AI Powered Data Analytics Mastery - AI Tools & Vibe Coding

Transform raw data into actionable insights through cleaning, preparing, and structuring, addressing data quality issues. Tell a data-driven story with visuals in reports and dashboards for stakeholders.

Learn storytelling with data using Power BI to compare case one and case two profits and sales, clean and transform data, and explain insights to stakeholders.

Explore how data analytics collects, cleans, structures, and models department data to reveal insights and guide KPI-driven decisions across sales, marketing, HR, IT, and more.

Gain an overview of data analysis tools, from SQL for querying and transforming data to reporting. See how Python, Excel, Power BI, Tableau, and Snowflake fit into AI-driven analytics.

Master the data analysis process—from data gathering and cleaning to modeling, reporting, and dashboard creation—automating refresh, securing access, and sharing insights with stakeholders.

Define artificial intelligence and generative AI, and show how they automate data processing. Illustrate how generative AI creates reports, summaries, SQL queries, and visualizations for data analysts.

Explore generative AI basics and learn how tools like ChatGPT, grok, N810, Lucidchart, and Copilot accelerate data analytics work from coding and DAX and Excel tasks to KPI planning.

Explore how generative AI, a subset of deep learning, creates new content, from text to code, enabling data analytics tasks like automated EDA reports and no-code project automation.

Demystify generative AI in layman's terms by showing how prompts drive responses from front-end tools like ChatGPT, using large language models trained on trillions of data.

Explore a comprehensive set of generative AI tools for data analytics, including ChatGPT, Grok, and GitHub Copilot, with alternatives like Polycom, N8N, and Lucidchart.

Explore the basics of natural language processing and how computers transform free text into structured data, enabling translation, sentiment analysis, chatbots, and text summarization.

Explore NLP applications like language translation, sentiment analysis, chatbots, and speech recognition, and understand how generative and predictive AI, plus text summarization, support data analytics.

Explore how tokenization converts documents into textual data, then into numeric vectors using bag of words, stopword removal, and embeddings, enabling vector search and AI explanations.

Identify stop words and remove them to reduce memory usage in NLP tasks. Tailor a stop word list to keep nouns and verbs while filtering out prepositions, pronouns, and articles.

Explore how Bag of Words converts text into numerical vectors, covering stopword removal, lowercasing, and vector representations, and see how vector indexes and embeddings power document understanding.

Part of speech tagging assigns nouns, verbs, adjectives, and adverbs to words, a fundamental NLP task that enables effective applications and chat responses.

Master n-grams, a basic NLP concept of sequences of n words used for pre-processing and next word prediction, with bigrams and three grams guiding model patterns.

Explore the evolution of large language models from statistical approaches to transformers like bert and gpt, and learn how consumer and developer use cases drive tool choices for data analysis.

Explore core LLM concepts, including prompts, inputs, and outputs, and how context windows and chunking determine what the model can process.

Master prompt engineering to craft prompts that elicit accurate, relevant outputs from AI models by applying context, task, persona, format, tone, and examples.

Watch a Grok demo comparing AI chat tools, showing how a data analyst develops KPIs, analyzes relationships, and uses attachments and workspaces for data-driven insights.

Master the key principles of prompt engineering by crafting clear, specific prompts, using structured formatting, and applying iteration and role assignment to refine AI outputs.

Identify common ai prompting pitfalls and apply practical fixes: specify domain and output, avoid overload, respect model limits, and iterate with focused prompts for better analytics.

Master zero-shot prompting and advanced prompt engineering by instructing language models in one go, generating sql queries, python code, and data cleaning steps without examples.

Master few shot prompting, embedding a few task examples in prompts to steer language models toward accurate outputs. See Python and SQL examples that illustrate code generation and query formation.

Master chain of thought prompting, including zero-shot cot and few-shot cot, to teach step-by-step reasoning that clarifies multi-step data analytics problems and improves accuracy and debugging.

Instruction prompting teaches giving a clear natural language instruction without examples to specify the task. It can generate SQL queries, Python code, and other outputs from AI tools.

Explore role-based prompting to tailor ai outputs by assigning roles, calculate average monthly sales growth for product categories in Q2 2025, and extract leadership-ready insights.

Promote ethical prompting to prevent misinformation, harm, and bias by writing fair, unbiased prompts; disclose ai use, respect privacy, and ensure outputs contribute positively to education and well-being.

Learn to download and install Microsoft SQL Server, choose between developer and express editions, install SSMS, connect to the database engine, and run a basic query.

Import data into Microsoft SQL Server by creating a database, importing a flat file from resources, and loading the Global Job Market 2025 dataset for analysis.

Define dataset columns with ChatGPT in Excel, covering job id, title, salary, experience, employment type, company location, remote ratio, and job requirements; plan Power Query data transformations for reporting.

Explore importing data from a Microsoft SQL Server into Excel using AI prompts with ChatGPT, guiding data discovery, connection setup, and loading a dataset into Excel for reporting.

Open Power Query Editor from Excel, enable column profiling, and use ChatGPT to craft prompts for exploring column profile, distribution, quality, and data types.

Learn data transformations in power query editor with ChatGPT guidance: remove the first row, filter NLP engineers, and replace L/M/S with large/medium/small, then close and load.

Design a dashboard with key performance indicators, chart recommendations, and slicers, using chatgpt to derive insights from data columns for visuals like salary by job title and industry postings.

Format a bar chart in Excel with ChatGPT guidance to remove field buttons, gridlines, and legends, then add data labels and rename the chart to 'average salary by job title'.

Create a column chart from a pivot table showing number of jobs by industry, format by removing legend and gridlines, and add data labels titled 'Number of jobs by industry'.

Create a pivot table using benefit score as the average and company size as rows, then visualize with a stacked column chart labeled average benefit score by company size.

Represent the remote ratio distribution across job titles with a pivot table, compute average, and visualize using a pie or donut chart, then add data labels and callouts for clarity.

Learn how to add and format a line chart in Excel to visualize the average years of experience by education level, using a pivot table and custom data labels.

Create a dashboard by assembling charts on a new sheet, add slicers, and use ChatGPT for step-by-step guidance to sync slicers so all charts filter together.

Install MySQL server and MySQL Workbench on Windows with a custom install, configure the port and root password, then create databases and tables and run basic queries for Power BI.

Import data into MySQL Workbench using the table data import wizard, creating and using a database, and reviewing the AI tools usage data table.

Import data from MySQL and Microsoft SQL server into a prompt two database, run selects, and prepare to combine and append data in Excel with grok for reporting.

Learn to import data from MySQL and SQL Server into Excel using get data from databases, including configuring ODBC when needed, loading tables, and appending datasets for reporting.

Learn to append two data sources into a single data set using Power Query Editor in Excel, ensuring matching columns and preparing data for reporting.

Hide nonessential tabs to focus on reporting data, then generate column definitions and dataset descriptions with grok prompts for ai tool usage in education.

Explore KPIs and charts for a data set with grok: average daily usage hours, most popular AI tools, impact on grades, professor approval rate, and awareness of AI tools.

Explore how to use grok to craft prompts and generate a step-by-step guide for analyzing column quality, profile, and distribution in Excel data with Power Query Editor.

Learn to clean data by replacing null and blank states with unknown, using grok to suggest steps, and applying changes in Excel with replace values and load operations.

Create and format a bar chart in Excel using a pivot table to show average daily usage by tools, with data labels and clean formatting for KPI dashboards.

Create and format a pie chart in Excel from a pivot table to visualize the popularity of AI tools, using data labels, callouts, and legend tweaks.

Analyze how different AI tools affect grades by creating a pivot table in Excel and visualizing the average impact with a bar chart.

Clean and transform data by converting values to text and replacing true with yes and false with no, then create a clustered bar chart for professor approval of AI tools.

Add a radar chart as per grok's recommendation to visualize average awareness of AI tools using a pivot table, and name the chart 'average awareness by tool'.

Explore data analysis using perplexity to generate insights, define columns, identify data cleaning issues, and propose KPIs and dashboard charts for a medical insurance dataset.

Explore a client interview scenario using perplexity to prepare banking data dashboards with Power BI and Tableau, covering data gathering, integration, cleaning, modeling, reporting, and banking KPIs.

Download and install Microsoft SQL Server developer edition for practice, install SQL Server Management Studio, connect to the database engine, and run a sample select statement.

Explore how to generate SQL queries with AI tools like perplexity, create and populate a table, and perform basic select, filter, sort, and update operations in Microsoft SQL Server.

AI tools like Perplexity troubleshoot and correct erroneous SQL code in MS SQL Server. Fix syntax, quotes, and grouping and ordering issues to produce a working query.

Explore how ai tools help convert sql code from mysql to sql server, addressing syntax differences, including top three highest paid employees, autoincrement, and database setup across platforms.

Explore a smartphones data set in SQL Server with perplexity AI prompts to import, describe table structure, view top ten records, and clean nulls and duplicates.

Learn to write SQL queries that replace null ratings with the average, back up tables before updates, and update the data set in one step for efficient data cleaning.

Explore replacing nulls in the fast charging column with the mod of remaining values using a common table expression in SQL Server, via perplexity prompts, updating 211 records.

Demonstrates moving data between test databases with sql, importing from excel, creating new tables, and filtering names starting with t while trimming spaces; ai tools aid debugging.

Explore SQL joins with Perplexity AI, including left, right, full outer, inner, and self joins. See examples with customers and orders, and note SQL Server versus MySQL handling nulls.

Explore date functions in MySQL Workbench and SQL Server, including current date and time, extracting date parts, adding or subtracting dates, calculating days between dates, with practical SQL examples.

Learn common text functions in SQL Server, including len, left, right, substring, and upper and lower, with practical examples and a MySQL vs. SQL Server comparison.

Explore number functions in SQL Server and MySQL with examples, covering absolute, ceiling, floor, round, power, square root, log, degrees, and radians, and syntax comparisons between SQL Server and MySQL.

Learn to create a stored procedure to transfer data from a source to a destination database each month using perplexity AI, with dynamic columns and identity insert handling.

Learn to use perplexity to generate SQL queries in SQL Server Management Studio, answering questions about the Indian kids screen time dataset—averages by age and gender, device usage, urban-rural trends, and health impacts.

Demonstrate how AI tools generate SQL to append two tables using union all, create a combined table, and add a nullable description column to unify four columns.

Install Python with Anaconda, create a new conda environment, and install numpy, pandas, and Jupyter; run a hello world in Jupyter and explore AI tools for data cleaning and analysis.

Explore basic Python programs generated with an AI tool like Perplexity, including the sum of two numbers, factorial, HCF and LCM, explained line by line and run in Jupyter Notebook.

Explore the difference between a pandas series and a data frame using perplexity, with practical, minimal theory and hands-on examples in Python and Jupyter notebook.

Explore how to perform left, right, inner, and self joins in pandas using two data frames, with code examples and outputs illustrating matched and missing values.

Learn to read Excel sheets with pandas, append two data frames using pd.concat, and remove duplicates with drop_duplicates for clean data.

explore how perplexity reads a csv into a pandas data frame and generates Python code to understand data, using df.head, df.info, describe, and missing value checks in a Jupyter notebook.

Leverage perplexity to generate Python programs that answer data questions from a CSV in a Jupyter notebook, computing average daily screen time by age and gender, and health impacts.

Learn to profile data with the Perplexity data profiling library, install via conda, resolve Python version issues, generate a profile report in Jupyter, and save an HTML summary.

Learn data cleaning in python with pandas, reading a csv, trimming spaces, renaming city to city 11, splitting electric range, and boosting base msrp by 10%.

Explore data visualization with perplexity, install matplotlib and seaborn, load a dataset in Jupyter Notebook, and generate bar, line, pie, scatter, and tree map charts using a Python script.

Create an insurance data frame using Python with Perplexity, build KPI charts, and export a pdf report. Clean data and derive insights on smoking, age, and BMI driving charges.

Build a banking data frame in Python, explore with Jupyter notebook, clean data, and export five KPI charts: bar, line, scatter, pie, and doughnut to a PDF report.

Learn how to fix Python scripts with syntax errors by using AI tools to diagnose issues in Jupyter notebook, correct definitions, indentation, and type errors, then test the rectified code.

Download, install, and launch Power BI Desktop, selecting language and completing the setup. Create reports with visuals and relationships, save as pbix, and publish to the Power BI service.

Create a free Power BI account with your organizational account, activate the free trial, and prepare to publish Power BI reports to this account.

Import data from a flat file into SQL Server for a Power BI project, create the PBI one database, and load dbo.diamonds for KPI reporting with AI tools guidance.

Learn how to define data columns and use perplexity to generate KPIs for a two-page Power BI report. Build visuals using DAX and SQL queries on the Debo Diamonds dataset.

Import data from Microsoft SQL Server into Power BI Desktop using Get Data and Import connectivity mode, then load and preview the diamonds table for analysis.

Explore data in Power Query Editor within Power BI, assess column quality, column profile, and column distribution, clean nulls via perplexity, replace values, and apply changes.

Learn to create a card visual in Power BI that displays the average diamond carat using a DAX measure, format the card, and apply filters for clarity to analyze averages.

Create a column chart in Power BI Desktop to show distribution of cut grades by color using a DAX measure. Format the chart with clear axes, colors, and data labels.

Create a new measure using DAX to compute the average depth from the diamonds table, then display it with a card visual in Power BI desktop, preserving formatting.

Create a scatter plot in Power BI showing carrot versus price, placing carrot on the x axis and price on the y axis, and customize gridlines, the title, and colors.

Learn to analyze a scatter plot with Perplexity AI, extract insights on price and carat, and obtain data-driven recommendations from AI tools for Power BI reports.

Create a second Power BI report page and visualize the average price with a card visual, building an average price measure and enabling basic depth filters.

Create a heat map in Power BI Desktop using the matrix visual, drag color to rows and the average price to values, then apply conditional formatting.

Create a Power BI bar chart showing the average price by clarity using the existing DAX measure, then format colors, data labels, and axis options to enhance readability.

Create a histogram in Power BI Desktop by loading data, creating bins with a chosen bin size, and formatting axes, labels, and grid lines.

Create table from a DAX expression in Power BI, format a table visual with carat, price, and color, set don't summarize, and sync length, width, and height slicers across pages.

Publish a Power BI report to the service by creating a free Power BI account, naming the report, and signing into a workspace to view multi-page reports.

Create a 10,000-record banking data set with perplexity and SQL server to power a two-page Power BI report, including data cleaning, DAX measures, and KPI prompts.

Standardize date formats across accounts, customers, and transactions with SQL update statements to mm dd yyyy, guided by perplexity for accurate data cleaning.

Combine the transactions, accounts, and customers tables using left joins to create a single dataset for Power BI analysis. Identify columns, generate SQL, and handle nulls when merging.

Connect to SQL Server and import the combined banking dataset into Power BI Desktop, load data, preview results, and identify null values for cleanup in preparation for KPI insights.

Explore KPI and DAX recommendations in Power BI using perplexity for a two-page banking report: overall banking performance and customer profile; visuals include card, donut, bar, histogram, treemap.

Learn data cleaning in Power Query Editor: replace nulls with unknown, normalize currency, and convert dates to date type for a clean reporting-ready data model.

Use Power Query Editor to set locale-based date types for the remaining date columns, including open date, DOB, and transaction date, then load and review in table and report views.

Create a pie chart or stacked column chart to show the number of transactions by transaction type, using a DAX measure in Power BI and the provided perplexity dataset.

Create a monthly transaction amount chart in Power BI by building a DAX measure to sum transactions, plotting months on the x axis, and applying formatting and data labels.

Identify top two customers by transaction amount in Power BI desktop using a bar chart, replacing blanks with unknown and filtering by the sum of amount.

Create a total balance by account type in Power BI using a DAX sum of the balance column, visualized as a clustered bar chart.

visualize inactive accounts in the last 90 days by year and month on the first report page using a line chart or table, with a new measure and step interpolation.

Create a second report page with a donut chart for customer count by gender using a distinct count DAX measure, and format it to match the first page pie chart.

Create Power BI Desktop visuals showing the distribution of customers by age group with a column chart or histogram, using DAX to derive customer age and age group.

Learn to add a treemap visual to a Power BI report, rename charts, and format visuals to display account type and account count by type alongside a column chart.

Add and customize remaining charts in a Power BI report, including total balance by name and monthly transaction balance, adjust data fields, labels, filters, colors, and prepare for publishing.

Publish the report to Power BI service, save as Power BI banking, and publish to your workspace, then explore interactive filtering across the two report pages.

Explore the DAX module, learn over 40 DAX functions without AI tools, and practice generating and correcting DAX formulas using AI tools, with parallels to SQL and Python error rectification.

Master DAX in Power BI to build date tables, calculations, and measures. Learn calendar, month, weekday, week num, format, concatenate, left, right, len, and mid functions.

Explore essential DAX aggregate functions in Power BI, including sum, min, max, average, count, product, and their x variants with filter and or conditions on the date table.

Master essential DAX functions, compare sum and sumx, and control calculations with calculate and calculate table, using all, all selected, and all except contexts.

Master essential DAX functions in Power BI by building measures in a measures table and visualizing results with card visuals, covering and, or, not, if, date diff, and switch.

Learn to apply the same period last year DAX function to compare total profit, total MTD, total YTD, and total QTD using a calendar table and DAX measures.

Explore DAX functions total MTD and total YTD in Power BI by building a calendar table, creating a profit measure, and calculating cumulative totals by day, month, quarter, and year.

Learn to use AI tools to learn DAX, generate data, create a calendar table in Power BI desktop, and derive month names, week names, and week numbers with DAX expressions.

Rectify incorrect DAX expressions using AI tools. The lecture demonstrates loading a CSV in Power BI, building a measure to sum products of two columns, and comparing some and SUMX.

Explore the basics of Microsoft Fabric, an end-to-end analytics platform that unifies data movement, processing, ingestion, transformation, and reporting, with Power BI integration.

Learn to create a Microsoft Fabric organization account with a work email, resolve access hurdles, and set up domain-based mail to access Fabric during the 60-day trial.

Create and manage a Microsoft Fabric workspace, assign admins, members, and viewers, and explore connecting Fabric with Power BI and creating lake houses, data flows, and other data sources.

Explore how lakehouse unifies data lake and data warehouse concepts, covering data sources, governance, cost, and performance, with practical startup steps for creating a lakehouse.

Explore lakehouse architecture, from diverse data sources and ingestion to transformation, storage, and consumption, and see how Power BI connects via direct links or SQL endpoints.

Create and configure a lakehouse, upload sales data, load it to a table, and connect to Power BI using fabric lakehouse connection for data exploration and visuals.

Create a sales sql database inside a fabric lake house, build a customer table, load data, and connect the sql database to Power BI through a data flow.

Explore how fabric data flows enable centralized data preparation, transformation, and scheduled refresh, connecting lakehouse data with Power BI via data flows for reusable, enterprise-ready analytics.

Explore kql, the kusto query language for log and telemetry data in fabric and adx. Learn its readability, time series analysis, inbuilt aggregations, custom functions, and the pipe operator.

Explore how KQL enables read-only log and telemetry data analysis in Azure Data Explorer, highlighting its edge over SQL for querying mixed structured, unstructured, and semi-structured data.

Master practical KQL basics, translating sql with explain. Craft select, where, top, order by, and between timestamp queries using is null and is not null.

Demonstrate wild card operations and the like operator in kql and sql, and explain group by, having, summarize, and sorting with nested and join queries.

Master nested queries in KQL by mirroring SQL style subqueries, using the hyphen explain command to generate SQL, and leveraging grok or ChatGPT to produce KQL equivalents.

Explore KQL join operations, including inner, left, right, and outer joins, by linking authentication events and employees on username, and build practical select queries with user agent projections.

Learn KQL capabilities beyond SQL by aggregating authentication events hourly, counting failed versus successful logins, and visualizing with line, pie, and bar charts.

Learn to integrate KQL with Power BI by creating a KQL query set in Azure Data Explorer fabric, linking a KQL database to Power BI, and building dashboards.

Enable Microsoft Copilot for Power BI and Fabric by configuring admin settings, creating an F2 fabric capacity, and linking your tenant for seamless AI-assisted data analytics.

Enable Copilot on Fabric in Power BI by creating a new workspace aligned with Fabric capacity, then explore Copilot’s ability to generate a customer demographics report from linked datasets.

Explore seven Copilot use cases in Power BI, including generating descriptions for measures, Dax, natural language tweaking, studying Dax, report creation, narrative visual, and chat with data.

Explore how Copilot accelerates Power BI data modeling by creating relationships, building a total orders measure, and auto-generating descriptions to clarify DAX in a collaborative workspace.

Demonstrate the new DAX query view in Power BI desktop, write and run DAX queries with Copilot, and validate results to identify the channel with the highest total orders.

Learn how to use copilot to generate and adjust a query that displays the distribution of total orders per year for the wholesale channel, and validate the results.

Explore DAX functions with Copilot and ChatGPT, including total YTD and the difference between SUM and SUMX. Learn about row level security and weekly refresh options in Power BI.

Explore how narrative visuals on a product analysis page summarize data with copilot, revealing total sales by product and unit price by product, powered by GPT.

Power BI copilot lets you chat with your data to answer questions and create visuals, while highlighting data privacy and upload size limits.

Learn to rapidly build an ai-powered power bi report with copilot and fabric by setting up an organization account, enabling copilot, and creating dashboards with narrative insights.