AI for Data Analytics & BI

Generative artificial intelligence (AI) focuses on creating models that can generate content such as text, images, or even multimedia. Unlike discriminative models that classify or label existing data, generative models operate by learning patterns from the provided data and producing novel outputs. You'll begin this course with an overview of generative. You will explore some notable examples of generative models, including OpenAI's ChatGPT and Google Bard. Next, you will look at the use of prompt engineering when interacting with AI chatbots. Then, you will then delve into the history and evolution of generative AI models including important milestones that culminated in the conversational agents that we work with today. Finally, you will explore the risks and ethical considerations associated with generative AI, such as unintentional use of copyrighted data, the use of personal data for training, and the creation of malicious deepfakes using AI. You will also learn how you can mitigate some of these risks while working with generative technologies.

Generative Pre-trained Transformer (GPT) models are advanced artificial intelligence (AI) systems designed to understand and generate human-like text based on the information they've been trained on. These models can perform a wide range of language tasks, from writing stories to answering questions, by learning patterns in vast amounts of text data. In this course, you will dive into the world of GPT models and the foundational models that are pivotal to the development of the GPT-n series. You will gain an understanding of the terminology and concepts that make GPT models outstanding in performing natural language processing tasks. Next, you will explore the concept of attention in language models and explore the mechanics of the Transformer architecture, the cornerstone of GPT models. Finally, you will explore the details of the GPT model. You will discover methods used to adapt these models for particular tasks through supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), and techniques such as prompt engineering and prompt tuning.

This course will demystify the world of artificial intelligence (AI) and machine learning (ML), taking you from foundational concepts to practical applications. You'll learn to distinguish AI and ML, explore how algorithms learn, and perform common tasks like classification and clustering. You will begin by learning to confidently distinguish between the broad umbrella of AI and the specific subset of ML, understanding how each contributes to the landscape of intelligent systems. Next, you'll explore the milestones that shaped AI. Then you will discover how to classify the diverse approaches of machine learning. Finally, you will explore the practical aspects of common machine learning problems. You'll learn the meaning of regression, classification, and clustering and how they're applied in real-world scenarios. Discover how to evaluate model performance and explore the workings of popular traditional models like linear regression and decision trees. You'll also be introduced to ensemble learning, where the "wisdom of the crowds" fuels even more accurate predictions.

Deep learning and neural networks have revolutionized various fields by enabling computers to automatically learn complex patterns from data. This led to breakthroughs in areas such as image recognition, natural language processing (NLP), and autonomous driving. In this course, you will compare and contrast traditional machine learning (ML) and deep learning models. You will see how deep learning models excel in automated feature extraction from raw data, tackling complex tasks with the power of vast datasets. You will explore the fundamental unit of deep learning, the neuron, and understand how it works. Next, you will explore the diverse neural network architectures designed for specific data types. You will learn how convolutional neural networks (CNNs) extract features from images and how recurrent neural networks (RNNs) are able to extract relationships in time-series data. Finally, you will explore how neural networks handle natural language processing. You will learn how attention-based models help models focus on crucial parts of the input data for enhanced predictions and how generative adversarial networks (GANs) work. You will also explore reinforcement learning, a machine learning technique where agents navigate uncertain environments to maximize rewards.

Generative artificial intelligence (GenAI) can create new content, such as text, images, and music. It is powered by machine learning (ML) models that have been trained on massive datasets of existing content. Prompt engineering is the process of designing and crafting prompts that guide generative AI models to produce the desired output. You will start this course by learning how you can leverage prompt engineering to improve your day-to-day and work-related tasks. Next, you will see examples of prompting in action with external generative AI chatbots such as ChatGPT, Google Bard, and Microsoft Bing Chat. As several of these tools may not be supported on many corporate devices, you will not be expected to create accounts on those platforms, but you will be able to apply the learnings and principles to any corporate conversational AI chatbot in similar ways.

Different types of prompts serve distinct purposes when interacting with language models. Each type enables tailored interactions, from seeking answers and generating code to engaging in creative storytelling or eliciting opinions. In this course, you will learn the four elements of a prompt: context, instruction, input data, and output format. Next, will also explore prompt categories, such as open-ended, close-ended, multi-part, scenario-based, and opinion-based. Finally, you will look at different types of prompts based on the output that they provide. You will use prompts that generate objective facts, abstractive and extractive summaries, classification and sentiment analysis, and answers to questions. You'll tailor prompts to perform grammar and tone checks, ideation and roleplay, and mathematical and logical reasoning.

Data generation prompts instruct language models to generate synthetic data, useful for creating datasets. Code generation prompts are used to produce code snippets or entire programs, aiding developers in coding tasks. Zero-shot prompts challenge models to respond to unfamiliar tasks, relying on their general knowledge. Few-shot prompts provide limited context to guide models in addressing specific tasks, enhancing their adaptability. You will start this course by working with data generation and code generation prompts. You will explore how to use starter code prompts, convert code from one language to another, and prompt models to explain a piece of code. Next, you will see how to leverage generative AI to debug your code and generate complex bits of code with step-by-step instructions. Finally, you will explore techniques to improve prompt performance.

Power BI's artificial intelligence (AI) capabilities offer a remarkable blend of data analytics and artificial intelligence. Power BI empowers users to unlock hidden patterns, generate predictive forecasts, and gain a deeper understanding of their data without requiring extensive data science expertise. You will start this course by generating insights on data and reports. You will explore how to generate these insights on datasets, reports, and even dashboard tiles. You'll also learn how to harness AI to explain fluctuations in your data. Next, you will learn how to perform text analytics in Power BI. You will explore how to use the Text APIs for language recognition, key phrase extraction, and sentiment analysis. Finally, you will use image analytics in Power BI by loading a dataset of images and generating tags for each set.

Machine learning (ML) in Power BI provides a dynamic and transformative dimension to data analysis. This feature enables users to create predictive models, discover patterns, and make data-driven decisions while requiring no programming or machine learning expertise. You will start this course by creating a binary classification model that will be used to predict categorical variables. You will load in data and perform exploratory data analysis, including visualizing the data and extracting insights. Then, you will create and train a binary classification model and use it for predictions. After training the model, you will view the training report that will allow you to evaluate your model's performance. Next, you will build a regression model to predict the value of a continuous variable. You will load in the data and perform preprocessing steps to clean your data. You will also perform exploratory data analysis and visualize your data to extract insights about patterns and trends in your data. Then, you will create and train your regression model and learn how to interpret the training report generated by Power BI. Finally, you will perform multi-class classification.

Power BI includes power features that offer valuable insights into your data. The Key Influencer visual helps identify the factors or attributes that have the most significant impact on a chosen outcome. On the other hand, the Decomposition Tree provides an intuitive way to break down complex data into understandable components, allowing users to explore data hierarchies and identify key contributors to a specific metric. You will start this course by learning how Power BI will leverage artificial intelligence (AI) for detecting anomalies in time series data. Next, you will use decomposition tree visualizations to drill-down into measures. You will also make use of AI splits, which are AI-generated drill-downs into high value and low value categories. Finally, you will use Key Influencer visualizations to help you identify factors in your data that drive specific outcomes.

Smart narratives and the Q&A feature in Power BI enhance data storytelling and interactivity for reports and dashboards. Smart narratives automate the creation of textual descriptions and insights from data. The Q&A feature, on the other hand, allows users to ask natural language questions about their data and receive immediate responses and insights. You will start this course by using smart narratives in Power BI to generate natural language summaries of visualizations, dashboards, and reports. You will configure dynamic variables in your narratives that update with your data. Next, you will use the Q&A feature to ask natural language questions about visualizations that will be answered with numbers, charts, or tables. You will also learn to use the Teach Q&A feature to teach the Q&A widget to work with organization-specific terminology. Finally, you will learn how to use Power BI Copilot. You will explore how to calculate measures using natural language queries to generate DAX commands and add those measures to your reports.

Python is a powerful programming language for data science, and pandas is a popular open-source data manipulation and analysis library in Python. Combined with prompt engineering techniques, working with data in Python is easy and intuitive, which allows you to be more productive and efficient. You will start this course by leveraging prompt engineering to work with pandas. You will explore libraries such as Matplotlib, seaborn, and Plotly, which are used for visualization and charting. With ChatGPT's help you will read data from a CSV file and inspect the DataFrame. You'll delve into pandas Series objects and explore their creation and manipulation. You will leverage prompt engineering techniques to access elements in a Series using index labels through loc, iloc, at, and iat functions and perform operations like modification and visualization. Finally, you will explore how to use pandas DataFrame objects and create basic DataFrames using lists and dictionaries for data assignment and inspection. You will also generate code to perform basic operations on DataFrames using tools such as ChatGPT and Bard.

With DataFrames in pandas you can filter, aggregate, join, pivot, and manipulate data efficiently. These operations enable data analysts and scientists to work with datasets for various data-driven tasks. Prompt engineering tools are adept at generating code to make these tasks simple. You will start this course by exploring the configurations you can apply to read in your data. You'll present your problem statement to ChatGPT and explore the use of arguments to configure various aspects of the file reading, such as defining column names, and specifying which columns to include in the DataFrame. Additionally, you will learn how to read data from different sources, including JSON, Excel, and the Clipboard and write files out to these different formats. Next, you'll delve into common DataFrame operations, examine statistics on your data, rename columns, iterate over, and sort your data. As you encounter issues, you will turn to prompt engineering to help debug them. Finally, you'll explore how you can enhance your data using computed columns. You'll harness the power of two essential functions, apply and map, to transform your records. You will also focus on utilizing generative AI for code generation and you will employ the chain-of-thought prompting method to guide the chatbot in generating code effectively.

Data manipulation involves getting your data in the right format to generate further insights. Prompt engineering allows you to specify your problem statements in natural language and generate code to meet your needs. You will begin this course by applying filters to your DataFrames in pandas. You will use logical and comparison operators to specify filter predicates and filter based on datetime data. Next, you will group and aggregate your DataFrames. You will use prompt engineering to explain your grouping and aggregation requirements and tweak generated code to tailor your solutions. Additionally, you will learn about the split-apply-combine method, a step-by-step technique for grouping and aggregation. You will then tackle data cleaning. You will remove rows with duplicate records and deal with missing values and other inaccuracies in your data. Finally, you will explore the use of pivot tables, which help rearrange and reshape data into a format more suitable for analysis.

Combining data is a key data manipulation technique and is well supported in the pandas library. Exploratory data analysis involves data visualization to understand the relationships that exist in your data. Prompt engineering can help you pick the right visualization for viewing and understanding relationships between variables and can also generate code for these visuals. You will start this course by combining data in DataFrames learning techniques to join DataFrames using different constructs such as the inner join, left and right joins, and the full outer join. Next, you will delve into time-series analysis and visualization. You will use prompt engineering help to visualize your time series data to identify trends and patterns. Finally, you will explore data visualization in Python. You will begin by crafting univariate visualizations that display information about a single variable. You'll see that tools such as ChatGPT and Bard can help you pick the right visualizations for different use cases. You will explore bivariate visuals and use Plotly to generate interactive visualizations which are more user-friendly and intuitive.