模型融合：Stacking源码解析

第一层：

训练数据：通过5-fold切分数据集分别训练和测试，将model1的预测值保存为P1，作为model2的训练数据。

测试数据：通过每次训练的model1预测所有的测试数据，然后取平均值得到T1。

如果第一层有三个模型，则得到预测值矩阵（P1, P2, P3）和 预测值矩阵 (T1, T2, T3)。

第二层：

预测值矩阵（P1, P2, P3）作为训练集，预测值矩阵 (T1, T2, T3)作为测试集。

import pandas as pd
import numpy as np
import re
import sklearn
import xgboost as xgb
import seaborn as sns
import matplotlib.pyplot as plt
# %matplotlib inline  # 使用jupyter notebook
import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls

import warnings
warnings.filterwarnings('ignore')

# Going to use these 5 base models for the stacking
from sklearn.ensemble import (RandomForestClassifier, AdaBoostClassifier,
                              GradientBoostingClassifier, ExtraTreesClassifier)
from sklearn.svm import SVC
from sklearn.model_selection import KFold

# Some useful parameters which will come in handy later on
ntrain = train.shape[0]
ntest = test.shape[0]
SEED = 0 # for reproducibility
NFOLDS = 5 # set folds for out-of-fold prediction
kf = KFold(n_splits=NFOLDS, random_state=SEED)

# Class to extend the Sklearn classifier
class SklearnHelper(object):
    def __init__(self, clf, seed=0, params=None):
        params['random_state'] = seed
        self.clf = clf(**params)

    def train(self, x_train, y_train):
        self.clf.fit(x_train, y_train)

    def predict(self, x):
        return self.clf.predict(x)
    
    def fit(self,x,y):
        return self.clf.fit(x,y)
    
    def feature_importances(self,x,y):
        print(self.clf.fit(x,y).feature_importances_)

def get_oof(clf, x_train, y_train, x_test):
    oof_train = np.zeros((ntrain,))
    oof_test = np.zeros((ntest,))
    # np.empty()返回一个随机元素的矩阵
    oof_test_skf = np.empty((NFOLDS, ntest))  

    for i, (train_index, test_index) in enumerate(kf.split(oof_train)):
        x_tr = x_train[train_index]
        y_tr = y_train[train_index]
        x_te = x_train[test_index]

        clf.train(x_tr, y_tr)

        oof_train[test_index] = clf.predict(x_te)
        # k则验证之后会产生[k x ntest]个验证集
        oof_test_skf[i, :] = clf.predict(x_test)
    # 按列取平均值
    oof_test[:] = oof_test_skf.mean(axis=0)
    return oof_train.reshape(-1, 1), oof_test.reshape(-1, 1)
    
# Random Forest classifier
# Extra Trees classifier
# AdaBoost classifer
# Gradient Boosting classifer
# Support Vector Machine

# Put in our parameters for said classifiers
# Random Forest parameters
rf_params = {
    'n_jobs': -1,
    'n_estimators': 500,
     'warm_start': True, 
     #'max_features': 0.2,
    'max_depth': 6,
    'min_samples_leaf': 2,
    'max_features' : 'sqrt',
    'verbose': 0
}

# Extra Trees Parameters
et_params = {
    'n_jobs': -1,
    'n_estimators':500,
    #'max_features': 0.5,
    'max_depth': 8,
    'min_samples_leaf': 2,
    'verbose': 0
}

# AdaBoost parameters
ada_params = {
    'n_estimators': 500,
    'learning_rate' : 0.75
}

# Gradient Boosting parameters
gb_params = {
    'n_estimators': 500,
     #'max_features': 0.2,
    'max_depth': 5,
    'min_samples_leaf': 2,
    'verbose': 0
}

# Support Vector Classifier parameters 
svc_params = {
    'kernel' : 'linear',
    'C' : 0.025
    }

# Create 5 objects that represent our 4 models
rf = SklearnHelper(clf=RandomForestClassifier, seed=SEED, params=rf_params)
et = SklearnHelper(clf=ExtraTreesClassifier, seed=SEED, params=et_params)
ada = SklearnHelper(clf=AdaBoostClassifier, seed=SEED, params=ada_params)
gb = SklearnHelper(clf=GradientBoostingClassifier, seed=SEED, params=gb_params)
svc = SklearnHelper(clf=SVC, seed=SEED, params=svc_params)

y_train = train['Survived'].ravel()
train = train.drop(['Survived'], axis=1)
x_train = train.values # Creates an array of the train data
x_test = test.values # Creats an array of the test data

# Create our OOF train and test predictions. These base results will be used as new features
et_oof_train, et_oof_test = get_oof(et, x_train, y_train, x_test) # Extra Trees
rf_oof_train, rf_oof_test = get_oof(rf,x_train, y_train, x_test) # Random Forest
ada_oof_train, ada_oof_test = get_oof(ada, x_train, y_train, x_test) # AdaBoost 
gb_oof_train, gb_oof_test = get_oof(gb,x_train, y_train, x_test) # Gradient Boost
svc_oof_train, svc_oof_test = get_oof(svc,x_train, y_train, x_test) # Support Vector Classifier

print("Training is complete")

# 输出训练和测试集中各种功能的重要性
rf_feature = rf.feature_importances(x_train,y_train)
et_feature = et.feature_importances(x_train, y_train)
ada_feature = ada.feature_importances(x_train, y_train)
gb_feature = gb.feature_importances(x_train,y_train)

cols = train.columns.values
# Create a dataframe with features
feature_dataframe = pd.DataFrame( {'features': cols,
     'Random Forest feature importances': rf_feature,
     'Extra Trees  feature importances': et_feature,
      'AdaBoost feature importances': ada_feature,
    'Gradient Boost feature importances': gb_feature
    })
# 计算特征重要性的平均值
# Create the new column containing the average of values
feature_dataframe['mean'] = feature_dataframe.mean(axis= 1) # axis = 1 computes the mean row-wise
feature_dataframe.head(3)

Parameters 参数说明

n_jobs : Number of cores used for the training process. If set to -1, all cores are used.

核心的使用数目，如果设置为-1，则使用所有核心。

n_estimators : Number of classification trees in your learning model ( set to 10 per default)

学习模型中的分类树数量（默认设置为10）

max_depth : Maximum depth of tree, or how much a node should be expanded. Beware if set to too high a number would run the risk of overfitting as one would be growing the tree too deep

树的最大深度，或节点应扩展的程度。如果设置太高，则会过拟合。

verbose : Controls whether you want to output any text during the learning process. A value of 0 suppresses all text while a value of 3 outputs the tree learning process at every iteration.

控制是否要在学习过程中输出任何文本。 值0将抑制所有文本，而值3则在每次迭代时输出树学习过程。

画图显示特征重要性：

# Scatter plot 
trace = go.Scatter(
    y = feature_dataframe['Random Forest feature importances'].values,
    x = feature_dataframe['features'].values,
    mode='markers',
    marker=dict(
        sizemode = 'diameter',
        sizeref = 1,
        size = 25,
#       size= feature_dataframe['AdaBoost feature importances'].values,
        #color = np.random.randn(500), #set color equal to a variable
        color = feature_dataframe['Random Forest feature importances'].values,
        colorscale='Portland',
        showscale=True
    ),
    text = feature_dataframe['features'].values
)
data = [trace]

layout= go.Layout(
    autosize= True,
    title= 'Random Forest Feature Importance',
    hovermode= 'closest',
#     xaxis= dict(
#         title= 'Pop',
#         ticklen= 5,
#         zeroline= False,
#         gridwidth= 2,
#     ),
    yaxis=dict(
        title= 'Feature Importance',
        ticklen= 5,
        gridwidth= 2
    ),
    showlegend= False
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig,filename='scatter2010')

# Scatter plot 
trace = go.Scatter(
    y = feature_dataframe['Extra Trees  feature importances'].values,
    x = feature_dataframe['features'].values,
    mode='markers',
    marker=dict(
        sizemode = 'diameter',
        sizeref = 1,
        size = 25,
#       size= feature_dataframe['AdaBoost feature importances'].values,
        #color = np.random.randn(500), #set color equal to a variable
        color = feature_dataframe['Extra Trees  feature importances'].values,
        colorscale='Portland',
        showscale=True
    ),
    text = feature_dataframe['features'].values
)
data = [trace]

layout= go.Layout(
    autosize= True,
    title= 'Extra Trees Feature Importance',
    hovermode= 'closest',
#     xaxis= dict(
#         title= 'Pop',
#         ticklen= 5,
#         zeroline= False,
#         gridwidth= 2,
#     ),
    yaxis=dict(
        title= 'Feature Importance',
        ticklen= 5,
        gridwidth= 2
    ),
    showlegend= False
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig,filename='scatter2010')

# Scatter plot 
trace = go.Scatter(
    y = feature_dataframe['AdaBoost feature importances'].values,
    x = feature_dataframe['features'].values,
    mode='markers',
    marker=dict(
        sizemode = 'diameter',
        sizeref = 1,
        size = 25,
#       size= feature_dataframe['AdaBoost feature importances'].values,
        #color = np.random.randn(500), #set color equal to a variable
        color = feature_dataframe['AdaBoost feature importances'].values,
        colorscale='Portland',
        showscale=True
    ),
    text = feature_dataframe['features'].values
)
data = [trace]

layout= go.Layout(
    autosize= True,
    title= 'AdaBoost Feature Importance',
    hovermode= 'closest',
#     xaxis= dict(
#         title= 'Pop',
#         ticklen= 5,
#         zeroline= False,
#         gridwidth= 2,
#     ),
    yaxis=dict(
        title= 'Feature Importance',
        ticklen= 5,
        gridwidth= 2
    ),
    showlegend= False
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig,filename='scatter2010')

# Scatter plot 
trace = go.Scatter(
    y = feature_dataframe['Gradient Boost feature importances'].values,
    x = feature_dataframe['features'].values,
    mode='markers',
    marker=dict(
        sizemode = 'diameter',
        sizeref = 1,
        size = 25,
#       size= feature_dataframe['AdaBoost feature importances'].values,
        #color = np.random.randn(500), #set color equal to a variable
        color = feature_dataframe['Gradient Boost feature importances'].values,
        colorscale='Portland',
        showscale=True
    ),
    text = feature_dataframe['features'].values
)
data = [trace]

layout= go.Layout(
    autosize= True,
    title= 'Gradient Boosting Feature Importance',
    hovermode= 'closest',
#     xaxis= dict(
#         title= 'Pop',
#         ticklen= 5,
#         zeroline= False,
#         gridwidth= 2,
#     ),
    yaxis=dict(
        title= 'Feature Importance',
        ticklen= 5,
        gridwidth= 2
    ),
    showlegend= False
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig,filename='scatter2010')

画图显示特征重要性的平均值：

y = feature_dataframe['mean'].values
x = feature_dataframe['features'].values
data = [go.Bar(
            x= x,
             y= y,
            width = 0.5,
            marker=dict(
               color = feature_dataframe['mean'].values,
            colorscale='Portland',
            showscale=True,
            reversescale = False
            ),
            opacity=0.6
        )]

layout= go.Layout(
    autosize= True,
    title= 'Barplots of Mean Feature Importance',
    hovermode= 'closest',
#     xaxis= dict(
#         title= 'Pop',
#         ticklen= 5,
#         zeroline= False,
#         gridwidth= 2,
#     ),
    yaxis=dict(
        title= 'Feature Importance',
        ticklen= 5,
        gridwidth= 2
    ),
    showlegend= False
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig, filename='bar-direct-labels')

现在已经获得了我们的第一级预测，可以用作下一个分类器的训练数据。 根据下面的代码，我们将新列作为我们之前的分类器中的第一级预测，并在此基础上训练下一个分类器。

# 第一级预测，用作下一个分类器的训练数据
# .ravel()  将多维数组降位一维
base_predictions_train = pd.DataFrame( {'RandomForest': rf_oof_train.ravel(),
     'ExtraTrees': et_oof_train.ravel(),
     'AdaBoost': ada_oof_train.ravel(),
      'GradientBoost': gb_oof_train.ravel()
    })
base_predictions_train.head()
# 二级训练集的相关热图 Heatmap
# 模型彼此之间更不相关，产生更好的分数
data = [
    go.Heatmap(
        z= base_predictions_train.astype(float).corr().values ,
        x=base_predictions_train.columns.values,
        y= base_predictions_train.columns.values,
          colorscale='Viridis',
            showscale=True,
            reversescale = True
    )
]
py.iplot(data, filename='labelled-heatmap')
# 第二级的数据集
x_train = np.concatenate(( et_oof_train, rf_oof_train, ada_oof_train, gb_oof_train, svc_oof_train), axis=1)
x_test = np.concatenate(( et_oof_test, rf_oof_test, ada_oof_test, gb_oof_test, svc_oof_test), axis=1)

# Second level learning model via XGBoost
# max_depth：树的深度。 如果设置得太高，则可能存在过度拟合的风险。
# gamma：在树的叶节点上进行进一步分区所需的最小损耗减少。算法越大，越保守。
# eta：每个增压步骤中使用的步长收缩，以防止过度拟合
gbm = xgb.XGBClassifier(
    #learning_rate = 0.02,
 n_estimators= 2000,
 max_depth= 4,
 min_child_weight= 2,
 #gamma=1,
 gamma=0.9,                        
 subsample=0.8,
 colsample_bytree=0.8,
 objective= 'binary:logistic',
 nthread= -1,
 scale_pos_weight=1).fit(x_train, y_train)
predictions = gbm.predict(x_test)

最后可以根据如下方式提高分数：

1.训练：实施良好的交叉验证策略以找到最佳参数值

2.模型：引入更多种类的基础模型进行学习。模型生成的结果越不相关，最终得分越高

参考资料：

https://www.kaggle.com/arthurtok/introduction-to-ensembling-stacking-in-python/notebook#Second-Level-Predictions-from-the-First-level-Output