Data Visualization Skill

Chart selection guidance, Python visualization code patterns, design principles, and accessibility considerations for creating effective data visualizations.

Chart Selection Guide

Choose by Data Relationship

When NOT to Use Certain Charts

• Pie charts: Avoid unless <6 categories and exact proportions matter less than rough comparison. Humans are bad at comparing angles. Use bar charts instead.
• 3D charts: Never. They distort perception and add no information.
• Dual-axis charts: Use cautiously. They can mislead by implying correlation. Clearly label both axes if used.
• Stacked bar (many categories): Hard to compare middle segments. Use small multiples or grouped bars instead.
• Donut charts: Slightly better than pie charts but same fundamental issues. Use for single KPI display at most.

Python Visualization Code Patterns

Setup and Style

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

# Professional style setup
plt.style.use('seaborn-v0_8-whitegrid')
plt.rcParams.update({
    'figure.figsize': (10, 6),
    'figure.dpi': 150,
    'font.size': 11,
    'axes.titlesize': 14,
    'axes.titleweight': 'bold',
    'axes.labelsize': 11,
    'xtick.labelsize': 10,
    'ytick.labelsize': 10,
    'legend.fontsize': 10,
    'figure.titlesize': 16,
})

# Colorblind-friendly palettes
PALETTE_CATEGORICAL = ['#4C72B0', '#DD8452', '#55A868', '#C44E52', '#8172B3', '#937860']
PALETTE_SEQUENTIAL = 'YlOrRd'
PALETTE_DIVERGING = 'RdBu_r'

Line Chart (Time Series)

fig, ax = plt.subplots(figsize=(10, 6))

for label, group in df.groupby('category'):
    ax.plot(group['date'], group['value'], label=label, linewidth=2)

ax.set_title('Metric Trend by Category', fontweight='bold')
ax.set_xlabel('Date')
ax.set_ylabel('Value')
ax.legend(loc='upper left', frameon=True)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

# Format dates on x-axis
fig.autofmt_xdate()

plt.tight_layout()
plt.savefig('trend_chart.png', dpi=150, bbox_inches='tight')

Bar Chart (Comparison)

fig, ax = plt.subplots(figsize=(10, 6))

# Sort by value for easy reading
df_sorted = df.sort_values('metric', ascending=True)

bars = ax.barh(df_sorted['category'], df_sorted['metric'], color=PALETTE_CATEGORICAL[0])

# Add value labels
for bar in bars:
    width = bar.get_width()
    ax.text(width + 0.5, bar.get_y() + bar.get_height()/2,
            f'{width:,.0f}', ha='left', va='center', fontsize=10)

ax.set_title('Metric by Category (Ranked)', fontweight='bold')
ax.set_xlabel('Metric Value')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

plt.tight_layout()
plt.savefig('bar_chart.png', dpi=150, bbox_inches='tight')

Histogram (Distribution)

fig, ax = plt.subplots(figsize=(10, 6))

ax.hist(df['value'], bins=30, color=PALETTE_CATEGORICAL[0], edgecolor='white', alpha=0.8)

# Add mean and median lines
mean_val = df['value'].mean()
median_val = df['value'].median()
ax.axvline(mean_val, color='red', linestyle='--', linewidth=1.5, label=f'Mean: {mean_val:,.1f}')
ax.axvline(median_val, color='green', linestyle='--', linewidth=1.5, label=f'Median: {median_val:,.1f}')

ax.set_title('Distribution of Values', fontweight='bold')
ax.set_xlabel('Value')
ax.set_ylabel('Frequency')
ax.legend()
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

plt.tight_layout()
plt.savefig('histogram.png', dpi=150, bbox_inches='tight')

Heatmap

fig, ax = plt.subplots(figsize=(10, 8))

# Pivot data for heatmap format
pivot = df.pivot_table(index='row_dim', columns='col_dim', values='metric', aggfunc='sum')

sns.heatmap(pivot, annot=True, fmt=',.0f', cmap='YlOrRd',
            linewidths=0.5, ax=ax, cbar_kws={'label': 'Metric Value'})

ax.set_title('Metric by Row Dimension and Column Dimension', fontweight='bold')
ax.set_xlabel('Column Dimension')
ax.set_ylabel('Row Dimension')

plt.tight_layout()
plt.savefig('heatmap.png', dpi=150, bbox_inches='tight')

Small Multiples

categories = df['category'].unique()
n_cats = len(categories)
n_cols = min(3, n_cats)
n_rows = (n_cats + n_cols - 1) // n_cols

fig, axes = plt.subplots(n_rows, n_cols, figsize=(5*n_cols, 4*n_rows), sharex=True, sharey=True)
axes = axes.flatten() if n_cats > 1 else [axes]

for i, cat in enumerate(categories):
    ax = axes[i]
    subset = df[df['category'] == cat]
    ax.plot(subset['date'], subset['value'], color=PALETTE_CATEGORICAL[i % len(PALETTE_CATEGORICAL)])
    ax.set_title(cat, fontsize=12)
    ax.spines['top'].set_visible(False)
    ax.spines['right'].set_visible(False)

# Hide empty subplots
for j in range(i+1, len(axes)):
    axes[j].set_visible(False)

fig.suptitle('Trends by Category', fontsize=14, fontweight='bold', y=1.02)
plt.tight_layout()
plt.savefig('small_multiples.png', dpi=150, bbox_inches='tight')

Number Formatting Helpers

def format_number(val, format_type='number'):
    """Format numbers for chart labels."""
    if format_type == 'currency':
        if abs(val) >= 1e9:
            return f'${val/1e9:.1f}B'
        elif abs(val) >= 1e6:
            return f'${val/1e6:.1f}M'
        elif abs(val) >= 1e3:
            return f'${val/1e3:.1f}K'
        else:
            return f'${val:,.0f}'
    elif format_type == 'percent':
        return f'{val:.1f}%'
    elif format_type == 'number':
        if abs(val) >= 1e9:
            return f'{val/1e9:.1f}B'
        elif abs(val) >= 1e6:
            return f'{val/1e6:.1f}M'
        elif abs(val) >= 1e3:
            return f'{val/1e3:.1f}K'
        else:
            return f'{val:,.0f}'
    return str(val)

# Usage with axis formatter
ax.yaxis.set_major_formatter(mticker.FuncFormatter(lambda x, p: format_number(x, 'currency')))

Interactive Charts with Plotly

import plotly.express as px
import plotly.graph_objects as go

# Simple interactive line chart
fig = px.line(df, x='date', y='value', color='category',
              title='Interactive Metric Trend',
              labels={'value': 'Metric Value', 'date': 'Date'})
fig.update_layout(hovermode='x unified')
fig.write_html('interactive_chart.html')
fig.show()

# Interactive scatter with hover data
fig = px.scatter(df, x='metric_a', y='metric_b', color='category',
                 size='size_metric', hover_data=['name', 'detail_field'],
                 title='Correlation Analysis')
fig.show()

Design Principles

Color

• Use color purposefully: Color should encode data, not decorate
• Highlight the story: Use a bright accent color for the key insight; grey everything else
• Sequential data: Use a single-hue gradient (light to dark) for ordered values
• Diverging data: Use a two-hue gradient with neutral midpoint for data with a meaningful center
• Categorical data: Use distinct hues, maximum 6-8 before it gets confusing
• Avoid red/green only: 8% of men are red-green colorblind. Use blue/orange as primary pair

Typography

• Title states the insight: "Revenue grew 23% YoY" beats "Revenue by Month"
• Subtitle adds context: Date range, filters applied, data source
• Axis labels are readable: Never rotated 90 degrees if avoidable. Shorten or wrap instead
• Data labels add precision: Use on key points, not every single bar
• Annotation highlights: Call out specific points with text annotations

Layout

• Reduce chart junk: Remove gridlines, borders, backgrounds that don't carry information
• Sort meaningfully: Categories sorted by value (not alphabetically) unless there's a natural order (months, stages)
• Appropriate aspect ratio: Time series wider than tall (3:1 to 2:1); comparisons can be squarer
• White space is good: Don't cram charts together. Give each visualization room to breathe

Accuracy

• Bar charts start at zero: Always. A bar from 95 to 100 exaggerates a 5% difference
• Line charts can have non-zero baselines: When the range of variation is meaningful
• Consistent scales across panels: When comparing multiple charts, use the same axis range
• Show uncertainty: Error bars, confidence intervals, or ranges when data is uncertain
• Label your axes: Never make the reader guess what the numbers mean

Accessibility Considerations

Color Blindness

• Never rely on color alone to distinguish data series
• Add pattern fills, different line styles (solid, dashed, dotted), or direct labels
• Test with a colorblind simulator (e.g., Coblis, Sim Daltonism)
• Use the colorblind-friendly palette: sns.color_palette("colorblind")

Screen Readers

• Include alt text describing the chart's key finding
• Provide a data table alternative alongside the visualization
• Use semantic titles and labels

General Accessibility

• Sufficient contrast between data elements and background
• Text size minimum 10pt for labels, 12pt for titles
• Avoid conveying information only through spatial position (add labels)
• Consider printing: does the chart work in black and white?

Accessibility Checklist

Before sharing a visualization:

• Chart works without color (patterns, labels, or line styles differentiate series)
• Text is readable at standard zoom level
• Title describes the insight, not just the data
• Axes are labeled with units
• Legend is clear and positioned without obscuring data
• Data source and date range are noted

中文字体配置（macOS）

matplotlib 默认 Arial 不支持中文，会渲染成方框。关键陷阱：plt.style.use(...) 会覆盖 rcParams 里的 font 设置，所以必须先 use style 再设置字体。

import matplotlib
import matplotlib.pyplot as plt

# 顺序很重要：style 在前，font 在后
plt.style.use('seaborn-v0_8-whitegrid')
matplotlib.rcParams['font.sans-serif'] = ['Heiti TC', 'PingFang HK', 'Songti SC', 'Yuanti SC']
matplotlib.rcParams['font.family'] = 'sans-serif'
matplotlib.rcParams['axes.unicode_minus'] = False

macOS 上确认可用的中文字体（实测）：Heiti TC、PingFang HK、Songti SC、Yuanti SC、STHeiti、Hiragino Sans GB。 注意：PingFang SC 在某些系统上不存在，要用 PingFang HK 替代。

排查字体可用性：

import matplotlib.font_manager as fm
fonts = sorted(set(f.name for f in fm.fontManager.ttflist))
print([f for f in fonts if any(k in f for k in ['Hei','Pin','Song','STH','Hira','Yu'])])

洞察卡片模式（KPI Summary Card）

数据图回答「数据是什么样」，但用户往往还需要「所以呢」—— 配一张文字版洞察卡作为同尺寸搭档，可以单独发也可以拼起来。

适用场景：研究报告首页、社交媒体配图、汇报展示、给非技术 stakeholder 看。

设计原则

• 每个洞察一个卡片：编号 + 标题 + 大数字 KPI + KPI 说明 + 一两行解读
• KPI 用大字号（≥24pt）+ 强色，是视觉锚点
• 标题用一句话陈述结论（"销量极度集中在头部 10%"），不要用维度名（"销量分布"）
• 底部一行最终结论，深色块包住，作为整张卡的钉子
• 配色用左侧色条区分类别：紫=中性、红=警示、绿=正向

代码模板（4 卡片 + 结论条）

import matplotlib.pyplot as plt
import matplotlib.patches as patches

fig, ax = plt.subplots(figsize=(16, 11), dpi=150)
ax.set_xlim(0, 100); ax.set_ylim(0, 100); ax.axis('off')
fig.patch.set_facecolor('white')

# Stripe 配色（也可换品牌色）
INK, SUB = '#1a1f36', '#697386'
ACCENT, DANGER, SUCCESS = '#635bff', '#df1b41', '#00875a'
BG_CARD, LINE = '#f6f9fc', '#e3e8ee'

# 标题区
ax.text(50, 95, '主标题', ha='center', fontsize=24, fontweight='bold', color=INK)
ax.text(50, 91, '副标题：数据来源/时间范围', ha='center', fontsize=11, color=SUB)
ax.plot([15, 85], [88, 88], color=LINE, linewidth=1)

# 卡片定义：(x, y, w, h, badge, color, title, kpi, kpi_label, body)
cards = [
    (4, 50, 46, 32, '①', ACCENT, '标题陈述结论', '57%', 'KPI 说明', '正文一两行解读'),
    # ... 其他 3 张
]

for x, y, w, h, badge, color, title, kpi, kpi_label, body in cards:
    # 卡片底
    ax.add_patch(patches.FancyBboxPatch((x, y), w, h,
        boxstyle="round,pad=0.5,rounding_size=1.2",
        linewidth=0, facecolor=BG_CARD, zorder=1))
    # 左侧色条
    ax.add_patch(patches.Rectangle((x+0.5, y+1), 0.6, h-2,
        facecolor=color, zorder=2))
    # 内容
    ax.text(x+3.5, y+h-4, badge, fontsize=22, fontweight='bold', color=color, va='top')
    ax.text(x+9, y+h-4.5, title, fontsize=14, fontweight='bold', color=INK, va='top')
    ax.text(x+3.5, y+h-13, kpi, fontsize=28, fontweight='bold', color=color, va='top')
    ax.text(x+3.5, y+h-19.5, kpi_label, fontsize=10, color=SUB, va='top')
    ax.text(x+3.5, y+h-23, body, fontsize=10.5, color=INK, va='top', linespacing=1.6)

# 底部结论条
ax.add_patch(patches.FancyBboxPatch((4, 4), 92, 6,
    boxstyle="round,pad=0.3,rounding_size=1",
    linewidth=0, facecolor=INK))
ax.text(50, 7, '一句话结论', ha='center', va='center',
        fontsize=13, fontweight='bold', color='white')

plt.tight_layout()
plt.savefig('insights.png', dpi=150, bbox_inches='tight', facecolor='white')

图表 + 洞察卡 拼接

数据图和洞察卡画好后，用 PIL 拼接成完整版（适合长图分享）：

from PIL import Image

img1 = Image.open('charts.png')
img2 = Image.open('insights.png')

# 统一宽度（窄的居中填白）
target_w = max(img1.width, img2.width)
def pad(img, w):
    if img.width == w: return img
    new = Image.new('RGB', (w, img.height), (255,255,255))
    new.paste(img, ((w - img.width)//2, 0))
    return new

img1, img2 = pad(img1, target_w), pad(img2, target_w)

# 上下拼接（手机阅读友好），中间留 30px 白边
gap = 30
combined = Image.new('RGB', (target_w, img1.height + img2.height + gap), (255,255,255))
combined.paste(img1, (0, 0))
combined.paste(img2, (0, img1.height + gap))
combined.save('combined.png', dpi=(150,150), optimize=True)

横向拼接同理（统一高度，宽度相加），适合宽屏展示。