Grow with Data Analysis

Data analysis is the process of inspecting, cleaning, transforming, and modelling data with the goal of discovering useful information, informing conclusions, and supporting decision-making. (1)

The above processes are executed with the support of different tools depending on the amount of data involved.

From a classical spreadsheet to more complex software allows the analyst to automatically extract information from vast amounts of data, often stored in different locations, transform them into something more specific and load them into a dashboard or other document for easy interpretation.

This process is generally referred to as ETL (Extract - Transform - Load).

Examples

Spreadsheets

Any spreadsheet can be manipulated to create condensed views, showing KPIs or a selection of data, like sales quantity for each item or store location, or repeated purchases from the same customer.

The example below is created from a medium size spreadsheet with 28 columns (A to AB) and, 78 rows.

Python

Python is a high-level programming language, it is the de facto language for Data Science, its flexibility allows the analyst to create automated algorithms to elaborate very high volumes of data, whether historical or live. 

Imagine Bob has a rental property in the mountains and has installed a temperature sensor that allows him to record every measurement in a database, this can allow Bob to monitor the temperature remotely or even to create a graph that represents the average Max and Min temperature in the location over a longer period of time, so when a client asks how cold it gets he can reply with certainty.  

Let's calculate the data points on a 10-year base

• 365 days in one year, 3650 days in 10 years (for simplicity you can skip the leap years)

• Continuous reading but we will use only the Max and Min every day so 2 readings each day

• 3650 Max temperature + 3650 Min temperature or a total of 7300 readings that need to be labelled and averaged across the 10 years.