Data Science Data Distribution

What Is a Data Distribution?

A distribution is simply a description of how often each value, or range of values, shows up in a dataset. Two datasets can share the same mean and still look completely different once you see how their values are spread out.

import numpy as np

# 250 random integers, each between 0 (inclusive) and 100 (exclusive)
data = np.random.randint(0, 100, 250)

print(data[:10])
print("mean:", np.mean(data))
print("std dev:", np.std(data))

Printing the raw numbers doesn't tell you much on its own - with 250 values, no one can eyeball a pattern. Grouping the values into a chart is what turns a list of numbers into a shape you can reason about.

Visualizing With a Histogram

import matplotlib.pyplot as plt

plt.hist(data, bins=10)
plt.xlabel("Value")
plt.ylabel("Count")
plt.show()

A histogram sorts values into equal-width bins and draws a bar for how many values fall in each one. Tall bars mark where values cluster; short or empty bars mark ranges the data rarely visits.

• Where the peak (or peaks) of the bars sit
• How wide or narrow the spread of bars is
• Whether one side trails off more slowly than the other (skew)
• Any bars sitting far away from the rest (possible outliers)

Distribution Shapes You'll See

Random integers like the ones above tend to spread out fairly evenly across their range - that's called a uniform distribution. Many real-world measurements instead cluster tightly around a center and taper off symmetrically at both ends, which is the normal distribution covered next.