Nitin Solanki

Explain implicit feedback

It is the feedback collected from users behavior. Users such as the time spent by them, the documents browsed by them, the type of documents browsed etc. are recorded in this type of feedback.

Data Science

Answered Nov 11, 2019 · 1.6K Views Read answer →

Explain with an example how to iterate a for loop over a matrix in R.

To iterate a loop over a matrix, we need to create a matrix first. Let us understand what a matrix is. A matrix is usually an array of numbers or a mathematical object defined in a rectangular shape. We can pass in different conditions to perform when we define a matrix. In our case, we need to define a matrix to…

Data Science

Answered Nov 10, 2019 · 1.5K Views Read answer →

A user wants to know in what way he can randomly select a number of rows without replacement from a dataframe in R.

Let us create a dataframe data = data.frame(matrix(rnorm(20), nrow=10)) Data Now to randomly select 3 rows, we can do the following data[sample(nrow(data), 3), ]

Data Science

Answered Nov 10, 2019 · 1.5K Views Read answer →

List all the tags present in Penn Treebank tagset

The following is the list of all the POS tags present in Penn TreeBank tagset

Data Science

Answered Nov 10, 2019 · 1.5K Views Read answer →

How can we create log files to track data merges?

To be able to make sure that this does not lead to any errors (e.g., inflated data sets due to non-unique identifiers), we can maintain a merge tracker like this. merge

Data Science

Answered Nov 9, 2019 · 1.5K Views Read answer →

How to train a multiple linear regression model to find the best combination of variables?

Automated model selection and model-averaging. Provides a wrapper for glm and other functions, automatically generating all possible models (under constraints set by the user) with the specified response and explanatory variables, and finding the best models in terms of some Information Criterion (AIC, AICc or BIC).…

Data Science

Answered Nov 9, 2019 · 1.5K Views Read answer →

You are given a data set on fraud detection. Classification model achieved accuracy of 95%.Is it good?

Accuracy of 96% is good. But we may have to check the following items: what was the dataset for the classification problem Is Sensitivity and Specificity are acceptable if there are only less negative cases, and all negative cases are not correctly classified, then it might be a problem In-Addition it is related to…

Data Science

Answered Nov 9, 2019 · 1.6K Views Read answer →

You are given a train data set with a lot of columns and rows. How do you reduce the dimension of this data?

A Data Dimension is a set of data attributes pertaining to something of interest to a business. We have following methods for reducing dimension of train data having lots of rows and columns: Principal Component Analysis (PCA) would help us here which can explain the maximum variance in the data set. We can also check…

Data Science

Answered Nov 9, 2019 · 1.6K Views Read answer →

How to export a file in R?

There are two types of files most commonly used in R. a)CSV File CSV or comma separated values are those files that contain data separated by commas. b) Excel File Excel files are those files that contain data separated by tabs. To export or to write a CSV file, we can use write.csv(df, file = "foo.csv") Here,…

Data Science

Answered Nov 9, 2019 · 1.7K Views Read answer →

Explain compound and statistical phrases

These phrases are used to index more than two tokens instead of single tokens. They collect pairs of words which are not stopword and based on frequency they use all pairs setting a threshold. In practice, both compound and single phrases are used where multiple tokens and single tokens are used.

Data Science

Answered Nov 9, 2019 · 1.5K Views Read answer →

What are the preprocessing steps required before implementing a retrieval?

Some of the preprocessing methods need to be implemented before initiating a query. Some of them are- a) Tokenizing-It converts the words in a document into tokens or simply chop off the words into pieces. b) Stopwords-They are common words including articles, determiners etc which are avoided for a better query. c)…

Data Science

Answered Nov 9, 2019 · 1.7K Views Read answer →

Explain linguistic and knowledge based approaches

In this approach, the algorithm retrieves information based on single word strings logically represented in a query. It is not so efficient compared to other approaches as it fails to capture the entire meaning of a query. In such case, much developed analysis is brought forward where roots and affixes are analyzed to…

Data Science

Answered Nov 9, 2019 · 1.6K Views Read answer →