Image for post
Image for post
Photo by Eric Krull on Unsplash

AI, Artificial Intelligence, is a term that is the use of cognitive science to create algorithms that mimic the reasoning that humans have for problem solving and generating knowledge from data. The term has been around a long time dating to last century in the 1900s. Recently, it has become a trending topic and important addition to many products and services. However, is it always needed or a useful addition?

Is it easier?

The short answer of “ Is AI easier?”, is “no”. It is also not always the answer. Using a cognitive reasoning is not always an answer, and many find computation based on number theory to be sufficient in most applications. If you want to calculate interest on a loan, would you use artificial intelligence? You won’t. …


Image for post
Image for post
Photo by Josh Redd on Unsplash

Accessible information on functions and libraries is important to reduce bugs and increase efficiency for implementations. Information when creating a new application or solution for data in Python can become out of date. This creates a need for many ways to distribute information for consumption and use.

Machine Learning is the use or creation of systems that use algorithms to determine or analyze patterns in data. This requires the use of statistics and coding to draw connections within a source without explicit instruction or steps.

Python is an open-source language that has related libraries and functions supporting Machine Learning.

Top 5 List

  1. Anaconda Blog is dedicated to the cloud and local environment product. The blog has up to date information supporting the Python environment and its libraries. …

Image for post
Image for post
Photo by Emily Morter on Unsplash

Most of data science is data preprocessing or making data usable for analysis and computation according to many, many sources. Using a cardiac dataset, preprocessing can be shown by example. An important task is either removing or imputing values for nulls in a dataset. Only keeping values within specified ranges or imputing value to replace what does not make sense is another. Are there ever negative heartbeats per minute?

Why an issue

Using data produces results. Results are from programmed algorithms, either built in or designed for a use. Numbers change results. When nulls or out of bound values are included in a set, they need to be cleaned for proper computation. Sometimes this is due to poor data entry and mistakes in recorded information. However, in large data sets, data automatically captured through sensors or live feeds, often will have errors. …

Image for post
Image for post
Photo by Mitchell Luo on Unsplash

By tools for analytics, the reference are to apps that allow for environments to create solutions, language, libraries, and even graphical user interface to manipulate data for insights from information. There are many tools for data analytics. What is available?


Anaconda provides environment for Python and R including machine learning for mac/linux/windows. After downloading the app and installing, the environment can be customized to include variety of data science tools with libraries. Anaconda is used desktop but also exists as a cloud version.

JetBrains is an organization with a lot of apps for specific goals. There is PyCharm for Python, DataGrip for Databases, RubyMine for Ruby, and more. For analytics, the tool set and ability to integrate across their tools is unique. The positive is creating full apps that have artificial intelligent components or subcomponents and code for other pieces of the app in languages like PHP that can work together in a JetBrains solution. …

Image for post
Image for post
Photo by Tengyart on Unsplash

Communication is complex. There is written, verbal, and non-verbal. With technology, communication is very important in written form. We type more often than speaking to our devices. Using algorithms for classification and natural language processing, it is possible to score text on a scale to find sentiment. What is the value of sentiment? Sentiment is the tine of the selected piece of text. That shows positive, negative, or neutral in tone for applications in marketing, healthcare, and other domains.

How It Works

Sentiment Analysis is found by ranking. It is a logical operation of sorting terms and scoring by association to find cues to grammar to determine parts of each sentence. Afterwards, there is scoring on grouped words by trained algorithm to assign a score for finding how positive or negative a selected text is based on generated rules. …

Image for post
Image for post
Photo by Gabriel Crismariu on Unsplash

An underlying principle of programming or coding, is logic. Determining logic is in the combination of key words, variables, entities, to create a flow for a goal. A classic is Hello World, print(“Hello World”), from Python resulting in a display of Hello World. Displaying a phrase in a command line is a very simple and rewarding goal. So are solving problems using classification and clustering for real world problems.

Classification is categorization of where to place an object or device and most commonly supervised learning with labeled data. Example from Scikit-Learn for Random Forrest.

Image for post
Image for post
Photo by Joshua Sortino on Unsplash

When using data, analytics show answers and insight into facts collected in a spreadsheet, document, or database. Being able to understand data in a visual context makes a story pop from numbers and is easily understood by a wide range of readers or viewers. Visualizations are a quick and easy way to tell a data story making numbers pop and information easy to understand. There are many types of visualizations. Using data, let’s show seven ways to see the same information.

How is Immunization and Exemption of Immunization Displayed?

Immunization Records of school age children in Washington State 2014–2015 to show the seven visualizations that make analysis of data easy to understand and showcase for an audience using Power BI. …

Image for post
Image for post
Photo by sarandy westfall on Unsplash

Image capture makes a snapshot in time of a person, place, or object. Many devices include cameras for taking pictures. This is integrated into everyday life. When taking the picture, there is recognition of that picture and often an autocorrection. Taking that further, there is Optical Character Recognition (OCR) that can take a picture of text and create a usable file that is same as document. Creating a definition of a picture, understanding content, is a complex task. OCR addresses this, and a piece of OCR is knowledge from images.

Why AI?

Creating software to translate an image into text is sophisticated but easier with updates to libraries in common tools such as pytesseract in Python. This is a complicated task that requires an image to be statistically evaluated and assigned the highest probably match for each portion for a recognizable letter. Then, these pieces placed together to output a result without error that is same as the original object. This approach is deep learning using recurrent neural network (RNN), Long Short Term Memory (LSTM), to take an image as input and output text from the image in a file. …


Sarah Mason

Sarah Mason is a data analytics consultant at Sarah Mason Consulting LLC. LinkedIn sarahsmason |

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store