The Theoretical Foundations of Data Visualization and Human Perception

The Theoretical Foundations of Data Visualization and Human Perception is how analytical work becomes persuasive. The best model in the world is worthless if stakeholders don't understand its implications; visualisation turns numbers into decisions and stories into action.

Why Theoretical Foundations Data Matters

Decisions are made by people, not by models. Well-chosen charts are often the difference between an analysis that changes behaviour and one that sits unread in a notebook.

• Map the most important variable to the most visible encoding.
• Prefer direct labels to legends whenever there is room.
• Use small multiples to reveal conditional patterns.
• Be ruthless about ink-to-data ratio — delete what does not inform.

How Theoretical Foundations Data Shows Up in Practice

In a typical project, the theoretical foundations of data visualization and human perception is combined with the rest of the Data Visualisation toolkit. You rarely use any one technique in isolation; the real skill is knowing which combination fits the problem you are trying to solve, and being able to explain that choice to a non-technical stakeholder.

Core for executive readouts, product dashboards, scientific papers and — increasingly — customer-facing interactive tools.

• Publication-quality Static Visualization with Matplotlib and
• Grammar Graphics Layered Declarative Approach Visualization
• Advanced Visualization Techniques and Custom Charting
• Development Interactive Web-based Visualizations Plotly Bokeh

Back to the Data Science curriculum →

# Example 1: Matplotlib figure with dual y-axes -- Theoretical Foundations Data Visualization Human Perception
import numpy as np
import matplotlib.pyplot as plt

rng   = np.random.default_rng(0)
days  = np.arange(1, 31)
rev   = 100 + 3 * days + rng.normal(0, 8, 30)
conv  = 0.025 + 0.0008 * days + rng.normal(0, 0.003, 30)

fig, ax1 = plt.subplots(figsize=(8, 4))
ax1.plot(days, rev,  color="#1f77b4", marker="o", label="Revenue")
ax1.set_xlabel("Day")
ax1.set_ylabel("Revenue (USD)", color="#1f77b4")

ax2 = ax1.twinx()
ax2.plot(days, conv, color="#d62728", marker="s", label="Conversion")
ax2.set_ylabel("Conversion rate", color="#d62728")

ax1.set_title("Revenue and conversion over 30 days")
fig.tight_layout()
fig.savefig("metrics.png", dpi=120)

# Example 2: Seaborn KDE grid with per-group densities -- Theoretical Foundations Data Visualization Human Perception
import seaborn as sns
import numpy as np
import pandas as pd

rng = np.random.default_rng(0)
df  = pd.DataFrame({
    "group": np.repeat(["A", "B", "C"], 400),
    "value": np.concatenate([
        rng.normal(50, 10, 400),
        rng.normal(58, 12, 400),
        rng.normal(63,  9, 400),
    ]),
})

sns.set_theme(style="whitegrid")
g = sns.displot(
    df, x="value", hue="group",
    kind="kde", fill=True, common_norm=False,
    palette="deep", height=4, aspect=1.6,
)
g.set_axis_labels("value", "density")
g.fig.suptitle("KDE by group", y=1.02)
g.fig.savefig("kde.png", dpi=120)

# Example 3: Interactive Plotly bubble chart export -- Theoretical Foundations Data Visualization Human Perception
import plotly.express as px

df  = px.data.gapminder().query("year == 2007")
fig = px.scatter(
    df, x="gdpPercap", y="lifeExp",
    size="pop", color="continent",
    hover_name="country", log_x=True,
    size_max=60, template="plotly_white",
    title="Life expectancy vs GDP per capita (2007)",
)
fig.update_layout(legend_title_text="Continent")
fig.write_html("gapminder.html")
fig.write_image("gapminder.png", scale=2)

# Example 4: Annotated bar chart with ranked categories -- Theoretical Foundations Data Visualization Human Perception
import matplotlib.pyplot as plt
import numpy as np

products = np.array(["Alpha", "Bravo", "Charlie", "Delta", "Echo", "Foxtrot"])
revenue  = np.array([ 42_000, 61_500, 28_300, 74_800, 19_200, 54_100])

order    = np.argsort(revenue)[::-1]
products = products[order]; revenue = revenue[order]

fig, ax = plt.subplots(figsize=(8, 4.5))
bars    = ax.barh(products, revenue, color="#4c78a8")
ax.invert_yaxis()
ax.set_xlabel("Revenue (USD)")
ax.set_title("Q2 revenue by product")
for bar, v in zip(bars, revenue):
    ax.text(v + 1_000, bar.get_y() + bar.get_height()/2,
            f"${v:,.0f}", va="center", fontsize=10)
ax.spines[["top", "right"]].set_visible(False)
fig.tight_layout(); fig.savefig("revenue.png", dpi=120)

# Example 5: Correlation heatmap with annotations -- Theoretical Foundations Data Visualization Human Perception
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

rng = np.random.default_rng(0)
df  = pd.DataFrame(rng.standard_normal((400, 6)),
                   columns=list("ABCDEF"))
df["B"] += 0.7 * df["A"]
df["D"] -= 0.5 * df["C"]

corr = df.corr().round(2)
fig, ax = plt.subplots(figsize=(6, 5))
sns.heatmap(corr, annot=True, cmap="coolwarm", center=0,
            vmin=-1, vmax=1, square=True,
            cbar_kws={"shrink": 0.7}, ax=ax)
ax.set_title("Feature correlations")
fig.tight_layout(); fig.savefig("corr.png", dpi=120)