The goal is to create a computer-generated news site that aggregates headlines from different news sources around the world:
Taking a look at the centroid table results I want to Understand the following:
https://ibb.co/n1mvnbk
I used K=5
and I am using TF-IDF
Explain what those numbers mean?
When an attribute is zero in multiple clusters, what does it mean?
When I sort the centroid table by each cluster at a descending order, I find some words or attributes that have a higher value with this cluster while zero values in other clusters. Does this mean that these words occur more or less frequently in this cluster?
How can I discuss the clustering model
Do all the clusters make sense and why?
Do you think k=5 is a good choice for this dataset? or I need to choose 3? How can I classify that?
I believe K=5 denotes number of cluster you are looking into current Dataset. On the basis 5 centroid will be placed in data will be around them.
Do you think k=5 is a good choice for this dataset? Its hard to predict this way. It is all done by mathematical combination and permutation.
You might use Elbow Method to identify correct number of cluster needed for any given dataset. This methodology is based on WCSS(Within Cluster Sums of Squares) which find distance between points and provide centroid points.
Those numbers are the average tf-idf of the cluster. So a 0 means that the word is not in the cluster, and the highest valued words are most characteristic words for the cluster.
Note that for text you'll want to use spherical k-means rather than regular k-means.
Choosing k is a big problem. Forget the elbow method, it never works except for you examples. Experiment with different k and choose the one that is most convincing or most useful. None of the usual heuristics for choosing the k in k-means will work here I fear (VRC is IMHO the best). The main reason is that the data cannot be well partitioned into k clusters. There is no reason to assume there are exactly k topics in the world, nor that every document only contains one topic. Instead, topics will be a complex structure itself. For example there is Trump, but there also is the Trump Erdogan meeting, and there is the impeachment. These are not disjoint. But you will also have articles that don't fit into any of these topics. This leads to the effect that the true best k would likely be very very large, as large as the number of articles (and hence not useful).
Related
Consider a search system where the user submits a query ‘query’ and retrieves products based on some ranking algorithm. Assume that these products are ordered according to their quality such that p_0, p_1, …, p_10 and so on.
I would like to generate vector embeddings that mimic this ranking algorithm. The closest product vector to a query vector should ideally be p_0, the next one should be p_1 and so on.
I have tried to building word2vec embeddings for products by feeding products that have appeared in the same search session as sentences. Then, I have calculated the weighted average of product vectors to find query vectors to make the query vector closer to the top result. Although the closest result is usually the best result for a given query, the subsequent results include some results that would never appear as a top result.
Is there a trick that the word2vec can learn the ranking algorithm or any other techniques that I can try? I have looked into multi-dimensional vector scaling with non-metric distances but it did not seem scalable to me for more than 100Ks of products.
There's no one trick – just iteratively improving your representations, & training set, & ranking methods to better meet your goals.
Word2vec-based representations can often help, but are still fairly simple & centered on individual words – whose senses may vary based on context & position in ways that a simple weighted-average-of-tokens fails to capture.
You may want to represent 'products' by more than just a string-of-word-tokens – to include other properties, as well. These could be scalar values like prices or various other kinds of ratings/properties, or extra synthetic labels, such as the result of other salient groupings (whether hand-edited or learned).
And even if just working with natural-language product descriptions – like product names, or descriptions, or reviews – there are other more-sophisticated text-representations that can be trained or used – such as sentence/document embeddings using deeper-networks than plain word2vec.
Most generically, if you have a bunch of quantitative representations of candidate results, and a query, and want to use some initial examples of "good" results to bootstrap more generalizable rules for scoring top results, you are attempting a "learning-to-rank" process:
https://en.wikipedia.org/wiki/Learning_to_rank
To suggest more specific steps would require a more specific description of inputs/outputs/goals, & what's been tried, and how what's been tried has failed.
For example, are your queries always just textual product names? In such a case, maybe plain keyword search is the central technology required – with things like word-vector-modelling just a tweak for handling some tough cases, like expanding the results, or adding more contrast to the rankings, when results are too few or to many.
Or, can you detect key gaps in the modeling related to exactly those cases where "results include some results that would [ideally] never appear as a top result"? If certain things like rare (poorly-modeled) words, or important qualities not yet captured in the model, seem to be to blame for such cases, that will guide the potential set of corrective changes.
In weka I have seen the F-measure of the 'yes' class and 'no' class seperately. But what is the advantage of using the weighted average F-measure to compare the performance of the models. Please help me to find the answer :)
Let's start with a smart example, classifying protein interactions in text using machine learning, where our classifier has attempted to classify sentences into two classes: (1) positive class (2) negative class. Positive class contains sentences that describe protein interactions and negative class comprises sentences that do not describe protein interactions. As a researcher, my focus will be the F-score of my classifiers for positive class. Why? Because I am interested to see my classifier's performance on classifying sentences that contain protein interactions and I do not care about its ability to classify negative sentences. Therefore, I will consider only the F-score of the positive class.
However, for another classical problem like spam classification, where our classifier classifies emails into two classes: (1) hams and (2) spams, the scenario is a bit different. As a researcher, I would like to know my classifier's ability to classify hams as well as spams. At that point, I can either check the F-scores of each class independently or in an aggregated fashion. The weighted average of F-scores of ham and spam class is a means to check the performance of our classifier for both (in this case both, for multi-class problems read all) classes. Because the weighted F-measure is just the sum of all F-measures, each weighted according to the number of instances with that particular class label and for two classes, it is calculated as follows:
Weighted F-Measure=((F-Measure for n class X number of instances from n class)+(F-Measure for y class X number of instances from y class))/total instances in dataset.
So, the bottom line is- if the classification is sensitive for all the classes, use the weighted average of F-scores of all classes.
As far as I remember, It can better handle "extreme" precision or recall (P, R) numbers, when one or both are close to either 0 or 1. (They are generally negatively correlated).
This might happen when you want to apply different algorithms on a dataset and you end up with some precision/recall numbers that you need to compare.
Turns out that the simple average (P+R)/2 is too simplistic.
If you have a dataset where either precision or recall are close to 1 or zero, F-measure still takes the other one into account, somewhat arbitrarily.
(The name itself does not mean anything).
Andrew Ng explains it well in his machine-learning course, week 6 "Handling skewed data"
I am working user behavior project. Based on user interaction I have got some data. There is nice sequence which smoothly increases and decreases over the time. But there are little discrepancies, which are very bad. Please refer to graph below:
You can also find data here:
2.0789 2.09604 2.11472 2.13414 2.15609 2.17776 2.2021 2.22722 2.25019 2.27304 2.29724 2.31991 2.34285 2.36569 2.38682 2.40634 2.42068 2.43947 2.45099 2.46564 2.48385 2.49747 2.49031 2.51458 2.5149 2.52632 2.54689 2.56077 2.57821 2.57877 2.59104 2.57625 2.55987 2.5694 2.56244 2.56599 2.54696 2.52479 2.50345 2.48306 2.50934 2.4512 2.43586 2.40664 2.38721 2.3816 2.36415 2.33408 2.31225 2.28801 2.26583 2.24054 2.2135 2.19678 2.16366 2.13945 2.11102 2.08389 2.05533 2.02899 2.00373 1.9752 1.94862 1.91982 1.89125 1.86307 1.83539 1.80641 1.77946 1.75333 1.72765 1.70417 1.68106 1.65971 1.64032 1.62386 1.6034 1.5829 1.56022 1.54167 1.53141 1.52329 1.51128 1.52125 1.51127 1.50753 1.51494 1.51777 1.55563 1.56948 1.57866 1.60095 1.61939 1.64399 1.67643 1.70784 1.74259 1.7815 1.81939 1.84942 1.87731
1.89895 1.91676 1.92987
I would want to smooth out this sequence. The technique should be able to eliminate numbers with characteristic of X and Y, i.e. error in mono-increasing or mono-decreasing.
If not eliminate, technique should be able to shift them so that series is not affected by errors.
What I have tried and failed:
I tried to test difference between values. In some special cases it works, but for sequence as presented in this the distance between numbers is not such that I can cut out errors
I tried applying a counter, which is some X, then only change is accepted otherwise point is mapped to previous point only. Here I have great trouble deciding on value of X, because this is based on user-interaction, I am not really controller of it. If user interaction is such that its plot would be a zigzag pattern, I am ending up with 'no user movement data detected at all' situation.
Please share the techniques that you are aware of.
PS: Data made available in this example is a particular case. There is no typical pattern in which numbers are going to occure, but we expect some range to be continuous with all the examples. Solution I am seeking is generic.
I do not know how much effort you want to involve in this problem but if you want theoretical guaranties,
topological persistence seems well adapted to your problem imho.
Basically with that method, you can filtrate local maximum/minimum by fixing a scale
and there are theoritical proofs that says that if you sampling is
close from your function, then you extracts correct number of maximums with persistence.
You can see these slides (mainly pages 7-9 to get the idea) to get an idea of the method.
Basically, if you take your points as a landscape and imagine a watershed starting from maximum height and decreasing, you have some picks.
Every pick has a time where it is born which is the time where it becomes emerged and a time where it dies which is when it merges with an higher pick. Now a persistence diagram pictures a point for every pick where its x/y coordinates are its time of birth/death (by assumption the first pick does not die and is not shown).
If a pick is a global maximal, then it will be further from the diagonal in the persistence diagram than a local maximum pick. To remove local maximums you have to remove picks close to the diagonal. There are fours local maximums in your example as you can see with the persistence diagram of your data (thanks for providing the data btw) and two global ones (the first pick is not pictured in a persistence diagram):
If you noise your data like that :
You will still get a very decent persistence diagram that will allow you to filter local maximum as you want :
Please ask if you want more details or references.
Since you can not decide on a cut off frequency, and not even on the filter you want to use, I would implement several, and let the user set the parameters.
The first thing that I thought of is running average, and you can see that there are so many things to set, to get different outputs.
I am trying to come up with an algorithm to find top-3 most frequently used adjectives for the product in the same sentence. I want to use association rule mining(Apriori algorithm).
For that I am planning of using the twitter data. I can more or less decompose twits in to sentences and then with filtering I can find product names and adjectives with it.
For instance, after filtering I have data like;
ipad mini, great
ipad mini, horrible
samsung galaxy s2, best
...
etc.
Product names and adjectives are previously defined. So I have a set of product names and set of adjectives that I am looking for.
I have read couple of papers about sentimental analysis and rule mining and they all say Apriori algorithm is used. But they don't say how they used it and they don't give details.
Therefore how can I reduce my problem to association rule mining problem?
What values should I use for minsup and minconf?
How can I modify Apriori algorithm to solve this problem?
What I' m thinking is;
I should find frequent adjectives separately for each product. Then by sorting I can get top-3 adjectives. But I do not know if it is correct.
Finding the top-3 most used adjectives for each product is not association rule mining.
For Apriori to yield good results, you must be interested in itemsets of length 4 and more. Apriori pruning starts at length 3, and begins to yield major gains at length 4. At length 2, it is mostly enumerating all pairs. And if you are only interested in pairs (product, adjective), then apriori is doing much more work than necessary.
Instead, use counting. Use hash tables. If you really have Exabytes of data, use approximate counting and heavy hitter algorithms. (But most likely, you don't have exabytes of data after extracting those pairs...)
Don't bother to investigate association rule mining if you only need to solve this much simpler problem.
Association rule mining is really only for finding patterns such as
pasta, tomato, onion -> basil
and more complex rules. The contribution of Apriori is to reduce the number of candidates when going from length n-1 -> n for length n > 2. And it gets more effective when n > 3.
Reducing your problem to Association Rule Mining (ARM)
Create a feature vector having all the topics and adjectives. If a feed contains topic then place 1 for it else 0 in tuple. For eg. Let us assume Topics are Samsung and Apple. And Adjectives are good and horrible. And feed contains Samsung good. Then corresponding tuple for it is :
Samsung Apple good horrible
1 0 1 0
Modification to Apriori Algorithm required
generate Association Rules of type 'topic' --> 'adjective' using constrained apriori algorithm. 'topic' --> 'adjective' is a constraint.
How to set MinSup and MinConf :
Read a paper entitled "Minin top-k association rules". Implement that with k=3 for 3 top adjectives.
I'm very new in image processing and my first assignment is to make a working program which can recognize faces and their names.
Until now, I successfully make a project to detect, crop the detected image, make it to sobel and translate it to array of float.
But, I'm very confused how to implement the Backpropagation MLP to learn the image so it can recognize the correct name for the detected face.
It's a great honor for all experts in stackoverflow to give me some examples how to implement the Image array to be learned with the backpropagation.
It is standard machine learning algorithm. You have a number of arrays of floats (instances in ML or observations in statistics terms) and corresponding names (labels, class tags), one per array. This is enough for use in most ML algorithms. Specifically in ANN, elements of your array (i.e. features) are inputs of the network and labels (names) are its outputs.
If you are looking for theoretical description of backpropagation, take a look at Stanford's ml-class lectures (ANN section). If you need ready implementation, read this question.
You haven't specified what are elements of your arrays. If you use just pixels of original image, this should work, but not very well. If you need production level system (though still with the use of ANN), try to extract more high level features (e.g. Haar-like features, that OpenCV uses itself).
Have you tried writing your feature vectors to an arff file and to feed them to weka, just to see if your approach might work at all?
Weka has a lot of classifiers integrated, including MLP.
As I understood so far, I suspect the features and the classifier you have chosen not to work.
To your original question: Have you made any attempts to implement a neural network on your own? If so, where you got stuck? Note, that this is not the place to request a complete working implementation from the audience.
To provide a general answer on a general question:
Usually you have nodes in an MLP. Specifically input nodes, output nodes, and hidden nodes. These nodes are strictly organized in layers. The input layer at the bottom, the output layer on the top, hidden layers in between. The nodes are connected in a simple feed-forward fashion (output connections are allowed to the next higher layer only).
Then you go and connect each of your float to a single input node and feed the feature vectors to your network. For your backpropagation you need to supply an error signal that you specify for the output nodes. So if you have n names to distinguish, you may use n output nodes (i.e. one for each name). Make them for example return 1 in case of a match and 0 else. You could very well use one output node and let it return n different values for the names. Probably it would even be best to use n completely different perceptrons, i.e. one for each name, to avoid some side-effects (catastrophic interference).
Note, that the output of each node is a number, not a name. Therefore you need to use some sort of thresholds, to get a number-name relation.
Also note, that you need a lot of training data to train a large network (i.e. to obey the curse of dimensionality). It would be interesting to know the size of your float array.
Indeed, for a complex decision you may need a larger number of hidden nodes or even hidden layers.
Further note, that you may need to do a lot of evaluation (i.e. cross validation) to find the optimal configuration (number of layers, number of nodes per layer), or to find even any working configuration.
Good luck, any way!