task01 HeartbeatClassification-数据挖掘

零基础入门数据挖掘-心跳信号分类预测baseline

导入第三方包

import os
import gc
import math

import pandas as pd
import numpy as np

import lightgbm as lgb
import xgboost as xgb
from catboost import CatBoostRegressor
from sklearn.linear_model import SGDRegressor, LinearRegression, Ridge
from sklearn.preprocessing import MinMaxScaler


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

from tqdm import tqdm
import matplotlib.pyplot as plt
import time
import warnings
warnings.filterwarnings('ignore')

读取数据

# 读取数据
train = pd.read_csv('train.csv')
test=pd.read_csv('testA.csv')
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

test.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...

# 查看数据
train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 100000 entries, 0 to 99999
Data columns (total 3 columns):
 #   Column             Non-Null Count   Dtype  
---  ------             --------------   -----  
 0   id                 100000 non-null  int64  
 1   heartbeat_signals  100000 non-null  object 
 2   label              100000 non-null  float64
dtypes: float64(1), int64(1), object(1)
memory usage: 2.3+ MB

train.describe()

	id	label
count	100000.000000	100000.000000
mean	49999.500000	0.856960
std	28867.657797	1.217084
min	0.000000	0.000000
25%	24999.750000	0.000000
50%	49999.500000	0.000000
75%	74999.250000	2.000000
max	99999.000000	3.000000

train.label.value_counts()

0.0    64327
3.0    17912
2.0    14199
1.0     3562
Name: label, dtype: int64

train.label.value_counts().plot(kind="bar")
plt.title("label class histogram")
plt.xlabel("label")
plt.ylabel("Frequency")

Text(0, 0.5, 'Frequency')

​

​

对label作计数统计，发现有样本不均衡现象：label为4的样本数量较少，label为1的样本数量较多

train.heartbeat_signals.apply(lambda x:len(x.split(",")))

0        205
1        205
2        205
3        205
4        205
        ... 
99995    205
99996    205
99997    205
99998    205
99999    205
Name: heartbeat_signals, Length: 100000, dtype: int64

查看heartbeat_signal列，发现每个样本的心跳信号是一列浮点数，分布在0~1之间，长度为205，且多数信号后面存在大量的0信号

数据预处理

train.memory_usage()

Index                   128
id                   800000
heartbeat_signals    800000
label                800000
dtype: int64

# 减少内存
def reduce_mem_usage(df):
    # df.memory_usage()返回每列的内存使用情况Series（以字节为单位）,然后求和并转换单位为mb
    start_mem = df.memory_usage().sum() / 1024**2 
    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))
    
    for col in df.columns:
        col_type = df[col].dtype
        
        if col_type != object:
            c_min = df[col].min()
            c_max = df[col].max()
            # 选择满足条件的占内存最小的类型来存储int和float型数据
            if str(col_type)[:3] == 'int':
                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
                    df[col] = df[col].astype(np.int8)
                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:
                    df[col] = df[col].astype(np.int16)
                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:
                    df[col] = df[col].astype(np.int32)
                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:
                    df[col] = df[col].astype(np.int64)  
            else:
                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
                    df[col] = df[col].astype(np.float16)
                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:
                    df[col] = df[col].astype(np.float32)
                else:
                    df[col] = df[col].astype(np.float64)
        else:
            # object类转化为category类型，category类型在底层使用了int值来表示一个列中的值，节省空间
            df[col] = df[col].astype('category')

    #计算类型转换后数据所占总内存
    end_mem = df.memory_usage().sum() / 1024**2 
    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
    
    return df

# 简单预处理
# 训练集
print("===============train===============")
train_list = []

# for循环每次取出一行数据（数据类型为np.array）
for items in train.values:
    # 拆分heartbeat_signals数据
    train_list.append([items[0]] + [float(i) for i in items[1].split(',')] + [items[2]])

train = pd.DataFrame(np.array(train_list))
train.columns = ['id'] + ['s_'+str(i) for i in range(len(train_list[0])-2)] + ['label']
train = reduce_mem_usage(train)

# 测试集
print("===============test===============")
test_list=[]
for items in test.values:
    test_list.append([items[0]] + [float(i) for i in items[1].split(',')])

test = pd.DataFrame(np.array(test_list))
test.columns = ['id'] + ['s_'+str(i) for i in range(len(test_list[0])-1)]
test = reduce_mem_usage(test)

===============train===============
Memory usage of dataframe is 157.93 MB
Memory usage after optimization is: 39.67 MB
Decreased by 74.9%
===============test===============
Memory usage of dataframe is 31.43 MB
Memory usage after optimization is: 7.90 MB
Decreased by 74.9%

train.head()

	id	s_0	s_1	s_2	s_3	s_4	s_5	s_6	s_7	s_8	...	s_196	s_197	s_198	s_199	s_200	s_201	s_202	s_203	s_204	label
0	0.0	0.991211	0.943359	0.764648	0.618652	0.379639	0.190796	0.040222	0.026001	0.031708	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	1.0	0.971680	0.929199	0.572754	0.178467	0.122986	0.132324	0.094421	0.089600	0.030487	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	2.0	1.000000	0.958984	0.701172	0.231812	0.000000	0.080688	0.128418	0.187500	0.280762	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	2.0
3	3.0	0.975586	0.934082	0.659668	0.249878	0.237061	0.281494	0.249878	0.249878	0.241455	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
4	4.0	0.000000	0.055817	0.261230	0.359863	0.433105	0.453613	0.499023	0.542969	0.616699	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	2.0

5 rows × 207 columns

训练数据、测试数据准备

# 数据和label的拆分
x_train = train.drop(['id','label'], axis=1) # 训练集数据
y_train = train['label'] # 训练集label
x_test=test.drop(['id'], axis=1) # 测试集数据

数据下采样

# 下采样
#取出label为1的样本的样本数、索引
number_records_1 = len(train[train.label == 1])
records_1_indices = np.array(train[train.label == 1.0].index)

#取出label为其他值的样本的索引
records_2_indices = np.array(train[train.label == 2.0].index)
records_3_indices = np.array(train[train.label == 3.0].index)
records_0_indices = np.array(train[train.label == 0.0].index)

# 随机选取与label1数目相同的其余label的标签
random_2_indices = np.random.choice(records_2_indices, number_records_1, replace = False) #replace=False 再一次抽取，样本不可重复出现
random_2_indices = np.array(random_2_indices)
random_3_indices = np.random.choice(records_3_indices, number_records_1, replace = False) #replace=False 再一次抽取，样本不可重复出现
random_3_indices = np.array(random_3_indices)
random_0_indices = np.random.choice(records_0_indices, number_records_1, replace = False) #replace=False 再一次抽取，样本不可重复出现
random_0_indices = np.array(random_0_indices)

# 组成最终的下采样后的数据集
under_sample_indices = np.concatenate([random_0_indices,random_2_indices,random_3_indices,records_1_indices])
under_sample_train = train.iloc[under_sample_indices,:]

x_undersample_train = under_sample_train.drop(['id','label'], axis=1).reset_index(drop = True)
y_undersample_train = under_sample_train['label'].reset_index(drop = True)

模型训练

# 定义绝对值损失函数
def abs_sum(y_pre,y_tru):
    y_pre=np.array(y_pre)
    y_tru=np.array(y_tru)
    loss=sum(sum(abs(y_pre-y_tru)))
    return loss

def cv_model(clf, train_x, train_y, test_x, clf_name):
    """
    clf:选择classifier分类器
    clf_name：分类器名称
    """
    folds = 5
    seed = 2021
    # 交叉验证
    kf = KFold(n_splits=folds, shuffle=True, random_state=seed)
    # 初始化预测的概率矩阵
    test = np.zeros((test_x.shape[0],4))

    cv_scores = []
    onehot_encoder = OneHotEncoder(sparse=False)
    for i, (train_index, valid_index) in enumerate(kf.split(train_x)):
        print('************************************ {} ************************************'.format(str(i+1)))
        trn_x, trn_y, val_x, val_y = train_x.iloc[train_index], train_y[train_index], train_x.iloc[valid_index], train_y[valid_index]
        
        if clf_name == "lgb":
            train_matrix = clf.Dataset(trn_x, label=trn_y)
            valid_matrix = clf.Dataset(val_x, label=val_y)

            params = {
                'boosting_type': 'gbdt',
                'objective': 'multiclass',
                'num_class': 4,
                'num_leaves': 2 ** 5,
                'feature_fraction': 0.8,
                'bagging_fraction': 0.8,
                'bagging_freq': 4,
                'learning_rate': 0.1,
                'seed': seed,
                'nthread': 28,
                'n_jobs':24,
                'verbose': -1,
            }

            # 创建模型
            model = clf.train(params, 
                      train_set=train_matrix, 
                      valid_sets=valid_matrix, 
                      num_boost_round=2000, 
                      verbose_eval=100, 
                      early_stopping_rounds=200)
            val_pred = model.predict(val_x, num_iteration=model.best_iteration)
            test_pred = model.predict(test_x, num_iteration=model.best_iteration) 
            
        val_y=np.array(val_y).reshape(-1, 1)
        val_y = onehot_encoder.fit_transform(val_y)
        print('预测的概率矩阵为：')
        print(test_pred)
        test += test_pred
        score=abs_sum(val_y, val_pred)
        cv_scores.append(score)
        print(cv_scores)
    print("%s_scotrainre_list:" % clf_name, cv_scores)
    print("%s_score_mean:" % clf_name, np.mean(cv_scores))
    print("%s_score_std:" % clf_name, np.std(cv_scores))
    test=test/kf.n_splits

    return test

def lgb_model(x_train, y_train, x_test):
    lgb_test = cv_model(lgb, x_train, y_train, x_test, "lgb")
    return lgb_test

lgb_test = lgb_model(x_train, y_train, x_test)

************************************ 1 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.0525735
[200]	valid_0's multi_logloss: 0.0422444
[300]	valid_0's multi_logloss: 0.0407076
[400]	valid_0's multi_logloss: 0.0420398
Early stopping, best iteration is:
[289]	valid_0's multi_logloss: 0.0405457
预测的概率矩阵为：
[[9.99969791e-01 2.85197261e-05 1.00341946e-06 6.85357631e-07]
 [7.93287264e-05 7.69060914e-04 9.99151590e-01 2.00810971e-08]
 [5.75356884e-07 5.04051497e-08 3.15322414e-07 9.99999059e-01]
 ...
 [6.79267940e-02 4.30206297e-04 9.31640185e-01 2.81516302e-06]
 [9.99960477e-01 3.94098074e-05 8.34030725e-08 2.94638661e-08]
 [9.88705846e-01 2.14081630e-03 6.67418381e-03 2.47915423e-03]]
[607.0736049372185]
************************************ 2 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.0566626
[200]	valid_0's multi_logloss: 0.0450852
[300]	valid_0's multi_logloss: 0.044078
[400]	valid_0's multi_logloss: 0.0455546
Early stopping, best iteration is:
[275]	valid_0's multi_logloss: 0.0437793
预测的概率矩阵为：
[[9.99991401e-01 7.69109547e-06 6.65504756e-07 2.42084688e-07]
 [5.72380482e-05 1.32812809e-03 9.98614607e-01 2.66534396e-08]
 [2.82123411e-06 4.13195205e-07 1.34026965e-06 9.99995425e-01]
 ...
 [6.96398024e-02 6.52459907e-04 9.29685742e-01 2.19960932e-05]
 [9.99972366e-01 2.75069005e-05 7.68142933e-08 5.07415018e-08]
 [9.67263676e-01 7.26154408e-03 2.41533542e-02 1.32142531e-03]]
[607.0736049372185, 623.4313863731124]
************************************ 3 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.0498722
[200]	valid_0's multi_logloss: 0.038028
[300]	valid_0's multi_logloss: 0.0358066
[400]	valid_0's multi_logloss: 0.0361478
[500]	valid_0's multi_logloss: 0.0379597
Early stopping, best iteration is:
[340]	valid_0's multi_logloss: 0.0354344
预测的概率矩阵为：
[[9.99972032e-01 2.62406774e-05 1.17282152e-06 5.54230651e-07]
 [1.05242811e-05 6.50215805e-05 9.99924453e-01 6.93812546e-10]
 [1.93240868e-06 1.10384984e-07 3.76773426e-07 9.99997580e-01]
 ...
 [1.34894410e-02 3.84569683e-05 9.86471555e-01 5.46564350e-07]
 [9.99987431e-01 1.25532882e-05 1.03902298e-08 5.46727770e-09]
 [9.78722948e-01 1.06329839e-02 6.94192038e-03 3.70214810e-03]]
[607.0736049372185, 623.4313863731124, 508.02381607269535]
************************************ 4 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.0564768
[200]	valid_0's multi_logloss: 0.0448698
[300]	valid_0's multi_logloss: 0.0446719
[400]	valid_0's multi_logloss: 0.0470399
Early stopping, best iteration is:
[250]	valid_0's multi_logloss: 0.0438853
预测的概率矩阵为：
[[9.99979692e-01 1.70821979e-05 1.27048476e-06 1.95571841e-06]
 [5.66207785e-05 4.02275314e-04 9.99541086e-01 1.82828519e-08]
 [2.62267451e-06 3.58613522e-07 4.78645006e-06 9.99992232e-01]
 ...
 [4.56636552e-02 5.69497433e-04 9.53758468e-01 8.37980573e-06]
 [9.99896785e-01 1.02796802e-04 2.46636563e-07 1.72061021e-07]
 [8.70911669e-01 1.73790185e-02 1.04478175e-01 7.23113697e-03]]
[607.0736049372185, 623.4313863731124, 508.02381607269535, 660.4867407547266]
************************************ 5 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.0506398
[200]	valid_0's multi_logloss: 0.0396422
[300]	valid_0's multi_logloss: 0.0381065
[400]	valid_0's multi_logloss: 0.0390162
[500]	valid_0's multi_logloss: 0.0414986
Early stopping, best iteration is:
[324]	valid_0's multi_logloss: 0.0379497
预测的概率矩阵为：
[[9.99993352e-01 6.02902202e-06 1.13002685e-07 5.06277302e-07]
 [1.03959552e-05 5.03778956e-04 9.99485820e-01 5.07638601e-09]
 [1.92568065e-07 5.07155306e-08 4.94690856e-08 9.99999707e-01]
 ...
 [8.83103121e-03 2.51969353e-05 9.91142776e-01 9.96143937e-07]
 [9.99984791e-01 1.51997858e-05 5.62426491e-09 3.80450197e-09]
 [9.86084001e-01 8.75968498e-04 1.09742304e-02 2.06580027e-03]]
[607.0736049372185, 623.4313863731124, 508.02381607269535, 660.4867407547266, 539.2160054696064]
lgb_scotrainre_list: [607.0736049372185, 623.4313863731124, 508.02381607269535, 660.4867407547266, 539.2160054696064]
lgb_score_mean: 587.6463107214719
lgb_score_std: 55.944536405714565

由于样本标签分布不均匀，前面对数据集做了下采样，再次训练模型：

lgb_test_undersamped = lgb_model(x_undersample_train, y_undersample_train, x_test)

************************************ 1 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.114481
[200]	valid_0's multi_logloss: 0.121278
[300]	valid_0's multi_logloss: 0.142431
Early stopping, best iteration is:
[129]	valid_0's multi_logloss: 0.11133
预测的概率矩阵为：
[[9.97909504e-01 2.05690126e-03 1.37408064e-05 1.98534778e-05]
 [5.29540833e-05 2.71891022e-03 9.97227460e-01 6.76094883e-07]
 [1.67245916e-05 2.31546330e-06 4.99075771e-06 9.99975969e-01]
 ...
 [7.31721572e-02 3.65607531e-02 8.87518521e-01 2.74856896e-03]
 [9.97227859e-01 2.75894404e-03 1.05707283e-05 2.62636571e-06]
 [1.72415730e-01 3.26642460e-01 6.65459626e-02 4.34395848e-01]]
[279.89382785738206]
************************************ 2 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.14047
[200]	valid_0's multi_logloss: 0.156166
[300]	valid_0's multi_logloss: 0.182637
Early stopping, best iteration is:
[107]	valid_0's multi_logloss: 0.139486
预测的概率矩阵为：
[[9.97637026e-01 2.26617101e-03 7.61022611e-05 2.07008734e-05]
 [1.73246625e-04 7.10584410e-03 9.92715902e-01 5.00693350e-06]
 [2.54639765e-05 7.61968678e-06 3.51436283e-05 9.99931773e-01]
 ...
 [7.12577218e-02 2.33032167e-01 6.92863112e-01 2.84699897e-03]
 [9.96584919e-01 3.37795178e-03 2.52579171e-05 1.18714552e-05]
 [2.97622604e-01 4.02905434e-01 1.41173366e-01 1.58298597e-01]]
[279.89382785738206, 364.5849925070536]
************************************ 3 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.117352
[200]	valid_0's multi_logloss: 0.116617
[300]	valid_0's multi_logloss: 0.135823
Early stopping, best iteration is:
[142]	valid_0's multi_logloss: 0.111634
预测的概率矩阵为：
[[9.98782396e-01 1.15469066e-03 4.32136748e-05 1.96997210e-05]
 [2.49293743e-05 1.90295485e-03 9.98071825e-01 2.90581742e-07]
 [9.10024124e-06 2.03901034e-06 2.20466441e-06 9.99986656e-01]
 ...
 [7.91691326e-02 7.11461731e-03 9.13350712e-01 3.65538181e-04]
 [9.99115803e-01 8.77129392e-04 4.65368198e-06 2.41390238e-06]
 [1.20920311e-01 5.60310816e-01 1.27816215e-01 1.90952657e-01]]
[279.89382785738206, 364.5849925070536, 291.81448543469014]
************************************ 4 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.118365
[200]	valid_0's multi_logloss: 0.115946
[300]	valid_0's multi_logloss: 0.128339
Early stopping, best iteration is:
[136]	valid_0's multi_logloss: 0.112798
预测的概率矩阵为：
[[9.99333742e-01 6.43997815e-04 1.77285801e-05 4.53125727e-06]
 [1.85250042e-05 2.45895523e-03 9.97522087e-01 4.32881200e-07]
 [5.27576705e-06 9.55304395e-07 5.44191422e-06 9.99988327e-01]
 ...
 [1.12449235e-01 3.01623502e-02 8.56576699e-01 8.11715852e-04]
 [9.96615832e-01 3.36790701e-03 9.43435168e-06 6.82690020e-06]
 [5.71821675e-01 2.57162461e-01 4.54324005e-02 1.25583463e-01]]
[279.89382785738206, 364.5849925070536, 291.81448543469014, 296.11137994407875]
************************************ 5 ************************************
[LightGBM] [Warning] num_threads is set with nthread=28, will be overridden by n_jobs=24. Current value: num_threads=24
Training until validation scores don't improve for 200 rounds
[100]	valid_0's multi_logloss: 0.116624
[200]	valid_0's multi_logloss: 0.127048
[300]	valid_0's multi_logloss: 0.148542
Early stopping, best iteration is:
[128]	valid_0's multi_logloss: 0.114111
预测的概率矩阵为：
[[9.99799720e-01 1.73361480e-04 1.06621394e-05 1.62564574e-05]
 [4.35885896e-05 1.67797711e-03 9.98277835e-01 5.99544292e-07]
 [1.21090595e-05 4.21721375e-06 1.20332494e-05 9.99971640e-01]
 ...
 [5.04861158e-02 5.72191215e-03 9.43613485e-01 1.78486939e-04]
 [9.94659919e-01 5.32772250e-03 6.54049986e-06 5.81780206e-06]
 [7.94347056e-02 2.73343032e-01 7.71439116e-02 5.70078350e-01]]
[279.89382785738206, 364.5849925070536, 291.81448543469014, 296.11137994407875, 296.42967075096817]
lgb_scotrainre_list: [279.89382785738206, 364.5849925070536, 291.81448543469014, 296.11137994407875, 296.42967075096817]
lgb_score_mean: 305.76687129883453
lgb_score_std: 30.013552465720718