vrijdag 30 december 2022

Answers from ChatGPT: How can data journalists use google sheets ml app?

Here are some answers by ChatGPT on the following questions:

How can data journalists use Google sheets ml app?

What is the use of the ml app in google sheets for data journalists?

Can you give an example?

What is the use of ChatGPT for data journalists?

zondag 18 december 2022

ChatGPT as a tool for data journalist

ChatGPT is becoming a big hit witin a week there are already millions of users. Access is simple; go to https://chat.openai.com/chat and log in for free with  for example a google account and you are in business. A hot topic is trying the most weird assignments.Just do a simple search on Twitter for chatGPT and you interesting examples. Of course there is discussion about the credibility..And of course there is more: fake news, students write essays with chatGPT, or journalist and communicators writing stories. How to improve your writing with chatGPT….

For data journalism chatGPT open news perspectives as well. Here are two examples related to simple data tasks in Calc and R. Chat GPT creates the R code and gives a howto for Calc.

Here is one way to calculate the squares of the first 10 numbers in R:

# Create a vector of the first 10 numbers
numbers <- 1:10

# Calculate the squares of the numbers
squares <- numbers^2

# Print the result
squares
This will output the following vector: 1 4 9 16 25 36 49 64 81 100.

Can you make a bar graph of this output
Certainly! Here is one way to create a bar graph of the squares of the first 10 numbers in R using the ggplot2 package:

# Load the ggplot2 package
library(ggplot2)

# Create a data frame with the numbers and their squares
df <- data.frame(numbers, squares)

# Create the bar graph
ggplot(df, aes(x = numbers, y = squares)) +
geom_col()
This will create a bar graph with the numbers on the x-axis and the squares on the y-axis. The bars will represent the squares of the corresponding numbers.
You can customize the appearance of the graph by adding additional layers to the ggplot function. For example, you can change the appearance of the bars using the fill parameter, or add a title using the ggtitle function.
Here is an example of a customized bar graph:

ggplot(df, aes(x = numbers, y = squares)) +
geom_col(fill = "orange") +
ggtitle("Squares of the First 10 Numbers") +
theme_minimal()
This will create a bar graph with orange bars and a title. The theme_minimal function sets a minimalistic theme for the graph.

­

Make a bar graph of the  square of the first 10 numbers in Calc(open office)

To create a bar graph of the results of the squares of the first 10 numbers in Calc, you can follow these steps:
1. Enter the numbers you want to square in cells A1 through A10.
2. In cells B1 through B10, enter the formulas to calculate the squares of the numbers in cells A1 through A10. You can use either the =POWER(A1, 2) or =A1^2 formula, as described in my previous response.
3. Select the range of cells containing the numbers and the squares (e.g., A1:B10).
4. Click the "Insert" tab and then click the "Bar" button in the "Charts" group.
5. From the list of chart types that appears, choose the type of bar chart you want to create (e.g., "Clustered Bar," "Stacked Bar," etc.).
6. A bar chart will be inserted in your spreadsheet, showing the squares of the first 10 numbers.
7. To customize the appearance of the chart, you can right-click on it and select "Format Chart Area" to open the "Format Chart Area" dialog box. From here, you can change the colors, fonts, and other formatting options for the chart.
I hope this helps! Let me know if you have any questions.

Machine Learning for data journalists

I have been writing about machine learning and data science as the next step for data journalists in 2019. For example: https://d3-media.blogspot.com/2019/03/kaggle-is-there-data-journalism-in.html. However this way of using ML had a steep learning curve. First you have be familiar with R and next you have to dig into various models of ML, like RandomForrest or Tensorflow.

Now there is light at the end of the tunnel, google sheets included an add-on for ML. Under extension in the ribbon you find ‘simple ML’ for sheets. This should give data journalism a new boost in working with statistical models. ML for sheets has two option, to predict missing values or to spot abnormal values. In order to get started you should read the documentation: https://simplemlforsheets.com/ and try the included dataset. Step by step you practice missing values, abnormal values, training and evaluating a model and finally predict values with a model. Have learned the hard way with R a couple of years ago, I was blown away; just a pushing a few buttons and done. No deep knowledge needed….however you better understand what you are doing. So if you have the taste, eat more ML at a special course by Google: Google Machine Learning Education: https://developers.google.com/machine-learning

donderdag 1 december 2022

From data journalism to data sensors

MEASUREMENT OF CO2