Class 01 – SQL – Main Clauses (SELECT, FROM, WHERE, GROUP BY, HAVING, ORDER BY) | Order of Operations | Commenting Queries | AS Keyword | TOPN Keyword

Class 03 – SQL – Text Functions (UPPER, LOWER, REPLACE, CHARINDEX, SUBSTRING) | DECLARE, NVARCHAR, SET Keywords | Conditional Functions (AND, ISNULL, IN, BETWEEN. LIKE, IFF, OR)

Class 04 – SQL – Conditional Functions (ISNULL, COALESCE, CASE, WHEN, THEN, END) | CAST Function

Class 05 – SQL – Theory (DBMS Vs RDBMS, SQL Server, Instances, Databases, Data Security, Type of Database Systems) | Data Normalization | Fact Tables vs Dimension Tables | Relationship and Keys | Star vs Snowflake Schema | ER Diagram | JOINS Theory (INNER, RIGHT, LEFT, FULL)

Class 06 – SQL – JOINS (INNER, RIGHT, LEFT, FULL) | VIEWS | UNION | UNION ALL | Sub Queries (Single, Multi Rows, Correlated, Table) | Common Table Expression CTE | CRUD (CREATE, READ, UPDATE, DELETE) | INSERT INTO | UPDATE | DELETE | Window Functions (RANK, OVER, PARTITION BY)

Class 07 – Basics of Python (Punctuations, Mathematical Operators, Brackets and Craces, Logical and Comparison) | Syntax and Semantics | Conditional Statement | Python Variables (Variables, Declaring and Assigning Variables, Naming Conventions, Types) | Practical Examples and Common Errors

Class 08 – Fundamental Data Structure in Python | List (Creating, Assessing, Modifying) | List (Insert, Remove, Pop, Random, Append) Functions

Class 09 – Data Types (Integers, Floating, Point Numbers, Strings, Booleans) | Advanced Data Types (Lists, Tuples, Sets, Dictionaries) | Operators (Arithmetic, Comparison, Logical) | Conditional Statements (IF, ELIF, ELSE) | Practical Example – Employees Bonus Calculator

Class 10 – Loops (For Loop and While Loop) | Iterating over Range | Iterating over String | Loop Control Statements (Break, Continue, Pass) | Nested Loops | Data Structure (List, Tuples, Sets, Dictionaries) | List Comprehension | Practical Example (Managing a To-Do List)

Class 11 – List Practical Examples (Managing an Inventory, Collecting Feedback) | Data Structure (Tuples) – Creating, Assessing and Operations | Mutable vs Immutable Tuples | Methods | Packing and Unpacking Tuples | Nested Tuples

Class 12 – Data Structure (Dictionaries) – Creating, Assessing and Modifying | Methods | Looping over Dictionaries | Nested Dictionaries | Dictionaries Comprehensions | Functions (Introduction to Functions, Defining Functions, Calling Functions, Parameters, Variable-Length Arguments, Return Statements)

Class 13 – Lambda Map Filter | Palindrome | Recursion | Lambda Functions | map() Function | filter() Functions

Class 14 – Importing Modules in Python: Modules and Package | Custom Packages | Standard Libraries | File Operations | Working with File Paths | Object Oriented Programming (OOP)

Class 15 – OOP Basics (Classes and Object / Instance variables and instance methods), Inheritance Python (Single Inheritace / Multiple Inheritance), Polymorphism: Method Overriding

Class 16 – Polymorphism: Functions and Methods | Polymorphism (Override – ABC) | Encapsulation (Public and Private Variable, Protected Method) and Abstraction | Magic Methods | Operation Overloading

Class 17 – Visualization with Python | Data Visualization with Matplotlib | Data Visualization with Seaborn | Pakistan Covid-19 Visual Analysis

Class 18 – Visualization in Python | Data Visualization with Matplotlib (Line, Bar, Histogram, Pie, Scatterplot) | Pandas with Matplotlib for Analysis and Visualizing | SeaBorn for Advanced Visuals (BoxPlot, BarPlot, VoilinPlot, PairPlot, Heatmap) | Pakistan Covid-19 Visual Analysis

Class 19 – Project: Car Price Prediction – Analyzing Data and Predicting Car Price using Pandas, NumPy, Matplotlib, SeaBorn, SkLearn (Data Manipulation and Pre-processing, Visualizing Dataset) | ExtraTreesRegressor | Random Forest Regressor

Class 20 – Project: Car Price Prediction (Advance Visualization) | Prediction Model Training | Hyperparameter Tuning | Predictions (RandomizedSearchCV)

Class 21 – Project: Car Prediction (Finalizing) | Natural Language Processing (NLP): Introduction | Tokenizing and Basic Terminology | Corpus and Documents | Vocabulary | Words

Class 22 – Roadmap to Natural Learning Processing (NLP) – Discussing Theories, Concepts and Practical Implications | Tokenizing and Basic Terminology | Corpus and Documents | Vocabulary | Words

Class 23 – Tokenization | Stemming in NLP (Porter Stemmer, Lancaster Stemmer, Snowball Stemmer, Lovins Stemmer, Feature Stemming Lemmatization) | RegeXp Stemmer | Snowball Stemmer | Wordnet Lemmatizer | Stopwords | Parts of Speech Tagging

Class 24 – Bag of Words Technique | Tokenized Text into Individual Words (Tokens) | Built Vocabulary of Unique Tokens in Corpus | Converted Documents into Numeric Vectors Using CountVectorizer | Created and Analyzed Document–Term Matrix (Documents as Rows, Token Counts as Columns) | Explored Impact of Stop-Words and N-Grams on Feature Size and Model Performance

Class 25 – Named Entity Recognition (NER) | Introduced Concept of Entities (PERSON | ORG | LOC | etc.) | Loaded Pre-Trained spaCy Model and Applied on Sample Sentences | Visualized Entities Using spaCy’s displaCy Renderer | Added Custom Entities via Pattern Matching | Discussed Evaluation Metrics: Precision | Recall | F1 Score for NER

Class 26 – SMS Spam Collection Dataset Analysis | Loaded Dataset into DataFrame | Cleaned and Preprocessed Text (Lowercasing | Removing Punctuation) | Vectorized Messages Using TF-IDF | Trained Classifier (Multinomial Naive Bayes) to Distinguish Spam vs. Ham | Evaluated Model Using Accuracy Score | Confusion Matrix | Classification Report

Class 27 – Artificial Neural Network (ANN) Project Initiation | Defined Feedforward Neural Network Architecture (Input | Hidden | Output Layers) | Selected Activation Functions (ReLU | Sigmoid) and Loss Function (Binary Crossentropy) | Compiled Model with Optimizer (Adam) and Accuracy Metrics | Trained Model Using model.fit() with Epochs | Batch Size | Training/Validation Split | Plotted Loss and Accuracy Curves to Monitor Training and Detect Overfitting

Class 28 – Artificial Neural Networks (ANNs) vs Recurrent Neural Networks (RNNs) | Forward Propagation | Backward Propagation | Project: Churn Prediction (Creating Environment, Installing Libraries)

Class 29 – Artificial Neural Network (ANN) Project: Feature Engineering | Understanding Activation Function, Dense, Sequential Network | Model Training: First Step for Finding Parameters in Model Training

Class 30 – Artificial Neural Network (ANN) Project: Churn Prediction – Building ANN Model, Compiling and Training the Model, Tensor Board Visualization (Dense, Sequential , EarlyStopping, TensorBoard, Optimizers, Loss Function, Epoch Accuracy, Keras/.h5, Logs)

Class 31 – Artificial Neural Network (ANN) Project: Churn Prediction – Finalizing and Deploying the Model

Class 32 – Artificial Neural Network (ANN) Project: Hardcoded Inputs for Predictions | Created App.py for Deploying Project on Testing Environment on StreamLit | Deployment on GitHub and on Live Environment

Class 33 – Project – Salary Prediction using Regression (Data Understanding + Clarity Overall) | LSTM RNN (Overview + Architecture + Forget Gate Understanding)

Class 34 – Recurrent Neural Network (RNN) – Long Short-Term Memory (LSTM) | LSTM RNN Architecture | Forget Gate | Input Gate / Candidate Memory | Output Gate

Class 35 – End to End LSTM RNN GRU RNN Project – Next Word Prediction using LSTM GRU RNN Model: Data Collection | Data Preparation and Pre-Processing | Model Building | Model Training | Model Evaluation | Deployment

Class 36 – Introduction to Generative AI | Understanding Differences Between AI | ML | DL | Generative AI | Overview of Large Language Models (LLMs) | Training Processes of OpenAI’s ChatGPT and LLaMA 3 | Supervised Fine-Tuning Explained | Evolution of AI Models | Deep Dive into LangChain Ecosystem | Beginning Creation of Virtual Environments for LangChain Development

Class 37 – Building LLM Applications with LangChain Expression Language (LCEL) | Using Language Models Effectively | Utilizing PromptTemplates and OutputParsers | Chaining Components with LCEL | Structuring Model Inputs via Human and System Messages | Extracting Content Using Output Parsers Instead of Raw AI Responses | Combining Multiple Components with LCEL | Simplifying and Structuring Inputs Using Prompt Templates

Class 38 – Building an LLM-Powered Chatbot Using LangChain | Implemented Message History to Retain Previous User Interactions | Managed Session IDs to Separate Conversations | Integrated Components into a Working Example Demonstrating Conversation Context Storage | Used Prompt Templates to Format Raw User Input for LLM Processing | Incorporated System Messages with Custom Instructions | Handled Input Variables Effectively | Combined Message History and Prompt Templates for Session-Based Interaction

Class 39 –

Class 40 –

Class 41 –

Class 42 –

Power BI (Class 01) – Introduction of Power BI | Basics of Power Query | ETL | Basic Transformations in Power Query – Replace Value, Deleting Columns, Extract with Delimiter

Power BI (Class 02) – Text Functions (Format Columns, Merge Columns, Split Columns) | Number Functions (Standard, Statistics, Rounding) | Basic Group By | Column Profiling, Quality and Distribution

Power BI (Class 03) – Date Tools (Year, Month, Day, Start of Month) | Categorical vs Time Series Analysis | Conditional Column | Column from Example | Orders of Operations

Power BI (Class 04) – Merge Queries | Appending Queries | Appending by Folders | Advanced Group By | Parameters

Power BI (Class 05) – Data Modelling | Star & Snow Flake Schema | Data Formatting

Power BI (Class 06) – DAX – Calculated Columns | Text Functions (UPPER, LOWER, CONCATENATE, LEFT, RIGHT, LEN, FIND, SEARCH, SUBSTITUTE) | Date Functions (DATEDIFF, DATEADD, YEAR, MONTH, DAY)

Power BI (Class 07) – DAX – Calculated Columns | Date Functions (WEEKDAY, WEEKNUM, NETWORKINGDAYS) | Logical Functions (IF, Nested IF, OR, AND, SWITCH) | Conditional Operators

Power BI (Class 08) – Advanced SWITCH Function | MID Function | Measures | Implicit vs Explicit Measures | Filter Context | Filter Flow | Aggregation Functions (SUM)

Power BI (Class 09) – Aggregation Functions (SUM, COUNT, COUNTROWS, AVERAGE, DISTINCTCOUNT, DIVIDE, MAX, MIN) | Filter Modifier Function (CALCULATE Function)

Power BI (Class 10) – CALCULATE Function | ALL Function | FILTER Function | Iterator Functions (SUMX, COUNTX)

Power BI (Class 11) – Time Intelligence Functions (DATESYTD, DATESMTD, DATESQTD, DATEADD, DATESINPERIOD, DATESBETWEEN) | IFERROR | IS Functions (ISBLANK, ISNUMBER, ISTEXT)

Power BI (Class 12) – Power BI Visual – Card Visual | Line Chart (Forecasting, Reference Line, Trend) | Bar Chart

Power BI (Class 13) – Power BI Visuals – KPI Charts | Pie and Donut Chart | Table and Matrix Visuals | Filters (Basic, Advanced, TOPN) | Filters on Card Visual

Power BI (Class 14) – Power BI Visual – Slicers | Area Chart | Guage Chart | Conditional Formatting | Drill Through and Cross Filter | Multi-Row Card Visual | Tooltips | Buttons | Bookmarks

Power BI (Class 15) – Variables in DAX | Iterator Function (RANKX for Dynamic TOPN Rankings) | Advanced RANKX Function | Create Table

Power BI (Class 16) – Maven Roasters: Rounding Functions (INT, ROUND, ROUNDDOWN, ROUNDUP, MROUND, TRUNC, FIXED, FLOOR, CEILING) | Information Functions (ISBLANK, ISNUMBER, ISTEXT, ISLOGICAL) | Conversion Functions (CURRENCY, FORMAT, DATEVALUE, VALUE, DATE, TIME)

Power BI (Class 17) – CALCULATE Modifier Functions (REMOVEFILTERS, KEEPFILTERS, ALLSELECTED, ALL, ALLEXCEPT)

Power BI (Class 18) – Maven Roasters (SELECTCOLUMNS, ADDCOLUMNS, SUMMARIZE, Case Study (SUMMARIZE)) | Relationship Functions (RELATED, RELATEDTABLES, USERELATIONSHIP, CROSSFILTER) | Automatic Calendar Table | COALESE Function

Power BI (Class 19) – Power BI Service | PL-300 Exam Preparation

Class 43 – Introduction to Concepts of Tools and Agents in LangChain, Defining Tools as External Resources for LLMs, Introducing Agents to Decide Tool Usage and Timing, Discussing Strategies to Enhance Search Engine Capabilities by Fetching and Integrating Real-Time Data, Outlining Deeper Future Implementations

Class 44 – Tool Creation, Custom Tools, Preparing for Agents, Combining LLM with Tool List, Creating Dynamic Agents, Wrapping Agents in AgentExecutor, Building Streamlit UI for User Queries and Groq API Key, Defining Multiple Tools with Dynamic Selection, Executing Queries with Real-Time Chain of thought Reasoning, Handling Errors, Unexpected Results, and Infinite Loops

Class 45 – Generative AI Project: Chat with SQL DB Using LangChain SQL Toolkit and AgentType | Project Demo Walkthrough | Automatic SQL Query Generation Using Agents | Overview of LangChain SQL Toolkit | Created Local SQLite Database | Defined Student Table with Relevant Columns | Connected Database to LangChain SQL Agent | Installed MySQL Workbench | Created Sample Table with 50 Rows | Verified Data Creation | Prepared for Streamlit Integration to Connect MySQL with LangChain and Enable Natural Language Querying via LLM

Class 46 – Chat with SQL DB – End-to-End Streamlit App Development | Built Streamlit App to Support SQLite and MySQL | Resolved Configure DB Function | Integrated User’s DB Choice with SQL Agents | Displayed Queries and Results in Streamlit Chat Interface | Tested Auto-Generated SQL Queries for Both SQLite and MySQL Scenarios

Class 47 – End-to-End Deployment – YouTube and Website Summarization Bot | Installed & Imported Streamlit | Validators | LangChain | YouTube Transcript API | Explained Role of Each Library | Designed UI with Page Title | Icon | Sidebar for Steps | API Key Input | Summary Length Slider | Implemented Input Validation for API Key and URL | Displayed Warnings for Missing/Invalid Inputs | Loaded Content via YouTubeLoader & UnstructuredURLLoader with Error Handling | Integrated ChatGroq LLM with API Key | Created Dynamic PromptTemplate | Ran load_summarize_chain for Summarization | Used Streamlit Spinner for UX Feedback | Displayed Clear Success/Error Messages | Organized Code into Logical Sections with Inline Comments

Class 48 –