Last active
May 16, 2016 14:23
-
-
Save walterreade/246314a9ff6196826bee8875f777490e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
""" | |
Regularized Tree Ensemble | |
@author: gert.jacobusse@rogatio.nl | |
@license: FreeBSD | |
Originally posted: | |
https://www.kaggle.com/c/bnp-paribas-cardif-claims-management/forums/t/20207/why-every-good-script-is-using-extratreeclassifier-one-way-or-the-other/115621 | |
""" | |
import numpy as np | |
from joblib import Parallel, delayed | |
from sklearn.tree import DecisionTreeClassifier | |
from sklearn.linear_model import LogisticRegression | |
class colsampler(): | |
colsamples=None | |
data=None | |
def __init__(self, ncol, psample=0.5, nsample=1000, randseed=0): | |
np.random.seed(randseed) | |
self.ncol=ncol | |
self.nsample=nsample | |
self.colsamples=[[c for c in xrange(ncol) if np.random.random()<psample] for s in xrange(nsample)] | |
def setdata(self,data): | |
assert type(data)==type(np.array([])) | |
assert len(data.shape)==2 | |
assert self.ncol==data.shape[1] | |
self.data=data | |
def getsample(self,fromsample=0): | |
assert type(self.data)==type(np.array([])) | |
for s in xrange(fromsample,self.nsample): | |
yield [row[self.colsamples[s]] for row in self.data] | |
def getsample_bynum(self,num): | |
assert type(self.data)!=type(None) | |
return [row[self.colsamples[num]] for row in self.data] | |
def fitmodel(model,cs,i,y): | |
model.fit(cs.getsample_bynum(i),y) | |
return model | |
def getholdoutpreds(model,cs,i,y): | |
n=len(y) | |
halfn=n/2 | |
x=cs.getsample_bynum(i) | |
holdoutpreds=np.zeros(n) | |
model.fit(x[halfn:],y[halfn:]) | |
holdoutpreds[:halfn]=model.predict(x[:halfn]) | |
model.fit(x[:halfn],y[:halfn]) | |
holdoutpreds[halfn:]=model.predict(x[halfn:]) | |
return holdoutpreds | |
class rteClassifier(): | |
def __init__(self,n_estimators=100,colsample_bytree=0.5,min_samples_split=1, | |
splitter='random', | |
stackingmodel=LogisticRegression(C=0.1,penalty='l1'), | |
samplingseed=0, | |
n_jobs=-1): | |
self.n_estimators=n_estimators | |
self.colsample_bytree=colsample_bytree | |
self.n_jobs=n_jobs | |
self.models=[DecisionTreeClassifier( | |
splitter=splitter, | |
max_features=None, | |
min_samples_split=min_samples_split | |
) for m in xrange(self.n_estimators)] | |
self.stackingmodel=stackingmodel | |
self.samplingseed=samplingseed | |
def fit(self,X,y): | |
perm=np.random.permutation(len(X)) | |
X=np.array(X)[perm] | |
y=np.array(y)[perm] | |
local_cs=colsampler(len(X[0]),psample=self.colsample_bytree,nsample=self.n_estimators,randseed=self.samplingseed) | |
local_cs.setdata(np.array(X)) | |
holdoutpreds=Parallel(n_jobs=self.n_jobs)(delayed(getholdoutpreds)(self.models[i],local_cs,i,y) for i in range(self.n_estimators)) | |
self.stackingmodel.fit([[holdoutpreds[j][i] for j in xrange(self.n_estimators)] | |
for i in xrange(len(y))],y) | |
self.models=Parallel(n_jobs=self.n_jobs)(delayed(fitmodel)(self.models[i],local_cs,i,y) for i in range(self.n_estimators)) | |
def predict_proba(self,X): | |
local_cs=colsampler(len(X[0]),psample=self.colsample_bytree,nsample=self.n_estimators,randseed=self.samplingseed) | |
local_cs.setdata(X) | |
preds=[self.models[i].predict(s) for i,s in enumerate(local_cs.getsample())] | |
return self.stackingmodel.predict_proba([[preds[j][i] for j in xrange(self.n_estimators)] | |
for i in xrange(len(preds[0]))]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment