I recently chatted with a data science leader who described their company reaching this state. They couldn’t show any business impact from the past two years of their product releases, so the finance team identified a surefire way for R&D to make a business impact: laying off much of the R&D team.

To this day, the field of machine learning does not have a single generally accepted approach to solving problems in terms of practical use of models.

The main reason I soured on data science is that the work felt like it didn’t matter, in multiple senses of the words “didn’t matter”:

To Uncover a Deepfake Video Call, Ask the Caller to Turn Sideways

# Input Input: 123, Output: Input: 121, Output: Input: 111, Output: Input: 123454321, Output: Input 123123, Output: # Instruction Output true if input is a palindrome # Output Input: 123, Output: false Input: 121, Output: true Input: 111, Output: true Input: 123454321, Output: true Input 123123, Output: false

Gary Klein himself has made a name developing techniques for extracting pieces of tacit knowledge and making it explicit. (The technique is called ‘The Critical Decision Method’, but it is difficult to pull off because it demands expertise in CDM itself).

There are a handful of tools that I used to use and now it’s narrowed down to just one or two: pandas-profiling and Dataiku for columnar or numeric data - here’s some getting started tips. I used to also load the data into bamboolib but the purpose of such a tool is different. For text data I have written my own profiler called nlp-profiler.

State of Data Science and Machine Learning 2021

It’s been a hot, hot year in the world of data, machine learning and AI. 

Why do 87% of data science projects never make it into production?

The main selling point for Anaconda back then was that it provided pre-compiled binaries. This was especially useful for data-science related packages which depend on libatlas, -lapack, -openblas, etc. and need to be compiled for the target system.

Simply put, there can be no data science without data engineering. Data engineering is the foundation for a successful data-driven company.

The console is a killer SQLite feature for data analysis: more powerful than Excel and more simple than pandas. One can import CSV data with a single command, the table is created automatically

This is not a problem if your DBMS supports SQL recursion: lots of data can be generated with a single query. The WITH RECURSIVE clause comes to the rescue.

…Well, deploying ML is still slow and painful

Downloading a pretrained model off the Tensorflow website on the Iris dataset probably is no longer enough to get that data science job. It’s clear, however, with the large number of ML engineer openings that companies often want a hybrid data practitioner: someone that can build and deploy models. Or said more succinctly, someone that can use Tensorflow but can also build it from source.

When machine learning become hot 🔥 5-8 years ago, companies decided they need people that can make classifiers on data. But then frameworks like Tensorflow and PyTorch became really good, democratizing the ability to get started with deep learning and machine learning. This commoditized the data modelling skillset. Today, the bottleneck in helping companies get machine learning and modelling insights to production center on data problems.

Overall the consolidation made the differences even more pronounced! There are ~70% more open data engineer than data scientist positions. In addition, there are ~40% more open ML engineer than data scientist positions. There are also only ~30% as many ML scientist as data scientist positions.

Data scientist: Use various techniques in statistics and machine learning to process and analyse data. Often responsible for building models to probe what can be learned from some data source, though often at a prototype rather than production level. Data engineer: Develops a robust and scalable set of data processing tools/platforms. Must be comfortable with SQL/NoSQL database wrangling and building/maintaining ETL pipelines. Machine Learning (ML) Engineer: Often responsible for both training models and productionizing them. Requires familiarity with some high-level ML framework and also must be comfortable building scalable training, inference, and deployment pipelines for models. Machine Learning (ML) Scientist: Works on cutting-edge research. Typically responsible for exploring new ideas that can be published at academic conferences. Often only needs to prototype new state-of-the-art models before handing off to ML engineers for productionization.

I scraped the homepage URLs of every YC company since 2012, producing an initial pool of ~1400 companies. Why stop at 2012? Well, 2012 was the year that AlexNet won the ImageNet competition, effectively kickstarting the machine learning and data-modelling wave we are now living through. It’s fair to say that this birthed some of the earliest generations of data-first companies. From this initial pool, I performed keyword filtering to reduce the number of relevant companies I would have to look through. In particular, I only considered companies whose websites included at least one of the following terms: AI, CV, NLP, natural language processing, computer vision, artificial intelligence, machine, ML, data. I also disregarded companies whose website links were broken.

There are 70% more open roles at companies in data engineering as compared to data science. As we train the next generation of data and machine learning practitioners, let’s place more emphasis on engineering skills.

When you think about it, a data scientist can be responsible for any subset of the following: machine learning modelling, visualization, data cleaning and processing (i.e. SQL wrangling), engineering, and production deployment.

The term that seemed to fit best was data scientist:  those who use both data and science to create something new.

2020 is a strong year for NLP. Companies like Hugging Face 🤗 , spaCy, Rasa became stronger and also more educational which ultimately drove a huge NLP revolution (at even Industry-level which is quite hard usually).

要模仿以顧客資料為基礎的產品改善，有多困難？即使那些資料是獨一無二或專屬的，而且能產生寶貴的見解，但如果競爭對手就算沒有類似資料也可以複製同樣的改善成果，那麼你仍很難建立持久的競爭優勢。

TFX and Tensorflow run anywhere Python runs, and that’s a lot of places

After consideration, you decide to use Python as your programming language, Tensorflow for model building because you will be working with a large dataset that includes images, and Tensorflow Extended (TFX), an open-source tool released and used internally at Google, for building your pipelines.

These components has built-in support for ML modeling, training, serving, and even managing deployments to different targets.

Most data scientists feel that model deployment is a software engineering task and should be handled by software engineers because the required skills are more closely aligned with their day-to-day work. While this is somewhat true, data scientists who learn these skills will have an advantage, especially in lean organizations. Tools like TFX, Mlflow, Kubeflow can simplify the whole process of model deployment, and data scientists can (and should) quickly learn and use them. 

TFX Component called TensorFlow Model Analysis (TFMA) allows you to easily evaluate new models against current ones before deployment. 

This has its pros and cons and may depend on your use case as well. Some of the pros to consider when considering using managed cloud services are:

The data is already in the cloud, so it may be better to build your ML system in the cloud. You’ll get better latency for I/O, easy scaling as data becomes larger (hundreds of gigabytes), and quick setup and configuration for any additional GPUs and TPUs. 

ML projects are never static. This is part of engineering and design that must be considered from the start. Here you should answer questions like:

The choice of framework is very important, as it can decide the continuity, maintenance, and use of a model. In this step, you must answer the following questions:

These questions are important as they will guide you on what frameworks or tools to use, how to approach your problem, and how to design your ML model.

you should not invest in an ML project if you have no plan to put it in production, except of course when doing pure research.

The difficulties in model deployment and management have given rise to a new, specialized role: the machine learning engineer. Machine learning engineers are closer to software engineers than typical data scientists, and as such, they are the ideal candidate to put models into production.

The goal of building a machine learning model is to solve a problem, and a machine learning model can only do so when it is in production and actively in use by consumers. As such, model deployment is as important as model building.

Venturebeat reports that 87% of data science projects never make it to production, while redapt claims it is 90%.

Statistical techniques: average, quantiles, probability distribution, association rulesSupervised ML algorithms: logistic regression, neural net, time-series analysisUnsupervised ML algorithms: Cluster analysis, Bayesian network, Peer group analysis, break point analysis, Benford’s law (law of anomalous numbers)

In machine learning, parlance fraud detection is generally treated as a supervised classification problem, where observations are classified as “fraud” or “non-fraud” based on the features in those observations. It is also an interesting problem in ML research due to imbalanced data — i.e. there’s a very few cases of frauds in an extremely large amount of transactions.

With ever-increasing online transactions and production of a large volume of customer data, machine learning has been increasingly seen as an effective tool to detect and counter frauds. However, there is no specific tool, the silver bullet, that works for all kinds of fraud detection problems in every single industry. The nature of the problem is different in every case and every industry. Therefore every solution is carefully tailored within the domain of each industry.

Facebook AI is introducing M2M-100, the first multilingual machine translation (MMT) model that can translate between any pair of 100 languages without relying on English data. It’s open sourced here. When translating, say, Chinese to French, most English-centric multilingual models train on Chinese to English and English to French, because English training data is the most widely available. Our model directly trains on Chinese to French data to better preserve meaning. It outperforms English-centric systems by 10 points on the widely used BLEU metric for evaluating machine translations. M2M-100 is trained on a total of 2,200 language directions — or 10x more than previous best, English-centric multilingual models. Deploying M2M-100 will improve the quality of translations for billions of people, especially those that speak low-resource languages. This milestone is a culmination of years of Facebook AI’s foundational work in machine translation. Today, we’re sharing details on how we built a more diverse MMT training data set and model for 100 languages. We’re also releasing the model, training, and evaluation setup to help other researchers reproduce and further advance multilingual models. 

For Decision Scientists, the business problem comes first. Analysis follows and is dependent on the question or business decision that needs to be made.

The number of hidden neurons should be between the size of the input layer and the size of the output layer. The number of hidden neurons should be 2/3 the size of the input layer, plus the size of the output layer. The number of hidden neurons should be less than twice the size of the input layer.

Sprawdźmy który rodzaj modelu daje najlepszą skuteczność: Python sns.boxplot(data=models_df, x='score', y='model') 1 sns.boxplot(data=models_df, x='score', y='model')

Przy tych danych wygląda, że właściwie nie ma większej różnicy (nie bijemy się tutaj o 0.01 punktu procentowego poprawy accuracy modelu). Może więc czas treningu jest istotny? Python sns.boxplot(data=models_df, x='time_elapsed', y='model') 1 sns.boxplot(data=models_df, x='time_elapsed', y='model')

Teraz w zagnieżdżonych pętlach możemy sprawdzić każdy z każdym podmieniając klasyfikatory i transformatory (cała pętla trochę się kręci):

The best data scientists are just people who try to understand the ins and outs of business processes and look at problems with healthy suspicion and curiosity. The ability to explain the nuances of manifolds in SVMs is not something that comes into it outside these contrived interviews. I prefer to ask candidates how they would approach solving a problem I’m facing at that moment rather than these cookie cutter tests which are easy to game and tell me nothing

What you actually need from an ML/Data Science person:- Experience with data cleaning (this is most of the gig)- A solid understanding of linear and logistic regression, along with cross-validation- Some reasonable coding skills (in both R and Python, with a side of SQL).

deep learning is good in some scenarios and not in others, so anyone who's just a deep learning developer is not going to be useful to most companies.

Imagine what it must be like for the senior leadership of an established company to actually become data-driven. All of a sudden the leadership is going to consent to having all of their strategic and tactical decision-making be questioned by a bunch of relatively new hires from way down the org chart, whose entire basis for questioning all that expertise and business acumen is that they know how to fiddle around with numbers in some program called R? And all the while, they're constantly whining that this same data is junk and unreliable and we need to upend a whole bunch of IT systems just so they can rock the boat even harder? Pffft.

This command will give you the top 25 stocks that had the highest anomaly score in the last 14 bars of 60 minute candles.

Once TPOT is finished searching (or you get tired of waiting), it provides you with the Python code for the best pipeline it found so you can tinker with the pipeline from there.

TPOT is a Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming

The Splitgraph DDN is a single SQL endpoint that lets you query over 40,000 public datasets hosted on or proxied by Splitgraph.You can connect to it from most PostgreSQL clients and BI tools without having to install anything else. It supports all read-only SQL constructs, including filters and aggregations. It even lets you run joins across distinct datasets.

I learned and did to make it possible to do Automated Speech Recognition research on a Colab instance.

Libra is a machine learning API designed for non-technical users. This means that it assumes that you have no background in ML whatsoever.

Most of the discourse is about how AI will “replace” humans. I prefer the Licklider school of thought: human-computer symbiosis. AI will make humans vastly more effective by automating tedious tasks. For example, humans can use text AI such as GPT-3 to generate ideas/boilerplate writing to get around the terror of the blank page, and then simply pick the best ones and refine/iterate on those. (AI Dril, which was based on GPT-2, was an early example of this). As AI gets better, “assistive creativity” will become a bigger thing, enabling humans to create sophisticated artifacts (including video games!) easier and better than ever.

You can create estimation plots here at estimationstats.com, or with the DABEST packages which are available in R, Python, and Matlab.

Relative to conventional plots, estimation plots offer five key benefits:

For comparisons between 3 or more groups that typically employ analysis of variance (ANOVA) methods, one can use the Cumming estimation plot, which can be considered a variant of the Gardner-Altman plot.

Efron developed the bias-corrected and accelerated bootstrap (BCa bootstrap) to account for the skew whilst obtaining the central 95% of the distribution.

We can calculate the 95% CI of the mean difference by performing bootstrap resampling.

Shown above is a Gardner-Altman estimation plot.

Jitter plots avoid overlapping datapoints (i.e. datapoints with the same y-value) by adding a random factor to each point along the orthogonal x-axes.

Unfortunately, the boxplot still doesn't show all our data.

The barplot has several shortcomings, even though its use in academic journals is endemic.

Kolejna zmienna - "Recency", czyli informacja o tym, jak dawno klient robił zakupy w sklepie.

df['Recency'] = (today - df.InvoiceDate)/np.timedelta64(1,'D')

abt = df.groupby(['CustomerID']).agg({'Recency':'min', 'MonetaryValue':'sum', 'InvoiceNo':'count'})

abt = df.groupby(['CustomerID']).agg({'Recency':'min', 'MonetaryValue':'sum', 'InvoiceNo':'count'})
abt.rename(columns = {'InvoiceNo':'Frequency'}, inplace = True)
abt = abt[['Recency', 'Frequency', 'MonetaryValue']]
abt.head()

Będę oceniać klientów kryteriami, jakie zakłada metoda RFM.

Usuwam brakujące wartości w zmiennej "CustomerID".

df = df[~df.CustomerID.isnull()]

df['CustomerID'] = df.CustomerID.astype(int)

df.drop(['Description', 'StockCode', 'Country'], axis = 1, inplace = True)

Sprawdzam braki danych.

print(str(round(df.isnull().any(axis=1).sum()/df.shape[0]*100,2))+'% obserwacji zawiera braki w danych.')

24.93% obserwacji zawiera braki w danych.

Buduję prosty data frame z podstawowymi informacjami o zbiorze.

summary = pd.DataFrame(df.dtypes, columns=['Dtype'])
summary['Nulls'] = pd.DataFrame(df.isnull().any())
summary['Sum_of_nulls'] = pd.DataFrame(df.isnull().sum())
summary['Per_of_nulls'] = round((df.apply(pd.isnull).mean()*100),2)
summary.Dtype = summary.Dtype.astype(str)
print(summary)

                      Dtype  Nulls  Sum_of_nulls  Per_of_nulls
InvoiceNo            object  False             0         0.000
StockCode            object  False             0         0.000
Description          object   True          1454         0.270
Quantity              int64  False             0         0.000
InvoiceDate  datetime64[ns]  False             0         0.000
UnitPrice           float64  False             0         0.000
CustomerID          float64   True        135080        24.930
Country              object  False             0         0.000

For many data scientists, the finished product of a work session is a business analysis. They need to show team members—who oftentimes aren’t technical—how their data became a specific recommendation or insight.

COVID-19 has spurred a shift to analyze things like supply chain disruptions, speech analytics, and filtering out pandemic-related behavior, such as binge shopping, Burtch Works says. Data teams are being asked to create new simulations for the coming recession, to create scorecards to track pandemic-related behavior, and add COVID-19 control variables to marketing attribution models, the company says.

Data scientists and data engineers have built-in job security relative to other positions as businesses transition their operations to rely more heavily on data, data science, and AI. That’s a long-term trend that is not likely to change due to COVID-19, although momentum had started to slow in 2019 as venture capital investments ebbed.

According to a Dice Tech Jobs report released in February, demand for data engineers was up 50% and demand for data scientists was up 32% in 2019 compared to the prior year.

Truth be told, we found that most companies we worked with preferred to own the analytical backend.

the limitations of the PPS

Although the PPS has many advantages over the correlation, there is some drawback: it takes longer to calculate.

How to use the PPS in your own (Python) project

The PPS clearly has some advantages over correlation for finding predictive patterns in the data. However, once the patterns are found, the correlation is still a great way of communicating found linear relationships.

Let’s compare the correlation matrix to the PPS matrix on the Titanic dataset.

Let’s use a typical quadratic relationship: the feature x is a uniform variable ranging from -2 to 2 and the target y is the square of x plus some error.

how do you normalize a score? You define a lower and an upper limit and put the score into perspective.

For a classification problem, always predicting the most common class is pretty naive. For a regression problem, always predicting the median value is pretty naive.

Let’s say we have two columns and want to calculate the predictive power score of A predicting B. In this case, we treat B as our target variable and A as our (only) feature. We can now calculate a cross-validated Decision Tree and calculate a suitable evaluation metric.

More often, relationships are asymmetric

there are many non-linear relationships that the score simply won’t detect. For example, a sinus wave, a quadratic curve or a mysterious step function. The score will just be 0, saying: “Nothing interesting here”. Also, correlation is only defined for numeric columns.

Creating meticulous tests before exploring the data is a big mistake, and will result in a well-crafted garbage-in, garbage-out pipeline. We need an environment flexible enough to encourage experiments, especially in the initial place.

The priorities in building a production machine learning pipeline—the series of steps that take you from raw data to product—are not fundamentally different from those of general software engineering.

A notebook, at a very basic level, is just a bunch of JSON that references blocks of code and the order in which they should be executed.But notebooks prioritize presentation and interactivity at the expense of reproducibility. YAML is the other side of that coin, ignoring presentation in favor of simplicity and reproducibility—making it much better for production.

Repeated measures involves measuring the same cases multiple times. So, if you measured the chips, then did something to them, then measured them again, etc it would be repeated measures. Replication involves running the same study on different subjects but identical conditions. So, if you did the study on n chips, then did it again on another n chips that would be replication.

To take full advantage of tabular augmentation for time-series you would perform the techniques in the following order: (1) transforming, (2) interacting, (3) mapping, (4) extracting, and (5) synthesising

process of modular feature engineering and observation engineering while emphasising the order of augmentation to achieve the best predicted outcome from a given information set

1) Redash and Falcon focus on people that want to do visualizations on top of SQL2) Superset, Tableau and PowerBI focus on people that want to do visualizations with a UI3) Metabase and SeekTable focus on people that want to do quick analysis (they are the closest to an Excel replacement)

JupyterLab project, which enables a richer UI including a file browser, text editors, consoles, notebooks, and a rich layout system.

Open an Anaconda command prompt and run conda create -n myenv python=3.7 pandas jupyter seaborn scikit-learn keras tensorflow

On the job, if you notice poor infrastructure, speak up to your manager early on. Clearly document the problem, and try to incorporate a data engineering, infrastructure, or devops team to help resolve the issue! I'd also encourage you to learn these skills too!

When I worked at Target HQ in 2012, employees would arrive to work early - often around 7am - in order to query the database at a time when few others were doing so. They hoped they’d get database results quicker. Yet, they’d still often wait several hours just to get results.

The Data Scientist, in many cases, should be called the Data Janitor. ¯_(ツ)_/¯

In regards to quality of data on the job, I’d often compare it to a garbage bag that ripped, had its content spewed all over the ground and your partner has asked you to find a beautiful earring that was accidentally inside.

On the job, I’d recommend you document your work well and calculate the monetary value of your analyses based on factors like employee salary, capital investments, opportunity cost, etc. These analyses will come in handy for a promotion/review packet later too.

you as a Data Scientist should try to find a situation to be incredibly valuable on the job! It’s tough to find that from the outskirts of applying to jobs, but internally, you can make inroads supporting stakeholders with evidence for their decisions!

As a Data Scientist in the org, are you essential to the business? Probably not. The business could go on for a while and survive without you. Sales will still be made, features will still get built, customer support will handle customer concerns, etc.

As the resident Data Scientist, you may become easily inundated with requests from multiple teams at once. Be prepared to ask these teams to qualify and defend their requests, and be prepared to say “no” if their needs fall outside the scope of your actual priority queue. I’d recommend utilizing the RICE prioritization technique for projects.

Common questions are: How many users click this button; what % of users that visit a screen click this button; how many users have signed up by region or account type? However, the data needed to answer those questions may not exist! If the data does exists, it’s likely “dirty” - undocumented, tough to find or could be factually inaccurate. It’ll be tough to work with! You could spend hours or days attempting to answer a single question only to discover that you can’t sufficiently answer it for a stakeholder. In machine learning, you may be asked to optimize some process or experience for consumers. However, there’s uncertainty with how much, if at all, the experience can be improved!

In one experience, a fellow researcher spent over a month researching a particular value among our customers through qualitative and quantitative data. She presented a well-written and evidence-backed report. Yet, a few days later, a key head of product outlined a vision for the team and supported it with a claim that was antithetical to the researcher’s findings! Even if a data science project you advocate for is greenlighted, you may be on your own as the rare knowledgeable person to plan and execute it. It’s unlikely leadership will be hands-on to help you research and plan out the project.

Because people don’t know what data science does, you may have to support yourself with work in devops, software engineering, data engineering, etc.

In 50+ interviews for data related jobs, I’ve been asked about AB testing, SQL analytics questions, optimizing SQL queries, how to code a game in Python, Logistic Regression, Gradient Boosted Trees, data structures and/or algorithms programming problems!

seven most common (and at times flagrant) ways that data science has failed to meet expectations in industry

In data science community the performance of the model on the test dataset is one of the most important things people look at. Just look at the competitions on kaggle.com. They are extremely focused on test dataset and the performance of these models is really good.

It's basically a look up table, interpolating between known data points. Except, unlike other interpolants like 'linear', 'nearest neighbour' or 'cubic', the underlying functional form is determined to best represent the kind of data you have.

In the interval scale, there is no true zero point or fixed beginning. They do not have a true zero even if one of the values carry the name “zero.” For example, in the temperature, there is no point where the temperature can be zero. Zero degrees F does not mean the complete absence of temperature. Since the interval scale has no true zero point, you cannot calculate Ratios. For example, there is no any sense the ratio of 90 to 30 degrees F to be the same as the ratio of 60 to 20 degrees. A temperature of 20 degrees is not twice as warm as one of 10 degrees.

As the interval scales, Ratio scales show us the order and the exact value between the units. However, in contrast with interval scales, Ratio ones have an absolute zero that allows us to perform a huge range of descriptive statistics and inferential statistics. The ratio scales possess a clear definition of zero. Any types of values that can be measured from absolute zero can be measured with a ratio scale. The most popular examples of ratio variables are height and weight. In addition, one individual can be twice as tall as another individual.

If you are interested in exploring the dataset used in this article, it can be used straight from S3 with Vaex. See the full Jupyter notebook to find out how to do this.

Vaex is an open-source DataFrame library which enables the visualisation, exploration, analysis and even machine learning on tabular datasets that are as large as your hard-drive. To do this, Vaex employs concepts such as memory mapping, efficient out-of-core algorithms and lazy evaluations.

The first step is to convert the data into a memory mappable file format, such as Apache Arrow, Apache Parquet, or HDF5

The describe method nicely illustrates the power and efficiency of Vaex: all of these statistics were computed in under 3 minutes on my MacBook Pro (15", 2018, 2.6GHz Intel Core i7, 32GB RAM). Other libraries or methods would require either distributed computing or a cloud instance with over 100GB to preform the same computations.

AWS offers instances with Terabytes of RAM. In this case you still have to manage cloud data buckets, wait for data transfer from bucket to instance every time the instance starts, handle compliance issues that come with putting data on the cloud, and deal with all the inconvenience that come with working on a remote machine. Not to mention the costs, which although start low, tend to pile up as time goes on.

when AUC is 0.5, it means model has no class separation capacity whatsoever.

ROC is a probability curve and AUC represents degree or measure of separability. It tells how much model is capable of distinguishing between classes.

In multi-class model, we can plot N number of AUC ROC Curves for N number classes using One vs ALL methodology. So for Example, If you have three classes named X, Y and Z, you will have one ROC for X classified against Y and Z, another ROC for Y classified against X and Z, and a third one of Z classified against Y and X.

When AUC is approximately 0, model is actually reciprocating the classes. It means, model is predicting negative class as a positive class and vice versa

AUC near to the 1 which means it has good measure of separability.

LR is nothing but the binomial regression with logit link (or probit), one of the numerous GLM cases. As a regression - itself it doesn't classify anything, it models the conditional (to linear predictor) expected value of the Bernoulli/binomially distributed DV.

BOW is often used for Natural Language Processing (NLP) tasks like Text Classification. Its strengths lie in its simplicity: it’s inexpensive to compute, and sometimes simpler is better when positioning or contextual info aren’t relevant

Notice that we lose contextual information, e.g. where in the document the word appeared, when we use BOW. It’s like a literal bag-of-words: it only tells you what words occur in the document, not where they occurred

Here’s my preferred way of doing it, which uses Keras’s Tokenizer class

process that takes input data through a series of transformation stages, producing data as output

Softmax turns arbitrary real values into probabilities

1. Logistic regression IS a binomial regression (with logit link), a special case of the Generalized Linear Model. It doesn't classify anything *unless a threshold for the probability is set*. Classification is just its application. 2. Stepwise regression is by no means a regression. It's a (flawed) method of variable selection. 3. OLS is a method of estimation (among others: GLS, TLS, (RE)ML, PQL, etc.), NOT a regression. 4. Ridge, LASSO - it's a method of regularization, NOT a regression. 5. There are tens of models for the regression analysis. You mention mainly linear and logistic - it's just the GLM! Learn the others too (link in a comment). STOP with the "17 types of regression every DS should know". BTW, there're 270+ statistical tests. Not just t, chi2 & Wilcoxon

400 sized probability sample (a small random sample from the whole population) is often better than a millions sized administrative sample (of the kind you can download from gov sites). The reason is that an arbitrary sample (as opposed to a random one) is very likely to be biased, and, if large enough, a confidence interval (which actually doesn't really make sense except for probability samples) will be so narrow that, because of the bias, it will actually rarely, if ever, include the true value we are trying to estimate. On the other hand, the small, random sample will be very likely to include the true value in its (wider) confidence interval

An exploratory plot is all about you getting to know the data. An explanatory graphic, on the other hand, is about telling a story using that data to a specific audience.

ggplot2 and dplyr are clear intellectual contributions because they provide tools (grammars) for visualization and data manipulation, respectively. The tools make the tasks radically easier by providing clear organizing principles coupled with effective code. Users often remark on the ease of manipulating data with dplyr and it is natural to wonder if perhaps the task itself is trivial. We claim it is not. Many probability challenges become dramatically easier, once you strike upon the “right” notation. In both cases, what feels like a matter of notation or syntax is really a more about exploiting the “right” abstraction.