Network Security Internet Technology Development Database Servers Mobile Phone Android Software Apple Software Computer Software News IT Information

In addition to Weibo, there is also WeChat

Please pay attention

WeChat public account

Shulou

Example Analysis of data Visualization and falsification in python

2025-01-21 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > Development >

Share

Shulou(Shulou.com)06/03 Report--

This article is to share with you about the example analysis of data visualization fraud in python, the editor thinks it is very practical, so I share it with you to learn. I hope you can get something after reading this article.

In the past, when we saw a poorly made chart, or a piece of data visualization, we used to laugh at them. But sometimes, especially in the past year, it seems more difficult to tell whether a visual work is a simple bad product or a false information deliberately created out of prejudice. Of course, it's nothing new to use data to lie, but now charts are becoming more and more popular, and they are all over the Internet, and many of them convey illusions. You may just glance at it, but a simple message can also take root in your head. Before you know it, the plum has turned the top on the table, and no one cares whether it will stop or keep spinning. Naturally, now we need to quickly see if a chart is lying, and this picture and text is your thoughtful guide. 1) truncated axis

The y-axis data on the left starts at 10, which is pure nonsense. The data on the right starts at 0. Good. Length is the key to the visual presentation of a bar chart, so when someone deliberately shortens the length by truncating several axes, the difference in the whole chart becomes more obvious. These people want to show more drastic changes than they really are. I discussed this issue in detail in another article. 2) double number axis

It uses a wide gap between the two ratios, perhaps to force causality. By using double axes, the magnitude of the data can be reduced or expanded according to two metrics. People usually use it to express correlation and causality. "because of this thing, another thing happened. Look, it's very clear." This project of false related data is an excellent example. 3) the sum is not right

The proportion of all the parts in the pie chart adds up to more than 100%. Some charts are designed to show certain parts of the population, and when these parts add up to more than the sum, the problem is big. For example, the pie chart represents a total of 100%, but what if the proportion of each sector adds up to more than 100%? It's weird. Take a look at this funny example. 4) only look at the absolute value

This is really just a population map. When you compare different places, categories, or groups, you must consider the relative value. A fair comparison of everything is relative. You can't say that the first town is more dangerous just because there are two robberies in one town and only one in the other town. What if the population of the first town is a thousand times that of the second? A more effective way is to compare percentages and proportions rather than absolute values and gross values. This chart bluntly shows the impact of the absolute population. 5) Limited range

The picture on the left looks like a big increase, but the figure on the right shows that this is only normal, and the increase in the selected time is actually not obvious. People tend to carefully select dates and time periods to match a specific narrative, so more consideration should be given to the historical background, frequent events, and reasonable benchmarks for comparison. When you study the overall situation, you may find something interesting. 6) Strange grading

There are only two grades on the left. what exactly do those greater than 1 include? Could be a cover. The picture on the right is better, showing more variables. Some visualization works oversimplify a complex model rather than showing a complete range of variables in the original data. Doing so can easily convert a continuous variable into a variable that belongs to a certain category. Broad grading is useful in some cases, but complexity is often the meaning of things. Oversimplification should be avoided. 7) chaotic area ratio

30 is three times as much as 10, but perhaps to increase significance, the largest rectangle on the picture is more than three times larger than the smallest one. If you encode visually according to the area, the size ratio of the drawing should be the proportion of the area. While some people are doing the visualization of area coding, they change the ratio of side length to highlight the size contrast, in order to catch the horse. Sometimes this kind of mistake is caused inadvertently, and it is even more necessary to be vigilant. 8) Control area dimension

The areas of the upper and lower figures are equal, but they look very different. Perhaps someone knows how to use area to do visual coding, but still (gu) is (yi) to make something like the picture above. I have never seen such an exaggerated example, but there may be one in the future. I bet even pictographs can appear. Just wait and see. 9) 3D for 3D

Never when you see a three-dimensional chart that is not necessary, please question its data, charts, authors and anything derived from them.

The above is the example analysis of data visualization and fraud in python. The editor believes that there are some knowledge points that we may see or use in our daily work. I hope you can learn more from this article. For more details, please follow the industry information channel.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.

Views: 227

*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.

Share To

Development

Wechat

© 2024 shulou.com SLNews company. All rights reserved.

12
Report