Back to the page

In the print window, choose “Save as PDF”.

doubtly doubtly.in

DAV Question Paper solution Dec 2023

Semester 6 AI-DS QP Solutions · Updated 30 May 2024 · Read online: www.doubtly.in/dav-question-paper-solution-dec-2023/

DAV Question Paper solution Dec 2023

download as an pdf :

https://drive.google.com/file/d/1ii57ewWx1IrbSarEgfZ9M6cWz7-md59p/view?usp=sharing

Q1. Attempt the following (any 4): (20) DAV Question Paper solution Dec 2023

a. Why is data analytics lifecycle essential?

https://www.rudderstack.com/learn/data-analytics/data-analytics-lifecycle

b. The regression lines of a sample are x +6y=6 and 3x+2y=10
Find (i) sample means x and y
(ii) coefficient of correlation between x and y

Please add an Answer or view existing answer for this question : /q/regression-lines-sample-6y6-3x2y10/

c. Differentiate between linear regression and logistic regression.

FeatureLinear RegressionLogistic Regression
Type of PredictionPredicts continuous numerical outcomes.Predicts categorical outcomes (binary or multi-class)
Output RangeUnbounded (can be any real number).Bounded between 0 and 1 (probability).
Nature of OutputDependent variable is continuous.Dependent variable is categorical.
Equation TypeLinear equation.Logistic (Sigmoid) function.
Example UsagePredicting house prices, stock prices.Predicting whether an email is spam or not.
Error MeasurementTypically uses Mean Squared Error (MSE) or similar.Typically uses Log Loss or Cross-Entropy Loss.
Assumption about ErrorsAssumes errors are normally distributed.Assumes errors follow a Bernoulli distribution.
Model InterpretabilityEasily interpretable, coefficients indicate impact.Less interpretable, coefficients represent log odds.
ComplexityLess complex.More complex due to non-linear transformation.
Overfitting ConcernsMore prone to overfitting.Less prone to overfitting due to regularization.
Handling OutliersSensitive to outliers, can significantly affect model.Less sensitive to outliers due to logistic function.
ApplicationsPrediction of quantities (sales, temperature).Classification tasks (spam detection, churn prediction).

d. What is Pandas? State and explain key features of Pandas.

Pandas is a powerful open-source data manipulation and analysis library for Python. It provides easy-to-use data structures and data analysis tools, making it a fundamental tool for data analytics and manipulation in Python. Here are some key features of Pandas:

  1. DataFrame: Pandas introduces the DataFrame, a two-dimensional labeled data structure with columns of potentially different types. It is similar to a spreadsheet or SQL table, where data can be easily manipulated and analyzed. DataFrames allow for easy indexing, slicing, and reshaping of data.
  2. Series: Pandas also offers a Series data structure, which is a one-dimensional labeled array capable of holding any data type. Series are the building blocks of DataFrames, representing columns or rows of data.
  3. Data Manipulation: Pandas provides a wide range of functions and methods for data manipulation, including merging, joining, grouping, sorting, filtering, and aggregating data. These operations enable users to clean, transform, and preprocess data efficiently.
  4. Missing Data Handling: Pandas offers robust support for handling missing or null values in datasets. It provides methods for detecting, removing, and filling missing data, allowing for cleaner and more accurate analysis.
  5. IO Tools: Pandas supports reading and writing data from various file formats, including CSV, Excel, SQL databases, JSON, HTML, and more. This makes it easy to import data from external sources and export results to different formats.
  6. Data Alignment and Arithmetic Operations: Pandas aligns data based on index labels, enabling easy arithmetic operations between DataFrames and Series. This feature simplifies calculations and data manipulation, especially when working with datasets of different shapes.
  7. Time Series Analysis: Pandas includes powerful tools for working with time series data. It provides date/time indexing, resampling, shifting, rolling window operations, and other functionalities essential for time-based analysis and visualization.
  8. Visualization: Pandas integrates with other Python libraries like Matplotlib and Seaborn to facilitate data visualization. It offers convenient plotting functions for generating various types of charts and graphs directly from DataFrame and Series objects.
  9. Efficiency and Performance: Pandas is optimized for speed and efficiency, with many operations implemented in highly optimized C or Cython code. It can handle large datasets efficiently, making it suitable for both exploratory analysis and production-level applications.
  10. Integration with NumPy and SciPy: Pandas seamlessly integrates with other essential data science libraries like NumPy and SciPy. This interoperability allows users to leverage the capabilities of these libraries for advanced numerical computation, statistical analysis, and scientific computing.

e. Explain term frequency (TF), document frequency (DF), and inverse document frequency (IDF)

Term Frequency (TF), Document Frequency (DF), and Inverse Document Frequency (IDF) are concepts commonly used in natural language processing and information retrieval for text analysis.

Term Frequency (TF):

DAV Question Paper solution Dec 2023

Document Frequency (DF):

Inverse Document Frequency (IDF):

The combination of TF and IDF is often used to compute a weight for each term in a document, known as TF-IDF (Term Frequency-Inverse Document Frequency). TF-IDF assigns a higher weight to terms that are frequent within a document (high TF) but rare across the corpus (high IDF), making it a useful metric for text mining tasks such as document classification, information retrieval, and keyword extraction.

Q2. Attempt the following:

a. Explain the data analytics lifecycle. (10) (repeated question)

Data Analytics Lifecycle :
The Data analytic lifecycle is designed for Big Data problems and data science projects. The cycle is iterative to represent real project. To address the distinct requirements for performing analysis on Big Data, step – by – step methodology is needed to organize the activities and tasks involved with acquiring, processing, analyzing, and repurposing data.

Phase 1: Discovery –

Phase 2: Data Preparation –

Phase 3: Model Planning –

Phase 4: Model Building –

Phase 5: Communication Results –

Phase 6: Operationalize –

b. Find two lines of regression from the following data: (10)

Age of Husband (x)25222826352022402018
Age of wife (y) 18152017221416211514

Estimate (i) the age of husband when the age of wife is 19 and (ii) the age of wife when
the age of the husband is 30

Answer : /q/find-lines-regression-data/

Q3 Attempt the following:

a. Explain Box-Jenkins intervention analysis.

Answer : /q/explain-box-jenkins-intervention-analysis/

b. What is text mining? Enlist and explain the seven practice areas of text analytics

Text mining, also known as text analytics, is the process of deriving meaningful information from natural language text. It involves various techniques from linguistics, computer science, and statistics to extract patterns, trends, and insights from unstructured text data.

The seven practice areas of text analytics are:

  1. Text Classification:
    • Text classification involves categorizing documents into predefined categories or classes based on their content. It is commonly used for sentiment analysis, spam detection, topic categorization, and more.
    • Techniques used in text classification include machine learning algorithms such as Naive Bayes, Support Vector Machines (SVM), and deep learning models like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN).
  2. Text Clustering:
    • Text clustering involves grouping similar documents together based on their content without predefined categories. It helps in exploring the underlying structure of large text collections and identifying themes or topics.
    • Clustering algorithms like K-means, hierarchical clustering, and DBSCAN are commonly used in text clustering.
  3. Information Extraction:
    • Information extraction focuses on identifying and extracting structured information from unstructured text, such as named entities, relationships, and events. This information is then organized into a structured format for further analysis.
    • Techniques include Named Entity Recognition (NER), relation extraction, and event extraction, often combined with machine learning algorithms.
  4. Sentiment Analysis:
    • Sentiment analysis aims to determine the sentiment or opinion expressed in a piece of text, whether it’s positive, negative, or neutral. It is widely used in social media monitoring, customer feedback analysis, and brand reputation management.
    • Approaches to sentiment analysis include lexicon-based methods, machine learning models (e.g., Support Vector Machines, Recurrent Neural Networks), and hybrid approaches.
  5. Topic Modeling:
    • Topic modeling is a statistical technique for discovering abstract topics or themes present in a collection of documents. It helps in uncovering the underlying structure of large text corpora and understanding the main themes discussed.
    • Popular topic modeling algorithms include Latent Dirichlet Allocation (LDA) and Non-negative Matrix Factorization (NMF).
  6. Text Summarization:
    • Text summarization involves automatically generating concise and coherent summaries of longer texts while preserving the most important information. It is useful for condensing large documents, news articles, or research papers.
    • Techniques for text summarization include extractive methods (e.g., selecting and combining important sentences) and abstractive methods (e.g., generating new sentences to convey the main ideas).
  7. Text Generation:
    • Text generation focuses on automatically producing human-like text based on a given input or context. It includes tasks like machine translation, dialogue generation, and story generation.
    • Techniques range from rule-based systems to advanced deep learning models such as Generative Adversarial Networks (GANs) and Transformers.

Q4. Attempt the following:

a. Explain different types of data visualizations in R programming language.

In R programming language, there are various types of data visualizations that can be created using different packages such as ggplot2, plotly, ggvis, lattice, and base R graphics. Here are some common types of data visualizations in R:

  1. Scatter Plots:
  1. Bar Plots:
  1. Histograms:
  1. Line Plots:
  1. Box Plots:
  1. Heatmaps:
  1. Scatterplot Matrices:

These are just a few examples of the types of visualizations you can create in R. Depending on your data and the insights you want to extract, you can choose the most appropriate type of visualization to effectively communicate your findings.

b. Fit a regression equation to estimate β0 ,β1 and β2 to the following data of a transport
company on the weights of 6 shipments, the distances they were moved and the damage
of the goods that was incurred. (10)

Weight X1 (1000)4.03.01.61.23.44.8
Distance X2 (100KM)1.52.21.02.00.81.6
Damage Y (Rs)1601126990123186

Estimate the damage when a shipment of 3700 kg is moved to a distance of 260 km

Answer : /q/fit-regression-equation-estimate-%ce%b20-%ce%b21-%ce%b22/

Q5. Attempt the following:

a. From the following results, obtain two regression equations and estimate the yield
when the rainfall is 29 cm and the rainfall when the yield is 600 kg. (10)

Yield in Kg. Rainfall in cm
Mean 508.4 26.7
SD 36.8 4.6
Coefficient of
Correlation
0.52

Answer : /q/estimate-yield-rainfall-29-cm-rainfall-yield-600-kg/

b. What is stepwise regression? State and explain different types of stepwise regression

Stepwise regression is a method used in statistical modeling to select a subset of predictor variables (independent variables) for a regression model. The main idea behind stepwise regression is to iteratively add or remove predictor variables from the model based on their statistical significance or contribution to the model’s predictive power. This process continues until a stopping criterion is met, such as reaching a predefined significance level or finding the best-performing model according to a chosen criterion (e.g., AIC, BIC).

There are typically two main types of stepwise regression:

  1. Forward Selection:
  1. Backward Elimination:

Additionally, there is a variant known as Bidirectional Elimination or Stepwise Regression with Both Directions:

Stepwise regression methods are commonly used for variable selection in situations where there are many potential predictor variables, and the goal is to identify the most relevant subset of variables for building a parsimonious and interpretable regression model. However, caution should be exercised when using stepwise regression, as it can lead to overfitting or selecting spurious variables if not performed carefully.

Q6. Write short notes on (any 2):

a. Time Series Analysis:

b. Exploratory Data Analysis (EDA):

c. Regression Plot:

d. Generalized Linear Model (GLM):

Practise this on Doubtly (free)