Course index
Find any lesson in the free academy
Search across 13 modules and 77 lessons — titles, summaries, objectives, code and practice tasks.
77 lessons
Results
Every lesson, in order
- Module 01 · Data analysis foundations and toolingIntroduction to Data AnalysisThere are many approaches and techniques to Data Analysis that are used in carrying out different businesses, sciences and research work. In business today, data analysis plays a vital role in… 8 min
- Module 01 · Data analysis foundations and toolingTools in Data ScienceSome of the popular data science tools that are listed below: 8 min
- Module 01 · Data analysis foundations and toolingOverview of Jupyter NotebookLet’s take a look at the basic overview of the Jupyter notebook. 8 min
- Module 01 · Data analysis foundations and toolingCell MenuWith the cell menu we can run the code in the cells. Also has option to run all the code in each and every cell at one shot which gives the output of the code in all cells. We can make a cells appear… 8 min
- Module 01 · Data analysis foundations and toolingGoogle ColaboratoryColab is a free platform for running Jupyter notebooks in the cloud. Before getting started, it is better for us to know that Python and all its major data analysis libraries are already installed.… 8 min
- Module 01 · Data analysis foundations and toolingYahoo Finance APIYahoo finance allows users to access the stock quotes, up-to-date news, portfolio management resources, international market data and so on. In order to access this resource, we, first, will install… 8 min
- Module 01 · Data analysis foundations and toolingFederal Reserve Economic Data (FRED)Using FRED API, we are allowed to retrieve economic data from the FRED website hosted by the Economic Research Division of the Federal Reserve Bank of St. Louis. 8 min
- Module 01 · Data analysis foundations and toolingWorld Bank DataEventually, I would like to introduce another database called World Bank Database, which is quite comprehensive and include many development indicators. It is free and open access to global… 8 min
- Module 02 · Python and engineering practicePython built for data workThe subset of Python that actually shows up in data science code: comprehensions, unpacking, generators, and the cost of mutability. 25 min
- Module 02 · Python and engineering practicepandas that scalesVectorised operations, correct joins, groupby-agg, and the memory habits that stop a 5 GB CSV from killing your kernel. 30 min
- Module 02 · Python and engineering practiceSQL and relational thinkingWindow functions, CTEs, and the join semantics that decide whether your metric is right or quietly double-counted. 28 min
- Module 02 · Python and engineering practiceFrom notebook to packageProject layout, virtual environments, pytest, and pre-commit — the mechanics that make your work reproducible by someone else. 26 min
- Module 03 · Math for data scienceVectorsAt its simplest, a vector is a numeric element that has both magnitude and direction. The magnitude represents a distance (for example, "2 miles") and the direction indicates which way the vector is… 8 min
- Module 03 · Math for data scienceIntroduction to MatricesA matrix arranges numbers into rows and columns, like this: 8 min
- Module 03 · Math for data scienceMatrix TransformationsMatrix decompositions are a useful tool for reducing a matrix to their constituent parts in order to simplify a range of more complex operations. Perhaps the most used type of matrix decomposition is… 8 min
- Module 04 · Statistics and probabilitySome Important Statistical ConceptsIn data science, we infer information based on sample. Therefore, we need to have a reliable and representative sample space drawn from population. As population is a collection of data that consists… 8 min
- Module 04 · Statistics and probabilityCentral Tendency and Dispersion MeasuresWe can use the randn() NumPy function to generate a sample of random numbers drawn from a Gaussian distribution. There are two key parameters that define any Gaussian distribution; they are the mean… 8 min
- Module 04 · Statistics and probabilitySimple Data VisualisationIt is the foundation for many other plotting libraries and plotting support in higher-level libraries such as Pandas. The Matplotlib provides a context, one in which one or more plots can be drawn… 8 min
- Module 04 · Statistics and probabilityRandom NumbersThe pseudorandom number generator is a mathematical function that generates a sequence of nearly random numbers. It takes a parameter to start off the sequence, called the seed. The function is… 8 min
- Module 04 · Statistics and probabilityEffect Size and Statistical PowerThe association between variables is often referred to as the r r family of effect size methods. This name comes from perhaps the most common method for calculating the effect size called Pearson’s… 8 min
- Module 04 · Statistics and probabilityResamplingObservations made in a domain represent samples of some broader idealized and unknown population of all possible observations that could be made in the domain. Statistical sampling is the process of… 8 min
- Module 04 · Statistics and probabilityEstimation StatisticsThe tolerance interval is a bound on an estimate of the proportion of data in a population. The interval is limited by the sampling error and by the variance of the population distribution. Given the… 8 min
- Module 04 · Statistics and probabilityNormalityA simple and commonly used plot to quickly check the distribution of a sample of data is the histogram. In the histogram, the data is divided into a pre-specified number of groups called bins. The… 8 min
- Module 04 · Statistics and probabilityStatistical DistributionsNormal distribution is the distribution we hear the most and it is not for no reason. Normally distributed data can be find in many fields such as pyhics and finance. This is not the only reason that… 8 min
- Module 05 · Experimentation and A/B testingThe Research QuestionA hypothesis can be defined as "a specific, clear, and testable predictive statement about the possible outcome of a scientific study based on a particular property of a population". A research… 8 min
- Module 05 · Experimentation and A/B testingA/B TestingThe three key concepts in A/B testing are: 8 min
- Module 05 · Experimentation and A/B testingT-test AnalysisThe one sample t test is used to compare a sample mean to a hypothesized mean to check if the difference between the two means is statistically significant. For example the weight of a new born baby… 8 min
- Module 05 · Experimentation and A/B testingPaired Sample t TestThe paired samples t test also known as repeated measures test is appropriate for comparing means from the same individual or objects. The two means are ussually measurements taken at different time… 8 min
- Module 06 · SQL for analyticsIntroduction to DatabaseA database is an organized collection of interrelated data used to model some type of organization or organizational process. You have a database as long as you’re collecting and storing data in some… 8 min
- Module 06 · SQL for analyticsSQL StatementsThe key to SQL is understanding the statements which could be categorized into five groups: 8 min
- Module 06 · SQL for analyticsBefore JoinsINTERSECT statement will return only those rows which will be common to both of the SELECT statements. 8 min
- Module 06 · SQL for analyticsSQL AggregatesBefore aggregations, let us summarize NULL concept in SQL. NULLs are datatypes that specifies “no data” exists. NULLs are often ignored in aggregate functions. NULLs are different than a zero - they… 8 min
- Module 06 · SQL for analyticsSubqueries1. Find the number of events that occur for each day for each channel. 8 min
- Module 06 · SQL for analyticsSQL Window FunctionsThe PARTITION BY clause divides rows into multiple groups or partitions to which the window function is applied. Some window functions don’t accept any arguments. 8 min
- Module 07 · Data exploration and feature engineeringHandling with Variable TypeIn this part of the curriculum, we will discuss main tools that we can use in data cleansing. Before proceeding, please keep in mind that tools that we are about to learn are not all-inclusive. As we… 8 min
- Module 07 · Data exploration and feature engineeringDetecting missing valuesBy eyeballing, it is easy to notice whether there is a missing value in Python. If you encounter a value of NAN(Not a Number) in the dataset, a ring should bell and say: Here you go, you have a… 8 min
- Module 07 · Data exploration and feature engineeringWhy should outliers be treated with caution?Some immediately treat outliers as something we need to delete but this is something that a data scientist should stay away. In machine learning, model are data dependent implying that it would not… 8 min
- Module 07 · Data exploration and feature engineeringStatistical Tools in Detecting the OutliersThe Z-Score is a scaling technique by which we have a dataset with mean 0 and standard deviation of 1. So, z-score converts a data considered to be normally distributed into the standard normal… 8 min
- Module 07 · Data exploration and feature engineeringFixing the OutliersNow, we know how to detect outliers and we are good at it but it is not the final step. Pretend that we detect the outliers, it is now time to make a decision about how to deal with them. In order to… 8 min
- Module 07 · Data exploration and feature engineeringUnivariate AnalysisThe term Exploratory Data Analysis (EDA) was first coined by John Tukey. This is a process in which we understand the data, check the shape and apply some visualizations, make decision about… 8 min
- Module 07 · Data exploration and feature engineeringCorrelationAs you may notice there are many ways to find the interaction between variables. However, it is no surprise that finding out the correlation coefficient is the best and easiest way. In Python, there… 8 min
- Module 07 · Data exploration and feature engineeringTransforming the FeaturesSince machine learning models work only on numerical data, we should convert our categorical data to a numerical value. One method for this purpose is called one-hot encoding. In one-hot encoding, we… 8 min
- Module 07 · Data exploration and feature engineeringPrincipal Components AnalysisPCA works best for normally distributed data and assumes the relationships among variables are linear. PCA also works best when the variables involved range from weak to moderately strong… 8 min
- Module 08 · Machine learningFraming the problem and splitting dataTurning a business question into a target, choosing a split that mirrors deployment, and killing leakage before it flatters you. 28 min
- Module 08 · Machine learningFeatures and model familiesEncoding, scaling, regularisation, and when linear models, tree ensembles or k-means are the right tool. 32 min
- Module 08 · Machine learningEvaluation, calibration and thresholdsChoosing metrics that match the decision, reading a confusion matrix under class imbalance, and turning probability into action. 30 min
- Module 08 · Machine learningExperiments and causal thinkingA/B tests, statistical power, common pitfalls, and what to do when you cannot randomise. 26 min
- Module 09 · Deep learning and LLMsNeural network fundamentalsLayers, activations, loss, backpropagation and the training loop — what every framework is doing under the abstraction. 30 min
- Module 09 · Deep learning and LLMsTransfer learning that actually worksPretrained backbones, freezing versus fine-tuning, augmentation, and parameter-efficient fine-tuning with LoRA. 26 min
- Module 09 · Deep learning and LLMsTransformers and embeddingsAttention, tokenisation, context windows, and using embeddings for search, clustering and deduplication. 28 min
- Module 09 · Deep learning and LLMsBuilding LLM applicationsPrompting, structured output, retrieval-augmented generation, tool use and how to evaluate a non-deterministic system. 32 min
- Module 10 · Natural language processingWhat is Natural Language ProcessingAs we said before, data scientists with NLP skills are high in demand in the industry. That's basically because there are many real-world applications that somehow involve NLP tasks. Here we mention… 8 min
- Module 10 · Natural language processingNLTK - Natural Language ToolKitTokenization is a method of breaking up a piece of text into many pieces, such as sentences and words, and is an essential first step for recipes in the later chapters. 8 min
- Module 10 · Natural language processingMetaCharactersSquare brackets specify a set of characters (a character class) you wish to match. All characters written between these square brackets are taken into account. Gr[ae]y can match both gray and grey. 8 min
- Module 10 · Natural language processingBag of WordsTo create a Count Vectorizer, we simply need to instantiate one. We are not using any parameters yet. 8 min
- Module 10 · Natural language processingSupervised/Unsupervised NLP ExampleX_train, X_test, y_train, y_test = train_test_split(X, 8 min
- Module 10 · Natural language processingIntro to word2vecIn considering the relationship between a word and its surrounding words, word2vec has two options that are the inverse of one another: 8 min
- Module 10 · Natural language processingSentiment Analysis Movie Reviewtype of text train: <class 'list'> length of text_train: 25000 text_train[1]: b"Zero Day leads you to think, even re-think why two boys/young men would do what they did - commit mutual suicide via… 8 min
- Module 10 · Natural language processingWhat is Markov chain?In the following examples, we'll use a library called markovify to generate the Markov chains using Jane Austen's novel Emma as our corpus. You can install markovify from the terminal (or command… 8 min
- Module 10 · Natural language processingChatbotBefore moving on to the implementation, let's talk a little bit about chatbots. In a nutshell: 8 min
- Module 11 · Data engineeringPipelines and idempotencyBatch versus streaming, ELT over ETL, and why every task you write must be safe to run twice. 27 min
- Module 11 · Data engineeringWarehouse modellingStar schemas, slowly changing dimensions, surrogate keys, and how to model events so metrics stay comparable. 30 min
- Module 11 · Data engineeringOrchestration and schedulingDAGs, dependencies, retries, backfills and alerting — running pipelines on a schedule without babysitting them. 24 min
- Module 11 · Data engineeringData quality and contractsTests on data, not just code: uniqueness, not-null, referential integrity, distribution drift, and how to fail loudly. 22 min
- Module 12 · Big data with SparkSpark Crash CourseThe dataset contains bike rental info from 2011 and 2012 in the Capital bikeshare system, plus additional relevant information such as weather. 8 min
- Module 12 · Big data with SparkDataPreProcessingcat > movies.csv <<EOF name,rating,studio,date Avengers Endgame, 5, marvel,1260759144 Batman Vs Superman,4 ,DC,835355664 The Joker ,, DC,835355681 Frozen,4,Disney,835355604 Hitman,,, EOF %sh ls -alh … 8 min
- Module 12 · Big data with SparkMLeap-Orange Telecom Customer Churnfrom pyspark.ml.feature import VectorAssembler from pyspark.ml.classification import LogisticRegression from pyspark.ml import Pipeline from pyspark.sql.functions import udf from pyspark.sql.types… 8 min
- Module 12 · Big data with SparkCapital Bike Rental-Python-1How to Ingest the data into Spark DataFrame. How to clean the Data with DataFrame, SQL Query. How to create a Machine Learning Pipeline. How to train a Machine Learning model. How to save & read the… 8 min
- Module 12 · Big data with SparkData IngestionWe begin by loading our data, which is stored in the CSV format. 8 min
- Module 12 · Big data with SparkData UnderstandingNow that we have preprocessed our features, we can quickly visualize our data to get a sense of whether the features are meaningful. 8 min
- Module 12 · Big data with SparkData Processing (Feature Engineering)For each of the categorical columns, we are going to create one StringIndexer where we 8 min
- Module 12 · Big data with SparkTrain the modelRandom forests and ensembles of decision trees are more powerful than a single decision tree alone. 8 min
- Module 12 · Big data with SparkModel tuning: Preparing K-fold Cross Validation and Grid Searchfor best model selection and makes sure that there's no overfitting. 8 min
- Module 13 · MLOps and deploymentServing a model behind an APIModel artefacts, input validation, batch versus real-time inference, and the latency budget. 28 min
- Module 13 · MLOps and deploymentReproducibility, tracking and CIExperiment tracking, data and model versioning, deterministic environments and automated retraining. 26 min
- Module 13 · MLOps and deploymentMonitoring, drift and incident responseWhat to monitor after launch, detecting data and concept drift, and running an ML incident. 28 min
- Module 13 · MLOps and deploymentProduct thinking and communicationScoping with stakeholders, presenting results without jargon, ethics and privacy, and the portfolio case study that gets you hired. 24 min
