tag:blogger.com,1999:blog-7958828565254404797.post6097450709972233953..comments2024-10-12T23:23:22.571-07:00Comments on ListenData: Decision Tree in R : Step by Step GuideDeepanshu Bhallahttp://www.blogger.com/profile/09802839558125192674noreply@blogger.comBlogger19125tag:blogger.com,1999:blog-7958828565254404797.post-66640750173437864242020-05-31T08:54:39.211-07:002020-05-31T08:54:39.211-07:00I loved the article (a big thank you),But I am not...I loved the article (a big thank you),But I am not being able install these libraries.<br />when I trying to install these libraries it giving me these errors<br />"install.packages(rattle)<br />Error in install.packages : object 'rattle' not found"<br />library(rattle)<br />library(rpart.plot)<br />library(RColorBrewer)gannu0062https://www.blogger.com/profile/09145304348471492707noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-12493629089082061502018-11-19T08:20:54.325-08:002018-11-19T08:20:54.325-08:00pred is used in predicting the class codes(0,1)
th...pred is used in predicting the class codes(0,1)<br />the auc means the area under the roc curve<br />plot the performance means will plot the roc curve tpr against the fprAnonymoushttps://www.blogger.com/profile/15131143794977292809noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-36328511818303296522018-09-25T03:50:12.170-07:002018-09-25T03:50:12.170-07:001.Please confirm why we should convert categorical...1.Please confirm why we should convert categorical var to factor in decision tree<br />2.how to do pre pruningDeeptinoreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-13065570983391903842018-06-05T14:31:14.704-07:002018-06-05T14:31:14.704-07:00I have a question. It is clear if we have n variab...I have a question. It is clear if we have n variables, the variable with the help of which we will get minimum GINI split, the code will use that variable to split the tree. But what if we get only a ROOT node as the output- as in which value is considered as the reference point to say that beyond the root node, there is no point of splitting as impurity will increase. We are comparing GINI split of all dependent variable with which value to arrive at this conclusion.Kirti Tewarihttps://www.blogger.com/profile/16821131883845818479noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-20456081332570825942018-06-04T06:35:57.224-07:002018-06-04T06:35:57.224-07:00It will be better if you explain data too. Withou...It will be better if you explain data too. Without understanding input data, this becomes mathematical exercise using R. Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-56989955607830623662018-04-19T20:18:03.145-07:002018-04-19T20:18:03.145-07:00Great Article ,provided clear cut concept.Thank yo...Great Article ,provided clear cut concept.Thank you.Anonymoushttps://www.blogger.com/profile/08572580883205048319noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-11622334805975761922017-06-21T07:51:04.844-07:002017-06-21T07:51:04.844-07:00I am not able to understand below listed code nor ...I am not able to understand below listed code nor you have provided complete explanation to the code/graphs<br /><br />#Scoring<br /> library(ROCR)<br /> val1 = predict(pruned, val, type = "prob")<br /> #Storing Model Performance Scores<br /> pred_val <-prediction(val1[,2],val$Creditability)<br /><br /> # Calculating Area under Curve<br /> perf_val <- performance(pred_val,"auc")<br /> perf_val<br /><br /> # Plotting Lift curve<br /> plot(performance(pred_val, measure="lift", x.measure="rpp"), colorize=TRUE)<br /><br /> # Calculating True Positive and False Positive Rate<br /> perf_val <- performance(pred_val, "tpr", "fpr")<br /><br /> # Plot the ROC curve<br /> plot(perf_val, col = "green", lwd = 1.5)<br /><br />Appreciate if you could please provide me an explanation. Anonymoushttps://www.blogger.com/profile/18131597193335641126noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-47931229408003713932017-05-25T10:50:11.596-07:002017-05-25T10:50:11.596-07:00?Nice Article. Are you on github??Nice Article. Are you on github?Anonymoushttps://www.blogger.com/profile/15376357183214949388noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-19632012594292843542017-03-11T02:02:43.915-08:002017-03-11T02:02:43.915-08:00The root node is the independent variable (predict...The root node is the independent variable (predictor). In this example, the dependent variable is binary in nature - whether to approve a loan to a prospective applicant.Deepanshu Bhallahttps://www.blogger.com/profile/09802839558125192674noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-9311672418742709242017-03-09T22:09:22.032-08:002017-03-09T22:09:22.032-08:00I have thought which I came across in beginning of...I have thought which I came across in beginning of tutorial with the mentioning of the "root" node. Isn't that the dependent variable from which mother and child node comes?Just asking to clear my doubt, because I see, that has been mentioned as the most important predictor.Sarbaruphttps://www.blogger.com/profile/14044414880800849780noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-74697359787053475702016-09-25T12:10:42.814-07:002016-09-25T12:10:42.814-07:00There should be a single bracket in 'rpart.con...There should be a single bracket in 'rpart.control(('. Use rpart.control( instead of rpart.control((. Let me know if it works. I am logged in via mobile. Will update the code in the article tomorrow. Deepanshu Bhallahttps://www.blogger.com/profile/04301769767832902721noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-41194201293178286262016-09-25T11:18:56.869-07:002016-09-25T11:18:56.869-07:00mtree <- rpart(Creditability~., data = train, m...mtree <- rpart(Creditability~., data = train, method="class", control = rpart.control((minsplit = 20, minbucket = 7, maxdepth = 10, usesurrogate = 2, xval =10 ))<br />Error: unexpected ',' in "mtree <- rpart(Creditability~., data = train, method="class", control = rpart.control((minsplit = 20,"<br /><br />I am getting this error can you please tell me the way, so that i don't get this errorSanal Nairhttps://www.blogger.com/profile/18360672327725406571noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-59540278484572665232016-06-11T08:24:24.072-07:002016-06-11T08:24:24.072-07:00amazing....amazing....Anonymoushttps://www.blogger.com/profile/10821097923988924777noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-55845930996337027542016-06-10T08:04:30.462-07:002016-06-10T08:04:30.462-07:00Decision tree algorithm is not available in SAS S...Decision tree algorithm is not available in SAS STAT. It is available in SAS Enterprise Miner. I don't have access to SAS Enterprise Miner. I can share some tutorial about how to build a decision tree in SAS Enterprise Miner if you want. Thanks! Deepanshu Bhallahttps://www.blogger.com/profile/04301769767832902721noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-68875144599315466322016-06-10T06:39:19.307-07:002016-06-10T06:39:19.307-07:00Please provide decision tree in sas if you can, th...Please provide decision tree in sas if you can, thankspadmahttps://www.blogger.com/profile/04907464389413757621noreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-74628219715854417932016-01-19T20:25:49.850-08:002016-01-19T20:25:49.850-08:00Sorry, I meant root node error.Sorry, I meant root node error.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-75394364041386651872016-01-19T20:24:51.055-08:002016-01-19T20:24:51.055-08:00Nice Article. Could you please let me know how to ...Nice Article. Could you please let me know how to calculate root mean error.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-60597688509125926372015-04-17T22:58:51.726-07:002015-04-17T22:58:51.726-07:00Remarkable and well definedRemarkable and well definedshree harinoreply@blogger.comtag:blogger.com,1999:blog-7958828565254404797.post-40098589849560738212015-04-14T11:46:44.811-07:002015-04-14T11:46:44.811-07:00Nice Article! Thanks for making decision tree so s...Nice Article! Thanks for making decision tree so simpler :-)Paulnoreply@blogger.com