Use Gemini to Make Charts

Contributed by: Thomas Nield

Difficulty level: Advanced

Visualizing data can be cumbersome, regardless of whether Excel, Python, R, Tableau, or another platform is doing the work. While it is rewarding work, there is definitely a learning curve. Thankfully, we can make Gemini our visualization assistant and have it help us discover specific techniques and produce plots for us.

Let’s use matplotlib and Python as our vehicle to make charts, although Gemini can certainly generate charting code for other platforms, given there is sufficient training data. Thankfully, matplotlib code is plentiful and mature so this should make Gemini effective on many asks.

Let’s say we wanted to plot a normal distribution with a mean of 14 and a standard deviation of 1:

Prompt: Can you use matplotlib and Python to show a normal distribution with a mean of 14.005 and a standard deviation of 0.955?

Gemini: Sure. Here is a Python code using matplotlib to show a normal distribution with a mean of 14.005 and a standard deviation of 0.955:

import matplotlib.pyplot as plt
import numpy as np

# Define the mean and standard deviation
mean = 14.005
sd = 0.955

# Generate a normal distribution with the specified mean and standard deviation
x = np.random.normal(mean, sd, 10000)

# Plot the normal distribution
plt.hist(x, bins=50, density=True)
plt.xlabel('Value')
plt.ylabel('Probability')
plt.title('Normal distribution with mean = {} and standard deviation = {}'.format(mean, sd))