When I use the Percentage split option in Weka I get good results:
Correctly Classified Instances 286 |86.1446 %
What I expect it to do, and what I read in the docs, is to split the data into training and testing based on the percentage I define. The problem is now, if I split it with a filter->RemovePercentage and train it with the exact same amount of training and testing data I get these result for the testing data:
Correctly Classified Instances 183 | 55.1205 %
The test set is for both exactly 332 instances. Why are these results not about the same?
I expect it to be the same as I do the same thing.
As explained by fracpete the percentage split randomizes the sample by default, this has caused this large gap. You can turn it off under "more options".
Related
For a project I am working on, which uses annual financial reports data (of multiple categories) from companies which have been successful or gone bust/into liquidation, I previously created a (fairly well performing) model on AWS Sagemaker using a multiple linear regression algorithm (specifically, the AWS stock algorithm for logistic regression/classification problems - the 'Linear Learner' algorithm)
This model just produces a simple "company is in good health" or "company looks like it will go bust" binary prediction, based on one set of annual data fed in; e.g.
query input: {data:[{
"Gross Revenue": -4000,
"Balance Sheet": 10000,
"Creditors": 4000,
"Debts": 1000000
}]}
inference output: "in good health" / "in bad health"
I trained this model by just ignoring what year for each company the values were from and pilling in all of the annual financial reports data (i.e. one years financial data for one company = one input line) for the training, along with the label of "good" or "bad" - a good company was one which has existed for a while, but hasn't gone bust, a bad company is one which was found to have eventually gone bust; e.g.:
label
Gross Revenue
Balance Sheet
Creditors
Debts
good
10000
20000
0
0
bad
0
5
100
10000
bad
20000
0
4
100000000
I hence used these multiple features (gross revenue, balance sheet...) along with the label (good/bad) in my training input, to create my first model.
I would like to use the same features as before as input (gross revenue, balance sheet..) but over multiple years; e.g take the values from 2020 & 2019 and use these (along with the eventual company status of "good" or "bad") as the singular input for my new model. However I'm unsure of the following:
is this an inappropriate use of logistic regression Machine learning? i.e. is there a more suitable algorithm I should consider?
is it fine, or terribly wrong to try and just use the same technique as before, but combine the data for both years into one input line like:
label
Gross Revenue(2019)
Balance Sheet(2019)
Creditors(2019)
Debts(2019)
Gross Revenue(2020)
Balance Sheet(2020)
Creditors(2020)
Debts(2020)
good
10000
20000
0
0
30000
10000
40
500
bad
100
50
200
50000
100
5
100
10000
bad
5000
0
2000
800000
2000
0
4
100000000
I would personally expect that a company which has gotten worse over time (i.e. companies finances are worse in 2020 than in 2019) should be more likely to be found to be a "bad"/likely to go bust, so I would hope that, if I feed in data like in the above example (i.e. earlier years data comes before later years data, on an input line) my training job ends up creating a model which gives greater weighting to the earlier years data, when making predictions
Any advice or tips would be greatly appreciated - I'm pretty new to machine learning and would like to learn more
UPDATE:
Using Long-Short-Term-Memory Recurrent Neural Networks (LSTM RNN) is one potential route I think I could try taking, but this seems to commonly just be used with multivariate data over many dates; my data only has 2 or 3 dates worth of multivariate data, per company. I would want to try using the data I have for all the companies, over the few dates worth of data there are, in training
I once developed a so called Genetic Time Series in R. I used a Genetic Algorithm which sorted out the best solutions from multivariate data, which were fitted on a VAR in differences or a VECM. Your data seems more macro economic or financial than user-centric and VAR or VECM seems appropriate. (Surely it is possible to treat time-series data in the same way so that we can use LSTM or other approaches, but these are very common) However, I do not know if VAR in differences or VECM works with binary classified labels. Perhaps if you would calculate a metric outcome, which you later label encode to a categorical feature (or label it first to a categorical) than VAR or VECM may also be appropriate.
However you may add all yearly data points to one data points per firm to forecast its survival, but you would loose a lot of insight. If you are interested in time series ML which works a little bit different than for neural networks or elastic net (which could also be used with time series) let me know. And we can work something out. Or I'll paste you some sources.
Summary:
1.)
It is possible to use LSTM, elastic NEt (time points may be dummies or treated as cross sectional panel) or you use VAR in differences and VECM with a slightly different out come variable
2.)
It is possible but you will loose information over time.
All the best,
Patrick
I have moderate experience with data science. I have a data set with 9500 observations and more than 4500 features most of which are highly correlated. Here is briefly what I have tried: I have dropped columns where there are less than 6000 non-NAs and have imputed NAs with their corresponding columns' median values when there are at least 6000 non-NAs. As for correlation, I have kept only features having at most 0.7 correlation with others. By doing so, I have reduced the number of features to about 750. Then I have used those features in my binary classification task in random forest.
My data set is highly unbalanced where ratio of (0:1) is (10:1). So when I apply RF with 10-fold cv, I observe too good results in each cv (AUC of 99%) which is to good to be true and in my test set I got way worse results such as 0.7. Here is my code:
import h2o
from h2o.estimators import H2ORandomForestEstimator
h2o.init(port=23, nthreads=4)
train = fs_rf[fs_rf['Year'] <= '201705']
test = fs_rf[fs_rf['Year'] > '201705']
train = train.drop('Year',axis=1)
test = test.drop('Year',axis=1)
test.head()
train = h2o.H2OFrame(train)
train['BestWorst2'] = train['BestWorst2'].asfactor()
test = h2o.H2OFrame(test)
test['BestWorst2'] = test['BestWorst2'].asfactor()
training_columns = train.drop('BestWorst2',axis=1).col_names
response_column = 'BestWorst2'
model = H2ORandomForestEstimator(ntrees=100, max_depth=20, nfolds=10, balance_classes=True)
model.train(x=training_columns, y=response_column, training_frame=train)
performance = model.model_performance(test_data=test)
print(performance)
How could I avoid this over-fitting? I have tried many different parameters in grid search but none of them improved the results.
This is not what I would call "overfitting". The reason you are seeing really good cross-validation metrics compared to your test metrics is that you have time-series data and so you can't use k-fold cross-validation to give you an accurate estimate of performance.
Performing k-fold cross-validation on a time-series dataset will give you overly-optimistic performance metrics because you are not respecting the time-series component in your data. Regular k-fold cross-validation will randomly sample from your whole dataset to create a train & validation set. Essentially, your validation strategy is "cheating" because you have "future" data included in your CV training sets (if that makes any sense).
I can see by your code that you understand that you need to train with "past" data and predict on "future" data, but if you want to read more about this topic, I'd recommend this article or this article.
One solution is to simply look at test set performance as way to evaluate your model. Another option is to use what's called "rolling" or "time-series" cross-validation, but H2O does not currently support that (though it seems like it might be added soon). Here's a ticket for this if you want to keep track of the progress.
I tried to run a simple classification on the iris.arff dataset in Weka, using the J48 algorithm. I used cross-validation with 10 folds and - if I'm not wrong - all the default settings for J48.
The result is a 96% accuracy with 6 incorrectly classified instances.
Here's my question: according to this the second number in the tree visualization is the number of the wrongly classified instances in each leaf, but then why their sum isn't 6 but 3?
EDIT: running the algorithm with different test options I obtain different results in terms of accuracy (and therefore number of errors), but when I visualize the tree I get always the same tree with the same 3 errors. I still can't explain why.
The second number in the tree visualization is not the number of the wrongly classified instances in each leaf - it's the total weight of those wrongly classified instances.
Did you, by any chance, weigh some of those instances with 0.5 instead of 1?
Another option is that you are actually executing two different models. One where you use the full training set to build the classifier (classifier.buildClassifier(instances)) and another one where you run Cross-validation (eval.crossValidateModel(...)) with 10 train/test folds. The first model will produce the visualised tree with less errors (larger trainingset) while the second model from CV produces the output statistics with more errors. This would explain why you get different stats when changing the test set but still the same tree that is built on the full set.
For the record: if you train (and visualise) the tree with the full dataset, you will appear to have less errors, but your model will actually be overfitted and the obtained performance measures will probably not be realistic. As such, your results from CV are much more useful and you should visualise the tree from that model.
I just wondered why is the % correctly classified differs from the Explorer and Experimenter aspects of Weka. I have checked to ensure I am employing 10-cross fold validation as well as all other paramaters!
Anyone have any ideas?
Thanks
I have the solution, as provided by Mark Hall, as I emailed him on the Weka Mail list. Here is the difference between Explorer and Experimenter:
The Experimenter operates differently from the Explorer. The Explorer
sums evaluation metrics over the folds of the cross validation - e.g.
percent correct is computed by summing all the correctly classified
instances over the test folds and then dividing by the total number of
instances. The Experimenter, on the other hand, computes averages over
the folds. Furthermore, the default in the Experimenter is to run 10
repetitions of 10-fold cross-validation (so 100 folds are averaged over).
Not sure but random seed might be different on Explorer and Experimenter. If this is the case, data sets will differ which results to different percentage.
I recently started using weka and I'm trying to classify tweets into positive or negative using Naive Bayes. So I have a training set with tweets that I gave the label for and a test set with tweets that all have the label "positive". When I ran Naive Bayes, I get the following results:
Correctly classified instances: 69 92%
Incorrectly classified instances: 6 8%
Then if I change the labels of the tweets in the test set to "negative" and ran again Naive Bayes, the results are inversed:
Correctly classified instances: 6 8%
Incorrectly classified instances: 69 92%
I thought that correctly classified instances show the accuracy of Naive Bayes and that it should be the same no matter the labels of the tweets in test set. Is there something wrong with my data or I don't understand correctly the meaning of correctly classified instances?
Thanks a lot for your time,
Nantia
The labels on the test set are supposed to be the actual correct classification. Performance is computed by asking the classifier to give its best guess about the classification for each instance in the test set. Then the predicted classifications are compared to the actual classifications to determine accuracy. Therefore, if you flip the 'correct' values that you give it, the results will be flipped as well.
Based on your training set, 69.92% of your instances are classified as positive. If the labels for the test set, that is the correct answers, indicate that they are all positive, then that makes 69.92% correct. If the test set (and thus the classification) is the same, but you switch the correct answers, then of course, the percentage correct will also be the opposite.
Keep in mind that in order to evaluate a classifier, you need the true labels of the test set. Otherwise you can't compare the classifier's answers with the true answers. It seems to me that you might have misunderstood this. You can obtain the labels for unseen data, if that is what you want, but in that case you can't evaluate classifier accuracy.