Python Dataviz Guide

import matplotlib.pyplot as plt
import matplotlib as mpl

# Publication-quality defaults
plt.rcParams.update({
    'figure.figsize': (6, 4),
    'figure.dpi': 150,
    'savefig.dpi': 300,
    'savefig.bbox': 'tight',
    'font.size': 11,
    'font.family': 'serif',
    'font.serif': ['Times New Roman'],
    'axes.labelsize': 12,
    'axes.titlesize': 13,
    'xtick.labelsize': 10,
    'ytick.labelsize': 10,
    'legend.fontsize': 10,
    'lines.linewidth': 1.5,
    'lines.markersize': 6,
    'axes.grid': True,
    'grid.alpha': 0.3,
})

import numpy as np

epochs = np.arange(1, 51)
acc_mean = 1 - 0.5 * np.exp(-epochs / 10)
acc_std = 0.03 * np.exp(-epochs / 20)

fig, ax = plt.subplots()
ax.plot(epochs, acc_mean, label='Our Method', color='#2563EB')
ax.fill_between(epochs, acc_mean - acc_std, acc_mean + acc_std,
                alpha=0.2, color='#2563EB')
ax.set_xlabel('Epoch')
ax.set_ylabel('Accuracy')
ax.set_ylim(0.4, 1.0)
ax.legend(frameon=False)
fig.savefig('accuracy_curve.pdf')  # Vector format for papers

fig, axes = plt.subplots(1, 3, figsize=(15, 4), sharey=True)

for ax, dataset, color in zip(axes, ['CIFAR-10', 'ImageNet', 'COCO'],
                                ['#2563EB', '#DC2626', '#16A34A']):
    x = np.random.randn(200)
    ax.hist(x, bins=30, color=color, alpha=0.7, edgecolor='white')
    ax.set_title(dataset)
    ax.set_xlabel('Score Distribution')

axes[0].set_ylabel('Count')
plt.tight_layout()
fig.savefig('multi_panel.pdf')

import seaborn as sns
import pandas as pd

data = pd.DataFrame({
    'Method': ['Baseline', 'Baseline', 'Ours', 'Ours', 'Ours+FT', 'Ours+FT'],
    'Metric': ['BLEU', 'ROUGE'] * 3,
    'Score': [34.2, 45.1, 41.8, 52.3, 48.5, 58.7]
})

fig, ax = plt.subplots(figsize=(8, 5))
sns.barplot(data=data, x='Metric', y='Score', hue='Method',
            palette=['#94A3B8', '#3B82F6', '#EF4444'], ax=ax)
ax.set_ylabel('Score')
ax.legend(title='Method', frameon=False)
fig.savefig('comparison.pdf')

corr_matrix = pd.DataFrame(
    np.random.randn(8, 8),
    columns=[f'Feature {i}' for i in range(8)]
).corr()

fig, ax = plt.subplots(figsize=(8, 7))
sns.heatmap(corr_matrix, annot=True, fmt='.2f', cmap='RdBu_r',
            center=0, square=True, linewidths=0.5, ax=ax)
ax.set_title('Feature Correlation Matrix')
fig.savefig('heatmap.pdf')

df = pd.DataFrame({
    'Group': np.repeat(['Control', 'Treatment A', 'Treatment B'], 100),
    'Value': np.concatenate([
        np.random.normal(50, 10, 100),
        np.random.normal(55, 8, 100),
        np.random.normal(60, 12, 100)
    ])
})

fig, ax = plt.subplots(figsize=(8, 5))
sns.violinplot(data=df, x='Group', y='Value', palette='Set2',
               inner='box', ax=ax)
ax.set_ylabel('Measurement')
fig.savefig('violin.pdf')

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,
                 title="GDP vs Life Expectancy (2007)")
fig.write_html("interactive_scatter.html")
fig.write_image("scatter.pdf")  # Requires kaleido