You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
If you modify a complex piece of code, and your tests pass on the first try, you should immediately proceed to break the code in an obvious way and rerun the tests, to check that you're actually testing what you think you're testing.
The machine learning equivalent: shuffle the labels in your test dataset (so they don't match the test inputs anymore, while keeping the same class distribution) and rerun evaluation. If your accuracy is still as high as before, you have a problem
The best accuracy achievable without looking at the inputs (i.e. just by learning the label distribution) can be a pretty good initial baseline for a difficult problem.
I do the equivalent of this with plain old regression as part of my model diagnostics. I also compare them to a trivial classifier. Worth the effort...a predictive model for apnea later predicted 6/24 infants developing apnea who would otherwise have been sent home from the ED.
In one of my machine learning class assignments, I implemented Naive Bayes classifier and got 100% accuracy. I was shocked. Then realized I was only testing 1st example 1000 times. 
Smiles.... I was analysing a supermarket sales and handled all missing values yet i have nan on my dataset and 0 on the isnull().sum()
Sorry if this seems like a trivial question but could you please tell me the reason we might get a high accuracy even after changing the test inputs? Could it be because of a class imbalance problem?
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
