Data Analyst

How can you speed up solving problems if the alphabet consists only of lowercase Latin letters?

class SparseVector: def __init__(self, nums: list[int]): def dotProduct(self, vec: 'SparseVector') -> int:

Were the features purely based on time series? Did you try using other data sources, such as news or other cryptocurrencies?

Is the feature 'Bitcoin price yesterday' suitable for a random forest, and what problems might arise?

How to make a user-defined class suitable for use as a dictionary key?

Can logistic regression overfit, and how can it be addressed?

Tell us about your experience, about a project or task you are proud of.

How is the final prediction in boosting obtained from three iterations?

Does it make sense to train gradient boosting on linear models instead of trees?

Is it necessary to preprocess features before training logistic regression with L2 regularization, and why?

How is gradient boosting trained?

# input: list[str] = ["abba", "bbaa", "hello", "leohl", "llm"] # output: list[list[str]] = [["abba", "bbaa"], ["hello", "leohl"], ["llm"]]

What is a list comprehension?

What is a generator?

What is logistic regression and where does its loss function come from?

What is the complexity of your anagram grouping solution?

Tell me more about L1 and L2 regularization.

How were the model hyperparameters selected and how was the quality measured?

What data types can be used as dictionary keys in Python?

What horizon was the forecast made for?