task3 HeartbeatClassification trfresh 特征提取

主要是利用tsfresh对数据做了处理，依旧使用了beseline中的lgb模型

数据处理

import pandas as pd
import numpy as np
import tsfresh as tsf
from tsfresh import extract_features, select_features
from tsfresh.utilities.dataframe_functions import impute
import lightgbm as lgb

from sklearn.model_selection import StratifiedKFold, KFold
from sklearn.metrics import log_loss
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder

data_train = pd.read_csv("train.csv")
data_test_A = pd.read_csv("testA.csv")

print(data_train.shape)
print(data_test_A.shape)

(100000, 3)
(20000, 2)

data_train.head()

	id	heartbeat_signals	label
0	0	0.9912297987616655,0.9435330436439665,0.764677...	0.0
1	1	0.9714822034884503,0.9289687459588268,0.572932...	0.0
2	2	1.0,0.9591487564065292,0.7013782792997189,0.23...	2.0
3	3	0.9757952826275774,0.9340884687738161,0.659636...	0.0
4	4	0.0,0.055816398940721094,0.26129357194994196,0...	2.0

data_test_A.head()

	id	heartbeat_signals
0	100000	0.9915713654170097,1.0,0.6318163407681274,0.13...
1	100001	0.6075533139615096,0.5417083883163654,0.340694...
2	100002	0.9752726292239277,0.6710965234906665,0.686758...
3	100003	0.9956348033996116,0.9170249621481004,0.521096...
4	100004	1.0,0.8879490481178918,0.745564725322326,0.531...

利用tsfresh对心跳信号序列处理

# 心跳信号行转列
train_heartbeat_df = data_train["heartbeat_signals"].str.split(",", expand=True).stack()
train_heartbeat_df = train_heartbeat_df.reset_index() # 重置索引
# 将level_0设为索引,可表示id，level_1是一个时间步特征
train_heartbeat_df = train_heartbeat_df.set_index("level_0") 
train_heartbeat_df.index.name = None

train_heartbeat_df = train_heartbeat_df.rename(columns={"level_1":"time", 0:"heartbeat_signals"})

train_heartbeat_df["heartbeat_signals"] = train_heartbeat_df["heartbeat_signals"].astype(float)
train_heartbeat_df

	time	heartbeat_signals
0	0	0.991230
0	1	0.943533
0	2	0.764677
0	3	0.618571
0	4	0.379632
...	...	...
99999	200	0.000000
99999	201	0.000000
99999	202	0.000000
99999	203	0.000000
99999	204	0.000000

20500000 rows × 2 columns

data_train_label = data_train["label"]
data_train = data_train.drop("label", axis=1)
data_train = data_train.drop("heartbeat_signals", axis=1) # 去掉原数据的heartbeat列
data_train = data_train.join(train_heartbeat_df)

data_train

	id	time	heartbeat_signals
0	0	0	0.991230
0	0	1	0.943533
0	0	2	0.764677
0	0	3	0.618571
0	0	4	0.379632
...	...	...	...
99999	99999	200	0.000000
99999	99999	201	0.000000
99999	99999	202	0.000000
99999	99999	203	0.000000
99999	99999	204	0.000000

20500000 rows × 3 columns

#测试集处理
# 心跳信号行转列
test_heartbeat_df = data_test_A["heartbeat_signals"].str.split(",", expand=True).stack()
test_heartbeat_df = test_heartbeat_df.reset_index() # 重置索引
# 将level_0设为索引,可表示id，level_1是一个时间步特征
test_heartbeat_df = test_heartbeat_df.set_index("level_0") 
test_heartbeat_df.index.name = None
test_heartbeat_df = test_heartbeat_df.rename(columns={"level_1":"time", 0:"heartbeat_signals"})
test_heartbeat_df["heartbeat_signals"] = test_heartbeat_df["heartbeat_signals"].astype(float)
test_heartbeat_df

	time	heartbeat_signals
0	0	0.991571
0	1	1.000000
0	2	0.631816
0	3	0.136230
0	4	0.041420
...	...	...
19999	200	0.000000
19999	201	0.000000
19999	202	0.000000
19999	203	0.000000
19999	204	0.000000

4100000 rows × 2 columns

data_test_A = data_test_A.drop("heartbeat_signals", axis=1) # 去掉原数据的heartbeat列
data_test_A = data_test_A.join(test_heartbeat_df)

data_test_A

	id	time	heartbeat_signals
0	100000	0	0.991571
0	100000	1	1.000000
0	100000	2	0.631816
0	100000	3	0.136230
0	100000	4	0.041420
...	...	...	...
19999	119999	200	0.000000
19999	119999	201	0.000000
19999	119999	202	0.000000
19999	119999	203	0.000000
19999	119999	204	0.000000

4100000 rows × 3 columns

特征提取

我16g的内存跑所有数据不是很ok，于是乎分成了10分分开跑，训练数据大概跑了一个半小时
一共得到787个特征

# 特征提取
train_features = pd.DataFrame([],dtype = float)
for i in range(10):
    l = len(data_train)/10
    m = int(i * l)
    n = int((i+1) * l)
    temp = extract_features(data_train.iloc[m:n,:], column_id='id', column_sort='time')
    print(temp.shape)
    train_features = train_features.append(temp)
train_features

Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [07:55<00:00, 15.86s/it]
Feature Extraction:   0%|                                                                       | 0/30 [00:00<?, ?it/s]

(10000, 787)


Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [08:08<00:00, 16.28s/it]
Feature Extraction:   0%|                                                                       | 0/30 [00:00<?, ?it/s]

(10000, 787)


Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [07:47<00:00, 15.59s/it]
Feature Extraction:   0%|                                                                       | 0/30 [00:00<?, ?it/s]

(10000, 787)


Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [07:55<00:00, 15.85s/it]
Feature Extraction:   0%|                                                                       | 0/30 [00:00<?, ?it/s]

(10000, 787)


Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [07:53<00:00, 15.80s/it]
Feature Extraction:   0%|                                                                       | 0/30 [00:00<?, ?it/s]

(10000, 787)


Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [08:14<00:00, 16.49s/it]
Feature Extraction:   0%|                                                                       | 0/30 [00:00<?, ?it/s]

(10000, 787)


Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [08:09<00:00, 16.32s/it]


(10000, 787)


Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [07:51<00:00, 15.73s/it]


(10000, 787)


Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [08:01<00:00, 16.05s/it]


(10000, 787)


Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [08:05<00:00, 16.17s/it]


(10000, 787)

	heartbeat_signals__variance_larger_than_standard_deviation	heartbeat_signals__has_duplicate_max	heartbeat_signals__has_duplicate_min	heartbeat_signals__has_duplicate	heartbeat_signals__sum_values	heartbeat_signals__abs_energy	heartbeat_signals__mean_abs_change	heartbeat_signals__mean_change	heartbeat_signals__mean_second_derivative_central	heartbeat_signals__median	...	heartbeat_signals__permutation_entropy__dimension_5__tau_1	heartbeat_signals__permutation_entropy__dimension_6__tau_1	heartbeat_signals__permutation_entropy__dimension_7__tau_1	heartbeat_signals__query_similarity_count__query_None__threshold_0.0	heartbeat_signals__matrix_profile__feature_"min"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"max"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"mean"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"median"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"25"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"75"__threshold_0.98
0	0.0	0.0	1.0	1.0	38.927945	18.216197	0.019894	-0.004859	0.000117	0.125531	...	2.184420	2.500658	2.722686	NaN	6.445546	12.165525	10.246524	10.746992	8.388625	11.484910
1	0.0	0.0	1.0	1.0	19.445634	7.705092	0.019952	-0.004762	0.000105	0.030481	...	2.710933	3.065802	3.224835	NaN	3.209140	12.649111	9.031069	9.437545	6.723180	12.094899
2	0.0	0.0	1.0	1.0	21.192974	9.140423	0.009863	-0.004902	0.000101	0.000000	...	1.263370	1.406001	1.509478	NaN	3.054539	8.246211	7.370478	8.246211	5.966122	8.246211
3	0.0	0.0	1.0	1.0	42.113066	15.757623	0.018743	-0.004783	0.000103	0.241397	...	2.986728	3.534354	3.854177	NaN	3.010557	9.797959	6.331360	6.406440	5.266743	7.091706
4	0.0	0.0	1.0	1.0	69.756786	51.229616	0.014514	0.000000	-0.000137	0.000000	...	1.914511	2.165627	2.323993	NaN	9.181236	13.429784	9.959913	9.516290	9.286013	10.270925
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
99995	0.0	0.0	1.0	1.0	63.323449	28.742238	0.023588	-0.004902	0.000794	0.388402	...	2.873602	3.391830	3.679969	NaN	2.436377	9.591663	5.635231	6.366205	3.596982	7.033638
99996	0.0	0.0	1.0	1.0	69.657534	31.866323	0.017373	-0.004543	0.000051	0.421138	...	3.085504	3.728881	4.095457	NaN	1.415410	7.483315	2.893592	2.684349	2.049241	3.334109
99997	0.0	0.0	1.0	1.0	40.897057	16.412857	0.019470	-0.004538	0.000834	0.213306	...	2.601062	2.996962	3.293562	NaN	5.748652	12.165525	8.524637	7.983410	7.062217	10.081756
99998	0.0	0.0	1.0	1.0	42.333303	14.281281	0.017032	-0.004902	0.000013	0.264974	...	3.236950	3.793512	4.018302	NaN	2.346822	8.246211	4.951374	4.727535	4.069786	5.615282
99999	0.0	0.0	1.0	1.0	53.290117	21.637471	0.021870	-0.004539	0.000023	0.320124	...	2.949266	3.462549	3.688612	NaN	1.959139	9.380832	4.573691	3.908621	3.094614	5.916164

100000 rows × 787 columns

测试数据做同样处理

test_fearues = extract_features(data_test_A, column_id='id', column_sort='time')

Feature Extraction: 100%|██████████████████████████████████████████████████████████████| 30/30 [16:03<00:00, 32.12s/it]

去除NaN值

# 去除抽取特征中的NaN值
impute(train_features)

	heartbeat_signals__variance_larger_than_standard_deviation	heartbeat_signals__has_duplicate_max	heartbeat_signals__has_duplicate_min	heartbeat_signals__has_duplicate	heartbeat_signals__sum_values	heartbeat_signals__abs_energy	heartbeat_signals__mean_abs_change	heartbeat_signals__mean_change	heartbeat_signals__mean_second_derivative_central	heartbeat_signals__median	...	heartbeat_signals__permutation_entropy__dimension_5__tau_1	heartbeat_signals__permutation_entropy__dimension_6__tau_1	heartbeat_signals__permutation_entropy__dimension_7__tau_1	heartbeat_signals__query_similarity_count__query_None__threshold_0.0	heartbeat_signals__matrix_profile__feature_"min"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"max"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"mean"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"median"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"25"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"75"__threshold_0.98
0	0.0	0.0	1.0	1.0	38.927945	18.216197	0.019894	-0.004859	0.000117	0.125531	...	2.184420	2.500658	2.722686	0.0	6.445546	12.165525	10.246524	10.746992	8.388625	11.484910
1	0.0	0.0	1.0	1.0	19.445634	7.705092	0.019952	-0.004762	0.000105	0.030481	...	2.710933	3.065802	3.224835	0.0	3.209140	12.649111	9.031069	9.437545	6.723180	12.094899
2	0.0	0.0	1.0	1.0	21.192974	9.140423	0.009863	-0.004902	0.000101	0.000000	...	1.263370	1.406001	1.509478	0.0	3.054539	8.246211	7.370478	8.246211	5.966122	8.246211
3	0.0	0.0	1.0	1.0	42.113066	15.757623	0.018743	-0.004783	0.000103	0.241397	...	2.986728	3.534354	3.854177	0.0	3.010557	9.797959	6.331360	6.406440	5.266743	7.091706
4	0.0	0.0	1.0	1.0	69.756786	51.229616	0.014514	0.000000	-0.000137	0.000000	...	1.914511	2.165627	2.323993	0.0	9.181236	13.429784	9.959913	9.516290	9.286013	10.270925
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
99995	0.0	0.0	1.0	1.0	63.323449	28.742238	0.023588	-0.004902	0.000794	0.388402	...	2.873602	3.391830	3.679969	0.0	2.436377	9.591663	5.635231	6.366205	3.596982	7.033638
99996	0.0	0.0	1.0	1.0	69.657534	31.866323	0.017373	-0.004543	0.000051	0.421138	...	3.085504	3.728881	4.095457	0.0	1.415410	7.483315	2.893592	2.684349	2.049241	3.334109
99997	0.0	0.0	1.0	1.0	40.897057	16.412857	0.019470	-0.004538	0.000834	0.213306	...	2.601062	2.996962	3.293562	0.0	5.748652	12.165525	8.524637	7.983410	7.062217	10.081756
99998	0.0	0.0	1.0	1.0	42.333303	14.281281	0.017032	-0.004902	0.000013	0.264974	...	3.236950	3.793512	4.018302	0.0	2.346822	8.246211	4.951374	4.727535	4.069786	5.615282
99999	0.0	0.0	1.0	1.0	53.290117	21.637471	0.021870	-0.004539	0.000023	0.320124	...	2.949266	3.462549	3.688612	0.0	1.959139	9.380832	4.573691	3.908621	3.094614	5.916164

100000 rows × 787 columns

impute(test_fearues)

	heartbeat_signals__variance_larger_than_standard_deviation	heartbeat_signals__has_duplicate_max	heartbeat_signals__has_duplicate_min	heartbeat_signals__has_duplicate	heartbeat_signals__sum_values	heartbeat_signals__abs_energy	heartbeat_signals__mean_abs_change	heartbeat_signals__mean_change	heartbeat_signals__mean_second_derivative_central	heartbeat_signals__median	...	heartbeat_signals__permutation_entropy__dimension_5__tau_1	heartbeat_signals__permutation_entropy__dimension_6__tau_1	heartbeat_signals__permutation_entropy__dimension_7__tau_1	heartbeat_signals__query_similarity_count__query_None__threshold_0.0	heartbeat_signals__matrix_profile__feature_"min"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"max"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"mean"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"median"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"25"__threshold_0.98	heartbeat_signals__matrix_profile__feature_"75"__threshold_0.98
100000	0.0	0.0	1.0	1.0	19.229863	7.907934	0.018374	-0.004861	-0.000021	0.027745	...	2.021451	2.356864	2.587925	0.0	2.692281	11.661904	9.456542	9.648131	8.525878	11.076665
100001	0.0	0.0	0.0	1.0	84.298932	38.292802	0.021483	-0.001195	0.000195	0.367241	...	4.099123	4.656875	4.882383	0.0	0.939893	4.470801	2.584921	2.493456	1.542105	3.698142
100002	0.0	0.0	1.0	1.0	47.789921	21.287039	0.021610	-0.004781	0.000749	0.260611	...	2.900488	3.321028	3.516715	0.0	5.684175	12.512693	9.751129	10.483467	8.221934	11.135462
100003	0.0	0.0	1.0	1.0	47.069011	28.749520	0.023874	-0.004881	0.000194	0.000000	...	1.530558	1.806294	1.979305	0.0	0.909721	4.898979	3.531943	4.898979	1.675526	4.898979
100004	0.0	0.0	1.0	1.0	24.899397	10.177998	0.020548	-0.004902	0.000276	0.034859	...	2.626554	2.960568	3.168085	0.0	5.033722	14.180087	11.450599	11.991037	11.825491	12.597792
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
119995	0.0	0.0	1.0	1.0	43.175130	18.967833	0.016106	-0.004902	0.000411	0.205399	...	3.150910	3.625398	3.843586	0.0	3.687770	8.700294	5.991330	6.323450	4.155558	7.191577
119996	0.0	0.0	1.0	1.0	31.030782	14.413244	0.021473	-0.004902	0.000429	0.000000	...	1.732287	1.955659	2.081946	0.0	10.456465	12.982197	11.338307	11.244766	10.763332	11.762948
119997	0.0	0.0	1.0	1.0	31.648623	13.083992	0.017566	-0.004665	0.000087	0.010807	...	2.248241	2.497097	2.663404	0.0	6.037870	11.661904	9.312119	8.973721	8.064338	10.409977
119998	0.0	0.0	1.0	1.0	19.305442	6.700835	0.019937	-0.004547	0.000617	0.000000	...	2.538456	2.912829	3.021449	0.0	10.350940	15.065584	12.961223	12.887409	12.118259	13.558463
119999	0.0	0.0	1.0	1.0	35.204569	15.514667	0.020292	-0.003261	0.000341	0.000000	...	1.936010	2.207142	2.454222	0.0	0.860493	5.656854	3.760221	3.602865	1.895006	5.656854

20000 rows × 787 columns

根据相关性筛选特征

from tsfresh import select_features

# 按照特征和数据label之间的相关性进行特征选择
train_features_filtered = select_features(train_features, data_train_label)

train_features_filtered

	heartbeat_signals__sum_values	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_38	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_37	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_36	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_35	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_34	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_33	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_32	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_31	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_30	...	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_84	heartbeat_signals__fft_coefficient__attr_"imag"__coeff_97	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_90	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_94	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_92	heartbeat_signals__fft_coefficient__attr_"real"__coeff_97	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_75	heartbeat_signals__fft_coefficient__attr_"real"__coeff_88	heartbeat_signals__fft_coefficient__attr_"real"__coeff_92	heartbeat_signals__fft_coefficient__attr_"real"__coeff_83
0	38.927945	0.660949	1.090709	0.848728	1.168685	0.982133	1.223496	1.236300	1.104172	1.497129	...	0.531883	-0.047438	0.554370	0.307586	0.564596	0.562960	0.591859	0.504124	0.528450	0.473568
1	19.445634	1.718217	1.280923	1.850706	1.460752	1.924501	1.925485	1.715938	2.079957	1.818636	...	0.563590	-0.109579	0.697446	0.398073	0.640969	0.270192	0.224925	0.645082	0.635135	0.297325
2	21.192974	1.814281	1.619051	1.215343	1.787166	2.146987	1.686190	1.540137	2.291031	2.403422	...	0.712487	-0.074042	0.321703	0.390386	0.716929	0.316524	0.422077	0.722742	0.680590	0.383754
3	42.113066	2.109550	0.619634	2.366413	2.071539	1.000340	2.728281	1.391727	2.017176	2.610492	...	0.601499	-0.184248	0.564669	0.623353	0.466980	0.651774	0.308915	0.550097	0.466904	0.494024
4	69.756786	0.194549	0.348882	0.092119	0.653924	0.231422	1.080003	0.711244	1.357904	1.237998	...	0.015292	0.070505	0.065835	0.051780	0.092940	0.103773	0.179405	-0.089611	0.091841	0.056867
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
99995	63.323449	0.840651	1.186210	1.396236	0.417221	2.036034	1.659054	0.500584	1.693545	0.859932	...	0.779955	0.005525	0.486013	0.273372	0.705386	0.602898	0.447929	0.474844	0.564266	0.133969
99996	69.657534	1.557787	1.393960	0.989147	1.611333	1.793044	1.092325	0.507138	1.763940	2.677643	...	0.539489	0.114670	0.579498	0.417226	0.270110	0.556596	0.703258	0.462312	0.269719	0.539236
99997	40.897057	0.469758	1.000355	0.706395	1.190514	0.674603	1.632769	0.229008	2.027802	0.302457	...	0.282597	-0.474629	0.460647	0.478341	0.527891	0.904111	0.728529	0.178410	0.500813	0.773985
99998	42.333303	0.992948	1.354894	2.238589	1.237608	1.325212	2.785515	1.918571	0.814167	2.613950	...	0.594252	-0.162106	0.694276	0.681025	0.357196	0.498088	0.433297	0.406154	0.324771	0.340727
99999	53.290117	1.624625	1.739088	2.936555	0.154759	2.921164	2.183932	1.485150	2.685922	0.583443	...	0.463697	0.289364	0.285321	0.422103	0.692009	0.276236	0.245780	0.269519	0.681719	-0.053993

100000 rows × 707 columns

选出测试集中相对应的特征

test_fearues = test_fearues.loc[:,list(train_features_filtered.columns)]
test_fearues

	heartbeat_signals__sum_values	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_38	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_37	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_36	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_35	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_34	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_33	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_32	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_31	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_30	...	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_84	heartbeat_signals__fft_coefficient__attr_"imag"__coeff_97	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_90	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_94	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_92	heartbeat_signals__fft_coefficient__attr_"real"__coeff_97	heartbeat_signals__fft_coefficient__attr_"abs"__coeff_75	heartbeat_signals__fft_coefficient__attr_"real"__coeff_88	heartbeat_signals__fft_coefficient__attr_"real"__coeff_92	heartbeat_signals__fft_coefficient__attr_"real"__coeff_83
100000	19.229863	2.381214	0.832151	2.509869	1.082112	2.517858	1.656104	2.257162	2.213421	1.815374	...	0.563470	-0.040576	0.485441	0.472059	0.448018	0.449347	0.479950	0.480448	0.442279	0.355992
100001	84.298932	0.987660	0.856174	0.616261	0.293339	0.191558	0.528684	1.010080	1.478182	1.713876	...	0.037307	0.010074	0.272897	0.247538	0.286948	0.143829	0.189416	0.124293	0.154624	0.077530
100002	47.789921	0.696393	1.165387	1.004378	0.951231	1.542114	0.946219	1.673430	1.445220	1.118439	...	0.738423	-0.159505	0.418298	0.566628	0.849684	0.950851	0.779324	0.439255	0.839315	0.454957
100003	47.069011	3.137668	0.044897	3.392946	3.054217	0.726293	3.582653	2.414946	1.257669	3.188068	...	0.273142	0.366949	0.891690	0.214585	0.927562	0.648872	0.730178	0.606528	0.830105	0.662320
100004	24.899397	0.496010	1.401020	0.536501	1.712592	1.044629	1.533405	1.330258	1.251771	1.441028	...	0.644046	-0.129700	0.578560	0.783258	0.480598	0.485003	0.667111	0.594234	0.447980	0.511133
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
119995	43.175130	1.776937	0.211527	1.986940	0.393550	1.693620	1.139395	1.459990	1.734535	1.025180	...	0.546742	-0.060254	0.507950	0.560192	0.541534	0.249750	0.608796	0.455444	0.535306	0.268471
119996	31.030782	1.451045	2.483726	1.105440	1.979721	2.821799	0.475276	2.782573	2.827882	0.520034	...	0.491662	0.016413	0.480380	0.459172	0.363756	0.427028	0.544692	0.754834	0.361866	0.536087
119997	31.648623	2.141301	0.546706	2.340499	1.362651	1.942634	2.043679	0.994065	2.248144	1.007128	...	0.529880	0.001012	0.768960	0.834159	0.672114	0.520215	0.341519	0.713419	0.664354	0.370047
119998	19.305442	0.221708	2.355288	1.051282	1.742370	2.164058	0.435583	2.649994	1.190594	2.328580	...	0.527500	-0.103574	0.521222	0.426435	0.636887	0.446365	0.551442	0.503703	0.635246	0.258394
119999	35.204569	0.827017	0.492990	1.627089	1.106799	0.639821	1.350155	0.533904	1.332401	1.229578	...	0.248776	0.091218	0.659750	0.636282	0.319922	0.472824	0.355830	0.346311	0.312797	0.540855

20000 rows × 707 columns

这里列名需要重命名一下，否则会报错

test_fearues.columns = range(test_fearues.shape[1])
train_features_filtered.columns = range(train_features_filtered.shape[1])
train_features_filtered

	0	1	2	3	4	5	6	7	8	9	...	697	698	699	700	701	702	703	704	705	706
0	38.927945	0.660949	1.090709	0.848728	1.168685	0.982133	1.223496	1.236300	1.104172	1.497129	...	0.531883	-0.047438	0.554370	0.307586	0.564596	0.562960	0.591859	0.504124	0.528450	0.473568
1	19.445634	1.718217	1.280923	1.850706	1.460752	1.924501	1.925485	1.715938	2.079957	1.818636	...	0.563590	-0.109579	0.697446	0.398073	0.640969	0.270192	0.224925	0.645082	0.635135	0.297325
2	21.192974	1.814281	1.619051	1.215343	1.787166	2.146987	1.686190	1.540137	2.291031	2.403422	...	0.712487	-0.074042	0.321703	0.390386	0.716929	0.316524	0.422077	0.722742	0.680590	0.383754
3	42.113066	2.109550	0.619634	2.366413	2.071539	1.000340	2.728281	1.391727	2.017176	2.610492	...	0.601499	-0.184248	0.564669	0.623353	0.466980	0.651774	0.308915	0.550097	0.466904	0.494024
4	69.756786	0.194549	0.348882	0.092119	0.653924	0.231422	1.080003	0.711244	1.357904	1.237998	...	0.015292	0.070505	0.065835	0.051780	0.092940	0.103773	0.179405	-0.089611	0.091841	0.056867
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
99995	63.323449	0.840651	1.186210	1.396236	0.417221	2.036034	1.659054	0.500584	1.693545	0.859932	...	0.779955	0.005525	0.486013	0.273372	0.705386	0.602898	0.447929	0.474844	0.564266	0.133969
99996	69.657534	1.557787	1.393960	0.989147	1.611333	1.793044	1.092325	0.507138	1.763940	2.677643	...	0.539489	0.114670	0.579498	0.417226	0.270110	0.556596	0.703258	0.462312	0.269719	0.539236
99997	40.897057	0.469758	1.000355	0.706395	1.190514	0.674603	1.632769	0.229008	2.027802	0.302457	...	0.282597	-0.474629	0.460647	0.478341	0.527891	0.904111	0.728529	0.178410	0.500813	0.773985
99998	42.333303	0.992948	1.354894	2.238589	1.237608	1.325212	2.785515	1.918571	0.814167	2.613950	...	0.594252	-0.162106	0.694276	0.681025	0.357196	0.498088	0.433297	0.406154	0.324771	0.340727
99999	53.290117	1.624625	1.739088	2.936555	0.154759	2.921164	2.183932	1.485150	2.685922	0.583443	...	0.463697	0.289364	0.285321	0.422103	0.692009	0.276236	0.245780	0.269519	0.681719	-0.053993

100000 rows × 707 columns

模型训练

使用baseline中的lgb模型

结果优化

概率较大的直接设为1，提高比赛分数，kkk

## 结果优化，概率较高的直接设为1，较低的直接设为0
def prob_opt(lgb_test,prob):
    for index,row in enumerate(lgb_test):
        row_max = max(row)
        if row_max > prob:
            for i in range(4):
                if row[i] > prob:
                    lgb_test[index,i] = 1
                else:
                    lgb_test[index,i] = 0
    return lgb_test

test = prob_opt(lgb_test,0.9)

temp=pd.DataFrame(test)
temp

	0	1	2	3
0	1.0	0.0	0.0	0.0
1	0.0	0.0	1.0	0.0
2	0.0	0.0	0.0	1.0
3	1.0	0.0	0.0	0.0
4	1.0	0.0	0.0	0.0
...	...	...	...	...
19995	1.0	0.0	0.0	0.0
19996	1.0	0.0	0.0	0.0
19997	0.0	0.0	1.0	0.0
19998	1.0	0.0	0.0	0.0
19999	1.0	0.0	0.0	0.0

20000 rows × 4 columns