Dear Gilles, > Hi Paul, > > a) Scaling has no effect on decision trees. Thanks!
> > b) You shouldn't set max_depth=5. Instead, build fully developed trees > (max_depth=None) or rather tune min_samples_split using > cross-validation. Do fully developed trees make sense for rather small datasets? Overall, I have 622 samples with 177 features each. Isn't there the risk of overfitting? Do you mean by "tune min_sample_split" the training/test set split? Or rather the ensemble method ExtraTreesRegressor: http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.ExtraTreesRegressor.html > > Hope this helps. You helped me a lot already! Paul > > Gilles > > > For the training/test set split, I make use of the train_test_split module: > > " > > from sklearn.cross_validation import train_test_split > > X_train,X_test,y_train,y_test = train_test_split > > (dataDescrs_array_scaled,data_activities,test_size=.4) > > " > > > > RF is trained as follows > > " > > from sklearn.ensemble import RandomForestClassifier > > clf_RF = RandomForestClassifier(n_estimators=100, > > max_depth=5,random_state=0,n_jobs=1) > > clf_RF = clf_RF.fit(X_train,y_train) > > y_predict = clf_RF.predict(X_test) > > accuracy = clf_RF.score(X_test,y_test) > > fpr, tpr, thresholds = metrics.roc_curve(y_test, y_predict) > > print metrics.confusion_matrix > > (y_test,y_predict),"\n",accuracy,"\n",metrics.auc(fpr,tpr) > > " > > > > The performance is rather modest: > > " > > [[175 7] > > [ 53 14]] > > 0.759036144578 > > 0.58524684271 > > " > > > > In my of my former mails, it was recommended to make use of reweighting and > > subsampling: > > http://www.mail-archive.com/scikit-learn- > [email protected]/msg04975.html > > In another thread, the flag "class_weight=auto" was mentioned: > > http://www.mail-archive.com/scikit-learn- > [email protected]/msg03759.html > > However, this does not work in conjunction with "RandomForestClassifier" - > > did I miss something? > > > > > > Cheers & Thanks, > > Paul This message and any attachment are confidential and may be privileged or otherwise protected from disclosure. If you are not the intended recipient, you must not copy this message or attachment or disclose the contents to any other person. If you have received this transmission in error, please notify the sender immediately and delete the message and any attachment from your system. Merck KGaA, Darmstadt, Germany and any of its subsidiaries do not accept liability for any omissions or errors in this message which may arise as a result of E-Mail-transmission or for damages resulting from any unauthorized changes of the content of this message and any attachment thereto. Merck KGaA, Darmstadt, Germany and any of its subsidiaries do not guarantee that this message is free of viruses and does not accept liability for any damages caused by any virus transmitted therewith. Click http://www.merckgroup.com/disclaimer to access the German, French, Spanish and Portuguese versions of this disclaimer. ------------------------------------------------------------------------------ LogMeIn Central: Instant, anywhere, Remote PC access and management. Stay in control, update software, and manage PCs from one command center Diagnose problems and improve visibility into emerging IT issues Automate, monitor and manage. Do more in less time with Central http://p.sf.net/sfu/logmein12331_d2d _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
