Beautiful Statistical
Visualizations with Seaborn

import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

# Seaborn ships with built-in example datasets
tips = sns.load_dataset("tips")
print(tips.head())
#    total_bill   tip     sex smoker  day    time  size
# 0       16.99  1.01  Female     No  Sun  Dinner     2
# 1       10.34  1.66    Male     No  Sun  Dinner     3

# Set a global theme — applies to all subsequent plots
sns.set_theme(style="whitegrid", palette="deep")

# ─── 1. Distribution plot ───────────────────────────
fig, ax = plt.subplots(figsize=(8, 4))
sns.histplot(tips["total_bill"], kde=True, ax=ax, color="steelblue")
ax.set_title("Distribution of Total Bill")
plt.tight_layout()
plt.show()

# ─── 2. Box plot ────────────────────────────────────
fig, ax = plt.subplots(figsize=(8, 4))
sns.boxplot(data=tips, x="day", y="total_bill", hue="smoker",
            palette="Set2", ax=ax)
ax.set_title("Total Bill by Day and Smoker Status")
plt.show()

# ─── 3. Violin plot ─────────────────────────────────
fig, ax = plt.subplots(figsize=(8, 5))
sns.violinplot(data=tips, x="day", y="total_bill",
               hue="sex", split=True, palette="muted")
ax.set_title("Bill Distribution: Violin with split hue")
plt.show()

# ─── 4. Bar plot (with CI) ──────────────────────────
fig, ax = plt.subplots(figsize=(8, 4))
sns.barplot(data=tips, x="day", y="tip",
            estimator="mean", errorbar="sd", palette="pastel")
ax.set_title("Mean Tip ± SD by Day")
plt.show()

# ─── 5. Count plot ──────────────────────────────────
fig, ax = plt.subplots(figsize=(6, 4))
sns.countplot(data=tips, x="day", hue="sex", palette="Set1")
ax.set_title("Number of Visits by Day and Gender")
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

# ─── Seaborn built-in styles ─────────────────────
# "darkgrid", "whitegrid", "dark", "white", "ticks"
sns.set_style("whitegrid")

# ─── Built-in palettes ───────────────────────────
# Qualitative: "deep", "muted", "pastel", "bright", "dark", "colorblind"
# Sequential:  "Blues", "Greens", "Purples", "rocket", "mako", "viridis"
# Diverging:   "coolwarm", "RdBu", "icefire"

palette_names = ["deep", "muted", "pastel", "colorblind", "rocket", "viridis"]

fig, axes = plt.subplots(len(palette_names), 1, figsize=(8, 8))
for ax, name in zip(axes, palette_names):
    sns.palplot(sns.color_palette(name, 8), ax=ax)
    ax.set_title(name, loc="left", fontsize=9)
plt.tight_layout()
plt.show()

# ─── Context scaling ─────────────────────────────
# "paper" < "notebook" < "talk" < "poster"
with sns.plotting_context("talk"):
    fig, ax = plt.subplots(figsize=(8, 4))
    sns.histplot(sns.load_dataset("tips")["tip"], kde=True, color="purple")
    ax.set_title("Talk context — larger text")
    plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

iris = sns.load_dataset("iris")

# ─── Basic pairplot ──────────────────────────────
# Diagonal: histogram/KDE; Off-diagonal: scatter plots
g = sns.pairplot(iris, hue="species", palette="deep",
                 diag_kind="kde",       # "hist" or "kde"
                 plot_kws={"alpha": 0.6, "s": 50})
g.fig.suptitle("Iris Pairplot — All Feature Pairs", y=1.02, fontsize=14)
plt.show()

# ─── Pairplot with regression ─────────────────────
g = sns.pairplot(iris.drop("species", axis=1),
                 kind="reg",        # scatter + regression line
                 corner=True)       # only lower triangle
plt.show()

# ─── Pairplot selecting specific columns ──────────
g = sns.pairplot(iris,
                 vars=["sepal_length", "petal_length"],
                 hue="species",
                 markers=["o", "s", "D"])
plt.show()

print(f"Pairplot grid size: {len(iris.columns)-1}×{len(iris.columns)-1}")
# → 4×4 plot grid (one per numeric column)

import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

# ─── Correlation heatmap ─────────────────────────
flights = sns.load_dataset("flights").pivot(
    index="month", columns="year", values="passengers"
)

fig, axes = plt.subplots(1, 2, figsize=(14, 5))

# Full heatmap with annotations
sns.heatmap(flights,
            ax=axes[0],
            cmap="YlOrRd",          # colormap
            annot=True,             # show values in cells
            fmt="d",                # integer format
            linewidths=0.5,
            cbar_kws={"label": "Passengers"})
axes[0].set_title("Monthly Airline Passengers")

# Correlation matrix heatmap with mask
iris = sns.load_dataset("iris").select_dtypes("number")
corr = iris.corr()
mask = np.triu(np.ones_like(corr, dtype=bool))  # upper triangle

sns.heatmap(corr,
            ax=axes[1],
            mask=mask,              # only lower triangle
            cmap="coolwarm",
            center=0,              # center colormap at 0
            annot=True, fmt=".2f",
            square=True,           # square cells
            linewidths=0.5)
axes[1].set_title("Iris Feature Correlation")

plt.tight_layout()
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

tips = sns.load_dataset("tips")

# ─── regplot: single regression with CI band ────
fig, axes = plt.subplots(1, 3, figsize=(15, 4))

sns.regplot(data=tips, x="total_bill", y="tip",
            ax=axes[0],
            ci=95,              # 95% confidence band
            scatter_kws={"alpha": 0.5, "color": "steelblue"},
            line_kws={"color": "red"})
axes[0].set_title("regplot: tip ~ total_bill")

# ─── lmplot: faceted regression ─────────────────
g = sns.lmplot(data=tips, x="total_bill", y="tip",
               hue="smoker",
               col="time",         # one column per 'time' value
               ci=95,
               scatter_kws={"alpha": 0.6})
g.set_titles("{col_name}")
plt.suptitle("lmplot: Faceted by Meal Time", y=1.03)
plt.show()

# ─── jointplot: marginal distributions ──────────
g = sns.jointplot(data=tips, x="total_bill", y="tip",
                  kind="reg",        # scatter + regression in center
                  color="purple",
                  marginal_kws={"bins": 20})
g.set_axis_labels("Total Bill ($)", "Tip ($)")
plt.suptitle("Jointplot with marginal KDE", y=1.02)
plt.show()

# ─── residplot: check regression residuals ──────
fig, ax = plt.subplots(figsize=(7, 4))
sns.residplot(data=tips, x="total_bill", y="tip",
              lowess=True,
              scatter_kws={"alpha": 0.5},
              line_kws={"color": "red"})
ax.axhline(0, ls="--", color="gray")
ax.set_title("Residual Plot — Non-linearity Check")
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

tips = sns.load_dataset("tips")

# ─── catplot: unified categorical figure-level ──
g = sns.catplot(
    data=tips,
    x="day", y="total_bill",
    hue="sex",
    col="time",             # separate column per meal time
    kind="violin",          # "box","strip","swarm","bar","point"
    split=True,
    height=5, aspect=0.8,
    palette="husl"
)
g.set_axis_labels("Day of Week", "Total Bill ($)")
g.set_titles("{col_name} Dining")
g.add_legend(title="Gender")
plt.suptitle("Tip Distributions by Time, Day, and Gender", y=1.02)
plt.show()

# ─── relplot: scatter/line figure-level ─────────
g = sns.relplot(
    data=tips,
    x="total_bill", y="tip",
    hue="smoker",
    size="size",            # encode party size as dot size
    style="sex",            # encode sex as marker shape
    col="time",
    height=4,
    palette="Set1"
)
g.set_titles("{col_name}")
plt.suptitle("relplot: size, hue, style, col encodings", y=1.02)
plt.show()

# ─── Manual FacetGrid ───────────────────────────
g = sns.FacetGrid(tips, col="day", col_wrap=2,
                  height=3.5, sharey=False)
g.map_dataframe(sns.scatterplot, x="total_bill", y="tip",
                hue="sex", palette="dark")
g.add_legend()
g.set_titles(col_template="{col_name}")
plt.suptitle("Custom FacetGrid — Tips per Day", y=1.02)
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.ticker as mticker

tips = sns.load_dataset("tips")

# ─── Full custom publication figure ─────────────
sns.set_theme(style="ticks", context="paper",
              font="DejaVu Sans", font_scale=1.1,
              rc={"axes.spines.right": False,
                  "axes.spines.top": False})

fig, axes = plt.subplots(1, 2, figsize=(11, 4))
fig.suptitle("Restaurant Tips Analysis", fontsize=14, fontweight="bold", y=1.02)

# Left: violin plot
sns.violinplot(data=tips, x="day", y="total_bill",
               hue="sex", split=True,
               inner="quart",          # show quartile lines inside
               palette={"Male": "#4C72B0", "Female": "#DD8452"},
               ax=axes[0], linewidth=1.2)
axes[0].set_xlabel("Day of Week", fontsize=11)
axes[0].set_ylabel("Total Bill ($)", fontsize=11)
axes[0].set_title("Bill Distribution by Day", fontsize=12)
axes[0].legend(title="Gender", frameon=False)

# Right: swarm over box
sns.boxplot(data=tips, x="time", y="tip",
            palette="pastel", ax=axes[1], width=0.5, linewidth=1.2)
sns.swarmplot(data=tips, x="time", y="tip",
              color="0.25", size=3.5, ax=axes[1])  # overlay raw data
axes[1].set_xlabel("Meal Time", fontsize=11)
axes[1].set_ylabel("Tip ($)", fontsize=11)
axes[1].set_title("Tip Distribution: Box + Swarm", fontsize=12)

# Formatting
for ax in axes:
    ax.yaxis.set_major_formatter(mticker.FormatStrFormatter("$%.0f"))
    sns.despine(ax=ax, trim=True)     # remove top/right spines

plt.tight_layout()
fig.savefig("tips_analysis.pdf", dpi=300, bbox_inches="tight")
plt.show()
print("Figure saved to tips_analysis.pdf")