Today's Interview QnAs

Company Name - Atos

Role - Data Scientist
_________________

Q1. Choose algorithm if your data has noise?

Ans. Algorithms like Probabilistic Random Forest and DBSCAN can work well when you've noise in data.


Q2. Is it fine if we don't do scaling before training model? Reason?

Ans. If the values of the features are closer to each other there are chances for the algorithm to get trained well and faster instead of the data set where the data points or features values have high differences with each other will take more time to understand the data and the accuracy will be lower.
So if the data in any conditions has data points far from each other, scaling is a technique to make them closer to each other or in simpler words, we can say that the scaling is used for making data points generalized so that the distance between them will be lower.


Q3. Tricks you use to faster your model training?

Ans. Reduce Calculations by normalization or standardization. Use high computational memory while training(like GPU instead of local memory).


Q4. What is SelectK best? how does it works?

Ans. The SelectKBest method selects the features according to the k highest score. By changing the 'score_func' parameter we can apply the method for both classification and regression data. Selecting best features is important process when we prepare a large dataset for training. The SelectKBest class just scores the features using a function (in this case f_classif but could be others) and then "removes all but the k highest scoring features".


Q5. How will you handle heavy data ?

Ans. 1. Allocate more memory 2. Work with smaller sample 3. Use a relational database like SQL 4. Use a big data platform such as Hadoop.

_______________

P.S.- If you wanna make your career into Data Science and become Interview ready, then join our "AI For ALL Data Science course". Get hands on practical learning experience, interview questions and answers PDF collection, capstone end-to-end projects and 1-1 Skype Course Support.

👉Course link in our Telegram Description section.

Happy Learning With CloudyML 💙

Today's Interview QnAs

Company Name - Larsen and Toubro

Role - Data Scientist

___________________


Q1. Ways to avoid overfitting

Ans. Some steps that we can take to avoid it:
1. Data augmentation
2. L1/L2 Regularization
3. Remove layers / number of units per layer
4. Cross-validation


Q2. Image classification algorithms

Ans. Image Classification algorithms are the algorithms which are used to classify labels for images using their characteristics. Example: Convolutional Neural Networks.


Q3. args will return?

Ans. The special syntax *args in function is used to pass a variable number of arguments to a function. It is used to pass a non-key worded, variable-length argument list. The syntax is to use the symbol * to take in a variable number of arguments; by convention, it is often used with the word args.


Q4. Difference between having and where clause in SQL.

Ans. WHERE Clause is used to filter the records from the table based on the specified condition. HAVING Clause is used to filter record from the groups based on the specified condition.


Q5. How do you handle categorical data?

Ans. One-Hot Encoding is the most common, correct way to deal with non-ordinal categorical data. It consists of creating an additional feature for each group of the categorical feature and mark each observation belonging (Value=1) or not (Value=0) to that group.


Q6. What Is Interpolation And Extrapolation?

Ans. Interpolation is the process of calculating the unknown value from known given values whereas extrapolation is the process of calculating unknown values beyond the given data points.


Q7. SQL joins and Groups

Ans. The SQL Joins clause is used to combine records from two or more tables in a database. The GROUP BY statement groups rows that have the same values into summary rows, like "find the number of customers in each country".


Q8. How do you handle null values and which Imputation method is more favorable?

Ans. Ways to handle missing values in the dataset:
*Deleting Rows with missing values.
*Impute missing values for continuous variable.
*Impute missing values for categorical variable.
*Other Imputation Methods.
*Using Algorithms that support missing values.
*Prediction of missing values.

Multiple imputation is more advantageous than the single imputation because it uses several complete data sets and provides both the within-imputation and between-imputation variability.

__________________

P.S.- if you wanna be a Data Scientist and Don't know where to start, join our Assignment based "AI For ALL-Data science course". You will get complete hands on practical learning experience with skype course support to resolve doubts everyday.

Capstone projects, interview QnAs PDF, assignment, tutorial videos, Quizzes, sample resumes and more

Check the course link in our Telegram Description.

Happy Learning With CloudyML 💙

Hello Data Science Enthusiast,

If you wanna switch your career in Data Science and want to Know The Biggest Hacks, JOIN US on 5th Dec, 2021.

Get Career Transition Secret that NOBODY will ever tell you !

Get an interactive session from Akash Raj who was a manual tester before becoming a Data Scientist. He is also the founder of CloduyML E-learning Platform which provides Data Science courses and career counselling at lowest price so everyone can learn. He will share his career hacks with you.

Topics gonna cover in this webinar:

1. How to grow on LinkedIn ?
2. How to optimize Naukri profile ?
3. How to get jobs in Start-up ?
4. How to ask for referrals ?
5. How to negotiate salary with HR ?

-----------------------------------------

Date : 5th Dec, 2021 (Sunday)

Timing : 07:00PM to 08:30PM (IST)

-----------------------------------------

Grab this wonderful life changing opportunity.

Register Here👉 https://bit.ly/Register-for-Free-Data-Science-Webinar

Thank You!

Today's Interview QnAs

Company Name - JPMorgan

Role - Data Scientist
__________________

Q1. Define Degree of Freedom with example.

Ans. Degrees of Freedom Definition Degrees of freedom (df) refers to the number of independent values (variable) in a data sample used to find the missing piece of information (fixed) without violating any constraints imposed in a dynamic system. Exp: degree of freedom for given sequence: x = 2, 8, 3, 6, 4, 2, 9, 5.
Given n=8
Therefore,
DF = n-1
DF = 8-1
DF = 7.


Q2. Explain the difference between Variance and R squared error.

Ans. Considering this aspect in regression analysis, the variance is the mean squared error that measures the squared and thus, the summed difference between the actual values and the values predicted through the formed regression equation. R-squared error is completely different in concept as compared to variance.


Q3. What is an example of a data set with a non-Gaussian distribution?

Ans. Any distribution of money or value will be non--Gaussian. For example: distributions of income; distributions of house prices; distributions of bets placed on a sporting event. These distributions cannot have negative values and will usually have extended right hand tails.

Q4. When is median better measure than the mean?

Ans. If your data contains outliers, then you would typically rather use the median because otherwise the value of the mean would be dominated by the outliers rather than the typical values. In conclusion, if you are considering the mean, check your data for outliers, if any then better choose median.


Q5. Correlation and what is its range?

Ans. “Correlation” on the other hand measures both the strength and direction of the linear relationship between two variables. It is scaled between the range, -1 and +1.


Q6. You have two dices to play with. You win Rs10 every time you roll a 5. If you play till you win and then stop, what is the expected winning money?

Ans. 1/6 = Probability of getting 5 on dice. It will be (1/6 + 5/6*1/6 + 5/6*5/6*1/6 +....)*10 = 1/6*1/(1-(5/6))*10 = 1*10. Expected money to win is 10Rs. As eventually, we're not stopping till win, so prize money is 10Rs.

Happy Learning With CloudyML 💙

Today's Interview QnAs

Company Name - Pwc

Role - Data Scientist
__________________

Q1. bias-variance trade-off?

Ans. The bias–variance tradeoff is the property of a model that the variance of the parameter estimated across samples can be reduced by increasing the bias in the estimated parameters.


Q2. equation to calculate the precision and recall rate.?

Ans. Precision = True positives/ (True positives + False positives) = TP/ (TP + FP).

Recall = TruePositives / (TruePositives + FalseNegatives) = TP / (TP + FN).


Q3. Normalisation and Standardization?

Ans. Normalization typically means rescales the values into a range of [0,1]. Standardization typically means rescales data to have a mean of 0 and a standard deviation of 1 (unit variance).


Q4. Difference between Point Estimates and Confidence Interval?

Ans. The two are closely related. In fact, the point estimate is located exactly in the middle of the confidence interval. However, confidence intervals provide much more information and are preferred when making inferences.


Q5. Statistical power of sensitivity ?

Ans. The statistical power of an A/B test refers to the test's sensitivity to certain magnitudes of effect sizes. More precisely, it is the probability of observing a statistically significant result at level alpha (α) if a true effect of a certain magnitude (MEI) is in fact present.



Q6. TF/IDF vectorization?

Ans. tf-idf vectorization gives a numerical representation of words entirely dependent on the nature and number of documents being considered. The same words will have different vector representations in another corpus.


Q7. Entropy and Information gain in Decision tree algorithm?

Ans. Entropy can be defined as a measure of the purity of the sub split. Entropy always lies between 0 to 1. The information gain is based on the decrease in entropy after a dataset is split on an attribute. Constructing a decision tree is all about finding attribute that returns the highest information gain (i.e., the most homogeneous branches).

Happy Learning With CloudyML 💙

Learn from Scratch and become a Job ready Data Scientist at just Rs 999/- Only.

Enroll Now👉http://bit.ly/Learn-Data-Science-from-zero

( Offer gonna end by 11:59PM, Today )

Today's Interview Quest N Ans

Company Name - IBM

Role - Data Scientist
_____________________

Q1. What is P-value?

Ans. The p-value is the probability that the null hypothesis is true. (1 – the p-value) is the probability that the alternative hypothesis is true. A low p-value shows that the results are replicable. A low p-value shows that the effect is large or that the result is of major theoretical, clinical or practical importance.


Q2. Forward and Backward selection? It's working?

Ans. Forward Selection chooses a subset of the predictor variables for the final model. Unlike forward stepwise selection, it begins with the full least squares model containing all p predictors, and then iteratively removes the least useful predictor, one-at-a-time. forward selection starts with a null model (with no predictors) and proceeds to add variables one at a time, and so unlike backward selection, it DOES NOT have to consider the full model (which includes all the predictors).


Q3. Fix multicollinearity?

Ans. To remove multicollinearities, we can do two things.
1. We can create new features
2. remove those features from our data.


Q4. Difference between Gradient boosting and random forest?

Ans. The two main differences are: How trees are built: random forests builds each tree independently while gradient boosting builds one tree at a time. Combining results: random forests combine results at the end of the process (by averaging or "majority rules") while gradient boosting combines results along the way.


Q5. Precision and Recall? How they are related to ROC curve?

Ans. The recall is the ratio of the relevant results returned by the search engine to the total number of the relevant results that could have been returned. The precision is the proportion of relevant results in the list of all returned search results. When dealing with highly skewed datasets, Precision-Recall (PR) curves give a more informative picture of an algorithm's performance. We show that a deep connection exists between ROC space and PR space, such that a curve dominates in ROC space if and only if it dominates in PR space.
____________________

P.S.- Want to turn interviews into offer? then join “AI for ALL” Data Science Course for complete Hands-on learning, Course Support, Capstone Projects and Interview questions answers.

👉Find the course link in our Telegram Description section

Happy Learning With CloudyML 💙

WE ARE HIRING

Role: Data Science Intern

It will be a Paid Internship.

Apply👉 https://forms.gle/pfuR2TZ8sCTyy7mB6

Finally the wait is over! The course you all were waiting for so long is here

We are Launching "Demystify Deep Learning" Course.

A complete Deep Learning Course in your favorite hands-on assignment mode which will contain:

1. Neural Network
2. Computer Vision
3. NLP
4. Time Series

With 15+ Real World Deep Learning projects and 1-1 Skype Doubt Clearance Support

You can get Early Bird Access with 50% extra discount on this course

This Offer will be valid till 3rd Dec.


To get complete course details, please check the link below

Course Link👉🏻 https://bit.ly/Demystify-Deep-Learning-Course


Happy Learning with CloudyML 💙

Today's Interview Quest N Ans

Company Name - Legato

Role - Data Scientist
____________________

Q1. Different activation function?

Ans. Binary Step Function, Linear Activation Function, Sigmoid/Logistic Activation Function, Tanh Function (Hyperbolic Tangent), ReLU Activation Function.


Q2. How do you handle imbalance data?

Ans. Follow these techniques:
Use the right evaluation metrics.
Use K-fold Cross-Validation in the right way.
Ensemble different resampled datasets.
Resample with different ratios.
Cluster the abundant class.
Design your own models.

Q3. Difference between sigmoid and softmax ?

Ans. The sigmoid function is used for the two-class logistic regression, whereas the softmax function is used for the multiclass logistic regression (a.k.a. MaxEnt, multinomial logistic regression, softmax Regression, Maximum Entropy Classifier).


Q4. Explain about optimizers?

Ans. Optimizers are algorithms or methods used to change the attributes of the neural network such as weights and learning rate to reduce the losses. Optimizers are used to solve optimization problems by minimizing the function.


Q5. Precision-Recall Trade off ?

Ans. The Idea behind the precision-recall trade-off is that when a person changes the threshold for determining if a class is positive or negative it will tilt the scales. It means that it will cause precision to increase and recall to decrease, or vice versa.


Q6. Decision Tree Parameters?

Ans. These are the parameters used for building Decision Tree: min_samples_split, min_samples_leaf, max_features and criterion.


Q7. Bagging and boosting ?

Ans. Bagging is a way to decrease the variance in the prediction by generating additional data for training from dataset using combinations with repetitions to produce multi-sets of the original data. Boosting is an iterative technique which adjusts the weight of an observation based on the last classification.
______________________

P.S. : If you wanna learn Data Science from scratch and become a interview ready Data Scientist, join our course.

It has Hands on guided Assignments, 1-1 Skype doubts clearance, capstone project, interview QnAs PDF collection, certification, sample resumes and more

👉🏻Course link is in our Telegram Description

Happy Learning With CloudyML 💙

If you wanna get more valuable and highly paid job opportunities in Data Science then you should learn Deep Learning too.

It is highly on-demand skill in Data Science field and key-technology of future.

Only prerequisite is Basic Knowledge of Python and that's it.

We have covered everything from basics in our "Demystify Deep Learning" course and created this course with so much effort and planning so you can enjoy this journey and become more skilled Data Scientist.

It covers complete concepts of

• Neural Network
• Computer Vision
• NLP
• Time Series

with 15+ real world industrial Deep Learning projects that you can add in your resume and 1-1 Skype Doubt Clearance Support

So step up and grab this opportunity because you can get all the content at just Rs. 2499/- only instead of Rs. 4999/- .


And Today by 11:59PM, this offer gonna end and from tomorrow price will become Rs. 4999/-

Hurry Up, it's NOW or NEVER !

Enroll Now👉🏻https://bit.ly/Demystify-Deep-Learning-Course