高级集成学习技巧

Examined ensemble methods

• Averaging (or blending)
• Weighted averaging
• Conditional averaging
• Bagging
• Boosting
• Stacking
• StackNet

Averaging ensemble methods

举个例子，假设咱们有一个名为age的变量，就像年龄同样，咱们试着预测它。咱们有两个模型：

• 低于50，模型效果更好
  

• 高于50，模型效果更好
  

那么若是咱们试图结合它们将会发生什么呢？

Averaging(or blending)

• (model1 + model2) / 2
  

$R^2$上升到0.95，较以前有所改善。但该模型并无比单模型作的好的地方更好，尽管如此，它平均表现更好。也许可能会有更好的组合呢？来试试加权平均

Weighted averaging

• (model1 x 0.7 + model 2 x 0.3)
  

看起来没有以前的好

Conditional averaging

• 各取好的部分
  

理想状况下，咱们但愿获得相似的结果

Bagging

Why Bagging

建模中有两个主要偏差来源

• 1.因为误差而存在偏差（underfitting）
• 2.因为方差而存在偏差（overfitting）

经过略微不一样的模型，确保预测不会有读取很是高的方差。这一般使它更具广泛性。

Parameters that control bagging?

• Changing the seed
• Row(Sub) sampling or Bootstrapping
• Shuffling
• Column(Sub) sampling
• Model-specific parameters
• Number of models (or bags)
• (Optionally) parallelism

Examples of bagging

Boosting

Boosting是对每一个模型构建的模型进行加权平均的一种形式，顺序地考虑之前的模型性能。

Weight based boosting

假设咱们有一个表格数据集，有四个特征。 咱们称它们为x0，x1，x2和x3，咱们但愿使用这些功能来预测目标变量y。
咱们将预测值称为pred，这些预测有必定的偏差。咱们能够计算这些绝对偏差，|y - pred|。咱们能够基于今生成一个新列或向量，在这里咱们建立一个权重列，使用1加上绝对偏差。固然有不一样的方法来计算这个权重，如今咱们只是以此为例。

全部接下来要作的是用这些特征去拟合新的模型，但每次也要增长这个权重列。这就是按顺序添加模型的方法。

Weight based boosting parameters

• Learning rate (or shrinkage or eta)
• 每一个模型只相信一点点：predictionN = pred0*eta + pred1*eta + ... + predN*eta
• Number of estimators
• estimators扩大一倍，eta减少一倍
• Input model - can be anything that accepts weights
• Sub boosting type:
• AdaBoost-Good implementation in sklearn(python)
• LogitBoost-Good implementation in Weka(Java)

Residual based boosting [&]

咱们使用一样的数据集作相同的事。预测出pred后

接下来会计算偏差

将error做为新的y获得新的预测new_pred

以Rownum=1为例：

最终预测=0.75 + 0.20 = 0.95更接近于1

这种方法颇有效，能够很好的减少偏差。

Residual based boosting parameters

• Learning rate (or shrinkage or eta)
• predictionN = pred0 + pred1*eta + ... + predN*eta
• 前面的例子，若是eta为0.1，则Prediction=0.75 + 0.2*(0.1) = 0.77
• Number of estimators
• Row (sub)sampling
• Column (sub)sampling
• Input model - better be trees.
• Sub boosting type:
• Full gradient based
• Dart

Residual based favourite implementations

• Xgboost
• Lightgbm
• H2O's GBM
• Catboost
• Sklearn's GBM

Stacking

Methodology

• Wolpert in 1992 introduced stacking. It involves:
• 1. Splitting the train set into two disjoint sets.
• 1. Train several base learners on the first part.
• 1. Make predictions with the base learners on the second (validation) part.

具体步骤

假设有A,B,C三个数据集，其中A,B的目标变量y已知。

而后

• 算法0拟合A，预测B和C，而后保存pred0到B1,C1
• 算法1拟合A，预测B和C，而后保存pred1到B1,C1

• 算法2拟合A，预测B和C，而后保存pred2到B1,C1
  

• 算法3拟合B1，预测C1，获得最终结果preds3

Stacking example

from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression
import numpy as np
from sklearn.model_selection import train_test_split
train = '' # your training set
y = ''     # your target variable
# split train data in 2 part, training and valdiation.
training, valid, ytraining, yvalid = train_test_split(train, y, test_size=0.5)
# specify models
model1 = RandomForestRegressor()
model2 = LinearRegression()
#fit models
model1.fit(training, ytraining)
model2.fit(trainging, ytraining)
# make predictions for validation
preds1 = model1.predict(valid)
preds2 = model2.predict(valid)
# make predictions for test data
test_preds1 = model1.predict(test)
test_preds2 = model2.predict(test)
# From a new dataset for valid and test via stacking the predictions
stacked_predictions = np.colum_stack((preds1, preds2))
stacked_test_predictions = np.column_stack((test_preds1, test_preds2))
# specify meta model
meta_model = LinearRegression()
meta_model.fit(stacked_predictions, yvalid)
# make predictions on the stacked predictions of the test data
final_predictions = meta_model.predict(stacked_test_predictions)

Stacking(past) example

能够看到，它与咱们使用Conditional averaging的结果很是近似。只是在50附件作的不够好，这是有道理的，由于模型没有见到目标变量，没法准确识别出50这个缺口。因此它只是尝试根据模型的输入来肯定。

Things to be mindful of

• With time sensitive data - respect time
• 若是你的数据带有时间元素，你须要指定你的stacking，以便尊重时间。
• Diversity as important as performance
• 单一模型表现很重要，但模型的多样性也很是重要。当模型是坏的或弱的状况，你不需太担忧，stacking实际上能够从每一个预测中提取到精华，获得好的结果。所以，你真正须要关注的是，我正在制做的模型能给我带来哪些信息，即便它一般很弱。
• Diversity may come from:
• Different algorithms
• Different input features
• Performance plateauing after N models
• Meta model is normally modest

StackNet

https://github.com/kaz-Anova/StackNet

Ensembling Tips and Tricks

$1^{st}$ level tips

• Diversity based on algorithms:
• 2-3 gradient boosted trees (lightgbm, xgboost, H2O, catboost)
• 2-3 Neural nets (keras, pytorch)
• 1-2 ExtraTrees/RandomForest (sklearn)
• 1-2 linear models as in logistic/ridge regression, linear svm (sklearn)
• 1-2 knn models (sklearn)
• 1 Factorization machine (libfm)
• 1 svm with nonlinear kernel(like RBF) if size/memory allows (sklearn)
• Diversity based on input data:
• Categorical features: One hot, label encoding, target encoding, likelihood encoding, frequency or counts
• Numerical features: outliers, binning, derivatives, percentiles, scaling
• Interactions: col1*/+-col2, groupby, unsupervised

$2^{st}$ level tips

• Simpler (or shallower) Algorithms:
• gradient boosted trees with small depth(like 2 or 3)
• Linear models with high regularization
• Extra Trees (just don't make them too big)
• Shallow networks (as in 1 hidden layer, with not that many hidden neurons)
• knn with BrayCurtis Distance

• Brute forcing a search for best linear weights based on cv

• Feature engineering:
• pairwise differences between meta features
• row-wise statistics like averages or stds
• Standard feature selection techniques
• For every 7.5 models in previous level we add 1 in meta (经验)

• Be mindful to target leakage

Additional materials

• MLWave.com的Kaggle 集成指南（方法概述）
• StackNet - 一个计算，可扩展和分析的元建模框架（KazAnova）
• Heamy - 一套用于竞争数据科学（包括整合）的有用工具