Advanced Visualization: Plotly and Interactive Charts

Static vs Interactive: The Decision Framework

The choice between static and interactive visualization is a cognitive design decision that affects how viewers process information.

Visualization Decision Framework Static (Matplotlib/Seaborn) Print / PDF / Paper Pixel-perfect control Reproducible figures Small file size (KB) Journal submissions Domain experts Best for: Academic papers, reports Interactive (Plotly) Web / Dashboard Hover tooltips Zoom / Pan / Filter Animation support Self-contained HTML Stakeholder exploration Best for: Dashboards, presentations Rendering Backends Matplotlib: CPU (Agg) Plotly: WebGL (GPU) Plotly: SVG (vector) Decision Tree Print/PDF → Matplotlib | Web/Dashboard → Plotly | Both → Matplotlib static + Plotly HTML ≤ 3 dims → Static OK | ≥ 4 dims → Interactive (hover/filter)

Plotly Express: The Grammar of Interactive Graphics

Scatter Plots

import plotly.express as px
import plotly.graph_objects as go
import plotly.subplots as sp
import pandas as pd
import numpy as np

df = px.data.gapminder()

fig = px.scatter(
    df.query("year == 2007"),
    x="gdpPercap", y="lifeExp",
    size="pop", color="continent",
    hover_name="country",
    log_x=True, size_max=60,
    title="GDP per Capita vs Life Expectancy (2007)",
    labels={
        "gdpPercap": "GDP per Capita (USD, log scale)",
        "lifeExp": "Life Expectancy (years)"
    }
)
fig.update_layout(template="plotly_white", font=dict(family="Inter", size=12))
fig.show()

Line Charts

df_canada = px.data.gapminder().query("country == 'Canada'")

fig = px.line(
    df_canada, x="year", y="lifeExp",
    title="Life Expectancy in Canada Over Time",
    markers=True,
    labels={"year": "Year", "lifeExp": "Life Expectancy (years)"},
    template="plotly_white"
)
fig.update_traces(line=dict(color="#2E86AB", width=3), marker=dict(size=8))
fig.show()

Bar Charts

df_tips = px.data.tips()

fig = px.bar(
    df_tips, x="day", y="total_bill", color="sex",
    barmode="group",
    title="Average Total Bill by Day and Gender",
    text_auto=".2f",
    template="plotly_white"
)
fig.show()

Histograms and Distribution Plots

fig = px.histogram(
    df_tips, x="total_bill", color="time",
    nbins=30, opacity=0.7,
    histnorm="probability density",
    marginal="rug",
    title="Distribution of Total Bills (Lunch vs Dinner)",
    template="plotly_white"
)
fig.show()

Box and Violin Plots

fig = px.box(
    df_tips, x="day", y="total_bill", color="day",
    points="all", notched=True,
    title="Total Bill Distribution by Day",
    template="plotly_white"
)
fig.show()

fig = px.violin(
    df_tips, x="day", y="total_bill", color="day",
    box=True, points="all",
    title="Violin Plot of Total Bills by Day",
    template="plotly_white"
)
fig.show()

Subplots: Multi-Panel Layouts

from plotly.subplots import make_subplots

fig = make_subplots(
    rows=2, cols=2,
    subplot_titles=("Scatter", "Bar", "Histogram", "Box"),
    horizontal_spacing=0.12,
    vertical_spacing=0.15
)

fig.add_trace(
    go.Scatter(x=df_tips["total_bill"], y=df_tips["tip"],
               mode="markers", marker=dict(size=6, opacity=0.6), name="Scatter"),
    row=1, col=1
)

day_means = df_tips.groupby("day")["total_bill"].mean().reset_index()
fig.add_trace(
    go.Bar(x=day_means["day"], y=day_means["total_bill"],
           name="Bar", marker_color="#2E86AB"),
    row=1, col=2
)

fig.add_trace(
    go.Histogram(x=df_tips["total_bill"], nbinsx=20,
                 name="Histogram", marker_color="#A23B72"),
    row=2, col=1
)

for day in df_tips["day"].unique():
    day_data = df_tips[df_tips["day"] == day]
    fig.add_trace(go.Box(y=day_data["total_bill"], name=day), row=2, col=2)

fig.update_layout(height=700, width=900, title_text="Multi-Panel Dashboard",
                  template="plotly_white", showlegend=False)
fig.show()

Secondary Y-Axes

months = pd.date_range("2024-01-01", periods=12, freq="MS")
revenue = np.random.uniform(50000, 120000, 12)
orders = np.random.poisson(200, 12)

fig = make_subplots(specs=[[{"secondary_y": True}]])

fig.add_trace(
    go.Scatter(x=months, y=revenue, name="Revenue ($)",
               line=dict(color="#2E86AB", width=3), mode="lines+markers"),
    secondary_y=False
)
fig.add_trace(
    go.Bar(x=months, y=orders, name="Orders",
           marker_color="#a23b727f"),
    secondary_y=True
)

fig.update_yaxes(title_text="Revenue ($)", secondary_y=False)
fig.update_yaxes(title_text="Number of Orders", secondary_y=True)
fig.update_layout(title="Revenue and Orders Over Time", template="plotly_white")
fig.show()

Statistical Visualizations

Correlation Heatmaps

numeric_cols = ["total_bill", "tip", "size"]
corr_matrix = df_tips[numeric_cols].corr()

fig = px.imshow(
    corr_matrix, text_auto=".3f",
    color_continuous_scale="RdBu_r",
    zmin=-1, zmax=1,
    title="Correlation Matrix Heatmap"
)
fig.show()

Geographical Maps

# Choropleth Map
df_2007 = px.data.gapminder().query("year == 2007")

fig = px.choropleth(
    df_2007, locations="iso_alpha", color="lifeExp",
    hover_name="country",
    color_continuous_scale=px.colors.sequential.Viridis,
    title="World Life Expectancy (2007)"
)
fig.update_layout(geo=dict(showframe=False, showcoastlines=True))
fig.show()

# Scatter Mapbox
np.random.seed(42)
df_map = pd.DataFrame({
    "lat": 40.7128 + np.random.normal(0, 0.05, 200),
    "lon": -74.0060 + np.random.normal(0, 0.05, 200),
    "value": np.random.exponential(50, 200)
})

fig = px.scatter_mapbox(
    df_map, lat="lat", lon="lon", color="value", size="value",
    color_continuous_scale="Viridis", size_max=15, zoom=11,
    mapbox_style="carto-positron"
)
fig.show()

Animated Charts

df = px.data.gapminder()

fig = px.scatter(
    df, x="gdpPercap", y="lifeExp", size="pop",
    color="continent", hover_name="country",
    log_x=True, size_max=55,
    range_x=[100, 100000], range_y=[25, 90],
    animation_frame="year", animation_group="country",
    title="Global Development Over Time (1952-2007)"
)
fig.show()

Dashboard-Ready: Updatemenus and Sliders

# Dropdown filter
fig = go.Figure()
continents = df["continent"].unique()
for continent in continents:
    cdf = df[df["continent"] == continent]
    fig.add_trace(go.Scatter(
        x=cdf["gdpPercap"], y=cdf["lifeExp"],
        mode="markers", marker=dict(size=cdf["pop"] / 2e7, opacity=0.6),
        name=continent,
        visible=True if continent == "Asia" else "legendonly"
    ))

fig.update_layout(
    updatemenus=[dict(
        buttons=[
            dict(label="All Continents", method="update",
                 args=[{"visible": [True] * len(continents)}])
        ] + [
            dict(label=c, method="update",
                 args=[{"visible": [i == idx for i in range(len(continents))]}])
            for idx, c in enumerate(continents)
        ],
        direction="down", showactive=True, x=0.17, y=1.15
    )],
    template="plotly_white", height=550
)
fig.show()

# Range slider
fig = go.Figure()
fig.add_trace(go.Scatter(
    x=df_canada["year"], y=df_canada["lifeExp"],
    mode="lines+markers", line=dict(color="#2E86AB", width=3),
    fill="tozeroy", fillcolor="#2e86ab33"
))
fig.update_layout(
    xaxis=dict(
        rangeselector=dict(buttons=[
            dict(count=10, label="10Y", step="year", stepmode="backward"),
            dict(count=20, label="20Y", step="year", stepmode="backward"),
            dict(step="all", label="All")
        ]),
        rangeslider=dict(visible=True), type="date"
    ),
    title="Life Expectancy with Range Slider", template="plotly_white"
)
fig.show()

Customizing Themes and Export

# Built-in templates
import plotly.io as pio
pio.templates.default = "plotly_white"

# Custom template
custom_template = go.layout.Template(
    layout=go.Layout(
        title=dict(font=dict(family="Inter", size=18, color="#1a1a2e"),
                   x=0.5, xanchor="center"),
        font=dict(family="Inter", size=12, color="#1a1a2e"),
        plot_bgcolor="white", paper_bgcolor="white",
        colorway=["#2E86AB", "#A23B72", "#F18F01", "#C73E1D", "#3B1F2B"]
    )
)

# Export
fig.write_image("figure.png", scale=3, width=800, height=500)  # 300 DPI
fig.write_image("figure.svg", width=800, height=500)  # Vector
fig.write_html("interactive.html", include_plotlyjs=True)  # Standalone

Library Comparison

Criterion	Matplotlib	Seaborn	Plotly
Best for	Fine-grained control	Statistical plots	Interactive dashboards
Interactivity	None	None	Native
Statistical models	Manual	Built-in	Limited
3D plotting	Axes3D	Limited	scatter_3d
Animation	FuncAnimation	Limited	animation_frame
Export quality	Excellent	Excellent	Good (kaleido)
Browser embedding	No	No	Yes

Key Takeaways

Practice Exercises

Create an interactive scatter plot using px.data.iris() with marginal distributions and a trendline
Build a 2x3 subplot dashboard using the px.data.gapminder() dataset
Create the animated Gapminder bubble chart with custom colorscale and range slider
Create a masked correlation heatmap (upper triangle only) with annotations
Create a choropleth map colored by GDP per capita with scatter_mapbox overlay