History

leestott 5329d79dbc 🌐 Update translations via Co-op Translator		2 months ago
..
README.md	🌐 Update translations via Co-op Translator	2 months ago
assignment.md	🌐 Update translations via Co-op Translator	2 months ago

README.md

Data Science for Real World


Data Science for Real World - Sketchnote by @nitya

We don dey near di end of dis learning journey!

We start wit di meaning of data science and ethics, check different tools & techniques for data analysis and visualization, review di data science lifecycle, and look how to scale and automate data science workflows wit cloud computing services. So, you fit dey wonder: "How I go fit use all dis things wey I don learn for real-world situations?"

For dis lesson, we go check how data science dey work for real-world industry and we go dive into examples for research, digital humanities, and sustainability. We go also look student project opportunities and end wit resources wey go help you continue your learning journey!

Pre-Lecture Quiz

Pre-lecture quiz

Data Science + Industry

Because AI don dey more accessible, developers don dey find am easy to design and add AI-driven decision-making and data-driven insights into user experiences and development workflows. Here be some examples of how data science dey "work" for real-world industry:

Google Flu Trends use data science to connect search terms wit flu trends. Even though di method get wahala, e show di possibilities (and challenges) of data-driven healthcare predictions.
UPS Routing Predictions - explain how UPS dey use data science and machine learning to predict di best routes for delivery, dey consider weather conditions, traffic patterns, delivery deadlines and more.
NYC Taxicab Route Visualization - data wey dem gather using Freedom Of Information Laws help show how NYC cabs dey move around di city, di money dem dey make, and di time trips dey take for each 24-hour period.
Uber Data Science Workbench - dey use data (like pickup & dropoff locations, trip duration, preferred routes etc.) wey dem gather from millions of Uber trips everyday to build data analytics tool wey dey help wit pricing, safety, fraud detection and navigation decisions.
Sports Analytics - dey focus on predictive analytics (team and player analysis - like Moneyball - and fan management) and data visualization (team & fan dashboards, games etc.) wit things like talent scouting, sports gambling and inventory/venue management.
Data Science in Banking - dey show di importance of data science for finance industry wit things like risk modeling and fraud detection, customer segmentation, real-time prediction and recommender systems. Predictive analytics dey also drive important things like credit scores.
Data Science in Healthcare - dey show things like medical imaging (e.g., MRI, X-Ray, CT-Scan), genomics (DNA sequencing), drug development (risk assessment, success prediction), predictive analytics (patient care & supply logistics), disease tracking & prevention etc.

Image Credit: Data Flair: 6 Amazing Data Science Applications

Di figure dey show other areas and examples of how data science techniques dey work. You wan check other applications? Look di Review & Self Study section below.

Data Science + Research


Data Science & Research - Sketchnote by @nitya

While real-world applications dey focus on industry use cases for big scale, research applications and projects fit dey useful for two reasons:

innovation opportunities - dey test advanced ideas fast and dey try user experiences for next-generation applications.
deployment challenges - dey check di possible wahala or unintended problems wey data science technologies fit cause for real-world situations.

For students, dis research projects fit give learning and collaboration opportunities wey fit help you understand di topic well, and make you sabi di people or teams wey dey work for areas wey you dey interested in. So, how research projects dey look and how dem fit make impact?

Make we check one example - di MIT Gender Shades Study from Joy Buolamwini (MIT Media Labs) wit one important research paper wey she write wit Timnit Gebru (wey dey Microsoft Research dat time) wey focus on:

What: Di aim of di research project na to check di bias wey dey automated facial analysis algorithms and datasets based on gender and skin type.
Why: Facial analysis dey used for areas like law enforcement, airport security, hiring systems and more - places wey wrong classifications (e.g., because of bias) fit cause economic and social wahala for di people or groups wey e affect. To understand (and remove or reduce) bias na di key to fairness for usage.
How: Researchers see say di benchmarks wey dem dey use before dey use mostly lighter-skinned people, so dem create new data set (1000+ images) wey balance di gender and skin type. Di data set dey used to check di accuracy of three gender classification products (from Microsoft, IBM & Face++).

Results show say even though di overall classification accuracy dey okay, di error rates dey different for di subgroups - wit misgendering higher for women or people wey get darker skin types, wey show say bias dey.

Key Outcomes: E show say data science need more representative datasets (balanced subgroups) and more inclusive teams (diverse backgrounds) to see and remove or reduce dis kind bias early for AI solutions. Research like dis dey help many organizations define principles and practices for responsible AI to make fairness better for their AI products and processes.

You wan learn about di research wey Microsoft dey do?

Check Microsoft Research Projects for Artificial Intelligence.
Explore student projects from Microsoft Research Data Science Summer School.
Check di Fairlearn project and Responsible AI initiatives.

Data Science + Humanities


Data Science & Digital Humanities - Sketchnote by @nitya

Digital Humanities dem define am as "di way wey dem dey use computational methods join wit humanistic inquiry". Stanford projects like "rebooting history" and "poetic thinking" dey show di connection between Digital Humanities and Data Science - dey use techniques like network analysis, information visualization, spatial and text analysis wey fit help us look historical and literary data sets again to get new insights and perspective.

You wan explore and expand project for dis area?

Check "Emily Dickinson and the Meter of Mood" - one good example from Jen Looper wey dey ask how we fit use data science to look poetry again and check di meaning and di contribution of di author for new ways. For example, we fit predict di season wey dem write poem by analyzing di tone or sentiment - and wetin dis one dey tell us about di author's state of mind for dat time?

To answer di question, we go follow di steps of our data science lifecycle:

Data Acquisition - to collect di dataset wey we go analyze. Options dey like using API (e.g., Poetry DB API) or scraping web pages (e.g., Project Gutenberg) wit tools like Scrapy.
Data Cleaning - dey explain how text fit dey formatted, sanitized and simplified wit basic tools like Visual Studio Code and Microsoft Excel.
Data Analysis - dey explain how we fit import di dataset into "Notebooks" for analysis wit Python packages (like pandas, numpy and matplotlib) to organize and visualize di data.
Sentiment Analysis - dey explain how we fit use cloud services like Text Analytics, wit low-code tools like Power Automate for automated data processing workflows.

Wit dis workflow, we fit check di seasonal impact on di sentiment of di poems, and e go help us form our own perspective about di author. Try am yourself - then expand di notebook to ask other questions or visualize di data for new ways!

You fit use some tools for di Digital Humanities toolkit to follow dis kind inquiry.

Data Science + Sustainability


Data Science & Sustainability - Sketchnote by @nitya

Di 2030 Agenda For Sustainable Development - wey all United Nations members adopt for 2015 - get 17 goals wey dey focus on Protecting di Planet from degradation and di impact of climate change. Di Microsoft Sustainability initiative dey support dis goals by dey find ways wey technology solutions fit help build better sustainable futures wit focus on 4 goals - to be carbon negative, water positive, zero waste, and bio-diverse by 2030.

To handle dis challenges for big scale and fast time, e need cloud-scale thinking - and big data. Di Planetary Computer initiative dey provide 4 things to help data scientists and developers for dis work:

Data Catalog - wit petabytes of Earth Systems data (free & Azure-hosted).
Planetary API - to help users search for di data wey dem need across space and time.
Hub - managed environment for scientists to process big geospatial datasets.
Applications - show wetin people dey use am do & tools wey fit help for sustainability insights.

Di Planetary Computer Project dey preview stage (as of Sep 2021) - see how you fit start to dey contribute to sustainability solutions wit data science.

Request access to begin your exploration and connect wit oda people.
Explore documentation to sabi di datasets and APIs wey dem support.
Check applications like Ecosystem Monitoring to get ideas for wetin you fit do.

Think about how you fit use data visualization to show or make di insights wey dey important for areas like climate change and deforestation more clear. Or think about how di insights fit help create new user experiences wey go make people change di way dem dey live to dey more sustainable.

Data Science + Students

We don talk about real-world applications for industry and research, and we don look examples of how data science dey work for digital humanities and sustainability. So how you fit take build your skills and share wetin you sabi as person wey dey start data science?

Here be some examples of data science student projects wey fit inspire you.

MSR Data Science Summer School wit GitHub projects wey dey explore topics like:
- Racial Bias in Police Use of Force | Github
- Reliability of NYC Subway System | Github
Digitizing Material Culture: Exploring socio-economic distributions in Sirkap - from Ornella Altunyan and team for Claremont, using ArcGIS StoryMaps.

🚀 Challenge

Search for articles wey dey recommend data science projects wey dey easy for beginners - like these 50 topic areas or these 21 project ideas or these 16 projects with source code wey you fit break down and remix. No forget to blog about wetin you dey learn and share your insights wit all of us.

Post-Lecture Quiz

Post-lecture quiz

Review & Self Study

You wan explore more use cases? Here be some articles wey fit help:

17 Data Science Applications and Examples - Jul 2021
11 Breathtaking Data Science Applications in Real World - May 2021
Data Science In The Real World - Article Collection
12 Real-World Data Science Applications with Examples - May 2024
Data Science In: Education, Agriculture, Finance, Movies, Health Care & more.

Assignment

Explore A Planetary Computer Dataset

Disclaimer:
Dis dokyument don use AI translation service Co-op Translator do di translation. Even as we dey try make am correct, abeg sabi say machine translation fit get mistake or no dey accurate well. Di original dokyument for im native language na di main source wey you go trust. For important information, e better make professional human translation dey use. We no go fit take blame for any misunderstanding or wrong interpretation wey fit happen because you use dis translation.