Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: [Scalar art] Generate an image of a sunny Berlin, New Hampshire cityscape. The sky is clear and crisp, with the city skyline visible in the distance. People are depicted engaging in outdoor activities, such as biking and walking, to convey the sense of a fresh, clean environment. In the foreground, a cozy living room is shown with a computer screen displaying the Google search bar featuring "Snoop Dogg." The search trends chart is displayed nearby, depicting a noticeable downward slope, indicating the decrease in interest in Snoop Dogg's music and news. The visual correlation between the clean air and the declining popularity of Snoop Dogg is emphasized without the use of words or speech bubbles. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

---

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Air pollution in Berlin, New Hampshire and Google searches for 'snoop dog'. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Scalar art Data cyber art Glitch art Low poly Symbolism
ChatGPT: Scalar art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air pollution in Berlin, New Hampshire and Google searches for 'snoop dog', in the following situation: The decrease in air pollution in Berlin, New Hampshire caused a decrease in Snoop Dogg searches because people didn't need the air "cleared" by his music anymore. It seems they no longer had to "drop it like it's hot" to combat the smog. Without the need for "gin and juice" to cope with the pollution, the city was just "living it up" in the clean, fresh air. This correlation suggests that Snoop Dogg's popularity was, quite literally, "up in smoke" along with the air pollution. His fans no longer felt the "pressure" to listen to his music, as the "puff puff pass" of clean air became the new attraction. In essence, as the pollution decreased, so did the "Snoop-mania" in a truly "smoke-free" turn of events. It's a "doggone" mystery, but it seems like Snoop Dogg was inadvertently "blowing" in the wind of air quality trends. Whether this was just a "gin and tonic" of fate or a "doggy style" coincidence, one thing's for sure – the air in Berlin, New Hampshire may have been cleaner, but it was also a little less "Snoopified.". Keep the description simple.
ChatGPT: On a sunny day in Berlin, New Hampshire, the air is noticeably clearer, with fewer emissions floating in the breeze. People are out and about, enjoying the clean, fresh air. Some are riding bikes, while others are taking leisurely strolls. The city skyline is visible in the distance, no longer obscured by a smoggy haze. Meanwhile, on a computer screen in a cozy living room, the Google search bar reads "Snoop Dogg." However, the search volume for the famous rapper has noticeably decreased, with fewer people searching for his music and latest news. The chart displaying search trends for "Snoop Dogg" is on a downward slope, mirroring the decline in air pollution levels. The music of Snoop Dogg, once a popular choice for combating the smog, seems to have taken a backseat as the city revels in its newfound clean air. These two scenes show a correlation between the decrease in air pollution and the declining popularity of Snoop Dogg in Berlin, New Hampshire.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ Scalar art ] and depicting this scene: On a sunny day in Berlin, New Hampshire, the air is noticeably clearer, with fewer emissions floating in the breeze. People are out and about, enjoying the clean, fresh air. Some are riding bikes, while others are taking leisurely strolls. The city skyline is visible in the distance, no longer obscured by a smoggy haze. Meanwhile, on a computer screen in a cozy living room, the Google search bar reads "Snoop Dogg." However, the search volume for the famous rapper has noticeably decreased, with fewer people searching for his music and latest news. The chart displaying search trends for "Snoop Dogg" is on a downward slope, mirroring the decline in air pollution levels. The music of Snoop Dogg, once a popular choice for combating the smog, seems to have taken a backseat as the city revels in its newfound clean air. These two scenes show a correlation between the decrease in air pollution and the declining popularity of Snoop Dogg in Berlin, New Hampshire. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [Scalar art] Generate an image of a sunny Berlin, New Hampshire cityscape. The sky is clear and crisp, with the city skyline visible in the distance. People are depicted engaging in outdoor activities, such as biking and walking, to convey the sense of a fresh, clean environment. In the foreground, a cozy living room is shown with a computer screen displaying the Google search bar featuring "Snoop Dogg." The search trends chart is displayed nearby, depicting a noticeable downward slope, indicating the decrease in interest in Snoop Dogg's music and news. The visual correlation between the clean air and the declining popularity of Snoop Dogg is emphasized without the use of words or speech bubbles.

---

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

AI academic paper

Sniffing Out Snoop Dog: The Link Between Berlin's Dirty Air and Google Searches for the Furry Rapper The Journal of Unlikely Correlations Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Air pollution in Berlin, New Hampshire Google searches for 'snoop dog' Neither / both
Issue:	What is the issue? The data is incorrect The chart isn't displaying properly There is a typo The source link is incorrect A calculation is wrong Something else
Additional details: Optional
Confirm you are a human:

Data details

Why this works

1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
2. Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
   no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
   p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.0447154,0.057377,0.0122449,0.0619835,0.0384615,0.00328947,0.0138122,0.00561798,0.0109589,0.00547945,0,0.019774,0.0109589,0.00842697,0.0110701,0,0,0.00555556,0,0.0110497,])
array_2 = np.array([50.8333,67.9167,40.5833,38.5,32.9167,24.3333,21.25,24.6667,17.75,13.5833,17.5,17.9167,15.25,11.25,9.41667,8.91667,9.41667,8.75,13.3333,10.4444,])
array_1_name = "Air pollution in Berlin, New Hampshire"
array_2_name = "Google searches for 'snoop dog'"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)

Reuseable content

• High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.
  
  If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.
  
  Alternatively you can use a tool like Inkscape.
  
• High resolution line chart, optimized for mobile
• Alternative high resolution line chart
• Scatterplot
• Portable line chart (png)
• Portable line chart (png), optimized for mobile
• Line chart for only Air pollution in Berlin, New Hampshire
• Line chart for only Google searches for 'snoop dog'
• AI-generated correlation image
• The spurious research paper: Sniffing Out Snoop Dog: The Link Between Berlin's Dirty Air and Google Searches for the Furry Rapper