Related
Given n samples with d features of stock A, we can build a (d+1) dimensional linear model to predict the profit. However, in some books, I found that if we have m different stocks with n samples and d features for each, then they merge these data to get m*n samples with d features to build a single (d+1) dimensional linear model to predict the profit.
My confusion is that, different stocks usually have little connection with each other, and their profit are influenced by different factors and environment, so why they can be merged to build a single model?
If you are using R as tool of choice, you might like the time series embedding howto and its appendix -- the mathematics behind that is Taken's theorem:
[Takens's theorem gives] conditions under which a chaotic dynamical system can be reconstructed from a sequence of observations of the state of a dynamical system.
It looks to me as the statement's you quote seem to relate to exactly this theorem: For d features (we are lucky, if we know that number - we usually don't), we need d+1 dimensions.
If more time series should be predicted, we can use the same embedding space if the features are the same. The dimensions d are usually simple variables (like e.g. temperature for different energy commodity stocks) - this example helped me to intuitively grasp the idea.
Further reading
Forecasting with Embeddings
Lets say I have 100 independent features - 90 are binary (e.g. 0/1) and 10 are continuous variables (e.g. age, height, weight, etc). I use the 100 features to predict a classifier problem with an adequate amount of samples.
When I set a XGBClassifier function and fit it, then the 10 most important features from the standpoint of gain are always the 10 continuous variable. For now I am not interested in cover or frequency. The 10 continuous variables take up like .8 to .9 of space in gain list ( sum(gain) = 1).
I tried tuning the gamma, reg_alpha , reg_lambda , max_depth, colsample. Still top 10 features by gain are always the 10 continuous features.
Any suggestions?
small update -- someone asked why I think this is happening. I believe it's because a continuous variable can be split on multiple times per decision tree. A binary variable can only be split on once. Hence, the higher prevalence of continuous variables in trees and thus a higher gain score
Yes, it's well-known that a tree(/forest) algorithm (xgboost/rpart/etc.) will generally 'prefer' continuous variables over binary categorical ones in its variable selection, since it can choose the continuous split-point wherever it wants to maximize the information gain (and can freely choose different split-points for that same variable at other nodes, or in other trees). If that's the optimal tree (for those particular variables), well then it's the optimal tree. See Why do Decision Trees/rpart prefer to choose continuous over categorical variables? on sister site CrossValidated.
When you say "any suggestions", depends what exactly do you want, it could be one of the following:
a) To find which of the other 90 binary categorical features give the most information gain
b) To train a suboptimal tree just to find out which features those are
c) To engineer some "compound" features by combining the binary features into n-bit categorical features which have more information gain (while being sure to remove the individual binary features from the input)
d) You could look into association rules : What is the practical difference between association rules and decision trees in data mining?
If you want to explore a)...c), suggest something vaguely like this:
exclude various subsets of the 10 continuous variables, then see which binary features show up as having the most gain. Let's say that gives you N candidate features. N will be << 90, let's assume N < 20 to make the following more computationally efficient.
then compute the pairwise measure of association or correlation (Spearman or Kendall) between each of the N features. Look at a corrplot. Pick the clusters of variables which are most associated with each other. Create compound n-bit variables which combine those individual binary features. Then retrain the tree, including the compound variables, and excluding the individual binary variables (to avoid changing the total variance in the input).
iterate for excluding various subsets of the 10 continuous variables. See which patterns emerge in your compound variables. I'm sure there's an algorithm for doing this (compound feature-engineering of n-bit categoricals) more formally and methodically, I just don't know it.
Anyway, for hacking a tree-based method for better performance, I imagine the most naive way is "at every step, pick the two most highly-correlated/associated categorical features and combine them". Then retrain the tree (include new feature, exclude its constituent features) and use the revised gain numbers.
perhaps a more robust way might be:
Pick some threshold T for correlation/association, say start at a high level T = 0.9 or 0.95
At each step, merge any features whose absolute correlation/association to each other >= T
If there were no merges at this step, reduce T by some value (like T -= 0.05) or ratio (e.g. T *= 0.9 . If still no merges, keep reducing T until there are merges, or until you hit some termination value (e.g. T = 0.03)
Retrain the tree including the compound variables, excluding their constituent subvariables.
Now go back and retrain what should be an improved tree with all 10 continuous variables, and your compound categorical features.
Or you could early-terminate the compound feature selection to see what the full retrained tree looks like.
This issue arose in the 2014 Kaggle Allstate Purchase Prediction Challenge, where the policy coverage options A,B,C,D,E,F,G were each categoricals with between 2-4 values, and very highly correlated with each other. (The current option of C, "C_previous", is one of the input features). See that competitions's forums and published solutions for more. Be aware that policy = (A,B,C,D,E,F,G) is the output. But C_previous is an input variable.
Some general fast-and-dirty rules-of-thumb on feature selection from Kaggle are:
throw out any near-constant/ very-low-variance variables (because they have near-zero information content)
throw out any very-high-cardinality categorical variables (cardinality >~ training-set-size/2), (because they will also tend to have low information content, but cause lots of spurious overfitting and blow up training time). This can include customer IDs, row IDs, transaction IDs, sequence IDs, and other variables which shouldn't be trained on in the first place but accidentally ended up in the training set.
I can suggest few things for you to try.
Test your model without this data (only 90 features) and evaluate the decrease in your score. If it's insignificant you might want to remove those features.
Turn them into groups.
For example, age can be categorized into groups, 0 : 0-7, 1 : 8-16, 2 : 17-25 and so on.
Turn them into binary. Out of the box idea on how to chose the best value to split them into binary is: Build 1 tree with 1 node (max depth = 1) and use only 1 feature. (1 out of the continuous features). then, dump the model to a .txt file and see the value it chose to split on. using this value, you can transform all that feature column into binary
I'm dealing myself with very similar problems right now, So i'll be happy to hear your results and the paths you chose to try.
I learned a lot from the answer by #smci, so I would recommend to follow his suggestions.
In the case, when your binary categorical features are in fact OHE representations of several categorical features with several classes in each, you can follow two more approaches:
Convert OHE into label encoding. Yes, this has the caveat that one introduces an order into a categorical features, which might be meaningless, for example green=3 > red=2 > blue=1. But in practice is seems that trees handle label=encoded categorical variables (even with meaningless order) reasonably well.
Convert OHE into target-/mean-/likelihood encoding. This is tricky, because you need to apply regularisation to avoid data leakage.
Both of those ideas are meant to group together several binary features into a single one based on prior knowledge about feature meaning. If you do not have that luxury, you can also try to deduce such groups by doing scalar product of columns and finding those giving zero product.
I'm trying to classify some data using knime with knime-labs deep learning plugin.
I have about 16.000 products in my DB, but I have about 700 of then that I know its category.
I'm trying to classify as much as possible using some DM (data mining) technique. I've downloaded some plugins to knime, now I have some deep learning tools as some text tools.
Here is my workflow, I'll use it to explain what I'm doing:
I'm transforming the product name into vector, than applying into it.
After I train a DL4J learner with DeepMLP. (I'm not really understand it all, it was the one that I thought I got the best results). Than I try to apply the model in the same data set.
I thought I would get the result with the predicted classes. But I'm getting a column with output_activations that looks that gets a pair of doubles. when sorting this column I get some related date close to each other. But I was expecting to get the classes.
Here is a print of the result table, here you can see the output with the input.
In columns selection it's getting just the converted_document and selected des_categoria as Label Column (learning node config). And in Predictor node I checked the "Append SoftMax Predicted Label?"
The nom_produto is the text column that I'm trying to use to predict the des_categoria column that it the product category.
I'm really newbie about DM and DL. If you could get me some help to solve what I'm trying to do would be awesome. Also be free to suggest some learning material about what attempting to achieve
PS: I also tried to apply it into the unclassified data (17,000 products), but I got the same result.
I won't answer with a workflow on this one because it is not going to be a simple one. However, be sure to find the text mining example on the KNIME server, i.e. the one that makes use of the bag of words approach.
The task
Product mapping to categories should be a straight-forward data mining task because the information that explains the target variable is available in a quasi-exhaustive manner. Depending on the number of categories to train though, there is a risk that you might need more than 700 instances to learn from.
Some resources
Here are some resources, only the first one being truly specialised in text mining:
Introduction on Information Retrieval, in particular chapter 13;
Data Science for Business is an excellent introduction to data mining, including text mining (chapter 10), also do not forget the chapter about similarity (chapter 6);
Machine Learning with R has the advantage of being accessible enough (chapter 4 provides an example of text classification with R code).
Preprocessing
First, you will have to preprocess your product labels a bit. Use KNIME's text analytics preprocessing nodes for that purpose, that is after you've transformed the product labels with Strings to Document:
Case Convert, Punctuation Erasure and Snowball Stemmer;
you probably won't need Stop Word Filter, however, there may be quasi-stop words such as "product", which you may need to remove manually with Dictionary Filter;
Be careful not to use any of the following without testing testing their impact first: N Chars Filter (g may be a useful word), Number Filter (numbers may indicate quantities, which may be useful for classification).
Should you encounter any trouble with the relevant nodes (e.g. Punctuation Erasure can be tricky amazingly thanks to the tokenizer), you can always apply String Manipulation with regex before converting the Strings to Document.
Keep it short and simple: the lookup table
You could build a lookup table based on the 700 training instances. The book Data mining techniques as well as resource (2) present this approach in some detail. If any model performs any worse than the lookup table, you should abandon the model.
Nearest neighbors
Neural networks are probably overkill for this task.
Start with a K Nearest Neighbor node (applying a string distance such as Cosine, Levensthein or Jaro-Winkler). This approach requires the least amount of data wrangling. At the very least, it will provide an excellent baseline model, so it is most definitely worth a shot.
You'll need to tune the parameter k and to experiment with the distance types. The Parameter Optimization Loop pair will help you with optimizing k, you can include a Cross-Validation meta node inside of the said loop to obtain an estimate of the expected performance given k instead of only one point estimate per value of k. Use Cohen's Kappa as an optimization criterion, as proposed by the resource number (3) and available via the Scorer node.
After the parameter tuning, you'll have to evaluate the relevance of your model using yet another Cross-Validation meta node, then follow up with a Loop pair including Scorer to calculate the descriptives on performance metric(s) per iteration, finally use Statistics. Kappa is a convenient metric for this task because the target variable consists of many product categories.
Don't forget to test its performance against the lookup table.
What next ?
Should lookup table or k-nn work well for you, then there's nothing else to add.
Should any of those approaches fail, you might want to analyse the precise cases on which it fails. In addition, training set size may be too low, so you could manually classify another few hundred or thousand instances.
If after increasing the training set size, you are still dealing with a bad model, you can try the bag of words approach together with a Naive Bayes classifier (see chapter 13 of the Information Retrieval reference). There is no room here to elaborate on the bag of words approach and Naive Bayes but you'll find the resources here above useful for that purpose.
One last note. Personally, I find KNIME's Naive Bayes node to perform poorly, probably because it does not implement Laplace smoothening. However, KNIME's R Learner and R Predictor nodes will allow you to use R's e1071 package, as demonstrated by resource (3).
I need some point of view to know if what I am doing is good or wrong or if there is better way to do it.
I have 10 000 elements. For each of them I have like 500 features.
I am looking to measure the separability between 2 sets of those elements. (I already know those 2 groups I don't try to find them)
For now I am using svm. I train the svm on 2000 of those elements, then I look at how good the score is when I test on the 8000 other elements.
Now I would like to now which features maximize this separation.
My first approach was to test each combination of feature with the svm and follow the score given by the svm. If the score is good those features are relevant to separate those 2 sets of data.
But this takes too much time. 500! possibility.
The second approach was to remove one feature and see how much the score is impacted. If the score changes a lot that feature is relevant. This is faster, but I am not sure if it is right. When there is 500 feature removing just one feature don't change a lot the final score.
Is this a correct way to do it?
Have you tried any other method ? Maybe you can try decision tree or random forest, it would give out your best features based on entropy gain. Can i assume all the features are independent of each other. if not please remove those as well.
Also for Support vectors , you can try to check out this paper:
http://axon.cs.byu.edu/Dan/778/papers/Feature%20Selection/guyon2.pdf
But it's based more on linear SVM.
You can do statistical analysis on the features to get indications of which terms best separate the data. I like Information Gain, but there are others.
I found this paper (Fabrizio Sebastiani, Machine Learning in Automated Text Categorization, ACM Computing Surveys, Vol. 34, No.1, pp.1-47, 2002) to be a good theoretical treatment of text classification, including feature reduction by a variety of methods from the simple (Term Frequency) to the complex (Information-Theoretic).
These functions try to capture the intuition that the best terms for ci are the
ones distributed most differently in the sets of positive and negative examples of
ci. However, interpretations of this principle vary across different functions. For instance, in the experimental sciences χ2 is used to measure how the results of an observation differ (i.e., are independent) from the results expected according to an initial hypothesis (lower values indicate lower dependence). In DR we measure how independent tk and ci are. The terms tk with the lowest value for χ2(tk, ci) are thus the most independent from ci; since we are interested in the terms which are not, we select the terms for which χ2(tk, ci) is highest.
These techniques help you choose terms that are most useful in separating the training documents into the given classes; the terms with the highest predictive value for your problem. The features with the highest Information Gain are likely to best separate your data.
I've been successful using Information Gain for feature reduction and found this paper (Entropy based feature selection for text categorization Largeron, Christine and Moulin, Christophe and Géry, Mathias - SAC - Pages 924-928 2011) to be a very good practical guide.
Here the authors present a simple formulation of entropy-based feature selection that's useful for implementation in code:
Given a term tj and a category ck, ECCD(tj , ck) can be
computed from a contingency table. Let A be the number
of documents in the category containing tj ; B, the number
of documents in the other categories containing tj ; C, the
number of documents of ck which do not contain tj and D,
the number of documents in the other categories which do
not contain tj (with N = A + B + C + D):
Using this contingency table, Information Gain can be estimated by:
This approach is easy to implement and provides very good Information-Theoretic feature reduction.
You needn't use a single technique either; you can combine them. Term-Frequency is simple, but can also be effective. I've combined the Information Gain approach with Term Frequency to do feature selection successfully. You should experiment with your data to see which technique or techniques work most effectively.
If you want a single feature to discriminate your data, use a decision tree, and look at the root node.
SVM by design looks at combinations of all features.
Have you thought about Linear Discriminant Analysis (LDA)?
LDA aims at discovering a linear combination of features that maximizes the separability. The algorithm works by projecting your data in a space where the variance within classes is minimum and the one between classes is maximum.
You can use it reduce the number of dimensions required to classify, and also use it as a linear classifier.
However with this technique you would lose the original features with their meaning, and you may want to avoid that.
If you want more details I found this article to be a good introduction.
My dataset is composed of millions of row and a couple (10's) of features.
One feature is a label composed of 1000 differents values (imagine each row is a user and this feature is the user's firstname :
Firstname,Feature1,Feature2,....
Quentin,1,2
Marc,0,2
Gaby,1,0
Quentin,1,0
What would be the best representation for this feature (to perform clustering) :
I could convert the data as integer using a LabelEncoder, but it doesn't make sense here since there is no logical "order" between two differents label
Firstname,F1,F2,....
0,1,2
1,0,2
2,1,0
0,1,0
I could split the feature in 1000 features (one for each label) with 1 when the label match and 0 otherwise. However this would result in a very big matrix (too big if I can't use sparse matrix in my classifier)
Quentin,Marc,Gaby,F1,F2,....
1,0,0,1,2
0,1,0,0,2
0,0,1,1,0
1,0,0,1,0
I could represent the LabelEncoder value as a binary in N columns, this would reduce the dimension of the final matrix compared to the previous idea, but i'm not sure of the result :
LabelEncoder(Quentin) = 0 = 0,0
LabelEncoder(Marc) = 1 = 0,1
LabelEncoder(Gaby) = 2 = 1,0
A,B,F1,F2,....
0,0,1,2
0,1,0,2
1,0,1,0
0,0,1,0
... Any other idea ?
What do you think about solution 3 ?
Edit for some extra explanations
I should have mentioned in my first post, but In the real dataset, the feature is the more like the final leaf of a classification tree (Aa1, Aa2 etc. in the example - it's not a binary tree).
A B C
Aa Ab Ba Bb Ca Cb
Aa1 Aa2 Ab1 Ab2 Ab3 Ba1 Ba2 Bb1 Bb2 Ca1 Ca2 Cb1 Cb2
So there is a similarity between 2 terms under the same level (Aa1 Aa2 and Aa3are quite similar, and Aa1 is as much different from Ba1 than Cb2).
The final goal is to find similar entities from a smaller dataset : We train a OneClassSVM on the smaller dataset and then get a distance of each term of the entiere dataset
This problem is largely one of one-hot encoding. How do we represent multiple categorical values in a way that we can use clustering algorithms and not screw up the distance calculation that your algorithm needs to do (you could be using some sort of probabilistic finite mixture model, but I digress)? Like user3914041's answer, there really is no definite answer, but I'll go through each solution you presented and give my impression:
Solution 1
If you're converting the categorical column to an numerical one like you mentioned, then you face that pretty big issue you mentioned: you basically lose meaning of that column. What does it really even mean if Quentin in 0, Marc 1, and Gaby 2? At that point, why even include that column in the clustering? Like user3914041's answer, this is the easiest way to change your categorical values into numerical ones, but they just aren't useful, and could perhaps be detrimental to the results of the clustering.
Solution 2
In my opinion, depending upon how you implement all of this and your goals with the clustering, this would be your best bet. Since I'm assuming you plan to use sklearn and something like k-Means, you should be able to use sparse matrices fine. However, like imaluengo suggests, you should consider using a different distance metric. What you can consider doing is scaling all of your numeric features to the same range as the categorical features, and then use something like cosine distance. Or a mix of distance metrics, like I mention below. But all in all this will likely be the most useful representation of your categorical data for your clustering algorithm.
Solution 3
I agree with user3914041 in that this is not useful, and introduces some of the same problems as mentioned with #1 -- you lose meaning when two (probably) totally different names share a column value.
Solution 4
An additional solution is to follow the advice of the answer here. You can consider rolling your own version of a k-means-like algorithm that takes a mix of distance metrics (hamming distance for the one-hot encoded categorical data, and euclidean for the rest). There seems to be some work in developing k-means like algorithms for mixed categorical and numerical data, like here.
I guess it's also important to consider whether or not you need to cluster on this categorical data. What are you hoping to see?
Solution 3:
I'd say it has the same kind of drawback as using a 1..N encoding (solution 1), in a less obvious fashion. You'll have names that both give a 1 in some column, for no other reason than the order of the encoding...
So I'd recommend against this.
Solution 1:
The 1..N solution is the "easy way" to solve the format issue, as you noted it's probably not the best.
Solution 2:
This looks like it's the best way to do it but it is a bit cumbersome and from my experience the classifier does not always performs very well with a high number of categories.
Solution 4+:
I think the encoding depends on what you want: if you think that names that are similar (like John and Johnny) should be close, you could use characters-grams to represent them. I doubt this is the case in your application though.
Another approach is to encode the name with its frequency in the (training) dataset. In this way what you're saying is: "Mainstream people should be close, whether they're Sophia or Jackson does not matter".
Hope the suggestions help, there's no definite answer to this so I'm looking forward to see what other people do.