IBM Data Analyst Capstone Project

Information
Technology Future
Skill.
Emmanuel Yangue
5-13-2022
OUTLINE
• Executive Summary
• Introduction
• Methodology
• Results
• Visualization – Charts
• Dashboard
• Discussion
• Findings & Implications
• Conclusion
• Appendix
EXECUTIVE SUMMARY
• Data Collection using API and Web scrapping
• Basic Data Exploration
• Data Wrangling
-Dealing with duplicate
- Missing values
- Normalization
• Data Exploratory Analysis (EDA)

- Distribution
- Outliers
- Correlation
• Data Visualization
• Dashboard
INTRODUCTION
• The purpose of this Project is to analyze Technology and programming
data to help identify Future skills requirement for this field.
• Data must be collected from various sources then analyzed.
• Result will be useful for IT department and investors.
• The resulting insight should help responding to questions such as
- Top programming Languages in Demand.
- Top databases skills in Demand.
- Top Platform
- Popular IDE
METHODOLOGY
• Data Collection Sources
(API, WEB SCRAPPING)
• Data Exploration
• Data Wrangling
• EDA
• Data Visualization
• Dashboard
RESULTS – Data Collection Using API
• Requests used to access API

• 1173 Jobs postings in Python Programming Language
• Washington DC has highest Job Posting
RESULTS – Basic Exploratory Data Survey
• Data Shape :
11552 Rows
85 Columns
• Average Age of Surveys Takers: 30.777
• 135 Countries took the survey.

RESULTS – Data Wrangling
• 154 Duplicate Values Removed dropping rows to 11398
• Total missing Values per Column:
• Data Normalized: “Median of Normalized Annual Compensation” = 100000

RESULTS – EDA – Distribution
• Survey Respondents Age summary Statistics:
• Age Distribution :
• Median Convert Comp for Woman: 55708

RESULTS – EDA – Outliers
• Most Outliers are found after Q3

RESULTS – EDA – Correlation
RESULTS – Data Visualization
using SQL
Age vs Work week hours Work week hours vs code rev hours
RESULTS – Data Visualization
using SQL
Median Converted Comp for Ages
Pie Chart between 45 & 60
PROGRAMMING LANGUAGE TRENDS
Current Year top 5 Next Year Top 5
PROGRAMMING LANGUAGE TRENDS - FINDINGS &
IMPLICATIONS
Findings Implications
• JavaScript, HTML, SQL, Python • Web and application

are still top 4 popular languages development are still demanded
now and, in the future. job.
• Power shell is losing is popularity • Databases manipulation is also
and will be replaced in the an important skill demanded.
future • Python is still an easy Language
• Type script is growing in for starters and Data science and
popularity. analysis.
DATABASE TRENDS
Current Year Top 5 Next Year Top 5
DATABASE TRENDS - FINDINGS &
IMPLICATIONS
Findings Implications
• MySQL is still at the top of the game is • Private Company owned databases
losing is grip over PostgreSQL. competitions are increasing.
• MySQL, MongoDB, and PostgreSQL • Open-Source database skills are still in

are still popular databases now and in high demand.
the future.
• MicrosoftSQL and SQLlite will be • Non relational database are also on

replaced by Elasticsearch and Redis. the rise.
LINK FOR DASHBOARD
https://dataplatform.cloud.ibm.com/das
hboards/5730f6bb-00cc-413e-b2be-
6a7c3eb40b83/view/6722c4253b9b0ff56
ef3cce407c82554753e240bb2bb830b80d
37b490b342497a96911c0c87d425ada17
5030f6bd430dca
Current Technology Trends
Future Technology Usage
Demographics
DISCUSSION
Findings
Implications
• The highly used languages and
databases will stay in high demand in • Man are still the leading gender in
the future technology
• The Platform used right are very • Other continent are still lagging
similar to the predicted platforms that behind America and Europe
will be used in the future.
• 24-34 is the highest age group for IT.
• jQuery will take the Lead in terms of
web Frame work with in the future
CONCLUSION
• Technology is still hot field to be interested
now and, in the future.
• Due to high demand in the field,
competition is getting high and there is a
need to quick adaptation to change.
• Companies need to look to new Horizon like
Central America and Africa.
• Artificial Intelligence and the like are new
area impacting the technology field and are
probably skills ones must seek to acquire.
APPENDIX – Popular-Languages CSV
Average Annual Salary Per Language
Swift
Python
C++
Javascript
Java
Go
C#
SQL
PHP
$0 $20,000 $40,000 $60,000 $80,000 $100,000 $120,000 $140,000

APPENDIX – GitHub job posting
Job Postings per Languages
Java
Python
Javascript
C#
C++
Oracle
SQL server
MongoDB
Scala
PostGreSQL
MySQL Server
0 2000 4000 6000 8000 10000 12000 14000

IBM Data Analyst Capstone Project

Uploaded by

IBM Data Analyst Capstone Project

Uploaded by

Information

• Data Exploratory Analysis (EDA)

• Requests used to access API

• Average Age of Surveys Takers: 30.777

• 135 Countries took the survey.

• 154 Duplicate Values Removed dropping rows to 11398

• Total missing Values per Column:

• Data Normalized: “Median of Normalized Annual Compensation” = 100000

• Median Convert Comp for Woman: 55708

• Most Outliers are found after Q3

• JavaScript, HTML, SQL, Python • Web and application

• MySQL, MongoDB, and PostgreSQL • Open-Source database skills are still in

• MicrosoftSQL and SQLlite will be • Non relational database are also on

$0 $20,000 $40,000 $60,000 $80,000 $100,000 $120,000 $140,000

0 2000 4000 6000 8000 10000 12000 14000

You might also like