Data

SHILPA

Kirk's four group actions were those of data acquisition, data examination, data transformation, and data exploration. Data transformation will be discussed in detail further. The process by which data is converted from one format or structure to another format or structure is known as data transformation. This process is critical to the activities, such as those of the integration of data and management of data. 

      Data transformation is the process of converting data from one format or structure to another format or structure. Data conversion is crucial for activities such as data integration and data management (Kirk, 2019). Changing data involves several activities: you can change the data types depending on your project needs, clean up the data by deleting blank values ​​or duplicate data, enriching the data, or aggregating. Data transformation allows companies to transfer data from different locations (Kirk, 2019). And formats as functional ideas. It does this by streamlining the processes of improving, standardizing, and consolidating a wide variety of data.

Actions covered by data transformation

Data design: When there is a large amount of data to be processed, the general tendency is to jump right into it. However, before converting data into analytical data, it is important for business users to engage in a comprehensive understanding of the business processes they are trying to analyze, implement and design in the format they are targeting (Tang et al., 2019).

Data profiling: Before moving on to data conversion, data profiling can help a person better understand the status of raw data. It is also easy to see how much work is needed to prepare them for analysis. This action is primarily intended to verify data prior to actual processing (Tang et al., 2019).

Data Cleaning: Armed with the knowledge gained from data profiling, you can easily understand what to do to use your data. Cleaning up data at the beginning of the data transition phase helps to ensure that not enough data enters the system and eventually reaches the end users (Tang et al., 2019).

Aligning Data with Target Format‌: Having sales data between data has long been a challenge for business intelligence users. One of the many benefits of static data is that it can erase existing asymmetric data (Tang et al., 2019).

Reference:

Kirk, A. (2019). Data Visualisation: A Handbook for Data Driven Design (p. 50). SAGE

Tang, Z., Peng, X., Li, T., Zhu, Y., & Metaxas, D. N. (2019).Adatransform: Adaptive data transformation. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2998-3006).

MANASA

Working with data helps us answer the specific enquiries that we are seeking for, though this process might look tedious, a structured approach helps in solving the objective posed.

Data Aquisition: Collection of raw materials.

     DAQ stands for Data Acquisition. Considering data as raw material, data collection is an exploitative process. To get started with the dataset you like, visit a resource like website, browse, browse through the various options and find and select the dataset you are interested in. Then download or receive an electronic copy of the data (Kirk, 2019). This completes the data collection. It could be a weekly collection of basic data. The person should have a clear idea of ​​the type of data needed to satisfy their curiosity and continue working with the data. Virtually any data may be available, research is needed to better understand the source and / or location of the data and the method used to access the data (Ajayi, 2019). In addition, curiosity, exploration or desire should be built around specific details, not all available data or everything in general. The data must be carefully selected to work in the future. Work is needed to determine the reason for choosing “specific” data and to establish a process for collecting data (Kirk, 2019).

    Basically, it is the process of collecting, filtering and cleaning data before further processing the data into groups of next steps. Data collection is governed by four Vs: volume, speed, variation, and cost. Most data collection scenarios volume, speed and type. However, determining whether the data value is high or low will take place in subsequent activity groups (Ajayi, 2019). The process needs to determine the current data collection requirements. This is followed by the disclosure of current methods used to collect data. Modern approaches determine the extent to which data collection needs are met.                                                            

Reference:

Kirk, A. (2019). Data visualisation: A handbook for data driven design. Los Angeles: Sage Publications.

Ajayi, C. O. (2019). Fundamentals of Data Visualization: A Primer on Making Informative and Compelling Figures. O'Reilly Media, Incorporated.