我们首先来梳理一下搭建模型的过程——
- import相关的包
- 读取数据,划分数据集
- 搭建模型,或是导入模型,设置模型相关参数
- 将数据导入模型,模型训练的相关参数
- 评估最优模型
目录
1.整体浏览,了解框架
这部分以#####为界,快速浏览,了解搭建框架
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")
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
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
##########################################
# 读取数据
data = pd.read_csv('data/train.csv')
# 简单预处理
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)
#############################################
from sklearn.model_selection import KFold
# 分离数据集,方便进行交叉验证
X_train = data.drop(['id','label'], axis=1)
y_train = data['label']
# 5折交叉验证
folds = 5
seed = 2021
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)
"""对训练集数据进行划分,分成训练集和验证集,并进行相应的操作"""
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)
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))
#################################################################
"""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)))
2.分步了解
2.1 读取数据,数据预处理
data = pd.read_csv('data/train.csv')
# 简单预处理
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)
reduce_mem_usage()这个函数通过限定数据的类型,减少数据的大小,进而提升计算机对数据的读取速度
比如0.8765432101234567直接用0.87654321代替,数据的精度变小
2.2 分离数据,交叉验证
from sklearn.model_selection import KFold
# 分离数据集,方便进行交叉验证
X_train = data.drop(['id','label'], axis=1)
y_train = data['label']
# 5折交叉验证
folds = 5
seed = 2021
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)
"""对训练集数据进行划分,分成训练集和验证集,并进行相应的操作"""
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)
2.2.1
什么是交叉验证,详见详解交叉验证
了解一下KFold的参数,KFold(n_splits=’warn’, shuffle=False, random_state=None)
参数——
- n_splits 表示划分为几块(至少是2)
- shuffle 表示是否打乱划分,默认False,即不打乱
- random_state 表示是否固定随机起点,Used when shuffle == True.
2.2.2
X_train_split, X_val, y_train_split, y_val
= train_test_split(X_train, y_train, test_size=0.2)
参数是X数据集,Y标签集,测试集数据分配的比例。比如test_size=0.2,便是数据集中训练集占总数据集的80%。
返回值便是 X训练数据值,X测试数据值,Y训练标签,Y测试标签。
2.3 设置模型参数
params = {
"learning_rate": 0.1,#学习率
"boosting": 'gbdt',#梯度提升决策树
"lambda_l2": 0.1,#
"max_depth": -1,
"num_leaves": 128,#叶节点的数目
"bagging_fraction": 0.8,
"feature_fraction": 0.8,#使用特征的子抽样的抽样率
"metric": None,
"objective": "multiclass",
"num_class": 4,
"nthread": 10,
"verbose": -1,
}
2.4 训练模型,评估结果
import lightgbm as lgb
lightgbm是boosting集合模型中的新进成员,由微软提供,它和XGBoost一样是对GBDT的高效实现,原理上它和GBDT及XGBoost类似,都采用损失函数的负梯度作为当前决策树的残差近似值,去拟合新的决策树。
详见——LightGBM
"""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)
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')#评估模型性能
print('未调参前lightgbm单模型在验证集上的f1:{}'.format(score))
2.5 交叉验证,减少训练误差
"""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)))
这部分的关键点在这里——
folds = 5
seed = 2021
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)
for i, (train_index, valid_index) in enumerate(kf.split(X_train, y_train))
将数据集平均分成5份,其中每次随机取4份为训练集,1份为测试集,每次取的不一样。
比如——
- 【1,2,3,4】【5】
- 【2,3,4,5】【1】
- 【1,3,4,5】【2】
- 【1,2,4,5】【3】
- 【1,2,3,5】【4】
3.测试结果如下
3.1 数据的简单处理
Memory usage of dataframe is 157.93 MB
Memory usage after optimization is: 39.67 MB
Decreased by 74.9%
3.2 未调参的训练结果
##########################################
Training until validation scores don't improve for 200 rounds
[50] valid_0's multi_logloss: 0.0518171 valid_0's f1_score: 0.954613
[100] valid_0's multi_logloss: 0.0456245 valid_0's f1_score: 0.962268
[150] valid_0's multi_logloss: 0.0470006 valid_0's f1_score: 0.965291
[200] valid_0's multi_logloss: 0.0484298 valid_0's f1_score: 0.966406
[250] valid_0's multi_logloss: 0.0498757 valid_0's f1_score: 0.966886
Early stopping, best iteration is:
[92] valid_0's multi_logloss: 0.045533 valid_0's f1_score: 0.96131
未调参前lightgbm单模型在验证集上的f1:0.961309560452836
3.3 调参后的训练结果
###########################################################################
************************************ 1 ************************************
Training until validation scores don't improve for 200 rounds
[100] valid_0's multi_logloss: 0.0408155 valid_0's f1_score: 0.966797
[200] valid_0's multi_logloss: 0.0437957 valid_0's f1_score: 0.971239
Early stopping, best iteration is:
[96] valid_0's multi_logloss: 0.0406453 valid_0's f1_score: 0.967452
[0.9674515729721614]
************************************ 2 ************************************
Training until validation scores don't improve for 200 rounds
[100] valid_0's multi_logloss: 0.0472933 valid_0's f1_score: 0.965828
[200] valid_0's multi_logloss: 0.0514952 valid_0's f1_score: 0.968138
Early stopping, best iteration is:
[87] valid_0's multi_logloss: 0.0467472 valid_0's f1_score: 0.96567
[0.9674515729721614, 0.9656700872844327]
************************************ 3 ************************************
Training until validation scores don't improve for 200 rounds
[100] valid_0's multi_logloss: 0.0378154 valid_0's f1_score: 0.971004
[200] valid_0's multi_logloss: 0.0405053 valid_0's f1_score: 0.973736
Early stopping, best iteration is:
[93] valid_0's multi_logloss: 0.037734 valid_0's f1_score: 0.970004
[0.9674515729721614, 0.9656700872844327, 0.9700043639844769]
************************************ 4 ************************************
Training until validation scores don't improve for 200 rounds
[100] valid_0's multi_logloss: 0.0495142 valid_0's f1_score: 0.967106
[200] valid_0's multi_logloss: 0.0542324 valid_0's f1_score: 0.969746
Early stopping, best iteration is:
[84] valid_0's multi_logloss: 0.0490886 valid_0's f1_score: 0.965566
[0.9674515729721614, 0.9656700872844327, 0.9700043639844769, 0.9655663272378014]
************************************ 5 ************************************
Training until validation scores don't improve for 200 rounds
[100] valid_0's multi_logloss: 0.0412544 valid_0's f1_score: 0.964054
[200] valid_0's multi_logloss: 0.0443025 valid_0's f1_score: 0.965507
Early stopping, best iteration is:
[96] valid_0's multi_logloss: 0.0411855 valid_0's f1_score: 0.963114
[0.9674515729721614, 0.9656700872844327, 0.9700043639844769, 0.9655663272378014, 0.9631137190307674]
lgb_scotrainre_list:[0.9674515729721614, 0.9656700872844327, 0.9700043639844769, 0.9655663272378014, 0.9631137190307674]
lgb_score_mean:0.9663612141019279
lgb_score_std:0.0022854824074775683