Data Engineering Intern

Stepwise solution of the problem:

1. Define a function named is_prime that takes an integer n as input.
2. Check if the input number n is less than or equal to 1. If it is, return False since 1 and all non-positive integers are not prime.
3. Use a loop that iterates from 2 to the square root of n. To optimize the loop, you can iterate up to the integer value of the square root of n (rounded down).
4. For each iteration, check if n is divisible by the current I value (i.e. if n % i == 0). If it is, return False, which means n is not prime.
5. If the loop completes without finding any divisors for n, return True, indicating that n is a prime number.

Ans:- Calculates the factorial of a given number

Answer: c) The characteristics or variables used for modeling

Answer: d) Isolation Forest

Answer: The number of leaves in a decision tree depends on the complexity of the data and the splitting criteria. However, in this case, with a maximum depth of 4, the decision tree will have 2^4 = 16 leaves, assuming that all possible splits are utilized to the maximum depth.

The predicted output (ŷ) can be calculated using the formula: ŷ = β₀ + β₁ * x₁ + β₂ * x₂

Substituting the values: ŷ = 2.5 + 1.8 * 5.2 + (-0.3) * 3.0
ŷ = 2.5 + 9.36 - 0.9
ŷ = 10.96

Answer: b) Stack

Answer: a) O(1)

Answer: b) O(log n)

Answer: b) Encapsulation

Answer: a) A template that defines the structure and behavior of objects

Answer: d) Instantiation

The correct answer is c) It ensures that the script's code inside the block is only executed when the script is run directly, not when it is imported as a module in another script.

Ans:- To transform raw data into a structured format

Ans:- Regression

Import Libraries: Import the necessary libraries, such as NumPy and scikit-learn, to use their functionalities for linear regression.

Prepare Data: Prepare your dataset with input features X and target variable y. Ensure that the data is in a suitable format for the chosen library.

Define Model: Choose whether you want to implement linear regression from scratch using NumPy or use scikit-learn's built-in Linear Regression model.

Fit the Model: For both approaches, fit the model to the data by calling the fit() method of the chosen model with the input features X and target variable y.

Get Coefficients: After fitting the model, you can access the coefficients (intercept and slope) of the fitted line. In NumPy, these coefficients are obtained through mathematical calculations, while in scikit-learn, you can retrieve them from the intercept_ and coef_ attributes of the fitted model.

Make Predictions: With the fitted model, you can use it to make predictions on new data or evaluate its performance on the training data.

Visualize Results: Optionally, you can visualize the data points and the fitted line to understand the quality of the linear regression model's fit.

Import Libraries: Import the necessary libraries, such as NumPy and scikit-learn, to use their functionalities for PCA and data manipulation.

Prepare Data: Load or create the dataset that you want to apply PCA to. Ensure that the data is organized with rows representing samples and columns representing features.

Standardize Data: If necessary, standardize the data by subtracting the mean and dividing by the standard deviation for each feature. Standardization is essential when features are on different scales to ensure a fair contribution of all features during PCA.

Compute Covariance Matrix: Calculate the covariance matrix of the standardized data. The covariance matrix represents the relationships between different features and serves as the basis for PCA.

Compute Eigenvectors and Eigenvalues: Find the eigenvectors and eigenvalues of the covariance matrix. Eigenvectors represent the principal components, and eigenvalues represent the variance explained by each principal component.

Select Principal Components: Decide on the number of principal components to retain. Usually, you choose the top 'k' principal components that explain most of the variance (e.g., 95% or 99%).

Project Data onto New Space: Project the original data onto the new space spanned by the selected principal components. This reduces the dimensionality of the data while preserving its important features.

Inverse Transform (Optional): If necessary, you can also perform an inverse transform to obtain the reconstructed data in the original feature space. This allows you to understand how the data looks after dimensionality reduction.

Analyze Results: Evaluate the results, check the variance explained by the selected principal components, and understand how the data is distributed in the reduced space.

Tip 1: Explain your projects clearly
Tip 2: Keep the interviewer involved in your explanations
Tip 3: Be confident and don't fake while explaining your skillset.

Tip 1 : Highlight your experience of collaborating in a team, emphasizing your ability to communicate effectively, listen to others' perspectives, and contribute to achieving team goals.
My Answer - I had worked in college fests with multiple teams. I had lead a team of 50 people being the sponsorship head of technical fest of IIT Mandi.

Tip 1 : Discuss a couple of your strengths that are relevant to the job, such as problem-solving or leadership. When discussing weaknesses, focus on areas where you have made improvements and demonstrate a willingness to learn and grow

Tip 1 : Share a work-related challenge, explain the steps you took to address it, and emphasize the positive outcome. Showcase your problem-solving skills and ability to remain composed in difficult situations.

Tip 1 : Start by providing a brief overview of your background, education, and work experience. Highlight your key skills and achievements relevant to the job you are interviewing for. Keep it concise and focus on your professional attributes.