BIG DATA - IMP NOTES OF BIG DATS
Bachelors of business administrative in computer application (Savitribai Phule Pune
University)
Scan to open on Studocu
Studocu is not sponsored or endorsed by any college or university
Downloaded by Sushant Tandale (
[email protected])
a) Explain different types of data analytics.
Data analytics involves examining, cleaning, transforming, and interpreting data to
make informed decisions. There are various types of data analytics:
1. Descriptive Analytics: This type focuses on summarizing historical data to
understand what has happened in the past. It includes basic statistical analysis,
data visualization, and reporting.
2. Diagnostic Analytics: Diagnostic analytics goes a step further by identifying the
reasons behind past events. It aims to answer "why" something happened by
examining the data in more detail.
3. Predictive Analytics: Predictive analytics uses historical data to make predictions
about future events. Machine learning algorithms are commonly used for
forecasting and modeling future trends.
4. Prescriptive Analytics: Prescriptive analytics not only predicts future outcomes
but also suggests actions to optimize those outcomes. It provides
recommendations on what actions to take to achieve desired results.
b) Give advantages and Disadvantages of Machine Learning.
Advantages of Machine Learning:
• Automation: ML can automate decision-making processes, reducing human
intervention.
• Scalability: It can handle large volumes of data and complex tasks.
• Improved Accuracy: ML models can make predictions with high accuracy.
• Adaptability: Models can adapt to new data and changing conditions.
• Speed: ML algorithms can process data and make predictions quickly.
Disadvantages of Machine Learning:
• Data Dependency: ML requires large, high-quality datasets for training.
• Over 昀椀 tting: Models can become too specialized on the training data and perform
poorly on new data.
• Interpretability: Some ML models are complex and di 昀케 cult to interpret.
• Bias and Fairness: Models can perpetuate bias in data if not properly managed.
• Resource Intensive: Training complex ML models can be computationally
expensive.
c) Explain the process of data analysis.
The process of data analysis involves the following steps:
1. Data Collection: Gather relevant data from various sources, such as databases,
surveys, or sensors.
2. Data Cleaning: Clean the data by addressing missing values, duplicates, outliers,
and inconsistencies.
3. Data Exploration: Explore the data using statistical and visualization techniques
to understand its characteristics and relationships.
4. Data Preprocessing: Prepare the data for analysis by transforming, normalizing,
and scaling it as needed.
5. Data Analysis: Apply statistical, machine learning, or other analytical methods to
extract insights and patterns from the data.
6. Interpretation: Interpret the results and draw conclusions based on the analysis.
7. Visualization: Create visual representations of the data and analysis results to
convey insights effectively.
8. Reporting: Present 昀椀 ndings and insights through reports or visualizations to
stakeholders.
9. Decision Making: Use the analysis results to make informed decisions or take
action.
d) Explain probability distribution modeling.
Probability distribution modeling involves representing the probability of different
outcomes in a random variable. There are various types of probability distributions,
such as the normal distribution, binomial distribution, and Poisson distribution. These
models describe the likelihood of various values or events occurring within a dataset.
For example, the normal distribution describes continuous data with a bell-shaped
curve, while the binomial distribution models the probability of success or failure in a
series of independent trials.
e) Explain applications of big data.
Big data has numerous applications, including:
1. Business Analytics: Analyzing large volumes of data to gain insights into
customer behavior, market trends, and operational e 昀케 ciency.
2. Healthcare: Analyzing patient records and medical data to improve diagnosis,
treatment, and disease management.
3. Finance: Detecting fraud, optimizing investment strategies, and risk assessment
through data analysis.
4. E-commerce: Personalizing product recommendations, optimizing pricing, and
supply chain management.
5. Social Media: Analyzing user-generated content to understand sentiment,
improve ad targeting, and enhance user experiences.
f) Explain Data frame with example.
A data frame is a data structure used in programming and data analysis. It is typically
used in R and other languages like Python (with libraries like Pandas). A data frame is a
two-dimensional, tabular data structure where each column can contain different types
of data, and it is similar to a spreadsheet or database table.
Example in R:
RCopy code
c "Alice" "Bob" "Charlie"
c 25 30 22 c 90 85 78
In this example, we create a data frame with three columns: Name, Age, and Score, and
three rows. It allows you to store and manipulate structured data e 昀케 ciently.
g) Explain types of regression models.
Regression models are used for predicting a continuous target variable based on one or
more predictor variables. There are various types of regression models:
1. Linear Regression: It models the relationship between the target variable and
predictor variables as a linear equation.
2. Logistic Regression: It's used for binary classi 昀椀 cation problems, where the
target variable has two classes.
3. Polynomial Regression: It extends linear regression by 昀椀 tting a polynomial
equation to the data, allowing for curved relationships.
4. Ridge Regression and Lasso Regression: These are variants of linear
regression that add regularization to prevent over 昀椀 tting.
5. Support Vector Regression (SVR): It uses support vector machines to 昀椀 nd a
hyperplane that best 昀椀 ts the data.
6. Random Forest Regression: An ensemble method that combines multiple
decision trees to make predictions.
h) What is a histogram? Explain with an example in R.
A histogram is a graphical representation of the distribution of a dataset. It divides the
data into bins or intervals and displays the frequency of data points falling into each bin.
It's a useful tool for visualizing the shape of a distribution.
Example in R:
RCopy code
c 34 45 56 60 72 80 88 92 95 98 105
110 120 "Histogram of Data" "Value" "Frequency"
"blue" "black" 5
In this example, we create a histogram of the 'data' variable with 昀椀 ve bins. The
histogram visually shows how the data is distributed and the frequency of values in
each bin.
i) Explain Naive Bayes with the help of an example.
Naive Bayes is a classi 昀椀 cation algorithm based on Bayes' theorem, which calculates the
probability of a given event occurring based on prior knowledge of related events. It is
"naive" because it makes a simplifying assumption that the features (variables) are
conditionally independent, which may not be true in practice.
Example:
Suppose you want to classify emails as either spam or not spam based on the presence
of certain words (features) in the email. You have two classes: "Spam" (S) and "Not
Spam" (NS).
1. You receive a new email with the words: "free," "money," "claim."
2. The Naive Bayes algorithm calculates the probability that this email is "Spam"
and "Not Spam" based on the presence of these words.
3. It computes P(S|words) and P(NS|words) using Bayes' theorem and the
assumption of conditional independence.
4. If P(S|words) > P(NS|words), the email is classi 昀椀 ed as "Spam." Otherwise, it's
classi 昀椀 ed as "Not Spam."
Naive Bayes is widely used in text classi 昀椀 cation, such as spam detection and sentiment
analysis.
j) Explain the types of Data Analytics.
Data analytics can be categorized into different types based on the objectives and
approaches:
1. Descriptive Analytics: It focuses on summarizing historical data to provide
insights into past events and trends. This type includes basic statistical analysis,
data visualization, and reporting.
2. Diagnostic Analytics: Diagnostic analytics delves deeper into data to identify
the reasons behind past events. It aims to answer "why" something happened by
examining the data in more detail.
3. Predictive Analytics: Predictive analytics uses historical data to make
predictions about future events. Machine learning algorithms are commonly used
for forecasting and modeling future trends.
4. Prescriptive Analytics: Prescriptive analytics not only predicts future outcomes
but also suggests actions to optimize those outcomes. It provides
recommendations on what actions to take to achieve desired results.
k) Explain correlation with its type.
Correlation is a statistical measure used to assess the degree to which two variables are
related or how they change together. There are two main types of correlation:
1. Positive Correlation: Positive correlation exists when both variables move in
the same direction. In other words, as one variable increases, the other also
increases, and when one decreases, the other also decreases. The correlation
coe 昀케 cient for positive correlation is between 0 and +1.
2. Negative Correlation: Negative correlation occurs when two variables move in
opposite directions. As one variable increases, the other decreases, and vice
versa. The correlation coe 昀케 cient for negative correlation is between -1 and 0.
The correlation coe 昀케 cient, often denoted as "r," quanti 昀椀 es the strength and direction
of the relationship between two variables. A value of +1 indicates a perfect positive
correlation, -1 indicates a perfect negative correlation, and 0 suggests no linear
correlation.
l) Explain support vector machine with an example.
A Support Vector Machine (SVM) is a supervised machine learning algorithm used for
classi 昀椀 cation and regression. It 昀椀 nds a hyperplane that best separates data into
different classes while maximizing the margin between the classes.
Example:
Suppose you want to classify points into two classes, A and B, based on their (x, y)
coordinates. You have the following points:
Class A: (1, 2), (2, 3), (2, 4) Class B: (4, 2), (5, 3), (6, 4)
1. SVM aims to 昀椀 nd the hyperplane that separates these two classes while
maximizing the margin between them. In this case, the hyperplane might be the
line y = 2.5.
2. SVM also identi 昀椀 es support vectors, which are the points closest to the
decision boundary. In this example, the support vectors might be (2, 3) and (5,
3).
3. When you receive a new point, say (3, 3), SVM can classify it by determining
which side of the hyperplane it falls on. In this case, it would be classi 昀椀 ed as
SVM is effective in high-dimensional spaces and can handle non-linear data through the
use of kernel functions.
m) Explain Machine Learning.
Machine learning is a sub 昀椀 eld of arti 昀椀 cial intelligence that focuses on developing
algorithms and models that enable computers to learn and make predictions or
decisions without being explicitly programmed. The core idea is to build systems that
can automatically improve their performance on a speci 昀椀 c task by learning from data.
Key concepts in machine learning include:
• Training Data: Machine learning models are trained on large datasets that
contain examples of inputs and their corresponding correct outputs or labels.
• Feature Engineering: Selecting and transforming relevant features (variables)
from the data to improve model performance.
• Model Building: Creating algorithms or models that can make predictions or
decisions based on input data.
• Learning: The process of adjusting the model's parameters to minimize errors
and improve predictions.
• Evaluation: Testing the model's performance on new, unseen data to assess its
generalization ability.
• Supervised, Unsupervised, and Reinforcement Learning: Different learning
paradigms where models are trained with or without labeled data, or through
trial and error.
Machine learning is used in various applications, including image and speech
recognition, natural language processing, recommendation systems, and predictive
analytics.
n) How Naive Bayes algorithm works.
The Naive Bayes algorithm is a classi 昀椀 cation algorithm based on Bayes' theorem and
the assumption of conditional independence among features. It works as follows:
1. Data Preparation: Collect and preprocess your training data, which consists of
features and labeled classes (e.g., spam or not spam for emails).
2. Calculating Prior Probabilities: Calculate the prior probabilities of each class.
In the case of email classi 昀椀 cation, this is the probability of an email being spam
or not spam.
3. Feature Extraction: Represent the data as a set of features. Each feature is a
characteristic of the data that is relevant to the classi 昀椀 cation task (e.g., the
presence of certain words in an email).
4. Calculating Likelihoods: Calculate the likelihood of each feature given each
class. This involves estimating how likely a particular feature value is to occur in
each class based on the training data.
5. Calculating Posterior Probabilities: Use Bayes' theorem to calculate the
posterior probabilities of each class given the features. This step combines the
prior probabilities and the likelihoods.
6. Making Predictions: For a new, unlabeled data point, calculate the posterior
probabilities for each class and choose the class with the highest posterior
probability as the predicted class.
The "naive" part of Naive Bayes comes from the assumption that the features are
conditionally independent, which simpli 昀椀 es the calculations. While this assumption may
not hold in all cases, Naive Bayes is known for its simplicity and e 昀케 ciency in text
classi 昀椀 cation and other tasks.
o) Explain Decision tree with an example.
A Decision Tree is a supervised machine learning algorithm that is used for both
classi 昀椀 cation and regression tasks. It is a tree-like model of decisions and their possible
consequences. Here's an example of a decision tree for classifying whether to play golf
based on weather conditions:
In this example:
• The root node represents the initial decision, which is whether to play golf.
• The internal nodes represent conditions or features to consider (e.g., "Outlook"
and "Humidity").
• The branches represent possible values or outcomes of those conditions.
• The leaf nodes represent the 昀椀 nal decision or classi 昀椀 cation (e.g., "Yes" or "No").
How the decision tree works:
1. Starting at the root, we evaluate the "Outlook" condition. If the outlook is
"Sunny," we follow the left branch; if it's "Overcast," we follow the middle branch;
if it's "Rainy," we follow the right branch.
2. At each internal node, we evaluate the condition speci 昀椀 ed. In the example,
we consider "Humidity" and "Windy."
3. We continue down the tree until we reach a leaf node, which provides the 昀椀 nal
decision. For instance, if we have a "Sunny" outlook, "Cool" humidity, and
"Windy" conditions, the decision is "No."
Decision trees are easy to interpret and visualize, making them useful for various
classi 昀椀 cation and regression tasks.
p) Explain the application of big data.
Big data has various applications across different domains, including:
1. Business and Marketing: Analyzing customer behavior, market trends, and
sentiment analysis for better decision-making and targeted advertising.
2. Healthcare: Utilizing large datasets to improve patient care, disease prediction,
and medical research, such as genomics.
3. Finance: Detecting fraud and anomalies, optimizing investment strategies, and
risk assessment.
4. E-commerce: Personalizing recommendations, optimizing pricing, and inventory
management.
5. Social Media: Analyzing user-generated content for sentiment analysis, ad
targeting, and content recommendations.
6. Manufacturing and Supply Chain: Monitoring and optimizing production
processes, inventory management, and logistics.
7. Transportation and Logistics: Analyzing tra 昀케 c data for route optimization,
predictive maintenance, and 昀氀 eet management.
8. Energy and Utilities: Optimizing energy usage, predictive maintenance for
infrastructure, and grid management.
9. Government and Public Services: Enhancing public safety, monitoring and
response to disasters, and analyzing demographic data for policymaking.
10. Scienti 昀椀 c Research: Analyzing large datasets in 昀椀 elds like astronomy, particle
physics, and climate science.
Big data technologies and analytics are essential for extracting valuable insights from
the vast amount of data generated in these domains.
q) Explain cluster analysis with its types.
Cluster analysis is a data analysis technique that groups similar data points into
clusters, making data segmentation and pattern recognition easier. There are several
types of cluster analysis:
1. Hierarchical Clustering: This method creates a hierarchy of clusters. It starts
with each data point as its cluster and then merges or divides clusters until a
dendrogram is formed, representing the hierarchy.
2. K-Means Clustering: K-Means is a partitioning method that divides data into a
prede 昀椀 ned number (k) of clusters. It assigns data points to the nearest cluster
centroid, and clusters are iteratively updated.
3. DBSCAN (Density-Based Spatial Clustering of Applications with Noise):
DBSCAN groups data points based on density. It forms clusters in areas with high
point density and considers data points in sparse regions as noise.
4. Agglomerative Clustering: Agglomerative clustering starts with each data
point as a single cluster and repeatedly merges the closest clusters until there is
one large cluster containing all data points.
5. Divisive Clustering: The opposite of agglomerative clustering, divisive
clustering starts with all data points in one cluster and recursively splits them
into smaller clusters based on some criteria.
6. Fuzzy Clustering: Unlike traditional clustering, fuzzy clustering assigns each
data point a degree of membership to multiple clusters. It allows data points to
belong partially to different clusters.
7. Mean Shift Clustering: Mean shift is a non-parametric clustering method that
iteratively shifts the cluster centers towards areas of high data point density.
Each type of cluster analysis is suitable for different data distributions and the speci 昀椀 c
problem you are trying to solve.
r) What is regression? Explain its types.
Regression is a statistical technique used to model and analyze the relationships
between a dependent variable (target) and one or more independent variables
(predictors or features). The main goal of regression is to understand and predict the
value of the dependent variable based on the values of the independent variables.
There are several types of regression:
1. Linear Regression: Linear regression models the relationship between the
dependent variable and one or more independent variables as a linear equation.
It is used for predicting continuous numeric values.
2. Logistic Regression: Logistic regression is used for binary classi 昀椀 cation
problems where the dependent variable is categorical with two classes. It models
the probability of one class.
3. Polynomial Regression: Polynomial regression extends linear regression by
昀椀 tting a polynomial equation to the data, allowing for curved relationships
between variables.
4. Ridge Regression and Lasso Regression: These are variants of linear
regression that add regularization to prevent over 昀椀 tting by penalizing large
coe 昀케 cients.
5. Support Vector Regression (SVR): SVR uses support vector machines to 昀椀 nd
a hyperplane that best 昀椀 ts the data for regression tasks.
6. Random Forest Regression: An ensemble method that combines multiple
decision trees for regression tasks.
7. Ordinal Regression: It is used when the dependent variable is ordinal (e.g.,
ratings on a scale) and models the ordinal relationship.
8. Time Series Regression: Used for time-dependent data, where the order and
timing of observations matter.
9. Multivariate Regression: Extends simple linear regression to model the
relationship between multiple independent variables and a dependent variable.
Each type of regression has its own assumptions, advantages, and use cases, making it
suitable for different scenarios.
s) Explain the 昀椀 ve applications of machine learning.
Machine learning has numerous applications across various domains. Here are 昀椀 ve
notable applications:
1. Image and Video Analysis: Machine learning is used for image classi 昀椀 cation,
object detection, facial recognition, and video content analysis. Applications
include autonomous vehicles, medical image analysis, and surveillance systems.
2. Natural Language Processing (NLP): NLP leverages machine learning to
process and understand human language. It's used in chatbots, language
translation, sentiment analysis, and text summarization.
3. Recommendation Systems: Machine learning is employed in recommendation
engines that suggest products, movies, music, or content based on a user's
preferences. Popular examples include Net 昀氀 ix's movie recommendations and
Amazon's product suggestions.
4. Healthcare and Medical Diagnosis: Machine learning helps in disease
diagnosis, medical image analysis, drug discovery, and patient risk assessment.
It improves healthcare decision-making and patient outcomes.
5. Financial Services: Machine learning is used for fraud detection, algorithmic
trading, credit scoring, and risk assessment. It helps 昀椀 nancial institutions make
data-driven decisions and manage risk.
These applications showcase the versatility and impact of machine learning in
automating tasks, improving decision-making, and solving complex problems in various
domains.
Explain the 昀椀 ve applications of machine learning AN SWER ALL THIS QUESTION WITH
QUESTION PRINT
s) Explain the 昀椀 ve applications of machine learning.
ChatGPT
Machine learning has numerous applications across various domains. Here are 昀椀 ve
notable applications:
1. Image and Video Analysis: Machine learning is used for image classi 昀椀 cation,
object detection, facial recognition, and video content analysis. Applications
include autonomous vehicles, medical image analysis, and surveillance systems.
2. Natural Language Processing (NLP): NLP leverages machine learning to
process and understand human language. It's used in chatbots, language
translation, sentiment analysis, and text summarization.
3. Recommendation Systems: Machine learning is employed in recommendation
engines that suggest products, movies, music, or content based on a user's
preferences. Popular examples include Net 昀氀 ix's movie recommendations and
Amazon's product suggestions.
4. Healthcare and Medical Diagnosis: Machine learning helps in disease
diagnosis, medical image analysis, drug discovery, and patient risk assessment.
It improves healthcare decision-making and patient outcomes.
5. Financial Services: Machine learning is used for fraud detection, algorithmic
trading, credit scoring, and risk assessment. It helps 昀椀 nancial institutions make
data-driven decisions and manage risk.
These applications showcase the versatility and impact of machine learning in
automating tasks, improving decision-making, and solving complex problems in various
domains.
ANSWER THE FOLLOWING 5MARKS
a) Tools used in Big Data:
Big data processing and analysis often require specialized tools and
frameworks. Some commonly used tools in the big data domain include:
1. Hadoop: An open-source framework for distributed storage and
processing of large datasets. It includes HDFS (Hadoop Distributed File
System) and MapReduce for parallel computation.
2. Apache Spark: A fast and powerful open-source data processing
engine that supports batch processing, real-time streaming, and
machine learning.
3. Cassandra: A NoSQL database that provides high scalability and
performance for handling large amounts of data.
4. Tableau, Power BI, and other BI tools: These tools are used for
visualizing and analyzing data in a user-friendly manner.
5. Python and R: Programming languages with libraries and packages
for big data analytics, machine learning, and data manipulation.
b) Advantages of Big Data:
The advantages of big data include:
1. Data-Driven Decision-Making: Big data enables organizations to
make informed decisions based on data analysis, leading to better
strategies and outcomes.
2. Improved Customer Insights: Analyzing large datasets helps in
understanding customer behavior, preferences, and needs, leading to
more personalized and effective marketing.
3. Enhanced Operational E 昀케 ciency: Big data analytics can optimize
processes, reduce costs, and improve operational e 昀케 ciency.
4. Competitive Advantage: Organizations that harness big data
effectively gain a competitive edge by identifying trends and
opportunities ahead of their competitors.
5. Innovation: Big data fosters innovation by enabling the development
of new products, services, and business models.
6. Predictive Analytics: It allows organizations to predict future trends,
customer demands, and potential issues.
7. Real-Time Analytics: Big data technologies can provide real-time
insights, allowing quick reactions to changing situations.
8. Scalability: Big data tools can handle massive amounts of data,
making them suitable for growing datasets.
c) Population and sample:
• Population: In statistics, a population refers to the entire group of
individuals or objects that you want to study or make inferences about.
It represents the complete set of elements that share a common
characteristic. For example, if you want to study the heights of all adult
individuals in a country, the entire adult population of that country
would be the population.
• Sample: A sample is a subset of the population that is selected for
data collection and analysis. It is used when it is impractical or too
costly to study the entire population. A well-designed sample should be
representative of the population from which it is drawn, allowing for
valid statistical inferences. In the example of studying heights, a
sample might consist of a randomly selected group of adults from the
country.
d) Data Visualization:
Data visualization is the presentation of data in graphical or visual formats to
help people understand, interpret, and derive insights from data. It is a
powerful tool for conveying complex information in a comprehensible and
engaging manner. Key aspects of data visualization include:
• Charts and Graphs: Various types of charts and graphs, such as bar
charts, line charts, pie charts, scatter plots, and heatmaps, are used to
represent data.
• Colors and Shapes: Visual elements like colors, shapes, and sizes
can be used to convey information and highlight patterns or trends.
• Interactive Tools: Data visualization tools often provide interactivity,
allowing users to explore and manipulate data for deeper insights.
• Storytelling: Effective data visualization often tells a story, helping
the audience understand the context and signi 昀椀 cance of the data.
• Dashboards: Dashboards are a collection of visualizations and
metrics that provide a comprehensive view of data at a glance.
• Infographics: Infographics combine text and visuals to present data
in a visually appealing and concise manner.
• Data Mapping: Geospatial data visualization uses maps to represent
data by location, enabling insights related to geography.
Data visualization tools like Tableau, Power BI, Matplotlib (for Python), and
ggplot2 (for R) are commonly used for creating informative and aesthetically
pleasing visual representations of data.
e) Data types in R:
R is a programming language and environment commonly used for data
analysis and statistical computing. It supports several fundamental data
types:
1. Numeric: Represents numerical values, which can be integers or
昀氀 oating-point numbers. For example, x <- 5 or y <- 3.14 .
2. Character: Stores text and strings. For example, name <- "John" or
city <- 'New York'.
3. Integer: Speci 昀椀 cally represents whole numbers as integers. For
example, count <- 10L.
4. Logical: Stores binary values, which can be either TRUE or FALSE. For
example, 昀氀 ag <- TRUE .
5. Complex: Used for complex numbers, which have both a real and
imaginary part. For example, z <- 3 + 2i.
6. Factor: Represents categorical or nominal data. Factors are commonly
used in statistical modeling. For example, gender <- factor(c("Male",
"Female", "Male")).
7. Date and Time: R has speci 昀椀 c data types for date and time, such as
Date and POSIXct , to handle temporal data.
These data types are essential for data manipulation, analysis, and
visualization in R.
a) What is big data?
• Big data refers to large and complex datasets that are beyond the
capacity of traditional data processing tools to capture, store, manage,
and analyze. It often involves massive volumes of structured and
unstructured data, such as text, images, and sensor data.
b) What is data manipulation?
• Data manipulation is the process of altering, transforming, and
cleaning data to make it more suitable for analysis. It includes tasks
like 昀椀 ltering, sorting, joining, aggregating, and reshaping data to
extract meaningful insights.
c) What is data science?
• Data science is an interdisciplinary 昀椀 eld that involves the use of
scienti 昀椀 c methods, algorithms, processes, and systems to extract
knowledge and insights from data. It combines expertise in statistics,
computer science, domain knowledge, and data visualization to solve
complex problems.
d) What is statistical inference?
• Statistical inference is the process of drawing conclusions or making
predictions about a population based on a sample of data. It involves
estimating population parameters and assessing the uncertainty
associated with those estimates using statistical methods.
e) Enlist the stages of data science:
1. Data Collection
2. Data Cleaning and Preprocessing
3. Data Exploration and Visualization
4. Feature Engineering
5. Model Building and Machine Learning
6. Model Evaluation and Validation
7. Deployment and Communication of Results
f) De 昀椀 ne Machine Learning:
• Machine Learning is a sub 昀椀 eld of arti 昀椀 cial intelligence that involves the
development of algorithms and models that allow computers to learn
from data and make predictions or decisions without being explicitly
programmed. It relies on patterns and statistical relationships in the
data.
g) De 昀椀 ne SVM:
• Support Vector Machine (SVM) is a supervised machine learning
algorithm used for classi 昀椀 cation and regression tasks. It 昀椀 nds a
hyperplane that best separates data into different classes while
maximizing the margin between the classes.
h) What is the use of a histogram?
• A histogram is used for visualizing the distribution of data. It displays
the frequency or count of data points within speci 昀椀 ed bins or intervals,
helping to identify patterns, trends, and the shape of the data
distribution.
i) What is data analysis?
• Data analysis is the process of inspecting, cleaning, transforming, and
interpreting data to discover meaningful insights, patterns, and trends.
It involves using various techniques and tools to extract useful
information from data.
j) What is the use of themes?
• Themes, in the context of data visualization and design, refer to a
consistent set of visual styles, colors, fonts, and elements used to
create a cohesive and visually appealing presentation of data. Themes
enhance the aesthetics and readability of charts, graphs, and reports.
k) What is population?
• In statistics, a population refers to the entire group or set of
individuals, items, or elements that share a common characteristic or
feature and are of interest for a particular study or analysis. It
represents the complete set from which a sample is drawn.
l) De 昀椀 ne sample.
• A sample is a subset of a population that is selected for data collection
and analysis. It is used to make inferences about the entire population,
as it is often impractical or too costly to study the entire population.
m) What is KNN?
• K-Nearest Neighbors (KNN) is a supervised machine learning algorithm
used for classi 昀椀 cation and regression tasks. It assigns a class or value
to a data point based on the majority class or the average of the K-
nearest data points in the training dataset.
n) De 昀椀 ne EM algorithm.
• The Expectation-Maximization (EM) algorithm is a statistical method
used for estimating parameters of statistical models when dealing with
unobservable or missing data. It iteratively optimizes the likelihood
function, making it useful in clustering and density estimation.
o) What is Apriori algorithm?
• The Apriori algorithm is a data mining algorithm used for association
rule mining in large datasets. It identi 昀椀 es frequent itemsets (groups of
items that often appear together) and generates association rules,
such as "If X, then Y," to reveal patterns in the data.
p) What is R?
• R is a programming language and open-source software environment
primarily used for statistical computing and data analysis. It provides a
wide range of statistical and graphical techniques and has a large
community of users and developers who contribute to its extensive
library of packages and extensions.
