Vishal Kapur
• Male
• New Delhi
• India

## Vishal Kapur's Discussions

### Time Series - Stock Prediction Many Stocks

Started Jun 14

Usually I see example where we  have taken the data for a particular stock say 'GE' one company and predicting the prices for GE. Now if i have data for let say for 20 companies for the time period.…Continue

### Creating Polynomial Features in ML using sklearn

Started this discussion. Last reply by Prateek Baranwal Feb 6.

I have 10 features and all of them are numeric.Does polynomial features only can be used on continuous variables and not on discrete variables?? Out of 10 features which I should pick for creating…Continue

### Passing Nan values to ML Algorithm

Started this discussion. Last reply by Prateek Baranwal Feb 6.

Suppose I have 10 independent variable, and I intentionally didn't remove the nan value from few of my independent variable and move it to numpy and then passed it to the ML algo. Will few of the…Continue

### Input to PCA

Started this discussion. Last reply by Prateek Baranwal Feb 6.

Suppose I have 20 independent vsariables and I am thinking to go for PCA, Do we need to do the scaling of all these 20 independent variable, or PCA will handle it... And I hope the output of PCA will…Continue

# Vishal Kapur's Page

## Latest Activity

Vishal Kapur's discussion was featured

### Time Series - Stock Prediction Many Stocks

Usually I see example where we  have taken the data for a particular stock say 'GE' one company and predicting the prices for GE. Now if i have data for let say for 20 companies for the time period. So what should be the approach. My model should have the capability to predict stock prices for any of the 20 companies.See More
Jun 14
Vishal Kapur's discussion was featured

### Creating Polynomial Features in ML using sklearn

I have 10 features and all of them are numeric.Does polynomial features only can be used on continuous variables and not on discrete variables?? Out of 10 features which I should pick for creating polynomial features??Choosing criteria..I should take independent features for creating polynomial features or I should take features which are highly correlated with the dependent Y variable??  See More
Dec 26, 2019
Vincent Granville liked Vishal Kapur's discussion Input to PCA
Oct 8, 2019
Vishal Kapur's discussion was featured

### Input to PCA

Suppose I have 20 independent vsariables and I am thinking to go for PCA, Do we need to do the scaling of all these 20 independent variable, or PCA will handle it... And I hope the output of PCA will be scaled features...See More
Oct 1, 2019
"But NAN values, can't be handled by neural networks, if suppose we have few missing value in one of the features, neural network give NAN as output."
Sep 19, 2019
Yassin Jomni replied to Vishal Kapur's discussion Input to PCA
"The result of the PCA won't be normalized. PCA is an orthogonal linear transformation between your initial data space and a new space that is spanned by the eigenvectors of the covariance/correlation matrix. The only thing you could say is…"
Sep 8, 2019
Yassin Jomni replied to Vishal Kapur's discussion Input to PCA
"It depends. You can compute the PCA on two ways: 1- By computing the eigenvalues and eigenvectors of the covariance matrix: In this case, you need to normalize your data (between 0-1) 2- By computing the eigenvalues and eigenvectors of the…"
Sep 8, 2019
T. Dickinson replied to Vishal Kapur's discussion Input to PCA
"Scaling the input variables is your job as the analyst. Do you want to center and spherize the data? if so, center the data by subtracting the mean vector from all data vectors and sweep out the standard deviations. The result will be a mean vector…"
Sep 3, 2019
Sep 1, 2019
"Thanks..  but just for knowledge, like any algo, such as SVM or linear regression will give error, if I pass nan value.. "
Aug 29, 2019
"NaN stands for "not a number". If it is a missing value instead, some algorithms such as decision trees handle them automatically. See also imputation methods (google the term) to estimate what the value could have been. Now if it is truly…"
Aug 29, 2019
Vishal Kapur's discussion was featured

### Passing Nan values to ML Algorithm

Suppose I have 10 independent variable, and I intentionally didn't remove the nan value from few of my independent variable and move it to numpy and then passed it to the ML algo. Will few of the algo give error. Can ML also such as (Decision tree, SVM etc) can handle nan value. If these ML algo doesn't give error, then how will these nan values will be treated/handled internally by the algo.See More
Aug 29, 2019
Vishal Kapur posted a discussion

### Passing Nan values to ML Algorithm

Suppose I have 10 independent variable, and I intentionally didn't remove the nan value from few of my independent variable and move it to numpy and then passed it to the ML algo. Will few of the algo give error. Can ML also such as (Decision tree, SVM etc) can handle nan value. If these ML algo doesn't give error, then how will these nan values will be treated/handled internally by the algo.See More
Aug 29, 2019
Vishal Kapur replied to Vishal Kapur's discussion Input to PCA
"Thanks, but I want to know, do we need to do the scaling of data before PCA, so that all independent variable lies betwee 0 & 1??"
Aug 28, 2019
Jeremy Ireland replied to Vishal Kapur's discussion Input to PCA
"PCA is one approach to it, however, what is your main goal? If you want to reduce variables and group them into indices, PCA is an adequate approach. If you intend on using all 20 IVs, some form of linear/log regression may be best. Is this survey…"
Aug 28, 2019
Vishal Kapur's discussion was featured

### Input to PCA

Suppose I have 20 independent vsariables and I am thinking to go for PCA, Do we need to do the scaling of all these 20 independent variable, or PCA will handle it... And I hope the output of PCA will be scaled features...See More
Aug 27, 2019

## Profile Information

Job Title:
Software Developer
Seniority:
Technical
Job Function:
Other
Industry:
Banking Technology
Interests:
Contributing, Networking, Finding a new position

## Comment Wall

Join Data Science Central