 10.4s
253:	learn: 17664624.5487132	total: 3.54s	remaining: 10.4s
254:	learn: 17663925.0646167	total: 3.55s	remaining: 10.4s
255:	learn: 17653813.6196925	total: 3.56s	remaining: 10.4s
256:	learn: 17636698.5157040	total: 3.58s	remaining: 10.3s
257:	learn: 17634671.9750893	total: 3.59s	remaining: 10.3s
258:	learn: 17633930.6422340	total: 3.61s	remaining: 10.3s
259:	learn: 17633026.0861171	total: 3.62s	remaining: 10.3s
260:	learn: 17632489.1254856	total: 3.63s	remaining: 10.3s
261:	learn: 17628474.9187765	total: 3.65s	remaining: 10.3s
262:	learn: 17627320.9817928	total: 3.66s	remaining: 10.3s
263:	learn: 17626116.4772868	total: 3.67s	remaining: 10.2s
264:	learn: 17623329.0754817	total: 3.69s	remaining: 10.2s
265:	learn: 17622243.1901613	total: 3.7s	remaining: 10.2s
266:	learn: 17550321.8250878	total: 3.71s	remaining: 10.2s
267:	learn: 17549755.3651767	total: 3.73s	remaining: 10.2s
268:	learn: 17545607.1212430	total: 3.74s	remaining: 10.2s
269:	learn: 17541242.2629221	total: 3.75s	remaining: 10.1s
270:	learn: 17499407.7313592	total: 3.76s	remaining: 10.1s
271:	learn: 17499145.8282321	total: 3.77s	remaining: 10.1s
272:	learn: 17498934.5535116	total: 3.78s	remaining: 10.1s
273:	learn: 17498347.2546318	total: 3.79s	remaining: 10.1s
274:	learn: 17498149.7061684	total: 3.8s	remaining: 10s
275:	learn: 17497860.3337909	total: 3.81s	remaining: 10s
276:	learn: 17497134.2565818	total: 3.83s	remaining: 9.98s
277:	learn: 17496943.1446578	total: 3.84s	remaining: 9.96s
278:	learn: 17495461.7397646	total: 3.85s	remaining: 9.95s
279:	learn: 17492860.8467310	total: 3.86s	remaining: 9.94s
280:	learn: 17492256.7750564	total: 3.88s	remaining: 9.92s
281:	learn: 17491315.8920024	total: 3.89s	remaining: 9.91s
282:	learn: 17488802.8492737	total: 3.9s	remaining: 9.89s
283:	learn: 17479802.6541152	total: 3.92s	remaining: 9.87s
284:	learn: 17477169.5331720	total: 3.93s	remaining: 9.86s
285:	learn: 17474743.6190942	total: 3.94s	remaining: 9.84s
286:	learn: 17468342.7955232	total: 3.96s	remaining: 9.83s
287:	learn: 17467579.9985437	total: 3.97s	remaining: 9.82s
288:	learn: 17467009.9684055	total: 3.98s	remaining: 9.8s
289:	learn: 17464125.0260113	total: 4s	remaining: 9.79s
290:	learn: 17463508.0564477	total: 4.01s	remaining: 9.77s
291:	learn: 17453183.2620432	total: 4.02s	remaining: 9.75s
292:	learn: 17452971.0671546	total: 4.03s	remaining: 9.73s
293:	learn: 17452198.5884342	total: 4.05s	remaining: 9.72s

294:	learn: 17450925.6159031	total: 4.06s	remaining: 9.7s
295:	learn: 17450685.1155343	total: 4.07s	remaining: 9.68s
296:	learn: 17447975.7379237	total: 4.08s	remaining: 9.66s
297:	learn: 17446417.7251561	total: 4.1s	remaining: 9.65s
298:	learn: 17446166.7629704	total: 4.11s	remaining: 9.63s
299:	learn: 17445963.1442260	total: 4.12s	remaining: 9.61s
300:	learn: 17445745.7958927	total: 4.13s	remaining: 9.58s
301:	learn: 17444963.9290154	total: 4.14s	remaining: 9.57s
302:	learn: 17432650.1591210	total: 4.15s	remaining: 9.55s
303:	learn: 17430525.1210288	total: 4.17s	remaining: 9.54s
304:	learn: 17418414.4601453	total: 4.18s	remaining: 9.52s
305:	learn: 17417977.4735651	total: 4.19s	remaining: 9.5s
306:	learn: 17335624.2943914	total: 4.2s	remaining: 9.49s
307:	learn: 17323558.9233681	total: 4.21s	remaining: 9.47s
308:	learn: 17323047.3527617	total: 4.22s	remaining: 9.45s
309:	learn: 17322403.3488620	total: 4.24s	remaining: 9.43s
310:	learn: 17322187.6973801	total: 4.25s	remaining: 9.41s
311:	learn: 17320898.8497406	total: 4.26s	remaining: 9.4s
312:	learn: 17312668.7000429	total: 4.27s	remaining: 9.38s
313:	learn: 17299277.5985403	total: 4.29s	remaining: 9.36s
314:	learn: 17298175.9786240	total: 4.3s	remaining: 9.35s
315:	learn: 17296005.0430765	total: 4.31s	remaining: 9.33s
316:	learn: 17295834.3986842	total: 4.33s	remaining: 9.32s
317:	learn: 17295646.8271436	total: 4.33s	remaining: 9.3s
318:	learn: 17295412.2240763	total: 4.35s	remaining: 9.28s
319:	learn: 17295269.3891063	total: 4.36s	remaining: 9.26s
320:	learn: 17294720.1427139	total: 4.37s	remaining: 9.24s
321:	learn: 17280405.8179874	total: 4.38s	remaining: 9.22s
322:	learn: 17279788.6705542	total: 4.39s	remaining: 9.2s
323:	learn: 17259578.2219214	total: 4.4s	remaining: 9.19s
324:	learn: 17258995.8851109	total: 4.41s	remaining: 9.16s
325:	learn: 17256802.0040208	total: 4.42s	remaining: 9.15s
326:	learn: 17245667.9352932	total: 4.44s	remaining: 9.13s
327:	learn: 17245157.2383849	total: 4.45s	remaining: 9.12s
328:	learn: 17244420.0505767	total: 4.46s	remaining: 9.11s
329:	learn: 17240620.9311856	total: 4.48s	remaining: 9.09s
330:	learn: 17240126.6382259	total: 4.49s	remaining: 9.07s
331:	learn: 17239554.3263042	total: 4.5s	remaining: 9.06s
332:	learn: 17239249.4122676	total: 4.52s	remaining: 9.05s
333:	learn: 17237315.5959603	total: 4.53s	remaining: 9.04s
334:	learn: 17237170.4183008	total: 4.54s	remaining: 9.02s
335:	learn: 17235498.1709182	total: 4.55s	remaining: 9s
336:	learn: 17154286.9322136	total: 4.57s	remaining: 8.98s
337:	learn: 17152860.5403583	total: 4.58s	remaining: 8.96s
338:	learn: 17139897.5803445	total: 4.59s	remaining: 8.95s
339:	learn: 17139685.6194353	total: 4.6s	remaining: 8.93s
340:	learn: 17129406.8909698	total: 4.61s	remaining: 8.92s
341:	learn: 17126386.5318429	total: 4.63s	remaining: 8.9s
342:	learn: 17125338.5826429	total: 4.64s	remaining: 8.89s
343:	learn: 17124937.1764028	total: 4.65s	remaining: 8.87s
344:	learn: 17124773.5128614	total: 4.66s	remaining: 8.85s
345:	learn: 17123822.0085471	total: 4.67s	remaining: 8.84s
346:	learn: 17122604.8415169	total: 4.68s	remaining: 8.82s
347:	learn: 17121767.5370013	total: 4.7s	remaining: 8.8s
348:	learn: 17109471.1428348	total: 4.71s	remaining: 8.79s
349:	learn: 17092688.7777393	total: 4.73s	remaining: 8.78s
350:	learn: 17081854.5539987	total: 4.74s	remaining: 8.76s
351:	learn: 17081117.2220910	total: 4.75s	remaining: 8.75s
352:	learn: 17079431.1991192	total: 4.76s	remaining: 8.73s
353:	learn: 17065749.4676464	total: 4.78s	remaining: 8.72s
354:	learn: 17050839.2238400	total: 4.79s	remaining: 8.7s
355:	learn: 17050106.8831270	total: 4.8s	remaining: 8.69s
356:	learn: 17046033.2332065	total: 4.82s	remaining: 8.67s
357:	learn: 17043704.2415802	total: 4.83s	remaining: 8.66s
358:	learn: 17034226.2631681	total: 4.84s	remaining: 8.64s
359:	learn: 17019515.6806659	total: 4.85s	remaining: 8.63s
360:	learn: 17018472.9763746	total: 4.87s	remaining: 8.61s
361:	learn: 17017909.7121151	total: 4.88s	remaining: 8.6s
362:	learn: 17017463.3942640	total: 4.89s	remaining: 8.58s
363:	learn: 17016467.4317116	total: 4.9s	remaining: 8.56s
364:	learn: 17016320.3746025	total: 4.91s	remaining: 8.55s
365:	learn: 17014043.0108512	total: 4.93s	remaining: 8.53s
366:	learn: 17013536.3710672	total: 4.94s	remaining: 8.51s
367:	learn: 17011993.2014165	total: 4.95s	remaining: 8.5s
368:	learn: 17011849.5641841	total: 4.96s	remaining: 8.48s
369:	learn: 17011403.7126883	total: 4.97s	remaining: 8.46s
370:	learn: 17009763.5741945	total: 4.98s	remaining: 8.45s
371:	learn: 17009382.7519630	total: 4.99s	remaining: 8.43s
372:	learn: 17008464.7915054	total: 5s	remaining: 8.41s
373:	learn: 17008143.8161261	total: 5.01s	remaining: 8.39s
374:	learn: 16996814.2215431	total: 5.03s	remaining: 8.38s
375:	learn: 16996377.3351825	total: 5.04s	remaining: 8.36s
376:	learn: 16996037.5806770	total: 5.05s	remaining: 8.34s
377:	learn: 16991953.6478199	total: 5.06s	remaining: 8.33s
378:	learn: 16961328.6727692	total: 5.08s	remaining: 8.32s
379:	learn: 16957664.4831621	total: 5.09s	remaining: 8.3s
380:	learn: 16956856.4526881	total: 5.1s	remaining: 8.29s
381:	learn: 16947754.5891887	total: 5.12s	remaining: 8.28s
382:	learn: 16937471.3061729	total: 5.13s	remaining: 8.26s
383:	learn: 16910717.2697228	total: 5.14s	remaining: 8.25s
384:	learn: 16883021.8749316	total: 5.15s	remaining: 8.23s
385:	learn: 16874077.6620256	total: 5.17s	remaining: 8.22s
386:	learn: 16859663.0508862	total: 5.18s	remaining: 8.2s
387:	learn: 16843794.6984628	total: 5.19s	remaining: 8.19s
388:	learn: 16843670.2191430	total: 5.2s	remaining: 8.17s
389:	learn: 16833049.2556840	total: 5.21s	remaining: 8.15s
390:	learn: 16821522.4443567	total: 5.23s	remaining: 8.14s
391:	learn: 16818181.1766856	total: 5.24s	remaining: 8.13s
392:	learn: 16817749.5049150	total: 5.25s	remaining: 8.12s
393:	learn: 16817402.3614282	total: 5.27s	remaining: 8.1s
394:	learn: 16815679.7151727	total: 5.28s	remaining: 8.09s
395:	learn: 16810641.8717564	total: 5.29s	remaining: 8.07s
396:	learn: 16810291.1871768	total: 5.3s	remaining: 8.06s
397:	learn: 16808056.2422004	total: 5.32s	remaining: 8.04s
398:	learn: 16807804.2454334	total: 5.33s	remaining: 8.03s
399:	learn: 16799998.1957230	total: 5.34s	remaining: 8.02s
400:	learn: 16799220.2656080	total: 5.36s	remaining: 8s
401:	learn: 16798913.0252067	total: 5.37s	remaining: 7.98s
402:	learn: 16798319.2545577	total: 5.38s	remaining: 7.97s
403:	learn: 16796848.5752647	total: 5.39s	remaining: 7.95s
404:	learn: 16757656.8985529	total: 5.4s	remaining: 7.93s
405:	learn: 16745513.4381725	total: 5.41s	remaining: 7.92s
406:	learn: 16735416.8114581	total: 5.43s	remaining: 7.91s
407:	learn: 16734295.1424370	total: 5.44s	remaining: 7.89s
408:	learn: 16733140.3781664	total: 5.45s	remaining: 7.88s
409:	learn: 16723800.8980695	total: 5.46s	remaining: 7.86s
410:	learn: 16721200.9625357	total: 5.48s	remaining: 7.85s
411:	learn: 16720027.8472987	total: 5.49s	remaining: 7.83s
412:	learn: 16717199.5760035	total: 5.5s	remaining: 7.82s
413:	learn: 16713362.4492616	total: 5.52s	remaining: 7.81s
414:	learn: 16712806.0473182	total: 5.53s	remaining: 7.8s
415:	learn: 16711241.9902750	total: 5.55s	remaining: 7.79s
416:	learn: 16710626.7325455	total: 5.56s	remaining: 7.77s
417:	learn: 16644768.4542531	total: 5.57s	remaining: 7.75s
418:	learn: 16644403.8081224	total: 5.58s	remaining: 7.74s
419:	learn: 16644106.9601552	total: 5.59s	remaining: 7.72s
420:	learn: 16643628.6346956	total: 5.6s	remaining: 7.71s
421:	learn: 16640073.3813320	total: 5.62s	remaining: 7.69s
422:	learn: 16639549.7950808	total: 5.63s	remaining: 7.68s
423:	learn: 16639069.1006878	total: 5.64s	remaining: 7.66s
424:	learn: 16638481.2382327	total: 5.65s	remaining: 7.65s
425:	learn: 16638208.9073863	total: 5.66s	remaining: 7.63s
426:	learn: 16609090.9227109	total: 5.67s	remaining: 7.61s
427:	learn: 16607897.8537223	total: 5.69s	remaining: 7.6s
428:	learn: 16607613.0069443	total: 5.7s	remaining: 7.58s
429:	learn: 16603866.7848843	total: 5.71s	remaining: 7.57s
430:	learn: 16566652.4020620	total: 5.72s	remaining: 7.55s
431:	learn: 16566149.6048169	total: 5.74s	remaining: 7.54s
432:	learn: 16564672.1011733	total: 5.75s	remaining: 7.53s
433:	learn: 16564610.7741058	total: 5.76s	remaining: 7.51s
434:	learn: 16564198.8911273	total: 5.77s	remaining: 7.49s
435:	learn: 16559675.2968062	total: 5.78s	remaining: 7.48s
436:	learn: 16558753.2346339	total: 5.79s	remaining: 7.46s
437:	learn: 16558452.1907641	total: 5.8s	remaining: 7.45s
438:	learn: 16546587.2383006	total: 5.82s	remaining: 7.43s
439:	learn: 16543823.0847287	total: 5.83s	remaining: 7.42s
440:	learn: 16542126.8424469	total: 5.84s	remaining: 7.4s
441:	learn: 16541624.1632076	total: 5.85s	remaining: 7.39s
442:	learn: 16540326.5322872	total: 5.86s	remaining: 7.37s
443:	learn: 16530336.2084291	total: 5.88s	remaining: 7.36s
444:	learn: 16530167.9665629	total: 5.89s	remaining: 7.34s
445:	learn: 16528821.2477933	total: 5.9s	remaining: 7.33s

446:	learn: 16528766.2012617	total: 5.91s	remaining: 7.31s
447:	learn: 16518018.7193100	total: 5.92s	remaining: 7.3s
448:	learn: 16508723.6897544	total: 5.94s	remaining: 7.29s
449:	learn: 16508487.2637814	total: 5.95s	remaining: 7.27s
450:	learn: 16473955.6540161	total: 5.96s	remaining: 7.26s
451:	learn: 16453172.0203944	total: 5.98s	remaining: 7.25s
452:	learn: 16451483.6324413	total: 5.99s	remaining: 7.23s
453:	learn: 16451257.8036014	total: 6s	remaining: 7.22s
454:	learn: 16448369.9508352	total: 6.02s	remaining: 7.21s
455:	learn: 16446719.1385193	total: 6.03s	remaining: 7.19s
456:	learn: 16420736.1369659	total: 6.04s	remaining: 7.18s
457:	learn: 16420629.2824606	total: 6.05s	remaining: 7.16s
458:	learn: 16420336.6729748	total: 6.07s	remaining: 7.15s
459:	learn: 16420155.4584530	total: 6.08s	remaining: 7.13s
460:	learn: 16419734.8233202	total: 6.09s	remaining: 7.12s
461:	learn: 16419517.6225944	total: 6.1s	remaining: 7.1s
462:	learn: 16406145.7183320	total: 6.12s	remaining: 7.09s
463:	learn: 16404609.0651931	total: 6.13s	remaining: 7.08s
464:	learn: 16404332.0732862	total: 6.14s	remaining: 7.07s
465:	learn: 16404019.7507952	total: 6.16s	remaining: 7.05s
466:	learn: 16403507.0137349	total: 6.17s	remaining: 7.04s
467:	learn: 16402993.5886996	total: 6.18s	remaining: 7.03s
468:	learn: 16385955.8460101	total: 6.19s	remaining: 7.01s
469:	learn: 16373237.2004642	total: 6.2s	remaining: 7s
470:	learn: 16373038.3665164	total: 6.21s	remaining: 6.98s
471:	learn: 16372801.5860356	total: 6.23s	remaining: 6.97s
472:	learn: 16360759.6605520	total: 6.24s	remaining: 6.95s
473:	learn: 16360169.9657388	total: 6.25s	remaining: 6.94s
474:	learn: 16351841.0373273	total: 6.26s	remaining: 6.92s
475:	learn: 16349809.4004009	total: 6.28s	remaining: 6.91s
476:	learn: 16344483.1074475	total: 6.3s	remaining: 6.9s
477:	learn: 16340922.7262468	total: 6.31s	remaining: 6.89s
478:	learn: 16334736.4373107	total: 6.32s	remaining: 6.88s
479:	learn: 16334043.7402281	total: 6.33s	remaining: 6.86s
480:	learn: 16333745.0129155	total: 6.35s	remaining: 6.85s
481:	learn: 16332170.0024156	total: 6.36s	remaining: 6.83s
482:	learn: 16331680.4256261	total: 6.37s	remaining: 6.82s
483:	learn: 16321943.5880137	total: 6.38s	remaining: 6.81s
484:	learn: 16313566.1128530	total: 6.4s	remaining: 6.79s
485:	learn: 16312784.3783495	total: 6.41s	remaining: 6.78s
486:	learn: 16304256.8971602	total: 6.42s	remaining: 6.76s
487:	learn: 16299338.9360929	total: 6.43s	remaining: 6.75s
488:	learn: 16298399.2768748	total: 6.45s	remaining: 6.74s
489:	learn: 16282861.5959599	total: 6.46s	remaining: 6.72s
490:	learn: 16278027.7798172	total: 6.47s	remaining: 6.71s
491:	learn: 16262455.7433251	total: 6.49s	remaining: 6.7s
492:	learn: 16254609.6670435	total: 6.5s	remaining: 6.68s
493:	learn: 16250306.9197526	total: 6.51s	remaining: 6.67s
494:	learn: 16249855.9315045	total: 6.53s	remaining: 6.66s
495:	learn: 16248555.7562997	total: 6.54s	remaining: 6.64s
496:	learn: 16247555.1566330	total: 6.55s	remaining: 6.63s
497:	learn: 16247235.5993966	total: 6.56s	remaining: 6.62s
498:	learn: 16246264.7483105	total: 6.57s	remaining: 6.6s
499:	learn: 16246007.7491962	total: 6.58s	remaining: 6.58s
500:	learn: 16222867.6954421	total: 6.59s	remaining: 6.57s
501:	learn: 16222688.8853061	total: 6.61s	remaining: 6.55s
502:	learn: 16217885.3385915	total: 6.62s	remaining: 6.54s
503:	learn: 16217409.1580145	total: 6.63s	remaining: 6.52s
504:	learn: 16216838.3191240	total: 6.64s	remaining: 6.51s
505:	learn: 16216329.9777509	total: 6.65s	remaining: 6.5s
506:	learn: 16201534.4156055	total: 6.67s	remaining: 6.48s
507:	learn: 16198138.1904772	total: 6.68s	remaining: 6.47s
508:	learn: 16197904.2583705	total: 6.69s	remaining: 6.45s
509:	learn: 16193656.6407621	total: 6.7s	remaining: 6.44s
510:	learn: 16180805.8618897	total: 6.71s	remaining: 6.42s
511:	learn: 16176908.1769610	total: 6.73s	remaining: 6.41s
512:	learn: 16168261.0438871	total: 6.74s	remaining: 6.4s
513:	learn: 16167754.4165306	total: 6.75s	remaining: 6.38s
514:	learn: 16166295.0362243	total: 6.77s	remaining: 6.37s
515:	learn: 16166058.4053693	total: 6.78s	remaining: 6.36s
516:	learn: 16155412.7707338	total: 6.79s	remaining: 6.34s
517:	learn: 16152266.1742558	total: 6.8s	remaining: 6.33s
518:	learn: 16151552.8907870	total: 6.82s	remaining: 6.32s
519:	learn: 16140281.4351978	total: 6.83s	remaining: 6.3s
520:	learn: 16133450.4403783	total: 6.84s	remaining: 6.29s
521:	learn: 16132209.1334220	total: 6.85s	remaining: 6.27s
522:	learn: 16118104.6552795	total: 6.86s	remaining: 6.26s
523:	learn: 16108764.2393062	total: 6.87s	remaining: 6.25s
524:	learn: 16108234.0634605	total: 6.89s	remaining: 6.23s
525:	learn: 16107619.6760099	total: 6.9s	remaining: 6.22s
526:	learn: 16104870.7442280	total: 6.91s	remaining: 6.2s
527:	learn: 16102428.3934069	total: 6.92s	remaining: 6.19s
528:	learn: 16102157.2857565	total: 6.93s	remaining: 6.17s
529:	learn: 16101584.7403855	total: 6.95s	remaining: 6.16s
530:	learn: 16101480.3344969	total: 6.96s	remaining: 6.15s
531:	learn: 16100595.6548675	total: 6.97s	remaining: 6.13s
532:	learn: 16097511.0825233	total: 6.99s	remaining: 6.12s
533:	learn: 16096615.9743637	total: 7s	remaining: 6.11s
534:	learn: 16096369.6922988	total: 7.01s	remaining: 6.09s
535:	learn: 16095946.1647864	total: 7.02s	remaining: 6.08s
536:	learn: 16095637.6185090	total: 7.03s	remaining: 6.06s
537:	learn: 16094682.0243853	total: 7.04s	remaining: 6.05s
538:	learn: 16094291.9050311	total: 7.05s	remaining: 6.03s
539:	learn: 16093984.5280001	total: 7.07s	remaining: 6.02s
540:	learn: 16090374.6401334	total: 7.08s	remaining: 6.01s
541:	learn: 16090226.8772271	total: 7.09s	remaining: 5.99s
542:	learn: 16090050.1805201	total: 7.1s	remaining: 5.98s
543:	learn: 16069181.1048944	total: 7.12s	remaining: 5.96s
544:	learn: 16068504.9399291	total: 7.13s	remaining: 5.95s
545:	learn: 16068245.3744393	total: 7.14s	remaining: 5.94s
546:	learn: 16065773.4114093	total: 7.15s	remaining: 5.92s
547:	learn: 16051662.5046318	total: 7.17s	remaining: 5.91s
548:	learn: 16035327.2446945	total: 7.18s	remaining: 5.9s
549:	learn: 16035199.2858857	total: 7.2s	remaining: 5.89s
550:	learn: 16033842.9666151	total: 7.21s	remaining: 5.88s
551:	learn: 15995073.4381976	total: 7.22s	remaining: 5.86s
552:	learn: 15994812.5505379	total: 7.23s	remaining: 5.85s
553:	learn: 15994595.9921031	total: 7.24s	remaining: 5.83s
554:	learn: 15992248.3834318	total: 7.26s	remaining: 5.82s
555:	learn: 15992027.4484601	total: 7.27s	remaining: 5.8s
556:	learn: 15990566.0719983	total: 7.28s	remaining: 5.79s
557:	learn: 15985609.0920187	total: 7.29s	remaining: 5.78s
558:	learn: 15984517.8156083	total: 7.3s	remaining: 5.76s
559:	learn: 15958775.9803743	total: 7.32s	remaining: 5.75s
560:	learn: 15958166.8639855	total: 7.33s	remaining: 5.73s
561:	learn: 15949224.5334582	total: 7.34s	remaining: 5.72s
562:	learn: 15948769.9101270	total: 7.35s	remaining: 5.71s
563:	learn: 15930009.9576761	total: 7.36s	remaining: 5.69s
564:	learn: 15917439.6202170	total: 7.38s	remaining: 5.68s
565:	learn: 15908669.4567536	total: 7.39s	remaining: 5.67s
566:	learn: 15908084.2939630	total: 7.4s	remaining: 5.65s
567:	learn: 15906697.1590494	total: 7.41s	remaining: 5.64s
568:	learn: 15906522.4609846	total: 7.43s	remaining: 5.63s
569:	learn: 15906139.9138507	total: 7.44s	remaining: 5.61s
570:	learn: 15905855.0642382	total: 7.45s	remaining: 5.6s
571:	learn: 15897372.3501416	total: 7.46s	remaining: 5.58s
572:	learn: 15893536.4661240	total: 7.47s	remaining: 5.57s
573:	learn: 15893206.2810918	total: 7.49s	remaining: 5.56s
574:	learn: 15892918.2703602	total: 7.5s	remaining: 5.54s
575:	learn: 15892752.8029869	total: 7.51s	remaining: 5.53s
576:	learn: 15885169.7413434	total: 7.52s	remaining: 5.51s
577:	learn: 15884936.8745209	total: 7.53s	remaining: 5.5s
578:	learn: 15876877.1991641	total: 7.54s	remaining: 5.49s
579:	learn: 15865774.4061534	total: 7.56s	remaining: 5.47s
580:	learn: 15859212.9207966	total: 7.57s	remaining: 5.46s
581:	learn: 15858807.6511813	total: 7.58s	remaining: 5.45s
582:	learn: 15850129.9468116	total: 7.6s	remaining: 5.43s
583:	learn: 15845554.5689368	total: 7.61s	remaining: 5.42s
584:	learn: 15844986.6765475	total: 7.62s	remaining: 5.41s
585:	learn: 15844796.1180439	total: 7.63s	remaining: 5.39s
586:	learn: 15844586.1630771	total: 7.65s	remaining: 5.38s
587:	learn: 15827685.4584540	total: 7.66s	remaining: 5.37s
588:	learn: 15826910.6044821	total: 7.68s	remaining: 5.36s
589:	learn: 15824060.9875073	total: 7.69s	remaining: 5.34s
590:	learn: 15818523.6912985	total: 7.7s	remaining: 5.33s
591:	learn: 15810640.6921394	total: 7.72s	remaining: 5.32s
592:	learn: 15795481.4197185	total: 7.73s	remaining: 5.3s

593:	learn: 15795256.4491006	total: 7.74s	remaining: 5.29s
594:	learn: 15784420.7363473	total: 7.76s	remaining: 5.28s
595:	learn: 15784290.1819258	total: 7.78s	remaining: 5.27s
596:	learn: 15783955.0773924	total: 7.79s	remaining: 5.26s
597:	learn: 15781518.5372107	total: 7.8s	remaining: 5.25s
598:	learn: 15779547.4210947	total: 7.82s	remaining: 5.24s
599:	learn: 15777334.3663340	total: 7.83s	remaining: 5.22s
600:	learn: 15774774.7721883	total: 7.85s	remaining: 5.21s
601:	learn: 15774672.2356339	total: 7.86s	remaining: 5.2s
602:	learn: 15773528.0736833	total: 7.87s	remaining: 5.18s
603:	learn: 15768721.3649454	total: 7.89s	remaining: 5.17s
604:	learn: 15768502.0877019	total: 7.9s	remaining: 5.16s
605:	learn: 15768057.4929247	total: 7.92s	remaining: 5.15s
606:	learn: 15767950.4285043	total: 7.93s	remaining: 5.14s
607:	learn: 15767445.1324607	total: 7.95s	remaining: 5.12s
608:	learn: 15767269.0628064	total: 7.96s	remaining: 5.11s
609:	learn: 15767020.8174624	total: 7.97s	remaining: 5.1s
610:	learn: 15762309.5160245	total: 7.99s	remaining: 5.09s
611:	learn: 15757527.7718093	total: 8s	remaining: 5.07s
612:	learn: 15757150.7731734	total: 8.02s	remaining: 5.06s
613:	learn: 15756885.6252756	total: 8.03s	remaining: 5.05s
614:	learn: 15755584.6816303	total: 8.05s	remaining: 5.04s
615:	learn: 15755485.6737331	total: 8.06s	remaining: 5.02s
616:	learn: 15754432.0517599	total: 8.07s	remaining: 5.01s
617:	learn: 15744535.8203508	total: 8.09s	remaining: 5s
618:	learn: 15740683.5538600	total: 8.1s	remaining: 4.99s
619:	learn: 15736903.5667213	total: 8.12s	remaining: 4.97s
620:	learn: 15736355.4210963	total: 8.13s	remaining: 4.96s
621:	learn: 15729940.4032081	total: 8.15s	remaining: 4.95s
622:	learn: 15729775.7542976	total: 8.17s	remaining: 4.94s
623:	learn: 15726578.4125003	total: 8.18s	remaining: 4.93s
624:	learn: 15713451.5317183	total: 8.2s	remaining: 4.92s
625:	learn: 15712116.7478338	total: 8.22s	remaining: 4.91s
626:	learn: 15712039.0336448	total: 8.23s	remaining: 4.9s
627:	learn: 15711687.4136682	total: 8.25s	remaining: 4.89s
628:	learn: 15711298.6681597	total: 8.27s	remaining: 4.88s
629:	learn: 15705228.0021081	total: 8.28s	remaining: 4.86s
630:	learn: 15705060.0247650	total: 8.29s	remaining: 4.85s
631:	learn: 15702513.1910574	total: 8.31s	remaining: 4.84s
632:	learn: 15702203.6145508	total: 8.32s	remaining: 4.82s
633:	learn: 15698975.2951288	total: 8.33s	remaining: 4.81s
634:	learn: 15694674.2341421	total: 8.34s	remaining: 4.8s
635:	learn: 15686913.9104937	total: 8.36s	remaining: 4.78s
636:	learn: 15686809.9586513	total: 8.37s	remaining: 4.77s
637:	learn: 15685604.3787689	total: 8.38s	remaining: 4.76s
638:	learn: 15685081.4917552	total: 8.4s	remaining: 4.74s
639:	learn: 15676541.2826685	total: 8.41s	remaining: 4.73s
640:	learn: 15672855.0180760	total: 8.42s	remaining: 4.72s
641:	learn: 15666780.7593096	total: 8.44s	remaining: 4.7s
642:	learn: 15659438.3508408	total: 8.45s	remaining: 4.69s
643:	learn: 15653755.4598701	total: 8.46s	remaining: 4.68s
644:	learn: 15652034.4638985	total: 8.48s	remaining: 4.67s
645:	learn: 15645095.6489597	total: 8.49s	remaining: 4.65s
646:	learn: 15641226.9420905	total: 8.5s	remaining: 4.64s
647:	learn: 15639833.9184524	total: 8.52s	remaining: 4.63s
648:	learn: 15639581.1651510	total: 8.53s	remaining: 4.61s
649:	learn: 15635923.3848062	total: 8.54s	remaining: 4.6s
650:	learn: 15635813.1152459	total: 8.55s	remaining: 4.58s
651:	learn: 15635469.3555938	total: 8.56s	remaining: 4.57s
652:	learn: 15635363.9174910	total: 8.57s	remaining: 4.56s
653:	learn: 15633936.7433448	total: 8.59s	remaining: 4.54s
654:	learn: 15633839.2271448	total: 8.6s	remaining: 4.53s
655:	learn: 15633735.8610291	total: 8.61s	remaining: 4.52s
656:	learn: 15633309.8063070	total: 8.63s	remaining: 4.5s
657:	learn: 15632683.8986677	total: 8.64s	remaining: 4.49s
658:	learn: 15632461.2639014	total: 8.65s	remaining: 4.48s
659:	learn: 15627123.1765533	total: 8.66s	remaining: 4.46s
660:	learn: 15626996.0787558	total: 8.68s	remaining: 4.45s
661:	learn: 15624291.0204091	total: 8.69s	remaining: 4.44s
662:	learn: 15617684.3098363	total: 8.71s	remaining: 4.42s
663:	learn: 15611967.2176796	total: 8.72s	remaining: 4.41s
664:	learn: 15598472.2546786	total: 8.73s	remaining: 4.4s
665:	learn: 15597526.0470563	total: 8.74s	remaining: 4.38s
666:	learn: 15597430.3920481	total: 8.75s	remaining: 4.37s
667:	learn: 15596422.7059295	total: 8.77s	remaining: 4.36s
668:	learn: 15591400.2242411	total: 8.78s	remaining: 4.34s
669:	learn: 15585199.5277811	total: 8.79s	remaining: 4.33s
670:	learn: 15585003.5063693	total: 8.8s	remaining: 4.32s
671:	learn: 15578765.7193891	total: 8.81s	remaining: 4.3s
672:	learn: 15577252.0151364	total: 8.83s	remaining: 4.29s
673:	learn: 15576511.8797514	total: 8.84s	remaining: 4.28s
674:	learn: 15576120.7606092	total: 8.85s	remaining: 4.26s
675:	learn: 15574398.5273782	total: 8.86s	remaining: 4.25s
676:	learn: 15565660.7493905	total: 8.88s	remaining: 4.24s
677:	learn: 15561009.3437211	total: 8.89s	remaining: 4.22s
678:	learn: 15548878.4770401	total: 8.9s	remaining: 4.21s
679:	learn: 15527713.9632219	total: 8.91s	remaining: 4.19s
680:	learn: 15519745.2151864	total: 8.93s	remaining: 4.18s
681:	learn: 15519391.2760902	total: 8.94s	remaining: 4.17s
682:	learn: 15514461.8611265	total: 8.95s	remaining: 4.15s
683:	learn: 15514296.1001141	total: 8.96s	remaining: 4.14s
684:	learn: 15514204.8658979	total: 8.97s	remaining: 4.13s
685:	learn: 15513977.3554214	total: 8.98s	remaining: 4.11s
686:	learn: 15513906.5046745	total: 9s	remaining: 4.1s
687:	learn: 15513701.8112778	total: 9.01s	remaining: 4.09s
688:	learn: 15513602.4959013	total: 9.02s	remaining: 4.07s
689:	learn: 15513510.7910896	total: 9.03s	remaining: 4.06s
690:	learn: 15513352.2070048	total: 9.04s	remaining: 4.04s
691:	learn: 15513238.8204588	total: 9.05s	remaining: 4.03s
692:	learn: 15513154.0618557	total: 9.06s	remaining: 4.01s
693:	learn: 15512878.9114412	total: 9.07s	remaining: 4s
694:	learn: 15509248.2055515	total: 9.09s	remaining: 3.99s
695:	learn: 15508734.7327170	total: 9.1s	remaining: 3.97s
696:	learn: 15508495.7881550	total: 9.11s	remaining: 3.96s
697:	learn: 15508349.6872134	total: 9.12s	remaining: 3.95s
698:	learn: 15508190.6588965	total: 9.13s	remaining: 3.93s
699:	learn: 15508018.8419773	total: 9.14s	remaining: 3.92s
700:	learn: 15507826.3791202	total: 9.16s	remaining: 3.9s
701:	learn: 15507705.8100928	total: 9.17s	remaining: 3.89s
702:	learn: 15507533.3512682	total: 9.18s	remaining: 3.88s
703:	learn: 15501571.2913355	total: 9.19s	remaining: 3.87s
704:	learn: 15495921.0773672	total: 9.21s	remaining: 3.85s
705:	learn: 15495385.0875416	total: 9.22s	remaining: 3.84s
706:	learn: 15495191.8032918	total: 9.23s	remaining: 3.83s
707:	learn: 15494128.9589635	total: 9.24s	remaining: 3.81s
708:	learn: 15493806.9566177	total: 9.26s	remaining: 3.8s
709:	learn: 15493694.0465547	total: 9.27s	remaining: 3.78s
710:	learn: 15493305.1729869	total: 9.28s	remaining: 3.77s
711:	learn: 15487948.0399475	total: 9.3s	remaining: 3.76s
712:	learn: 15487843.0916850	total: 9.31s	remaining: 3.75s
713:	learn: 15482765.7669785	total: 9.32s	remaining: 3.73s
714:	learn: 15474767.3580796	total: 9.33s	remaining: 3.72s
715:	learn: 15472407.8166003	total: 9.35s	remaining: 3.71s
716:	learn: 15467592.3874842	total: 9.36s	remaining: 3.69s
717:	learn: 15467435.4901525	total: 9.37s	remaining: 3.68s
718:	learn: 15462871.2869120	total: 9.38s	remaining: 3.67s
719:	learn: 15462771.0380185	total: 9.39s	remaining: 3.65s
720:	learn: 15462475.2715024	total: 9.4s	remaining: 3.64s
721:	learn: 15454885.7938423	total: 9.42s	remaining: 3.63s
722:	learn: 15450557.5824215	total: 9.43s	remaining: 3.61s
723:	learn: 15446455.2317749	total: 9.44s	remaining: 3.6s
724:	learn: 15445711.0004476	total: 9.46s	remaining: 3.59s
725:	learn: 15441822.5331613	total: 9.47s	remaining: 3.57s
726:	learn: 15441182.6843715	total: 9.48s	remaining: 3.56s
727:	learn: 15441088.8915881	total: 9.49s	remaining: 3.55s
728:	learn: 15441002.5272406	total: 9.51s	remaining: 3.53s
729:	learn: 15440884.2830869	total: 9.52s	remaining: 3.52s
730:	learn: 15440734.2579995	total: 9.53s	remaining: 3.51s
731:	learn: 15440611.8887909	total: 9.54s	remaining: 3.49s
732:	learn: 15440249.4221271	total: 9.55s	remaining: 3.48s
733:	learn: 15440158.8154476	total: 9.56s	remaining: 3.46s
734:	learn: 15436472.7845071	total: 9.57s	remaining: 3.45s

735:	learn: 15433672.4484876	total: 9.59s	remaining: 3.44s
736:	learn: 15433490.1840146	total: 9.6s	remaining: 3.43s
737:	learn: 15433308.6881010	total: 9.61s	remaining: 3.41s
738:	learn: 15433042.7409848	total: 9.63s	remaining: 3.4s
739:	learn: 15432541.8769518	total: 9.64s	remaining: 3.39s
740:	learn: 15431856.6761047	total: 9.66s	remaining: 3.38s
741:	learn: 15431804.7359345	total: 9.67s	remaining: 3.36s
742:	learn: 15427355.2392047	total: 9.68s	remaining: 3.35s
743:	learn: 15427218.1028185	total: 9.69s	remaining: 3.33s
744:	learn: 15424332.1093472	total: 9.7s	remaining: 3.32s
745:	learn: 15388321.8033125	total: 9.71s	remaining: 3.31s
746:	learn: 15377267.9048803	total: 9.73s	remaining: 3.29s
747:	learn: 15374625.6198420	total: 9.74s	remaining: 3.28s
748:	learn: 15370386.0426691	total: 9.75s	remaining: 3.27s
749:	learn: 15359901.4299089	total: 9.77s	remaining: 3.25s
750:	learn: 15358774.7332579	total: 9.78s	remaining: 3.24s
751:	learn: 15358651.8711020	total: 9.79s	remaining: 3.23s
752:	learn: 15358300.8764559	total: 9.8s	remaining: 3.21s
753:	learn: 15357884.8170886	total: 9.81s	remaining: 3.2s
754:	learn: 15357643.0994172	total: 9.83s	remaining: 3.19s
755:	learn: 15357565.0887636	total: 9.84s	remaining: 3.17s
756:	learn: 15351820.0777339	total: 9.85s	remaining: 3.16s
757:	learn: 15351414.2517094	total: 9.86s	remaining: 3.15s
758:	learn: 15349501.7532204	total: 9.88s	remaining: 3.14s
759:	learn: 15348526.7586048	total: 9.89s	remaining: 3.12s
760:	learn: 15348352.7244253	total: 9.9s	remaining: 3.11s
761:	learn: 15347292.4488773	total: 9.91s	remaining: 3.1s
762:	learn: 15347207.8865499	total: 9.93s	remaining: 3.08s
763:	learn: 15342959.4790246	total: 9.94s	remaining: 3.07s
764:	learn: 15342697.6483068	total: 9.95s	remaining: 3.06s
765:	learn: 15313028.1511576	total: 9.96s	remaining: 3.04s
766:	learn: 15310947.6382018	total: 9.98s	remaining: 3.03s
767:	learn: 15263340.9642127	total: 9.99s	remaining: 3.02s
768:	learn: 15259807.2026083	total: 10s	remaining: 3s
769:	learn: 15259504.1148296	total: 10s	remaining: 2.99s
770:	learn: 15259395.2637694	total: 10s	remaining: 2.98s
771:	learn: 15256045.7141942	total: 10s	remaining: 2.96s
772:	learn: 15252870.9021417	total: 10.1s	remaining: 2.95s
773:	learn: 15248430.3201074	total: 10.1s	remaining: 2.94s
774:	learn: 15246752.4177458	total: 10.1s	remaining: 2.93s
775:	learn: 15245960.1417687	total: 10.1s	remaining: 2.91s
776:	learn: 15245917.6645107	total: 10.1s	remaining: 2.9s
777:	learn: 15245817.5185452	total: 10.1s	remaining: 2.89s
778:	learn: 15245619.8351855	total: 10.1s	remaining: 2.87s
779:	learn: 15244869.5667520	total: 10.1s	remaining: 2.86s
780:	learn: 15244818.8943236	total: 10.2s	remaining: 2.85s
781:	learn: 15244254.3637038	total: 10.2s	remaining: 2.83s
782:	learn: 15243818.2939855	total: 10.2s	remaining: 2.82s
783:	learn: 15243668.1645179	total: 10.2s	remaining: 2.81s
784:	learn: 15240656.8617467	total: 10.2s	remaining: 2.8s
785:	learn: 15237802.6637690	total: 10.2s	remaining: 2.78s
786:	learn: 15235097.3769887	total: 10.2s	remaining: 2.77s
787:	learn: 15231063.4576018	total: 10.3s	remaining: 2.76s
788:	learn: 15224406.4239600	total: 10.3s	remaining: 2.74s
789:	learn: 15220791.2846445	total: 10.3s	remaining: 2.73s
790:	learn: 15220221.4180094	total: 10.3s	remaining: 2.72s
791:	learn: 15220121.7499013	total: 10.3s	remaining: 2.71s
792:	learn: 15218396.9325757	total: 10.3s	remaining: 2.69s
793:	learn: 15213830.8844557	total: 10.3s	remaining: 2.68s
794:	learn: 15212644.4009126	total: 10.3s	remaining: 2.67s
795:	learn: 15212570.5272286	total: 10.4s	remaining: 2.65s
796:	learn: 15172874.1552397	total: 10.4s	remaining: 2.64s
797:	learn: 15164671.3501787	total: 10.4s	remaining: 2.63s
798:	learn: 15162711.8871221	total: 10.4s	remaining: 2.62s
799:	learn: 15162618.0050229	total: 10.4s	remaining: 2.6s
800:	learn: 15161186.8924011	total: 10.4s	remaining: 2.59s
801:	learn: 15160994.4738412	total: 10.4s	remaining: 2.58s
802:	learn: 15159385.3831268	total: 10.4s	remaining: 2.56s
803:	learn: 15159166.1576231	total: 10.5s	remaining: 2.55s
804:	learn: 15156764.1801770	total: 10.5s	remaining: 2.54s
805:	learn: 15146691.8394282	total: 10.5s	remaining: 2.52s
806:	learn: 15146533.6706853	total: 10.5s	remaining: 2.51s
807:	learn: 15146408.7773292	total: 10.5s	remaining: 2.5s
808:	learn: 15142359.7678728	total: 10.5s	remaining: 2.48s
809:	learn: 15142322.1248825	total: 10.5s	remaining: 2.47s
810:	learn: 15132770.1153732	total: 10.5s	remaining: 2.46s
811:	learn: 15101480.9924963	total: 10.6s	remaining: 2.44s
812:	learn: 15101445.1875248	total: 10.6s	remaining: 2.43s
813:	learn: 15075376.4419388	total: 10.6s	remaining: 2.42s
814:	learn: 15073160.0820287	total: 10.6s	remaining: 2.4s
815:	learn: 15072725.5140996	total: 10.6s	remaining: 2.39s
816:	learn: 15072585.7018342	total: 10.6s	remaining: 2.38s
817:	learn: 15071522.0001919	total: 10.6s	remaining: 2.37s
818:	learn: 15071382.2097110	total: 10.6s	remaining: 2.35s
819:	learn: 15071301.2886091	total: 10.7s	remaining: 2.34s
820:	learn: 15071025.2992144	total: 10.7s	remaining: 2.33s
821:	learn: 15069498.2268762	total: 10.7s	remaining: 2.31s
822:	learn: 15061575.7065075	total: 10.7s	remaining: 2.3s
823:	learn: 15061416.4068476	total: 10.7s	remaining: 2.29s
824:	learn: 15060945.6687130	total: 10.7s	remaining: 2.27s
825:	learn: 15051099.8538783	total: 10.7s	remaining: 2.26s
826:	learn: 15050450.9663299	total: 10.7s	remaining: 2.25s
827:	learn: 15049722.9751983	total: 10.8s	remaining: 2.23s
828:	learn: 15049467.7452535	total: 10.8s	remaining: 2.22s
829:	learn: 15049412.7697933	total: 10.8s	remaining: 2.21s
830:	learn: 15048891.7740041	total: 10.8s	remaining: 2.19s
831:	learn: 15048043.0994998	total: 10.8s	remaining: 2.18s
832:	learn: 15046697.3368860	total: 10.8s	remaining: 2.17s
833:	learn: 15038272.8803419	total: 10.8s	remaining: 2.15s
834:	learn: 15034639.9951102	total: 10.8s	remaining: 2.14s
835:	learn: 15030153.8614245	total: 10.9s	remaining: 2.13s
836:	learn: 15027964.0190757	total: 10.9s	remaining: 2.12s
837:	learn: 15023890.1409211	total: 10.9s	remaining: 2.1s
838:	learn: 15022954.0613643	total: 10.9s	remaining: 2.09s
839:	learn: 15022653.7321874	total: 10.9s	remaining: 2.08s
840:	learn: 15021763.5899870	total: 10.9s	remaining: 2.06s
841:	learn: 15021552.9666208	total: 10.9s	remaining: 2.05s
842:	learn: 15017213.3112838	total: 10.9s	remaining: 2.04s
843:	learn: 15006868.9919636	total: 11s	remaining: 2.02s
844:	learn: 15006047.4873296	total: 11s	remaining: 2.01s
845:	learn: 15003167.3995596	total: 11s	remaining: 2s
846:	learn: 15001516.1719277	total: 11s	remaining: 1.99s
847:	learn: 15000023.6971343	total: 11s	remaining: 1.97s
848:	learn: 14996097.9901016	total: 11s	remaining: 1.96s
849:	learn: 14995809.9617414	total: 11s	remaining: 1.95s
850:	learn: 14991694.0680204	total: 11s	remaining: 1.93s
851:	learn: 14990806.5441048	total: 11.1s	remaining: 1.92s
852:	learn: 14990539.4146062	total: 11.1s	remaining: 1.91s
853:	learn: 14990428.7975864	total: 11.1s	remaining: 1.89s
854:	learn: 14989061.7567162	total: 11.1s	remaining: 1.88s
855:	learn: 14983131.0103419	total: 11.1s	remaining: 1.87s
856:	learn: 14982655.3316759	total: 11.1s	remaining: 1.86s
857:	learn: 14977099.0608273	total: 11.1s	remaining: 1.84s
858:	learn: 14976713.9058693	total: 11.2s	remaining: 1.83s
859:	learn: 14976613.3364184	total: 11.2s	remaining: 1.82s
860:	learn: 14964115.6999829	total: 11.2s	remaining: 1.81s
861:	learn: 14961152.7626425	total: 11.2s	remaining: 1.79s
862:	learn: 14960316.8698796	total: 11.2s	remaining: 1.78s
863:	learn: 14960206.5805103	total: 11.2s	remaining: 1.77s
864:	learn: 14948350.2065232	total: 11.2s	remaining: 1.75s
865:	learn: 14948237.8225238	total: 11.3s	remaining: 1.74s
866:	learn: 14948145.1280412	total: 11.3s	remaining: 1.73s
867:	learn: 14947479.9936319	total: 11.3s	remaining: 1.72s
868:	learn: 14946706.9144290	total: 11.3s	remaining: 1.7s
869:	learn: 14946008.4529886	total: 11.3s	remaining: 1.69s
870:	learn: 14938382.9733130	total: 11.3s	remaining: 1.68s
871:	learn: 14935923.0018589	total: 11.3s	remaining: 1.66s
872:	learn: 14935763.9386719	total: 11.4s	remaining: 1.65s
873:	learn: 14935390.9032799	total: 11.4s	remaining: 1.64s
874:	learn: 14924136.4999000	total: 11.4s	remaining: 1.63s
875:	learn: 14923231.4975181	total: 11.4s	remaining: 1.61s
876:	learn: 14920764.7489123	total: 11.4s	remaining: 1.6s

877:	learn: 14920619.6869935	total: 11.4s	remaining: 1.59s
878:	learn: 14920259.9887151	total: 11.4s	remaining: 1.57s
879:	learn: 14918671.6063618	total: 11.4s	remaining: 1.56s
880:	learn: 14909484.3446534	total: 11.5s	remaining: 1.55s
881:	learn: 14909331.3722806	total: 11.5s	remaining: 1.53s
882:	learn: 14909000.4744294	total: 11.5s	remaining: 1.52s
883:	learn: 14907810.4215534	total: 11.5s	remaining: 1.51s
884:	learn: 14907739.9399244	total: 11.5s	remaining: 1.5s
885:	learn: 14907643.8234156	total: 11.5s	remaining: 1.48s
886:	learn: 14902234.6414918	total: 11.5s	remaining: 1.47s
887:	learn: 14899639.1808572	total: 11.5s	remaining: 1.46s
888:	learn: 14898572.6302420	total: 11.6s	remaining: 1.44s
889:	learn: 14898481.9011232	total: 11.6s	remaining: 1.43s
890:	learn: 14898396.0569341	total: 11.6s	remaining: 1.42s
891:	learn: 14897825.8306216	total: 11.6s	remaining: 1.4s
892:	learn: 14897667.5383103	total: 11.6s	remaining: 1.39s
893:	learn: 14894977.2967186	total: 11.6s	remaining: 1.38s
894:	learn: 14894451.1015405	total: 11.6s	remaining: 1.36s
895:	learn: 14894302.6357933	total: 11.6s	remaining: 1.35s
896:	learn: 14892042.1460828	total: 11.7s	remaining: 1.34s
897:	learn: 14891913.2181914	total: 11.7s	remaining: 1.32s
898:	learn: 14891548.8875063	total: 11.7s	remaining: 1.31s
899:	learn: 14891535.2806629	total: 11.7s	remaining: 1.3s
900:	learn: 14885531.4554658	total: 11.7s	remaining: 1.29s
901:	learn: 14885300.5490787	total: 11.7s	remaining: 1.27s
902:	learn: 14882237.8064495	total: 11.7s	remaining: 1.26s
903:	learn: 14871534.0201501	total: 11.7s	remaining: 1.25s
904:	learn: 14870231.5883229	total: 11.8s	remaining: 1.23s
905:	learn: 14870176.1224648	total: 11.8s	remaining: 1.22s
906:	learn: 14869680.0980501	total: 11.8s	remaining: 1.21s
907:	learn: 14869457.0180442	total: 11.8s	remaining: 1.2s
908:	learn: 14868933.3692698	total: 11.8s	remaining: 1.18s
909:	learn: 14863961.6816683	total: 11.8s	remaining: 1.17s
910:	learn: 14863914.5911026	total: 11.8s	remaining: 1.16s
911:	learn: 14855476.3946477	total: 11.8s	remaining: 1.14s
912:	learn: 14855166.2145584	total: 11.9s	remaining: 1.13s
913:	learn: 14850934.1124148	total: 11.9s	remaining: 1.12s
914:	learn: 14846483.1667184	total: 11.9s	remaining: 1.1s
915:	learn: 14837736.3329095	total: 11.9s	remaining: 1.09s
916:	learn: 14837595.6179847	total: 11.9s	remaining: 1.08s
917:	learn: 14830817.0386636	total: 11.9s	remaining: 1.06s
918:	learn: 14830573.0969752	total: 11.9s	remaining: 1.05s
919:	learn: 14830470.0025192	total: 12s	remaining: 1.04s
920:	learn: 14829815.6285131	total: 12s	remaining: 1.03s
921:	learn: 14825434.2189552	total: 12s	remaining: 1.01s
922:	learn: 14819445.0181126	total: 12s	remaining: 1s
923:	learn: 14819398.6279561	total: 12s	remaining: 988ms
924:	learn: 14818813.5923928	total: 12s	remaining: 975ms
925:	learn: 14815956.9177135	total: 12s	remaining: 962ms
926:	learn: 14815788.2679741	total: 12s	remaining: 948ms
927:	learn: 14815448.9260298	total: 12.1s	remaining: 935ms
928:	learn: 14815074.5372959	total: 12.1s	remaining: 923ms
929:	learn: 14814229.2585638	total: 12.1s	remaining: 910ms
930:	learn: 14804039.0241152	total: 12.1s	remaining: 897ms
931:	learn: 14803929.0738285	total: 12.1s	remaining: 883ms
932:	learn: 14803822.0317935	total: 12.1s	remaining: 870ms
933:	learn: 14802847.7620639	total: 12.1s	remaining: 857ms
934:	learn: 14802644.0143811	total: 12.1s	remaining: 844ms
935:	learn: 14801390.4240818	total: 12.2s	remaining: 831ms
936:	learn: 14801273.4225706	total: 12.2s	remaining: 818ms
937:	learn: 14801021.8599058	total: 12.2s	remaining: 805ms
938:	learn: 14800715.3029627	total: 12.2s	remaining: 792ms
939:	learn: 14799551.6406369	total: 12.2s	remaining: 779ms
940:	learn: 14795598.5613345	total: 12.2s	remaining: 766ms
941:	learn: 14794465.0278834	total: 12.2s	remaining: 753ms
942:	learn: 14794259.7563387	total: 12.2s	remaining: 740ms
943:	learn: 14794156.6214413	total: 12.3s	remaining: 727ms
944:	learn: 14792982.4344262	total: 12.3s	remaining: 714ms
945:	learn: 14792468.8012658	total: 12.3s	remaining: 701ms
946:	learn: 14792139.9923168	total: 12.3s	remaining: 688ms
947:	learn: 14786295.7938911	total: 12.3s	remaining: 675ms
948:	learn: 14783272.8762359	total: 12.3s	remaining: 662ms
949:	learn: 14782689.5513664	total: 12.3s	remaining: 649ms
950:	learn: 14782664.1266181	total: 12.3s	remaining: 636ms
951:	learn: 14774339.7873426	total: 12.4s	remaining: 623ms
952:	learn: 14769038.5403572	total: 12.4s	remaining: 610ms
953:	learn: 14761312.5028488	total: 12.4s	remaining: 597ms
954:	learn: 14760414.3496721	total: 12.4s	remaining: 584ms
955:	learn: 14752950.6860631	total: 12.4s	remaining: 571ms
956:	learn: 14752691.2767919	total: 12.4s	remaining: 558ms
957:	learn: 14752196.9268404	total: 12.4s	remaining: 545ms
958:	learn: 14750149.4071752	total: 12.5s	remaining: 532ms
959:	learn: 14749691.8632556	total: 12.5s	remaining: 519ms
960:	learn: 14749496.6164671	total: 12.5s	remaining: 507ms
961:	learn: 14749338.8909588	total: 12.5s	remaining: 494ms
962:	learn: 14749291.1143099	total: 12.5s	remaining: 481ms
963:	learn: 14739582.8672605	total: 12.5s	remaining: 468ms
964:	learn: 14739542.4442574	total: 12.5s	remaining: 455ms
965:	learn: 14739306.4391584	total: 12.5s	remaining: 442ms
966:	learn: 14708630.7344942	total: 12.6s	remaining: 429ms
967:	learn: 14680984.5320050	total: 12.6s	remaining: 416ms
968:	learn: 14677319.7390898	total: 12.6s	remaining: 403ms
969:	learn: 14677109.6650390	total: 12.6s	remaining: 389ms
970:	learn: 14676355.6242387	total: 12.6s	remaining: 376ms
971:	learn: 14667109.8761175	total: 12.6s	remaining: 363ms
972:	learn: 14643934.7657464	total: 12.6s	remaining: 350ms
973:	learn: 14642633.8347823	total: 12.6s	remaining: 337ms
974:	learn: 14642167.8071045	total: 12.7s	remaining: 324ms
975:	learn: 14641845.3365852	total: 12.7s	remaining: 311ms
976:	learn: 14640306.5144587	total: 12.7s	remaining: 298ms
977:	learn: 14640184.9147582	total: 12.7s	remaining: 286ms
978:	learn: 14640008.8483425	total: 12.7s	remaining: 273ms
979:	learn: 14636344.5519428	total: 12.7s	remaining: 260ms
980:	learn: 14633576.2663352	total: 12.7s	remaining: 247ms
981:	learn: 14624796.2134142	total: 12.7s	remaining: 234ms
982:	learn: 14624250.6774943	total: 12.8s	remaining: 221ms
983:	learn: 14615917.0650799	total: 12.8s	remaining: 208ms
984:	learn: 14615782.8388140	total: 12.8s	remaining: 195ms
985:	learn: 14612724.2754075	total: 12.8s	remaining: 182ms
986:	learn: 14609973.2837772	total: 12.8s	remaining: 169ms
987:	learn: 14605203.8050795	total: 12.8s	remaining: 156ms
988:	learn: 14605011.6874159	total: 12.8s	remaining: 143ms
989:	learn: 14594552.7887146	total: 12.8s	remaining: 130ms
990:	learn: 14591881.9316489	total: 12.9s	remaining: 117ms
991:	learn: 14581962.3358039	total: 12.9s	remaining: 104ms
992:	learn: 14581829.5331587	total: 12.9s	remaining: 90.8ms
993:	learn: 14581669.7347033	total: 12.9s	remaining: 77.9ms
994:	learn: 14577373.3119596	total: 12.9s	remaining: 64.9ms
995:	learn: 14577196.6327960	total: 12.9s	remaining: 51.9ms
996:	learn: 14577122.1536884	total: 12.9s	remaining: 38.9ms
997:	learn: 14574702.1336653	total: 12.9s	remaining: 25.9ms
998:	learn: 14574660.6060510	total: 13s	remaining: 13ms
999:	learn: 14574625.9856659	total: 13s	remaining: 0us

Pipeline(steps=[('preprocessor',
                 ColumnTransformer(transformers=[('num', StandardScaler(),
                                                  ['geo_lat', 'geo_lon',
                                                   'level', 'levels', 'rooms',
                                                   'area', 'kitchen_area']),
                                                 ('cat',
                                                  OrdinalEncoder(handle_unknown='use_encoded_value',
                                                                 unknown_value=99999999),
                                                  ['region', 'building_type',
                                                   'object_type'])])),
                ('model',
                 <catboost.core.CatBoostRegressor object at 0x7be8319969b0>)])

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Pipeline

Pipeline(steps=[('preprocessor',
                 ColumnTransformer(transformers=[('num', StandardScaler(),
                                                  ['geo_lat', 'geo_lon',
                                                   'level', 'levels', 'rooms',
                                                   'area', 'kitchen_area']),
                                                 ('cat',
                                                  OrdinalEncoder(handle_unknown='use_encoded_value',
                                                                 unknown_value=99999999),
                                                  ['region', 'building_type',
                                                   'object_type'])])),
                ('model',
                 <catboost.core.CatBoostRegressor object at 0x7be8319969b0>)])

preprocessor: ColumnTransformer

ColumnTransformer(transformers=[('num', StandardScaler(),
                                 ['geo_lat', 'geo_lon', 'level', 'levels',
                                  'rooms', 'area', 'kitchen_area']),
                                ('cat',
                                 OrdinalEncoder(handle_unknown='use_encoded_value',
                                                unknown_value=99999999),
                                 ['region', 'building_type', 'object_type'])])

num

['geo_lat', 'geo_lon', 'level', 'levels', 'rooms', 'area', 'kitchen_area']

StandardScaler

StandardScaler()

cat

['region', 'building_type', 'object_type']

OrdinalEncoder

OrdinalEncoder(handle_unknown='use_encoded_value', unknown_value=99999999)

CatBoostRegressor

<catboost.core.CatBoostRegressor object at 0x7be8319969b0>

        model_params = {
            "geo_lat":56.327686,
            "geo_lon":43.928062,
            "region":2871.000000,
            "building_type":1.000000,
            "level":8.000000,
            "levels":10.000000,
            "rooms":2.000000,
            "area":56.000000,
            "kitchen_area":8.500000,
            "object_type":1.000000,
            "floor_level":0,
            }
        df_pred = pd.DataFrame(model_params, index=[0])

pipeline.predict(df_pred)

array([3414175.89042869])

predictions = pipeline.predict(X_test) 

metrics = {}
metrics["mae"] = mean_absolute_error(y_test, predictions)   
metrics["mape"] = mean_absolute_percentage_error(y_test, predictions)
metrics["mse"] = mean_squared_error(y_test, predictions)

metrics

{'mae': 1447931.3425270966,
 'mape': 1.6294525363466488e+18,
 'mse': 281898017343454.56}

# Работаем с MLflow локально
TRACKING_SERVER_HOST = "127.0.0.1"
TRACKING_SERVER_PORT = 5000

registry_uri = f"http://{TRACKING_SERVER_HOST}:{TRACKING_SERVER_PORT}"
tracking_uri = f"http://{TRACKING_SERVER_HOST}:{TRACKING_SERVER_PORT}"

mlflow.set_tracking_uri(tracking_uri)   
mlflow.set_registry_uri(registry_uri)   

# название тестового эксперимента, запуска (run) внутри него, имени, под которым модель будет регистрироваться
EXPERIMENT_NAME = "estate_project"
RUN_NAME = "baseline model"
REGISTRY_MODEL_NAME = "estate_model_rf"

Логируем вручную

# Обязательно логируем сигнатуру модели и пример входных данных. Подготовим их
from mlflow.models import infer_signature

signature =  infer_signature(model_input = X_train.head(5))
input_example = X_train.head(5)

# Будем логировать requirements и артефакт - текстовый файл
req_file = 'requirements.txt'
art = 'comment.txt'

# Параметры, котороые будут залогированы, можем задавать вручную или полностью взять из модели
#params_dict = {'n_estimators': 10, 'max_depth': 10}
params_dict = pipeline.get_params()

# Когда создаем новый эксперимент, то: 
experiment_id = mlflow.create_experiment(EXPERIMENT_NAME)

# Впоследствии. чтобы добавлять запуски в этот же эксепримент мы должны получить его id:
#experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id

with mlflow.start_run(run_name=RUN_NAME, experiment_id=experiment_id) as run:
    # получаем уникальный идентификатор запуска эксперимента
    run_id = run.info.run_id 
    mlflow.sklearn.log_model(pipeline, 
                             artifact_path="models",
                             signature=signature,
                             input_example=input_example,
                             pip_requirements=req_file
                             )
    mlflow.log_metrics(metrics)
    mlflow.log_artifact(art)
    mlflow.log_params(params_dict)

run = mlflow.get_run(run_id) 
assert (run.info.status =='FINISHED')

Удаление runs, experiments

Использовать осторожно

experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id
#mlflow.delete_experiment(experiment_id)

mlflow.search_runs(
    #experiment_ids=[experiment_id],
    experiment_names=[EXPERIMENT_NAME],
    # filter_string='status = "FAILED"'
    #filter_string='metrics.mae > 1'
    
)

#mlflow.delete_run('74d2a7a40c07413c9cf65df841164356')

Автологирование

После включения будет срабатывать на каждом обучении модели (на методе fit()).

Есть плюсы, есть и минусы. Предлагается сделать прогон и сравнить с результатами вручную

mlflow.sklearn.autolog()

with mlflow.start_run(run_name='auto', experiment_id=experiment_id) as run:
    pipeline.fit(X_train, y_train)

# Отключаем автологирование
mlflow.sklearn.autolog(disable=True)

Model #2

Обучим вторую "маленькую" модель

regressor2 = RandomForestRegressor(n_estimators=10, max_depth=6)

pipeline = Pipeline(steps=[('preprocessor', preprocessor), 
                           ('model', regressor2)])

pipeline.fit(X_train, y_train)

predictions = pipeline.predict(X_test) 
metrics = {}
metrics["mae"] = mean_absolute_error(y_test, predictions)   
metrics["mape"] = mean_absolute_percentage_error(y_test, predictions)
metrics["mse"] = mean_squared_error(y_test, predictions)

metrics

# !!! Проверить название прогона а также все логируемые параметры и артефакты, что они соответствуют второй "маленькой" модели. 


RUN_NAME = 'smaller_model'

experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id

with mlflow.start_run(run_name=RUN_NAME, experiment_id=experiment_id) as run:
    # получаем уникальный идентификатор запуска эксперимента
    run_id = run.info.run_id 
    mlflow.sklearn.log_model(pipeline, 
                             artifact_path="models",
                             signature=signature,
                             input_example=input_example,
                             pip_requirements=req_file
                             )
    mlflow.log_metrics(metrics)
    mlflow.log_artifact(art)
    mlflow.log_params(pipeline.get_params())

run = mlflow.get_run(run_id) 
assert (run.info.status =='FINISHED')

# No model
# Логировать можно только артефакты, без модели. Например, залогироавть графики после этапа EDA

RUN_NAME = 'no_model'
experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id

with mlflow.start_run(run_name=RUN_NAME, experiment_id=experiment_id) as run:
    run_id = run.info.run_id 
    mlflow.log_artifact(art)


run = mlflow.get_run(run_id) 
assert (run.info.status =='FINISHED')

run_id = '06fa7ec1f1b74aedb3509c88dc4ee1c0' # Указываем run id
mlflow.register_model(f"runs:/{run_id}/models", REGISTRY_MODEL_NAME)

# Можно регистрировать сразу при создании прогона

experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id

with mlflow.start_run(run_name='register_at_run', experiment_id=experiment_id) as run:
    # получаем уникальный идентификатор запуска эксперимента
    run_id = run.info.run_id 
    mlflow.sklearn.log_model(pipeline, 
                             artifact_path="models",
                             signature=signature,
                             input_example=input_example,
                             pip_requirements=req_file,
                             registered_model_name = REGISTRY_MODEL_NAME # Указываем для какой модели регистрируем
                             )
    mlflow.log_metrics(metrics)
    mlflow.log_artifact(art)
    mlflow.log_params(pipeline.get_params())

run = mlflow.get_run(run_id) 
assert (run.info.status =='FINISHED')

# Можно найти зарегистрированные модели
model_reg = mlflow.search_registered_models()
model_reg[0]

model_name = REGISTRY_MODEL_NAME
model_version = 1

model_loaded = mlflow.sklearn.load_model(model_uri=f"models:/{model_name}/{model_version}")

model_loaded.predict(X_test.iloc[0:1])

y_test.iloc[0]

Feature engineering

Sklearn

from sklearn.preprocessing import QuantileTransformer, SplineTransformer, PolynomialFeatures, MinMaxScaler

X_train_sklearn = X_train.copy()

PolynomialFeatures

Создает полином степени degree из указанных признаков

pf = PolynomialFeatures(degree=2)

X_train_sklearn

pf.fit_transform(X_train_sklearn[['area','kitchen_area']])

SplineTransformer

Cоздаёт новую матрицу признаков, состоящую из сплайнов порядка degree. Количество сгенерированных сплайнов равно n_splines=n_knots + degree - 1 для каждого признака, где

n_knots определяет количество узлов (точек, в которых сопрягаются сплайны) для каждого признака.

degree определяет порядок полинома, используемого для построения сплайнов.

sp = SplineTransformer(n_knots=3, degree=3)

sp.fit_transform(X_train_sklearn[['area']])

QuantileTransformer

Этот метод преобразует признаки, чтобы они распределялись равномерно или нормально — так данные меньше подвергаются влиянию выбросов. Преобразование применяется к каждому признаку независимо. Идея метода такова: оценить функцию распределения признака, чтобы преобразовать исходные значения в равномерное или нормальное распределение.

output_distribution='uniform' или output_distribution='normal' соответственно

Пример использования: если у вас есть данные о доходах с широким диапазоном значений, квантильное преобразование сделает их более сопоставимыми и устойчивыми к выбросам.

qt = QuantileTransformer()

qt.fit_transform(X_train_sklearn[['area']])

Объединяем в ColumnTransformer и создаем Pipeline

pf = PolynomialFeatures(degree=2)
qt = QuantileTransformer()
sp = SplineTransformer(n_knots=3, degree=3)

# Значения преобразованных признаков нужно отскейлить, поэтому создаем pipeline из двух шагов - преобразование и скейлинг
pf_pipeline = Pipeline(steps=[
    ('poly', pf),
    ('scale', StandardScaler())
])

preprocessor_sklearn = ColumnTransformer(
    transformers=[
        ('num', s_scaler, num_features),  # преобразования для числовых признаков
        ('cat', l_encoder, cat_features), # преобразования для категориальных признаков
        ('quantile', qt,num_features),
        ('poly', pf_pipeline, ['area', 'kitchen_area']), # В преобразования добавляем созданный ранее pipeline
        ('spline', sp, ['area'])
    ],
    remainder='drop',
    ) # Удаляем столбцы, которые не затронуты преобразования

Посмотрим что из себя теперь представляет датафрейм

## не влезаем в float64 в полиномальном преобразовании. Использовать его нужно с умом!
X_train_sklearn[['area', 'kitchen_area']] = X_train_sklearn[['area', 'kitchen_area']].astype('float128')
X_train_sklearn[['area', 'kitchen_area']] = X_train_sklearn[['area', 'kitchen_area']].astype('float128')

X_train_sklearn_raw = preprocessor_sklearn.fit_transform(X_train_sklearn)
X_train_sklearn = pd.DataFrame(X_train_sklearn_raw, columns=preprocessor_sklearn.get_feature_names_out())

# Удобно использовать для отображения всех строк\столбцов в DataFrame
with pd.option_context('display.max_rows', 5, 'display.max_columns', None):
    display (X_train_sklearn)

	num__geo_lat	num__geo_lon	num__level	num__levels	num__rooms	num__area	num__kitchen_area	cat__region	cat__building_type	cat__object_type	quantile__geo_lat	quantile__geo_lon	quantile__level	quantile__levels	quantile__rooms	quantile__area	quantile__kitchen_area	poly__1	poly__area	poly__kitchen_area	poly__area^2	poly__area kitchen_area	poly__kitchen_area^2	spline__area_sp_0	spline__area_sp_1	spline__area_sp_2	spline__area_sp_3	spline__area_sp_4
0	0.495902	-0.449742	0.359235	-0.214789	0.253413	0.063735	-0.186285	20.0	1.0	0.0	0.766257	0.511028	0.717217	0.536537	0.600601	0.623624	0.374875	0.0	0.063735	-0.186285	-0.010002	-0.132188	-0.002792	0.155806	0.666179	0.178013	0.000002	0.0
1	0.177806	1.433673	-0.246529	-0.367718	0.253413	-0.114293	-0.186285	70.0	1.0	0.0	0.297142	0.867999	0.522022	0.386887	0.600601	0.541542	0.374875	0.0	-0.114293	-0.186285	-0.017375	-0.169370	-0.002792	0.156921	0.666275	0.176803	0.000001	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
410773	-0.748366	-0.804077	-0.650371	0.702788	0.253413	1.365441	1.501833	52.0	3.0	0.0	0.193143	0.114753	0.309810	0.741742	0.600601	0.961367	0.984535	0.0	1.365441	1.501833	0.068438	1.570163	0.008616	0.147820	0.665159	0.187011	0.000010	0.0
410774	1.257769	-1.101815	-0.044608	0.091070	1.175911	0.553789	-0.142544	14.0	1.0	0.0	0.908036	0.075725	0.604605	0.645646	0.867367	0.841842	0.436436	0.0	0.553789	-0.142544	0.014463	-0.002742	-0.002649	0.152767	0.665860	0.181370	0.000004	0.0

410775 rows × 28 columns

Создаем пайплайн с препроцессингом и моделью

pipeline_sklearn = Pipeline(steps=[
    ('transform', preprocessor_sklearn),
    ('model', regressor)
])

model_sklearn = pipeline_sklearn.fit(X_train, y_train)

model_sklearn

predictions = model_sklearn.predict(X_test) 
metrics = {}
metrics["mae"] = mean_absolute_error(y_test, predictions)   
metrics["mape"] = mean_absolute_percentage_error(y_test, predictions)
metrics["mse"] = mean_squared_error(y_test, predictions)

metrics

experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id
RUN_NAME = 'fe_sklearn'

with mlflow.start_run(run_name=RUN_NAME, experiment_id=experiment_id) as run:
    # получаем уникальный идентификатор запуска эксперимента
    run_id = run.info.run_id 
    mlflow.sklearn.log_model(model_sklearn, 
                             artifact_path="models",
                             signature=signature,
                             input_example=input_example,
                             pip_requirements=req_file
                             )
    mlflow.log_metrics(metrics)
    mlflow.log_artifact(art)
    mlflow.log_params(model_sklearn.get_params())

run = mlflow.get_run(run_id) 
assert (run.info.status =='FINISHED')

Autofeat

from autofeat import AutoFeatRegressor
transformations = ["1/", "exp", "log", "abs", "sqrt", "^2", "^3", "1+", "1-", "sin", "cos", "exp-", "2^"] 

afreg = AutoFeatRegressor(verbose=1, feateng_steps=2, max_gb=8, transformations=["log", "sqrt"],feateng_cols=num_features)
X_train_arf = afreg.fit_transform(X_train,y_train)
X_train_arf

# Создаем обертку, в которой добавляем метод get_feature_names_out() для получения названий признаков
import numpy as np

class AutoFeatWrapper():
    def __init__(self, feateng_cols, feateng_steps=1, max_gb=16, transformations=["1/", "exp", "log"], n_jobs=-1, verbose=1):
        self.feateng_cols = feateng_cols
        self.feateng_steps = feateng_steps
        self.max_gb = max_gb
        self.transformations = transformations
        self.n_jobs = n_jobs
        self.afreg = AutoFeatRegressor(feateng_cols=self.feateng_cols,
                                     feateng_steps=self.feateng_steps,
                                     max_gb=self.max_gb,
                                     transformations=self.transformations,
                                     n_jobs=self.n_jobs)
        
    def fit(self, X, y=None):
        self.afreg.fit(X, y)
        return self
    
    def transform(self, X):
        return self.afreg.transform(X)
    
    def get_feature_names_out(self, input_features=None):
        # Преобразуем данные и возвращаем имена фичей из DataFrame
        transformed_X = self.afreg.transform(pd.DataFrame(np.zeros((1, len(self.feateng_cols))), columns=self.feateng_cols))
        return transformed_X.columns.tolist()

afreg_pipeline = Pipeline(steps=[
    ('autofeat', AutoFeatWrapper( feateng_steps=2, max_gb=16, transformations=["log", "sqrt"],feateng_cols=num_features)),
    ('scaler', StandardScaler()),
])

preprocessor_afr = ColumnTransformer(
    transformers=[
        ('num', s_scaler, num_features),  # преобразования для числовых признаков
        ('cat', l_encoder, cat_features), # преобразования для категориальных признаков
        ('afr', afreg_pipeline, num_features), # преобразования autofeat
    ],
    remainder='drop', # Удаляем столбцы, которые не затронуты преобразованиями
    ) 

X_train_afr_raw =  preprocessor_afr.fit_transform(X_train,y_train)
X_train_afr = pd.DataFrame(X_train_afr_raw, columns=preprocessor_afr.get_feature_names_out())

with pd.option_context('display.max_rows', 5, 'display.max_columns', None):
    display (X_train_afr)

	num__geo_lat	num__geo_lon	num__level	num__levels	num__rooms	num__area	num__kitchen_area	cat__region	cat__building_type	cat__object_type	afr__geo_lat	afr__geo_lon	afr__level	afr__levels	afr__rooms	afr__area	afr__kitchen_area	afr__area*rooms	afr__area*geo_lon	afr__levels*rooms	afr__area*kitchen_area	afr__sqrt(area)*geo_lat	afr__sqrt(area)*log(level)	afr__kitchen_area*log(level)	afr__sqrt(area)*kitchen_area	afr__geo_lon*log(kitchen_area)	afr__sqrt(area)*sqrt(kitchen_area)	afr__sqrt(geo_lon)*sqrt(kitchen_area)	afr__log(area)	afr__rooms*log(level)	afr__kitchen_area*rooms	afr__kitchen_area*levels	afr__sqrt(geo_lon)*sqrt(level)	afr__area**(3/2)	afr__geo_lat*log(kitchen_area)	afr__geo_lat*log(geo_lon)
0	0.495902	-0.449742	0.359235	-0.214789	0.253413	0.063735	-0.186285	20.0	1.0	0.0	0.495902	-0.449742	0.359235	-0.214789	0.253413	0.063735	-0.186285	0.006208	-0.195129	0.060916	-0.132188	0.373151	0.688076	0.044178	-0.211335	-0.481294	-0.153548	-0.490805	0.307835	0.690329	-0.132529	-0.352834	0.323880	-0.008748	-0.031529	0.068167
1	0.177806	1.433673	-0.246529	-0.367718	0.253413	-0.114293	-0.186285	70.0	1.0	0.0	0.177806	1.433673	-0.246529	-0.367718	0.253413	-0.114293	-0.186285	-0.083402	0.655053	-0.054279	-0.169370	0.005114	0.071369	-0.173647	-0.252775	1.191304	-0.267268	0.615798	0.031907	0.282625	-0.132529	-0.418643	0.552794	-0.056540	-0.143829	1.129118
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
410773	-0.748366	-0.804077	-0.650371	0.702788	0.253413	1.365441	1.501833	52.0	3.0	0.0	-0.748366	-0.804077	-0.650371	0.702788	0.253413	1.365441	1.501833	0.661427	0.375199	0.752088	1.570163	1.274445	-0.002521	0.745507	2.382258	0.071599	2.828890	1.431272	1.729715	-0.160491	1.581436	2.432437	-0.843150	0.411475	1.671069	-1.052343
410774	1.257769	-1.101815	-0.044608	0.091070	1.175911	0.553789	-0.142544	14.0	1.0	0.0	1.257769	-1.101815	-0.044608	0.091070	1.175911	0.553789	-0.142544	0.807887	-0.330070	0.982478	-0.002742	1.338996	0.635065	-0.040302	-0.055435	-1.025588	0.202136	-0.916054	0.940624	1.217910	0.311575	-0.174762	-0.415359	0.135617	0.359680	-0.246790

410775 rows × 36 columns

pipeline_afr = Pipeline(steps=[('preprocessor', preprocessor_afr), 
                               ('model', regressor)])

pipeline_afr.fit(X_train, y_train)

predictions = pipeline_afr.predict(X_test) 

metrics = {}
metrics["mae"] = mean_absolute_error(y_test, predictions)   
metrics["mape"] = mean_absolute_percentage_error(y_test, predictions)
metrics["mse"] = mean_squared_error(y_test, predictions)

metrics

experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id

with mlflow.start_run(run_name='autofeat', experiment_id=experiment_id) as run:
    # получаем уникальный идентификатор запуска эксперимента
    run_id = run.info.run_id 
    mlflow.sklearn.log_model(pipeline_afr, 
                             artifact_path="models",
                             signature=signature,
                             input_example=input_example,
                             pip_requirements=req_file
                             )
    mlflow.log_metrics(metrics)
    mlflow.log_artifact(art)
    mlflow.log_params(pipeline_afr.get_params())

run = mlflow.get_run(run_id) 
assert (run.info.status =='FINISHED')

FEATURE SELECTION

RFE

Используем autofeat признаки

Поскольку autofeat дает разные совокупности сгенерированных признаков, мы можем добавить выбор информативных только как шаг пайплайна

from sklearn.feature_selection import RFE
X_train_afr

	num__geo_lat	num__geo_lon	num__level	num__levels	num__rooms	num__area	num__kitchen_area	cat__region	cat__building_type	cat__object_type	...	afr__sqrt(area)*sqrt(kitchen_area)	afr__sqrt(geo_lon)*sqrt(kitchen_area)	afr__log(area)	afr__rooms*log(level)	afr__kitchen_area*rooms	afr__kitchen_area*levels	afr__sqrt(geo_lon)*sqrt(level)	afr__area**(3/2)	afr__geo_lat*log(kitchen_area)	afr__geo_lat*log(geo_lon)
0	0.495902	-0.449742	0.359235	-0.214789	0.253413	0.063735	-0.186285	20.0	1.0	0.0	...	-0.153548	-0.490805	0.307835	0.690329	-0.132529	-0.352834	0.323880	-0.008748	-0.031529	0.068167
1	0.177806	1.433673	-0.246529	-0.367718	0.253413	-0.114293	-0.186285	70.0	1.0	0.0	...	-0.267268	0.615798	0.031907	0.282625	-0.132529	-0.418643	0.552794	-0.056540	-0.143829	1.129118
2	0.440548	0.047222	-0.448450	-0.367718	-0.669085	-0.456947	-0.142544	15.0	3.0	1.0	...	-0.454880	-0.067183	-0.603122	-0.512211	-0.487813	-0.383803	-0.243092	-0.140800	0.063464	0.460495
3	-1.588818	-0.722477	-0.246529	-0.979436	0.253413	-0.181292	-0.142544	18.0	1.0	0.0	...	-0.254514	-0.607607	-0.080304	0.282625	-0.088119	-0.662523	-0.369355	-0.073838	-0.672113	-1.481033
4	1.493662	1.125819	0.157313	0.549858	0.253413	0.615045	-0.011322	10.0	2.0	0.0	...	0.438600	0.891383	1.009612	0.574497	0.045112	0.208478	0.945981	0.154902	0.780855	1.923382
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
410770	0.592011	0.355014	0.561156	1.008646	0.253413	-0.079836	-0.092653	54.0	2.0	0.0	...	-0.120035	0.237580	0.087725	0.792500	-0.037463	0.322797	0.974381	-0.047496	0.243018	0.789871
410771	0.240478	0.392697	-0.650371	-0.979436	0.253413	-0.334434	-0.404989	45.0	3.0	0.0	...	-0.716150	-0.510766	-0.357277	-0.160491	-0.354582	-0.778657	-0.406361	-0.111897	-0.808157	0.574534
410772	-1.936771	-0.688830	0.359235	0.855717	-0.669085	-0.456947	-0.142544	18.0	0.0	1.0	...	-0.454880	-0.581851	-0.603122	-0.211576	-0.487813	0.173638	0.170166	-0.140800	-0.798234	-1.663294
410773	-0.748366	-0.804077	-0.650371	0.702788	0.253413	1.365441	1.501833	52.0	3.0	0.0	...	2.828890	1.431272	1.729715	-0.160491	1.581436	2.432437	-0.843150	0.411475	1.671069	-1.052343
410774	1.257769	-1.101815	-0.044608	0.091070	1.175911	0.553789	-0.142544	14.0	1.0	0.0	...	0.202136	-0.916054	0.940624	1.217910	0.311575	-0.174762	-0.415359	0.135617	0.359680	-0.246790

410775 rows × 36 columns

rfe_selector = RFE(estimator=regressor, n_features_to_select=12, step = 0.2) #drop 20% of features each iteration
X_train_rfe = rfe_selector.fit_transform(X_train_afr,y_train)

X_train_afr_rfe = pd.DataFrame(X_train_rfe, columns=rfe_selector.get_feature_names_out())
X_train_afr_rfe

	num__geo_lat	num__geo_lon	afr__geo_lon	afr__area*kitchen_area	afr__sqrt(area)*geo_lat	afr__sqrt(area)*log(level)	afr__kitchen_area*log(level)	afr__sqrt(area)*sqrt(kitchen_area)	afr__rooms*log(level)	afr__kitchen_area*rooms	afr__sqrt(geo_lon)*sqrt(level)	afr__geo_lat*log(geo_lon)
0	0.495902	-0.449742	-0.449742	-0.132188	0.373151	0.688076	0.044178	-0.153548	0.690329	-0.132529	0.323880	0.068167
1	0.177806	1.433673	1.433673	-0.169370	0.005114	0.071369	-0.173647	-0.267268	0.282625	-0.132529	0.552794	1.129118
2	0.440548	0.047222	0.047222	-0.226261	-0.425530	-0.335537	-0.239271	-0.454880	-0.512211	-0.487813	-0.243092	0.460495
3	-1.588818	-0.722477	-0.722477	-0.165302	-0.723225	0.034116	-0.129771	-0.254514	0.282625	-0.088119	-0.369355	-1.481033
4	1.493662	1.125819	1.125819	0.094342	1.522265	0.862773	0.194490	0.438600	0.574497	0.045112	0.945981	1.923382
...	...	...	...	...	...	...	...	...	...	...	...	...
410770	0.592011	0.355014	0.355014	-0.120841	0.206926	0.714499	0.226990	-0.120035	0.792500	-0.037463	0.974381	0.789871
410771	0.240478	0.392697	0.392697	-0.296252	-0.297209	-0.551021	-0.560144	-0.716150	-0.160491	-0.354582	-0.406361	0.574534
410772	-1.936771	-0.688830	-0.688830	-0.226261	-1.192706	0.306280	0.100868	-0.454880	-0.211576	-0.487813	0.170166	-1.663294
410773	-0.748366	-0.804077	-0.804077	1.570163	1.274445	-0.002521	0.745507	2.828890	-0.160491	1.581436	-0.843150	-1.052343
410774	1.257769	-1.101815	-1.101815	-0.002742	1.338996	0.635065	-0.040302	0.202136	1.217910	0.311575	-0.415359	-0.246790

410775 rows × 12 columns

rfe_pipeline = Pipeline(steps=[
    ('preprocessor', preprocessor_afr), 
    ('rfe_extractor', RFE(estimator=regressor, n_features_to_select=12, step = 0.2)),
    ('model', regressor)
])

rfe_pipeline.fit(X_train, y_train)

predictions_rfe = rfe_pipeline.predict(X_test)

metrics = {}
metrics["mae"] = mean_absolute_error(y_test, predictions_rfe)   
metrics["mape"] = mean_absolute_percentage_error(y_test, predictions_rfe)
metrics["mse"] = mean_squared_error(y_test, predictions_rfe)

metrics

{'mae': 1431925.3203264712,
 'mape': 1.239752923791043e+18,
 'mse': 261947924998018.2}

experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id
RUN_NAME = 'rfe_feature_selection'

with mlflow.start_run(run_name=RUN_NAME, experiment_id=experiment_id) as run:
    # получаем уникальный идентификатор запуска эксперимента
    run_id = run.info.run_id 
    mlflow.sklearn.log_model(rfe_pipeline, 
                             artifact_path="models",
                             signature=signature,
                             input_example=input_example,
                             pip_requirements=req_file
                             )
    mlflow.log_metrics(metrics)
    mlflow.log_artifact(art)
    mlflow.log_params(model_sklearn.get_params())

run = mlflow.get_run(run_id) 
assert (run.info.status =='FINISHED')

Downloading artifacts: 100%|██████████| 7/7 [00:00<00:00, 40.15it/s]
2024/10/17 14:26:50 INFO mlflow.tracking._tracking_service.client: 🏃 View run rfe_feature_selection at: http://127.0.0.1:5000/#/experiments/1/runs/96f0bbcd6d88466abcf38f3b53f06ff1.
2024/10/17 14:26:50 INFO mlflow.tracking._tracking_service.client: 🧪 View experiment at: http://127.0.0.1:5000/#/experiments/1.

Используем sklearn признаки

Тут мы можем отобрать признаки один раз на обучении, а далее в качестве шага пайплайна использовать написанный класс ColumnExtractor для выбора нуных столбцов

rfe_skl_selector = RFE(estimator=regressor, n_features_to_select=12, step = 0.2) #drop 20% of features each iteration
X_train_skl_rfe = rfe_skl_selector.fit_transform(X_train_sklearn,y_train)

X_train_skl_rfe = pd.DataFrame(X_train_skl_rfe, columns=rfe_skl_selector.get_feature_names_out())
X_train_skl_rfe

	num__geo_lat	num__geo_lon	num__level	num__rooms	num__kitchen_area	cat__region	quantile__geo_lat	quantile__geo_lon	quantile__level	poly__area kitchen_area	spline__area_sp_0	spline__area_sp_2
0	0.495902	-0.449742	0.359235	0.253413	-0.186285	20.0	0.766257	0.511028	0.717217	-0.132188	0.155806	0.178013
1	0.177806	1.433673	-0.246529	0.253413	-0.186285	70.0	0.297142	0.867999	0.522022	-0.169370	0.156921	0.176803
2	0.440548	0.047222	-0.448450	-0.669085	-0.142544	15.0	0.732330	0.629984	0.417417	-0.226261	0.159080	0.174488
3	-1.588818	-0.722477	-0.246529	0.253413	-0.142544	18.0	0.148789	0.295262	0.522022	-0.165302	0.157341	0.176349
4	1.493662	1.125819	0.157313	0.253413	-0.011322	10.0	0.985937	0.758363	0.662663	0.094342	0.152390	0.181792
...	...	...	...	...	...	...	...	...	...	...	...	...
410770	0.592011	0.355014	0.561156	0.253413	-0.092653	54.0	0.788393	0.686728	0.771271	-0.120841	0.156705	0.177037
410771	0.240478	0.392697	-0.650371	0.253413	-0.404989	45.0	0.494062	0.717240	0.309810	-0.296252	0.158306	0.175314
410772	-1.936771	-0.688830	0.359235	-0.669085	-0.142544	18.0	0.131352	0.327613	0.717217	-0.226261	0.159080	0.174488
410773	-0.748366	-0.804077	-0.650371	0.253413	1.501833	52.0	0.193143	0.114753	0.309810	1.570163	0.147820	0.187011
410774	1.257769	-1.101815	-0.044608	1.175911	-0.142544	14.0	0.908036	0.075725	0.604605	-0.002742	0.152767	0.181370

410775 rows × 12 columns

rfe_cols = X_train_skl_rfe.columns.tolist()
rfe_cols

['num__geo_lat',
 'num__geo_lon',
 'num__level',
 'num__rooms',
 'num__kitchen_area',
 'cat__region',
 'quantile__geo_lat',
 'quantile__geo_lon',
 'quantile__level',
 'poly__area kitchen_area',
 'spline__area_sp_0',
 'spline__area_sp_2']

rfe_idx = rfe_skl_selector.support_
rfe_idx

array([ True,  True,  True, False,  True, False,  True,  True, False,
       False,  True,  True,  True, False, False, False, False, False,
       False, False, False,  True, False,  True, False,  True, False,
       False])

# Отбираемые столбцы нужно залогировать, иначе мы потеряем информацию о том, какие призныки выбраны
with open('rfe_skl_idx.txt', 'w+') as f:
    f.write(str(rfe_idx))
with open('rfe_skl_cols.txt', 'w+') as f:
    f.write(str(rfe_cols))

class ColumnExtractor(object):

    def __init__(self, cols):
        self.cols = cols

    def transform(self, X):
        return X[:,self.cols]
    
    def fit(self, X, y=None):
        return self

rfe_skl_pipeline = Pipeline(steps=[
    ('preprocessor', preprocessor_sklearn), 
    ('rfe_extractor', ColumnExtractor(rfe_idx)),
    ('model', regressor)
])

rfe_skl_pipeline.fit(X_train, y_train)

predictions_rfe_skl = rfe_skl_pipeline.predict(X_test)

metrics = {}
metrics["mae"] = mean_absolute_error(y_test, predictions_rfe_skl)   
metrics["mape"] = mean_absolute_percentage_error(y_test, predictions_rfe_skl)
metrics["mse"] = mean_squared_error(y_test, predictions_rfe_skl)

metrics
experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id
RUN_NAME = 'rfe_skl_feature_selection'

with mlflow.start_run(run_name=RUN_NAME, experiment_id=experiment_id) as run:
    # получаем уникальный идентификатор запуска эксперимента
    run_id = run.info.run_id 
    mlflow.sklearn.log_model(rfe_pipeline, 
                             artifact_path="models",
                             signature=signature,
                             input_example=input_example,
                             pip_requirements=req_file
                             )
    mlflow.log_metrics(metrics)
    mlflow.log_artifact('rfe_skl_cols.txt')
    mlflow.log_artifact('rfe_skl_idx.txt')
    mlflow.log_params(model_sklearn.get_params())

run = mlflow.get_run(run_id) 
assert (run.info.status =='FINISHED')

Downloading artifacts: 100%|██████████| 7/7 [00:00<00:00, 193.34it/s]
2024/10/17 14:32:07 INFO mlflow.tracking._tracking_service.client: 🏃 View run rfe_skl_feature_selection at: http://127.0.0.1:5000/#/experiments/1/runs/e55206caeb1549e4aa0d98343d5c1d4d.
2024/10/17 14:32:07 INFO mlflow.tracking._tracking_service.client: 🧪 View experiment at: http://127.0.0.1:5000/#/experiments/1.

mlextend

https://github.com/rasbt/mlxtend/blob/master/docs/sources/user_guide/feature_selection/SequentialFeatureSelector.ipynb

from mlxtend.feature_selection import SequentialFeatureSelector 
#from sklearn.feature_selection import SequentialFeatureSelector

sfs = SequentialFeatureSelector(RandomForestRegressor(n_estimators=3), 
                                k_features=3,
                                forward=True,
                                floating=False, # True to drop selected features
                                scoring='neg_mean_absolute_error',
                                cv=2)

sfs.fit(X_train_sklearn,y_train)

selected_features_sfs = X_train_sklearn.loc[:, sfs.k_feature_names_]
selected_features_sfs

	num__geo_lon	quantile__geo_lat	spline__area_sp_3
0	-0.449742	0.766257	1.826008e-06
1	1.433673	0.297142	1.310449e-06
2	0.047222	0.732330	6.098363e-07
3	-0.722477	0.148789	1.144942e-06
4	1.125819	0.985937	4.240047e-06
...	...	...	...
410770	0.355014	0.788393	1.401454e-06
410771	0.392697	0.494062	8.202272e-07
410772	-0.688830	0.131352	6.098363e-07
410773	-0.804077	0.193143	1.004843e-05
410774	-1.101815	0.908036	3.903343e-06

410775 rows × 3 columns

rfe_sfs_idx = list(sfs.k_feature_idx_)
rfe_sfs_idx
rfe_sfs_col = list(sfs.k_feature_names_)
rfe_sfs_col

['num__geo_lon', 'quantile__geo_lat', 'spline__area_sp_3']

import matplotlib.pyplot as plt
from mlxtend.plotting import plot_sequential_feature_selection as plot_sfs

fig = plot_sfs(sfs.get_metric_dict(), kind='std_dev')

plt.title('Sequential Forward Selection (w. StdDev)')
plt.grid()
plt.show()

rfe_sfs_pipeline = Pipeline(steps=[
    ('preprocessor', preprocessor_sklearn), 
    ('rfe_extractor', ColumnExtractor(rfe_sfs_idx)),
    ('model', regressor)
])

rfe_sfs_pipeline.fit(X_train, y_train)

predictions_sfs = rfe_sfs_pipeline.predict(X_test)

metrics = {}
metrics["mae"] = mean_absolute_error(y_test, predictions_sfs)   
metrics["mape"] = mean_absolute_percentage_error(y_test, predictions_sfs)
metrics["mse"] = mean_squared_error(y_test, predictions_sfs)

metrics
experiment_id = mlflow.get_experiment_by_name(EXPERIMENT_NAME).experiment_id
RUN_NAME = 'rfe_sfs_feature_selection'

with mlflow.start_run(run_name=RUN_NAME, experiment_id=experiment_id) as run:
    # получаем уникальный идентификатор запуска эксперимента
    run_id = run.info.run_id 
    mlflow.sklearn.log_model(rfe_sfs_pipeline, 
                             artifact_path="models",
                             signature=signature,
                             input_example=input_example,
                             pip_requirements=req_file
                             )
    mlflow.log_metrics(metrics)
    mlflow.log_artifact('rfe_skl_cols.txt')
    mlflow.log_artifact('rfe_skl_idx.txt')
    mlflow.log_params(model_sklearn.get_params())

run = mlflow.get_run(run_id) 
assert (run.info.status =='FINISHED')

Можно совмещать признаки, выбранные по sfs и sbs: брать их объединение или пересечение. Можно комбинировать с признаками, выделенными разными подходами - целое поле для исследований

HYPERPARAMS

Gridsearch

from sklearn.model_selection import  GridSearchCV

param_grid = {
    'model__depth': [1,3,5]
}

gs = GridSearchCV(rfe_sfs_pipeline, param_grid, cv=2, scoring='neg_mean_absolute_error')
gs.fit(X_train, y_train)
print("Лучшие гиперпараметры:", gs.best_params_)

gs_pipeline  = Pipeline(steps=[
    ('preprocessor', preprocessor_sklearn), 
    ('rfe_extractor', ColumnExtractor(rfe_sfs_idx)),
    ('model', CatBoostRegressor(depth=5))
])

# Проведем стандартную проверку на тестовом множестве и залогируем run

Вместо GridSearch можно использовать RandomSearch

Optuna

import optuna

def objective(trial):
    # предлагаем гиперпараметры
    depth = trial.suggest_int('depth', 1, 10)
    learning_rate = trial.suggest_float('learning_rate', 0.001, 0.1)

    # создаём и обучаем модель
    opt_pipeline  = Pipeline(steps=[
        ('preprocessor', preprocessor_sklearn), 
        ('rfe_extractor', ColumnExtractor(rfe_sfs_idx)),
        ('model', CatBoostRegressor(depth=depth, learning_rate=learning_rate, verbose=0))
    ])

    opt_pipeline.fit(X_train, y_train)

    # предсказываем и вычисляем RMSE
    preds = opt_pipeline.predict(X_test)
    mae =  mean_absolute_error(y_test, preds)   

    return mae

study = optuna.create_study(direction='minimize')
study.optimize(objective, n_trials=10)

# выводим результаты
print('Number of finished trials:', len(study.trials))
print('Best trial:', study.best_trial.params) 

opt_pipeline  = Pipeline(steps=[
    ('preprocessor', preprocessor_sklearn), 
    ('rfe_extractor', ColumnExtractor(rfe_sfs_idx)),
    ('model', CatBoostRegressor(depth=3, learning_rate=0.02789))
])

# Проведем стандартную проверку на тестовом множестве и залогируем run

Выбираем лучшую модель. Обучаем ее на всей выборке (а не только на train-части). Далее будем деплоить именно её