Communist, Reader, Tennis, & Data Analyst
Between Snowflake & Tableau
Joined November 2021
- Tweets90
- Following287
- Followers61
- Likes94
Data Sapien retweeted
20 things to know about AI Engineering before reading Advanced course:
- context engineering (prompt caching, KV cache, context rot)
- structured outputs (JSON schema, constrained decoding)
- tool calling & MCP
- agent loops, handoffs, termination conditions
- orchestration (LangGraph, checkpointing, HITL)
- workflow patterns (chaining, routing, parallelization)
- document parsing (OCR, layout, tables)
- chunking (recursive, semantic, overlap)
- embeddings (bi-encoders, dimensionality, MTEB)
- vector indexes (HNSW, IVF, pgvector, Qdrant)
- hybrid search (BM25 + vector, metadata filters)
- query transformation (HyDE, step-back, multi-query)
- reranking (cross-encoders)
- GraphRAG & knowledge graphs
- evals (golden sets, LLM-as-judge, Ragas)
- observability (tracing, OpenTelemetry, Langfuse)
- guardrails (OWASP LLM01, least privilege, sandboxing)
- caching & routing (semantic cache, cascades, fallbacks)
- fine-tuning (LoRA, QLoRA, DPO, distillation)
- inference serving (vLLM, quantization, continuous batching)
i am going to release this new article approximately on Monday/Tuesday
spent there already ~10 days of deep research, collected 112 resources (it's not finalized even on half yet kek) and already 8,000 words
so, everybody who is interested to figure out in AI Engineering as me, turn on your notis for the next week 🔔
Data Sapien retweeted
When was the last time a sitting High Court judge reviewed a movie running in theaters, on a platform like LiveLaw?
livelaw.in/articles/masterpi…
Data Sapien retweeted
How to get 36 LPA job opportunities as an AI Engineer with 4 YOE. Just like me. Real Deal. No BS Guide...
Customer service assistance were so rude on this they are not even talking me properly and they saying they cant take my product as return. This is so so disdainful @amazonIN
I received wrong item instead of my order which is worth or 7,299 INR (new balance shoes). I raised a return request but the portal isnt reflecting it and not even one call was attempted from your side this is very disgrace and unhappy with your customer service. @amazonIN
I received wrong item instead of my order which is worth or 7,299 INR (new balance shoes). I raised a return request but the portal isnt reflecting it and not even one call was attempted from your side this is very disgrace and unhappy with your customer service. @amazonIN
Data Sapien retweeted
#Giveaway Alert 🚨
We’re giving away the Apple iPhone 16 Pro Max 512 GB
Steps to Enter ⬇️
🔄 RETWEET
✅ FOLLOW 👉🏾 @dealztrendz
We’ll pick 🔟 random followers & each will get a Apple iPhone 16 Pro Max 512 GB 만우절
GET SET GO 만우절 #DealzTrendzGiveaway
Data Sapien retweeted
#Interviews
Two scenario-based SQL Interview questions !
Question 1:
Scenario: You have a table called "orders" with columns "order_id", "customer_id", "order_date", and "total_amount". Write a query to find the customers who have placed an order in the last 30 days, but not in the last 14 days.
Answer:
```
SELECT customer_id
FROM orders
WHERE order_date BETWEEN DATEADD(DAY, -30, GETDATE()) AND DATEADD(DAY, -14, GETDATE())
GROUP BY customer_id
HAVING COUNT(order_id) > 0;
```
Question 2:
Scenario: You have a table called "products" with columns "product_id", "product_name", "price", and "product_category". Write a query to find the products that have a price greater than the average price of all products in their category, but less than the maximum price in their category.
Answer:
```
SELECT p1.product_id, p1.product_name, p1.price
FROM products p1
JOIN (
SELECT product_category, AVG(price) AS avg_price, MAX(price) AS max_price
FROM products
GROUP BY product_category
) p2 ON p1.product_category = p2.product_category
WHERE p1.price > p2.avg_price AND p1.price < p2.max_price;
```
Data Sapien retweeted
In which order SQL queries run?🔎👇
In SQL, the order in which queries are processed is typically defined by the logical query processing order. The logical query processing order is different from the order in which the SQL statements are written in the query.
Here is the general logical order in which SQL queries are processed:
1. FROM clause:
The data sources (tables, views, etc.) specified in the FROM clause are processed first.
This involves reading the data from the tables and combining data from multiple sources if there are joins.
2. WHERE clause:
The WHERE clause is applied to filter the rows based on the specified conditions.
Rows that do not meet the criteria in the WHERE clause are excluded from further processing.
3. GROUP BY clause:
If a GROUP BY clause is present, rows are then grouped based on the specified columns.
Aggregate functions (like SUM, COUNT, AVG) are then applied to each group.
4. HAVING clause:
If a HAVING clause is present, it filters groups based on aggregate conditions.
Groups that do not meet the criteria in the HAVING clause are excluded.
5. SELECT clause:
The SELECT clause is then applied to the result set.
Columns are selected, and expressions are computed.
6. ORDER BY clause:
If an ORDER BY clause is present, the result set is then sorted based on the specified columns.
7. LIMIT/OFFSET (if applicable):
If there is a LIMIT or OFFSET clause (used in some database systems), the final result set is then limited or offset accordingly.
Data Sapien retweeted
செயற்கை நுண்ணறிவியல் நுட்பங்களை மாணவர்கள் கற்க விரும்பினால் இலவசமாக மைக்ரோ சாப்ட் வழங்கும் ஏ.ஐ பாடங்களை படிக்கலாம்.
இதோ சுட்டி microsoft.github.io/AI-For-B…
Data Sapien retweeted
Power BI for Data Science Complete Study Plan
10 hours a week to dedicate to this, here's a 12-week study plan
Week 1: Introduction to Power BI
Day 1-3: Begin with the official Power BI Guided Learning resources to get familiar with the platform.
Link: learn.microsoft.com/en-us/tr…
Day 4-7: Watch the "Getting Started with Power BI" series
Link: youtube.com/watch?v=Vqz2d7pT…
Week 2: Data Loading and Transformation
Day 1-4: Explore the Power Query Editor and learn how to load and transform data.
youtube.com/watch?v=TF0sGXS0…
Day 5-7: Watch the tutorial on data transformation in Power BI
youtube.com/watch?v=PiFAa_jj…
Week 3: Building Visualizations
Day 1-4: Dive into creating basic visualizations like tables, charts, and maps using the official documentation.
[youtube.com/watch?v=Df81TjRV…!)
Day 5-7: Watch tutorials on creating all the visuals
youtube.com/watch?v=GYpiIsf7…
Week 4: Advanced Visualizations
Day 1-4: Explore the advanced Power BI tutorials
youtube.com/watch?v=ppD-jKqs…
Day 5-7: Watch tutorials on including custom visuals and slicers.
Customer Visuals: youtube.com/watch?v=x_tSlWhF…
Slicers: youtube.com/watch?v=-xl-uhgz…
Week 5: Data Modeling and DAX
Day 1-4: Learn about data modeling and the DAX language
Dax: youtube.com/watch?v=waG_JhBg…
Data Modelling: youtube.com/watch?v=1Z_f6jkj…
Day 5-7: Watch DAX tutorials on Power BI's YouTube channel.
youtube.com/watch?v=sCAQtqHI…
Week 6: Dashboard Design, Publishing And Project
Explore dashboard creation, Design, and publishing options in Power BI.
Design: youtube.com/watch?v=Lfzu74XD…
Publish: youtube.com/watch?v=KpZPUdzN…
Project: youtube.com/watch?v=pixlHHe_…
Throughout your study plan, remember to practice what you learn by working on personal projects or datasets related to your data science field.
- - -
That’s all for now!
- Smash the LIKE button and REPOST
- BOOKMARK because you’ll definitely want to revisit this again
- Follow me for more posts like this
Data Sapien retweeted
Inferential Statistics is used to Test Hypotheses
At its core, hypothesis testing involves assessing the validity of a proposed hypothesis by evaluating sample data.
It’s often employed to make informed decisions based on available evidence.
The process typically begins with formulating two distinct hypotheses: the null hypothesis (H0) and the alternative hypothesis (H1).
The null hypothesis represents the absence of any significant effect or difference, while the alternative hypothesis suggests the presence of a notable effect or difference.
These hypotheses serve as the foundation for statistical inference.
Subsequently, a relevant statistical test is selected based on the nature of the data and the research question at hand.
Some of the prominent tests include the t-test, ANOVA**(Analysis of Variance), Chi-squared test, Regression analysis, etc.**
This chosen test generates a test statistic, which quantifies the extent to which the observed data aligns with the expectations set by the null hypothesis.
By comparing the test statistic to a critical value or calculating a p-value, data scientists can make informed decisions about the hypotheses.
A p-value is a crucial metric in hypothesis testing, representing the probability of observing data as extreme as, or more extreme than, the data actually obtained under the assumption that the null hypothesis is true.
A small p-value indicates strong evidence against the null hypothesis, prompting researchers to consider the alternative hypothesis as a more viable explanation for the observed data.
It is important to establish a significance level (often denoted as alpha) before conducting hypothesis testing.
This significance level sets the threshold for determining whether the obtained p-value is sufficiently low to reject the null hypothesis.
A lower significance level corresponds to a more stringent criterion for rejecting the null hypothesis.
Its blend of structured statistical methods and critical thinking fosters accurate decision-making, making it an indispensable tool within the toolkit of a discerning data scientist.
---
That’s all for now!
- Smash the LIKE button and REPOST
- BOOKMARK because you’ll definitely want to revisit this again
- Follow me for more posts like this
Data Sapien retweeted
My 9 favorite websites to practice coding exercises until you're a MASTER:
9. Mode (SQL)
8. DataLemur (SQL)
7. LeetCode (Python)
6. Codewars (Python)
5. Stratascratch (SQL)
4. HackerRank (Python)
3. Kaggle (Data Science)
2. W3 Resource (pandas)
1. bnomial (Machine Learning)
Data Sapien retweeted
"I will finish my DATA ANALYTIC course in 2months then secure a job in the 3rd month"
SQL:
