I am trying to apply t a SARIMAX model to predict monthly sales, but when I try to fit the model i have this warning:
Too few observations to estimate starting parameters for seasonal
ARMA, All parameters except for variances will be set to zeros.
Even when the dataset shows a clearly seasonality.
Seasonal_Decompose:
I've used a Stepwise search to find the best model orders but still having the warning and pretty bad RMSE compared to the test data.
stepwise_model = auto_arima(df_arima['sales_diff'],
start_p=1, start_q=1,
max_p=3, max_q=3, m=12,
start_P=0, seasonal=True,
d=1, D=1, trace=True,
error_action='ignore',
suppress_warnings=True,
stepwise=True)
PD, the original data is non-stationary so have to work with the differencing to make it stationary.
Any tip to work around that?
Related
I am new to time-series machine learning and have a, perhaps, trivial question.
I would like like to forecast the temperature for a particular region. I could train a model using the hourly data points from the first 6 days of the week and then evaluate its performance on the final day. Therefore the training set would have 144 data points (6*24) and the test set would have 24 data points (24*1). Likewise, I can train a new model for regions B-Z and evaluate each of their individual performances. My question is, can you train a SINGLE model for the predictions across multiple different regions? So the region label should be an input of course since that will effect the temperature evolution.
Can you train a single model that forecasts for multiple trajectories rather than just one? Also, what might be a good metric for evaluating its performance? I was going to use mean absolute error but maybe a correlation is better?
Yes you can train with multiple series of data from different region the question that you ask is an ultimate goal of deep learning by create a 1 model to do every things, predict every region correctly and so on. However, if you want to generalize your model that much you normally need a really huge model, I'm talking about 100M++ parameter and to train that data you also need tons of Data maybe couple TB or PB, so you also need a super powerful computer to train that thing something like GOOGLE data center. Coming to your next question, the metric, you may use just simple RMS error or mean absolute error will work fine.
Here is what you need to focus Training Data, there is no super model that take garbage and turn it in to gold, same thing here garbage in garbage out. You need a pretty good datasets that can represent whole environment of what u are trying to solve. For example, you want to create model to predict that if you hammer a glass will it break, so you have maybe 10 data for each type of glass and all of them break when u hammer it. so, you train the model and it just predict break every single time, then you try to predict with a bulletproof glass and it does not break, so your model is wrong. Therefore, you need a whole data of different type of glass then your model maybe predict it correctly. Then compare this to your 144 data points, I'm pretty sure it won't work for your case.
Therefore, I would say yes you can build that 1 model fits all but there is a huge price to pay.
Here's the situation I am worrying about.
Let me say I have a model trained with min-max scaled data. I want to test my model, so I also scaled the test dataset with my old scaler which was used in the training stage. However, my new test data's turned out to be the newer minimum, so the scaler returned negative value.
As far as I know, minimum and maximum aren't that stable value, especially in the volatile dataset such as cryptocurrency data. In this case, should I update my scaler? Or should I retrain my model?
I happen to disagree with #Sharan_Sundar. The point of scaling is to bring all of your features onto a single scale, not to rigorously ensure that they lie in the interval [0,1]. This can be very important, especially when considering regularization techniques the penalize large coefficients (whether they be linear regression coefficients or neural network weights). The combination of feature scaling and regularization help to ensure your model generalizes to unobserved data.
Scaling based on your "test" data is not a great idea because in practice, as you pointed out, you can easily observe new data points that don't lie within the bounds of your original observations. Your model needs to be robust to this.
In general, I would recommend considering different scaling routines. scikitlearn's MinMaxScaler is one, as is StandardScaler (subtract mean and divide by standard deviation). In the case where your target variable, cryptocurrency price can vary over multiple orders of magnitude, it might be worth using the logarithm function for scaling some of your variables. This is where data science becomes an art -- there's not necessarily a 'right' answer here.
(EDIT) - Also see: Do you apply min max scaling separately on training and test data?
Ideally you should scale first and then only split into test and train. But its not preferable to use minmax scaler with data which can have dynamically varying min and max values with significant variance in realtime scenario.
I have a dataframe which contains three more or less significant correlations between target column and other columns ( LinarRegressionModel.coef_ from sklearn shows 57, 97 and 79). And I don't know what exact model to choose: should I use only most correlated column for regression or use regression with all three predictors. Is there any way to compare models effectiveness? Sorry, I'm very new to data analysis, I couldn't google any tools for this task
Well first at all, you must know that when we are choosing the best model to apply to new data, we are going to choose the best model to fit out of sample data, which is the kind of samples that might are not present in the training process, after all, you want to predict new probabilities or cases. In your case, predict a new number.
So, how can we do this? Well, the best is to use metrics which can help us to choose which model is better for our dataset.
There are so many kinds of metrics for regression:
MAE: Mean absolute error is the mean of the absolute value of the errors. This is the easiest of the metrics to understand since it’s just the average error.
MSE: Mean squared error is the mean of the squared error. It’s more popular than a mean absolute error because the focus is geared more towards large errors.
RMSE: Root means the squared error is the square root of the mean squared error. This is one of the most popular of the evaluation metrics because root means the squared error is interpretable in the same units as the response vector or y units, making it easy to relate its information.
RAE: Relative absolute error, also known as the residual sum of a square, where y bar is a mean value of y, takes the total absolute error and normalizes it by dividing by the total absolute error of the simple predictor.
You can work with any of these, but I highly recommend to use MSE and RMSE.
I want to predict stock price.
Normally, people would feed the input as a sequence of stock prices.
Then they would feed the output as the same sequence but shifted to the left.
When testing, they would feed the output of the prediction into the next input timestep like this:
I have another idea, which is to fix the sequence length, for example 50 timesteps.
The input and output are exactly the same sequence.
When training, I replace last 3 elements of the input by zero to let the model know that I have no input for those timesteps.
When testing, I would feed the model a sequence of 50 elements. The last 3 are zeros. The predictions I care are the last 3 elements of the output.
Would this work or is there a flaw in this idea?
The main flaw of this idea is that it does not add anything to the model's learning, and it reduces its capacity, as you force your model to learn identity mapping for first 47 steps (50-3). Note, that providing 0 as inputs is equivalent of not providing input for an RNN, as zero input, after multiplying by a weight matrix is still zero, so the only source of information is bias and output from previous timestep - both are already there in the original formulation. Now second addon, where we have output for first 47 steps - there is nothing to be gained by learning the identity mapping, yet network will have to "pay the price" for it - it will need to use weights to encode this mapping in order not to be penalised.
So in short - yes, your idea will work, but it is nearly impossible to get better results this way as compared to the original approach (as you do not provide any new information, do not really modify learning dynamics, yet you limit capacity by requesting identity mapping to be learned per-step; especially that it is an extremely easy thing to learn, so gradient descent will discover this relation first, before even trying to "model the future").
Question: What is the most efficient way to get the delta of my weights in the most efficient way in a TensorFlow network?
Background: I've got the operators hooked up as follows (thanks to this SO question):
self.cost = `the rest of the network`
self.rmsprop = tf.train.RMSPropOptimizer(lr,rms_decay,0.0,rms_eps)
self.comp_grads = self.rmsprop.compute_gradients(self.cost)
self.grad_placeholder = [(tf.placeholder("float", shape=grad[1].get_shape(), name="grad_placeholder"), grad[1]) for grad in self.comp_grads]
self.apply_grads = self.rmsprop.apply_gradients(self.grad_placeholder)
Now, to feed in information, I run the following:
feed_dict = `training variables`
grad_vals = self.sess.run([grad[0] for grad in self.comp_grads], feed_dict=feed_dict)
feed_dict2 = `feed_dict plus gradient values added to self.grad_placeholder`
self.sess.run(self.apply_grads, feed_dict=feed_dict2)
The command of run(self.apply_grads) will update the network weights, but when I compute the differences in the starting and ending weights (run(self.w1)), those numbers are different than what is stored in grad_vals[0]. I figure this is because the RMSPropOptimizer does more to the raw gradients, but I'm not sure what, or where to find out what it does.
So back to the question: How do I get the delta on my weights in the most efficient way? Am I stuck running self.w1.eval(sess) multiple times to get the weights and calc the difference? Is there something that I'm missing with the tf.RMSPropOptimizer function.
Thanks!
RMSprop does not subtract the gradient from the parameters but use more complicated formula involving a combination of:
a momentum, if the corresponding parameter is not 0
a gradient step, rescaled non uniformly (on each coordinate) by the square root of the squared average of the gradient.
For more information you can refer to these slides or this recent paper.
The delta is first computed in memory by tensorflow in the slot variable 'momentum' and then the variable is updated (see the C++ operator).
Thus, you should be able to access it and construct a delta node with delta_w1 = self.rmsprop.get_slot(self.w1, 'momentum'). (I have not tried it yet.)
You can add the weights to the list of things to fetch each run call. Then you can compute the deltas outside of TensorFlow since you will have the iterates. This should be reasonably efficient, although it might incur an extra elementwise difference, but to avoid that you might have to hack around in the guts of the optimizer and find where it puts the update before it applies it and fetch that each step. Fetching the weights each call shouldn't do wasteful extra evaluations of part of the graph at least.
RMSProp does complicated scaling of the learning rate for each weight. Basically it divides the learning rate for a weight by a running average of the magnitudes of recent gradients of that weight.