Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [decision-trees]

The tag has no usage guidance.

1
vote
0answers
7 views

Get Decision Tree Prediction With Random Forest

If I give random forest parameters as RandomForestClassifier(n_estimators=10,bootstrap=False,max_features=None,random_state=2019) Should it be creating 10 same ...
0
votes
0answers
3 views

Building a minimal encoding of nominal labels from numerical features

I have a set of ~500 objects, only a single instance of each kind, and each has ~500 numerical features ... I need to find the minimal encoding which allows to identify objects. I am interested in ...
1
vote
0answers
7 views

Is it possible to have a better performance with C4.5 than Bagged tree?

I am not sure but I have read that bagged trees is used to improve the accuracy of a signle tree methods such as C4.5 but applying both of them over the same dataset I got better accuracy with C4.5, ...
2
votes
1answer
39 views

How to extract the sample split (values) of decision tree leaves ( terminal nodes) applying h2o library

Sorry for a long story, but it is a long story. :) I am using h2o library for python to build a decision tree and to extract a decision rules out of it. I use some data for training where labels get ...
1
vote
1answer
17 views

Use prediction as feature for a decision tree

I'm working at classifying documents according to their content. First I built a decision tree model that gives 90% of goods results. Then I tried a TFIDF/SVC approach which also gives 90% of good ...
1
vote
1answer
26 views

receive value error decision tree classifier after one-hot encoding

I am trying to build a decision tree model. After one-hot encoding, it seems somehow the data still has a problem. When I run the following code, I receive this error: ...
1
vote
1answer
32 views

SciKit-Learn Decision Tree Overfitting

I'm pursuing a computer science minor at my university, and one class I'm in is Machine Learning. We have a project to utilize a few algorithms we have learned so far. I've been using SciKit-Learn to ...
0
votes
0answers
18 views

Visualization decision tree [closed]

Run into problem when i visualizing decision tree here is the code: ...
1
vote
0answers
11 views

Assessing performance of an agent based on commission rate, market share and revenue

I have a set of data for agents selling properties (apartments) for a company in different states. The company would like to assess the performance of the different agents given the following: Number ...
6
votes
1answer
72 views

Will unnecessary features harm the tree based model?

Is it necessary to drop noisy features (eg column of random numbers) from tree features? I think it's not. sometimes it may benefit but will never cause any harm to the model. Because at each split ...
0
votes
0answers
12 views

Insights from RandomForestRegressor (or any RF output)

Beyond the feature importance calculations from a RandomForestRegressor in sklearn, what are some good strategies to draw ...
0
votes
0answers
24 views

Decision Tree Classifier For Minimizing Arbitrary Cost Function

Assume the input $X$ of $n$ data points, and $m$ features. Also, assume I have four different Heuristic algorithms ($h_1$, $h_2$, $h_3$, $h_4$) that are obtained independently of $X$. Problem: ...
1
vote
1answer
16 views

Desicision tree classification with a “false” attribute

This is a pretty specific problem but I think it can help me understand better the whole concept of the subject. A doctor in the hospital is in charge of 20 medical students. For every patient, the ...
1
vote
2answers
48 views

Accuracy differs between MATLAB and scikit-learn for a decision tree

Is there any possibility to vary the accuracy of same data set in matlab and jupyter notebook by using python code ? For same data set, at first I applied it in matlab and get 96% accuracy for ...
0
votes
0answers
10 views

Should we invest more in exploration (as opposed to exploitation) when the distribution is fat-tailed in contrast to a bell-curve?

Not sure if this falls under data science but here it goes: In the exploration/exploitation trade-off (deliberation vs commitment to one choice), should we invest more in exploration when the ...
1
vote
1answer
15 views

WEKA Random Forest J48 Attribute Importance

I have been using WEKA to classify very long duration audio recordings. The best performing classifiers have been Random Forest and J48. The attributes used to classify the audio are acoustic indices. ...
0
votes
0answers
14 views

Learn a boolean function

My ploblem is as follows: I have a pool of 32-bit physical addresses. Each address maps to a bank in the DRAM (16 bank in total). I can detect subsets of addresses mapping to the same bank. For ...
1
vote
1answer
38 views

Why does Feature Importance change with each iteration of a Decision Tree Classifier?

After applying PCA to reduce the number of features, I am using a DecisionTreeClassifier for a ML problem Additionally I want to compute the feature_importances_. However, with each iteration of the ...
0
votes
1answer
52 views

How to represent linear regression in a decision tree form

I have read that decision trees can represent any hypothesis and are thus completely expressive. So how do we represent the hypothesis of linear regression in the form of a decision tree ? I am ...
0
votes
1answer
49 views

Value of features is zero in Decision tree Classifier

I used CountVectorizer and TfidfVectorizer seperately to vectorize text which is 100K reviews and passed the vector data to a Decision tree Classifier. Upon using _feature_importances__ attribute of ...
0
votes
0answers
52 views

Feature importance and probability score out of Decision Trees

We all know that Decision trees are super interpretable but one thing that I am not able to understand is the mathematics behind it. So, I have three questions here : How do Decision tree and Radom ...
3
votes
3answers
79 views

how to evaluate feature quality for decision tree model

Most of the tutorials assume that the features are known before generating the model and give no way to select 'good' feature and to discard 'bad' ones. The naive method is to test the model with new ...
0
votes
1answer
60 views

Is there any implementation of Extended Isolation Forest algorithm in R/Python?

I am using isofor package for regular Isolation Forest but I came by an article about Extended Isolation Forest and need your advise which package has this ...
1
vote
0answers
32 views

How to figure out if the problem is solvable by any machine learning algorithm?

I am trying to solve a problem in the domain of the audiology, to predict the value of an audio gain in dB. My data is made of: 10,000 training samples 1,000 validation samples 10 features The ...
0
votes
1answer
40 views

When is a neural network better “traditional” models like decisions trees and lassos?

There's a whole theory of statistical inference based off calculus studying consistency, efficiency, robustness, BLUE, unbiasedness of linear models (Gaussian,Exponential, Chi-square, F-distribution, ...
0
votes
0answers
11 views

Which class to choose in decision tree when gini = 0.5?

Referring to the decision tree above,we have a box where $gini = 0.5$, in that case, how does the decision tree model in sk decide the class is died or survived? Or is there anyway that we can change ...
2
votes
0answers
40 views

Target transformation for tree models

Can anybody explain why/if target variable transformations could help when dealing with tree based models? I've seen this excellent reply which explains quite well why it shouldn't affect if ...
0
votes
2answers
26 views

How important is it for each row of data to have the same number of features?

I'm using decision tree learning to try and classify a device based its components. Different devices have a different number of components and the location of these components within the device is ...
0
votes
1answer
42 views

Random Forest, Duplicating Data increases Accuracy. Why? [closed]

I duplicated my training data for the random forest classifier (Sklearn) and the accuracy of the prediction increased by about 3%. Why?
0
votes
0answers
7 views

Proof of $R(t) \ge R(t_l) + R(t_r)$

In minimal complexity cost prunning of decision trees I found the following inequality $R(t) \ge R(t_l) + R(t_r)$ where $t$ is the current node and $t_l$, $t_r$ are the left node and the right node ...
1
vote
0answers
10 views

How to reduce the number of rules in decision tree with Support and Confidence

The following is a set of rules in decison tree. How to reduce the number of rules in the set with Support and Confidence? If Ascites = 'Yes' then if Class = 'Live' then if Spiders = 'Yes' then if ...
1
vote
1answer
107 views

LightGBM - Why Exclusive Feature Bundling (EFB)?

I'm currently studying GBDT and started reading LightGBM's research paper: https://papers.nips.cc/paper/6907-lightgbm-a-highly-efficient-gradient-boosting-decision-tree.pdf In section 4. they explain ...
0
votes
1answer
84 views

Forcing a multi-label multi-class tree-based classifier to make more label predictions per document

I'm been experimenting with tree based classifiers for multi-label document classification. All the trees I've created, however, tend to predict only one or two labels per document. Whereas the ...
3
votes
1answer
46 views

How to prefer no choice instead of bad choice with sklearn decision tree

I'm using sklearn decision trees to classify documents in two possible types "type1" and "type2". I've isolated few features that seem pertinent and tried to combine them manually to evaluate the ...
1
vote
2answers
40 views

data pre-processing before image classification

I'm working on a machine learning project, Images classification (shape: 100 x 100)-> (vector of 10000), I did some pre-processing before applying decision trees algorithm , I got an accuracy of 55 % ...
4
votes
2answers
121 views

Why Decision trees performs better than logistic regression [closed]

I'm working on a machine learning project, a classification of (100 x 100) Images (every pixel contains 0 or 255), my training set contains 10000 examples (which I split into 2 parts 80% training/20% ...
3
votes
1answer
266 views

How max_features parameter works in DecisionTreeClassifier?

What is the parameter max_features in DecisionTreeClassifier responsible for? I thought it defines the number of features the ...
0
votes
1answer
46 views

Why xgboost can not deal with this simple sentence case?

There is only 1 feature dim. But the result is unreasonable. The code and data is below. The purpose of the code is to judge whether the two sentences are the same. In fact, the final input to the ...
1
vote
0answers
29 views

Decision Trees How to Calculate Entropy Gain for Continuous Values for split point?

I'm trying to calculate the entropy gain to decide the best decision split node, however I am having trouble understanding how to do this with doubles. I have columns listed out as A1 and A2 the ...
4
votes
3answers
79 views

Default parameters for decision trees give better results than parameters optimised using GridsearchCV

I am using Gridsearch for a DecisionTreeClassifier predicting a binary outcome. When I run fit and predict with default parameters, I get the following results: ...
2
votes
1answer
24 views

“help” decision tree by tying 2 features together

Assuming I have in my dataset 2 (or more) features that are for sure linked (for example: feature B indicates the amount of relevance of feature A), is there a way I could design a decision tree that ...
0
votes
2answers
50 views

Would a decision tree classifier be applicable here?

File from a situation where it is required to predict today’s stockprice from the stock prices of the previous three days: Could you use a decision tree classifier for this task? Why or why not?
2
votes
0answers
23 views

Is linear regression on the trees of XGBoost (rather than taking their mean) useful/popular?

Given training data $(\underline{x}_1, y_1),...,(\underline{x_N}, y_N)$, one can choose a variety of ensemble method for trees. These algorithms output a set of trees $T_1, ..., T_n$, and then the ...
1
vote
1answer
32 views

Decision Tree: Efficient splitting of nodes, minimize number of gini evaluations

I have a dataset specific problem where i need to use a splitting function other than gini_index. This requires me to re-write a decision tree from scratch. I have a working model, but itis highly ...
0
votes
0answers
10 views

how can decision rules be deduplicated?

I just fell on the interesting skope-rules package, which estimates decision rules from bagged trees. The best rules are then deduplicated, but the deduplication method is not detailed. Can someone ...
1
vote
1answer
16 views

AUC with sklearn vary each time script is started

I'm using the following code to perform a tree classification. I set up an int value for random_state in train_test_split ...
1
vote
2answers
43 views

When creating a classification model, should predictors with little correlation to the response variable be included in the model?

I am building a predictive model designed to predict attrition within my organization. I am trying to decide whether to add certain predictors to my model. I used a Kruskal-Wallis rank sum test to ...
0
votes
1answer
38 views

How to migrate R decision tree to Java

I have trained a conditional inference decision tree in R using library party with function ctree and saved the model in an <...
0
votes
1answer
26 views

How I can interpret the attached tree?

Is the total sample size = 30.891 and the overall percentage of “yes” = 11,3%? How I can describe the leaves predicting "yes" outcome in term of explicative variables and values? What are the ...
1
vote
0answers
28 views

Do C 4.5 or C 5.0 perform multi way split or binary split?

Suppose that I am using a continuous variable as an independent variable (although a bad choice) for C 4.5 or C 5.0 (tree based classifier). I am having a hard time figuring out does C 4.5 or C 5.0 ...