对智慧海洋的数据进行模型融合

模型融合

类型：

• 简单加权融合:
  –回归（分类概率）：算术平均融合（Arithmetic mean），几何平均融合（Geometric mean）
  – 分类：投票（Voting)
• boosting/bagging（在xgboost，Adaboost,GBDT中已经用到）:
  – 多树的提升方法
• stacking/blending:
  – 构建多层模型，并利用预测结果再拟合预测。

下面直接对数据进行模型融合：

1、导入相关库和降低内存函数

import pandas as pd
import numpy as np
import warnings
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns

warnings.filterwarnings('ignore')
%matplotlib inline

import itertools
import matplotlib.gridspec as gridspec
from sklearn import datasets
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB 
from sklearn.ensemble import RandomForestClassifier,RandomForestRegressor
from sklearn.linear_model import LogisticRegression
# from mlxtend.classifier import StackingClassifier
from sklearn.model_selection import cross_val_score, train_test_split
# from mlxtend.plotting import plot_learning_curves
# from mlxtend.plotting import plot_decision_regions

from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import train_test_split
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import VotingClassifier
import lightgbm as lgb
from sklearn.neural_network import MLPClassifier,MLPRegressor
from sklearn.metrics import mean_squared_error, mean_absolute_error

import pandas as pd
import numpy as np
from sklearn.metrics import classification_report, f1_score
from sklearn.model_selection import StratifiedKFold, KFold,train_test_split

降低内存使用的函数：

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