数据挖掘心电图分类（四）之建模与调参

今天，我们就在这里进行建模以及调参
首先一样的，我们先导入库进来

import pandas as pd
import numpy as np
from sklearn.metrics import f1_score

import os
import seaborn as sns
import matplotlib.pyplot as plt

import warnings
warnings.filterwarnings("ignore")

因为数据比较大，所以占用内存比较多，因此，我们就调整一下数据类型，来帮助我们减少数据所占用的内存空间。以下是减少内存的函数。

def reduce_mem_usage(df):
    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()
            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:
            df[col] = df[col].astype('category')

    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

接下来就是读取数据了，然后再做一些简单的预处理。

data = pd.read_csv('../dataset/train.csv')

data_list = []
for items in data.values:
    data_list.append([items[0]] + [float(i) for i in items[1].split(',')] + [items[2]])

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

data = reduce_mem_usage(data)

可以看到

这里我们使用lightgbm进行建模。

LightGBM

LightGBM是个快速的，分布式的，高性能的基于决策树算法的梯度提升框架。可用于排序，分类，回归以及很多其他的机器学习任务中。
在竞赛当中，除了XGBoost还有LightGBM，LightGBM在不降低准确率的前提下，速度提升了10倍左右，占用内存下降了3倍左右。
这里对比一下XGBoost和LightGBM：

from sklearn.model_selection import train_test_split
import lightgbm as lgb
# 数据集划分
X_train_split, X_val, y_train_split, y_val = train_test_split(X_train, y_train, test_size=0.2)
train_matrix = lgb.Dataset(X_train_split, label=y_train_split)
valid_matrix = lgb.Dataset(X_val, label=y_val)

params = {
    "learning_rate": 0.1,
    "boosting": 'gbdt',  
    "lambda_l2": 0.1,
    "max_depth": -1,
    "num_leaves": 128,
    "bagging_fraction": 0.8,
    "feature_fraction": 0.8,
    "metric": None,
    "objective": "multiclass",
    "num_class": 4,
    "nthread": 10,
    "verbose": -1,
}

"""使用训练集数据进行模型训练"""
model = lgb.train(params, 
                  train_set=train_matrix, 
                  valid_sets=valid_matrix, 
                  num_boost_round=2000, 
                  verbose_eval=50, 
                  early_stopping_rounds=200,
                  feval=f1_score_vali)

其中训练的参数代表意义：

训练后的结果可以看到：

因为树模型中没有f1-score评价指标，所以需要自定义评价指标，在模型迭代中返回验证集f1-score变化情况。

def f1_score_vali(preds, data_vali):
    labels = data_vali.get_label()
    preds = np.argmax(preds.reshape(4, -1), axis=0)
    score_vali = f1_score(y_true=labels, y_pred=preds, average='macro')
    return 'f1_score', score_vali, True

训练完了之后就对验证集进行验证准确率了。

val_pre_lgb = model.predict(X_val, num_iteration=model.best_iteration)
preds = np.argmax(val_pre_lgb, axis=1)
score = f1_score(y_true=y_val, y_pred=preds, average='macro')
print('未调参前lightgbm单模型在验证集上的f1：{}'.format(score))

更进一步的，使用k折交叉验证进行模型性能评估,我们这里指定k为5，使用lightgbm 5折交叉验证进行建模预测

cv_scores = []
for i, (train_index, valid_index) in enumerate(kf.split(X_train, y_train)):
    print('************************************ {} ************************************'.format(str(i+1)))
    X_train_split, y_train_split, X_val, y_val = X_train.iloc[train_index], y_train[train_index], X_train.iloc[valid_index], y_train[valid_index]
    
    train_matrix = lgb.Dataset(X_train_split, label=y_train_split)
    valid_matrix = lgb.Dataset(X_val, label=y_val)

    params = {
                "learning_rate": 0.1,
                "boosting": 'gbdt',  
                "lambda_l2": 0.1,
                "max_depth": -1,
                "num_leaves": 128,
                "bagging_fraction": 0.8,
                "feature_fraction": 0.8,
                "metric": None,
                "objective": "multiclass",
                "num_class": 4,
                "nthread": 10,
                "verbose": -1,
            }
    
    model = lgb.train(params, 
                      train_set=train_matrix, 
                      valid_sets=valid_matrix, 
                      num_boost_round=2000, 
                      verbose_eval=100, 
                      early_stopping_rounds=200,
                      feval=f1_score_vali)
    
    val_pred = model.predict(X_val, num_iteration=model.best_iteration)
    
    val_pred = np.argmax(val_pred, axis=1)
    cv_scores.append(f1_score(y_true=y_val, y_pred=val_pred, average='macro'))
    print(cv_scores)

print("lgb_scotrainre_list:{}".format(cv_scores))
print("lgb_score_mean:{}".format(np.mean(cv_scores)))
print("lgb_score_std:{}".format(np.std(cv_scores)))

然后对于调参，我们经常使用到的就是网格搜索。

sklearn 提供GridSearchCV用于进行网格搜索，只需要把模型的参数输进去，就能给出最优化的结果和参数。相比起贪心调参，网格搜索的结果会更优，但是网格搜索只适合于小数据集，一旦数据的量级上去了，很难得出结果。

同样以Lightgbm算法为例，进行网格搜索调参,通过网格搜索确定最优参数

from sklearn.model_selection import GridSearchCV

def get_best_cv_params(learning_rate=0.1, n_estimators=581, num_leaves=31, max_depth=-1, bagging_fraction=1.0, 
                       feature_fraction=1.0, bagging_freq=0, min_data_in_leaf=20, min_child_weight=0.001, 
                       min_split_gain=0, reg_lambda=0, reg_alpha=0, param_grid=None):
    # 设置5折交叉验证
    cv_fold = KFold(n_splits=5, shuffle=True, random_state=2021)

    model_lgb = lgb.LGBMClassifier(learning_rate=learning_rate,
                                   n_estimators=n_estimators,
                                   num_leaves=num_leaves,
                                   max_depth=max_depth,
                                   bagging_fraction=bagging_fraction,
                                   feature_fraction=feature_fraction,
                                   bagging_freq=bagging_freq,
                                   min_data_in_leaf=min_data_in_leaf,
                                   min_child_weight=min_child_weight,
                                   min_split_gain=min_split_gain,
                                   reg_lambda=reg_lambda,
                                   reg_alpha=reg_alpha,
                                   n_jobs= 8
                                  )

    f1 = make_scorer(f1_score, average='micro')
    grid_search = GridSearchCV(estimator=model_lgb, 
                               cv=cv_fold,
                               param_grid=param_grid,
                               scoring=f1

                              )
    grid_search.fit(X_train, y_train)

    print('模型当前最优参数为:{}'.format(grid_search.best_params_))
    print('模型当前最优得分为:{}'.format(grid_search.best_score_))

最后得出比较合适的参数之后，就可以进行确认调优了：

final_params = {
                'boosting_type': 'gbdt',
                'learning_rate': 0.01,
                'num_leaves': 29,
                'max_depth': 7,
                'objective': 'multiclass',
                'num_class': 4,
                'min_data_in_leaf':45,
                'min_child_weight':0.001,
                'bagging_fraction': 0.9,
                'feature_fraction': 0.9,
                'bagging_freq': 40,
                'min_split_gain': 0,
                'reg_lambda':0,
                'reg_alpha':0,
                'nthread': 6
               }

cv_result = lgb.cv(train_set=lgb_train,
                   early_stopping_rounds=20,
                   num_boost_round=5000,
                   nfold=5,
                   stratified=True,
                   shuffle=True,
                   params=final_params,
                   feval=f1_score_vali,
                   seed=0,
                  )

在实际调整过程中，我们可先设置一个较大的学习率比如0.1，然后通过cv函数进行树个数的确定之后，就可以进行参数的调整优化。

然后确定完其他参数之后，针对最优的参数设置一个较小的学习率，比如0.05或者0.01，同样通过cv函数确定树的个数，确定最终的参数。