10. 发散型条形图
如果您想根据单个指标查看项目的变化情况，并可视化此差异的顺序和数量，那么发散条是一个很好的工具。它有助于快速区分数据中组的性能，并且非常直观，并且可以立即传达这一点。
# Prepare Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mtcars.csv")
x = df.loc[:, ['mpg']]
df['mpg_z'] = (x - x.mean())/x.std()
df['colors'] = ['red'if x < 0else'green'for x in df['mpg_z']]
df.sort_values('mpg_z', inplace=True)
df.reset_index(inplace=True)
# Draw plot
plt.figure(figsize=(14,10), dpi= 80)
plt.hlines(y=df.index, xmin=0, xmax=df.mpg_z, color=df.colors, alpha=0.4, linewidth=5)
# Decorations
plt.gca().set(ylabel='$Model$', xlabel='$Mileage$')
plt.yticks(df.index, df.cars, fontsize=12)
plt.title('Diverging Bars of Car Mileage', fontdict={'size':20})
plt.grid(linestyle='--', alpha=0.5)
plt.show()
11. 发散型文本
分散的文本类似于发散条，如果你想以一种漂亮和可呈现的方式显示图表中每个项目的价值，它更喜欢。
# Prepare Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mtcars.csv")
x = df.loc[:, ['mpg']]
df['mpg_z'] = (x - x.mean())/x.std()
df['colors'] = ['red'if x < 0else'green'for x in df['mpg_z']]
df.sort_values('mpg_z', inplace=True)
df.reset_index(inplace=True)
# Draw plot
plt.figure(figsize=(14,14), dpi= 80)
plt.hlines(y=df.index, xmin=0, xmax=df.mpg_z)
for x, y, tex in zip(df.mpg_z, df.index, df.mpg_z):
t = plt.text(x, y, round(tex, 2), horizontalalignment='right'if x < 0else'left',
verticalalignment='center', fontdict={'color':'red'if x < 0else'green', 'size':14})
# Decorations
plt.yticks(df.index, df.cars, fontsize=12)
plt.title('Diverging Text Bars of Car Mileage', fontdict={'size':20})
plt.grid(linestyle='--', alpha=0.5)
plt.xlim(-2.5, 2.5)
plt.show()
12. 发散型包点图
发散点图也类似于发散条。然而，与发散条相比，条的不存在减少了组之间的对比度和差异。
# Prepare Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mtcars.csv")
x = df.loc[:, ['mpg']]
df['mpg_z'] = (x - x.mean())/x.std()
df['colors'] = ['red'if x < 0else'darkgreen'for x in df['mpg_z']]
df.sort_values('mpg_z', inplace=True)
df.reset_index(inplace=True)
# Draw plot
plt.figure(figsize=(14,16), dpi= 80)
plt.scatter(df.mpg_z, df.index, s=450, alpha=.6, color=df.colors)
for x, y, tex in zip(df.mpg_z, df.index, df.mpg_z):
t = plt.text(x, y, round(tex, 1), horizontalalignment='center',
verticalalignment='center', fontdict={'color':'white'})
# Decorations
# Lighten borders
plt.gca().spines["top"].set_alpha(.3)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(.3)
plt.gca().spines["left"].set_alpha(.3)
plt.yticks(df.index, df.cars)
plt.title('Diverging Dotplot of Car Mileage', fontdict={'size':20})
plt.xlabel('$Mileage$')
plt.grid(linestyle='--', alpha=0.5)
plt.xlim(-2.5, 2.5)
plt.show()
13. 带标记的发散型棒棒糖图
带标记的棒棒糖通过强调您想要引起注意的任何重要数据点并在图表中适当地给出推理，提供了一种可视化分歧的灵活方式。
# Prepare Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mtcars.csv")
x = df.loc[:, ['mpg']]
df['mpg_z'] = (x - x.mean())/x.std()
df['colors'] = 'black'
# color fiat differently
df.loc[df.cars == 'Fiat X1-9', 'colors'] = 'darkorange'
df.sort_values('mpg_z', inplace=True)
df.reset_index(inplace=True)
# Draw plot
import matplotlib.patches as patches
plt.figure(figsize=(14,16), dpi= 80)
plt.hlines(y=df.index, xmin=0, xmax=df.mpg_z, color=df.colors, alpha=0.4, linewidth=1)
plt.scatter(df.mpg_z, df.index, color=df.colors, s=[600if x == 'Fiat X1-9'else300for x in df.cars], alpha=0.6)
plt.yticks(df.index, df.cars)
plt.xticks(fontsize=12)
# Annotate
plt.annotate('Mercedes Models', xy=(0.0, 11.0), xytext=(1.0, 11), xycoords='data',
fontsize=15, ha='center', va='center',
bbox=dict(boxstyle='square', fc='firebrick'),
arrowprops=dict(arrowstyle='-[, widthB=2.0, lengthB=1.5', lw=2.0, color='steelblue'), color='white')
# Add Patches
p1 = patches.Rectangle((-2.0, -1), width=.3, height=3, alpha=.2, facecolor='red')
p2 = patches.Rectangle((1.5, 27), width=.8, height=5, alpha=.2, facecolor='green')
plt.gca().add_patch(p1)
plt.gca().add_patch(p2)
# Decorate
plt.title('Diverging Bars of Car Mileage', fontdict={'size':20})
plt.grid(linestyle='--', alpha=0.5)
plt.show()
14.面积图
通过对轴和线之间的区域进行着色，区域图不仅强调峰值和低谷，而且还强调高点和低点的持续时间。高点持续时间越长，线下面积越大。
import numpy as np
import pandas as pd
# Prepare Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/economics.csv", parse_dates=['date']).head(100)
x = np.arange(df.shape[0])
y_returns = (df.psavert.diff().fillna(0)/df.psavert.shift(1)).fillna(0) * 100
# Plot
plt.figure(figsize=(16,10), dpi= 80)
plt.fill_between(x[1:], y_returns[1:], 0, where=y_returns[1:] >= 0, facecolor='green', interpolate=True, alpha=0.7)
plt.fill_between(x[1:], y_returns[1:], 0, where=y_returns[1:] <= 0, facecolor='red', interpolate=True, alpha=0.7)
# Annotate
plt.annotate('Peak
1975', xy=(94.0, 21.0), xytext=(88.0, 28),
bbox=dict(boxstyle='square', fc='firebrick'),
arrowprops=dict(facecolor='steelblue', shrink=0.05), fontsize=15, color='white')
# Decorations
xtickvals = [str(m)[:3].upper()+"-"+str(y) for y,m in zip(df.date.dt.year, df.date.dt.month_name())]
plt.gca().set_xticks(x[::6])
plt.gca().set_xticklabels(xtickvals[::6], rotation=90, fontdict={'horizontalalignment': 'center', 'verticalalignment': 'center_baseline'})
plt.ylim(-35,35)
plt.xlim(1,100)
plt.title("Month Economics Return %", fontsize=22)
plt.ylabel('Monthly returns %')
plt.grid(alpha=0.5)
plt.show()
15. 有序条形图
有序条形图有效地传达了项目的排名顺序。但是，在图表上方添加度量标准的值，用户可以从图表本身获取精确信息。
# Prepare Data
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")
df = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.mean())
df.sort_values('cty', inplace=True)
df.reset_index(inplace=True)
# Draw plot
import matplotlib.patches as patches
fig, ax = plt.subplots(figsize=(16,10), facecolor='white', dpi= 80)
ax.vlines(x=df.index, ymin=0, ymax=df.cty, color='firebrick', alpha=0.7, linewidth=20)
# Annotate Text
for i, cty in enumerate(df.cty):
ax.text(i, cty+0.5, round(cty, 1), horizontalalignment='center')
# Title, Label, Ticks and Ylim
ax.set_title('Bar Chart for Highway Mileage', fontdict={'size':22})
ax.set(ylabel='Miles Per Gallon', ylim=(0, 30))
plt.xticks(df.index, df.manufacturer.str.upper(), rotation=60, horizontalalignment='right', fontsize=12)
# Add patches to color the X axis labels
p1 = patches.Rectangle((.57, -0.005), width=.33, height=.13, alpha=.1, facecolor='green', transform=fig.transFigure)
p2 = patches.Rectangle((.124, -0.005), width=.446, height=.13, alpha=.1, facecolor='red', transform=fig.transFigure)
fig.add_artist(p1)
fig.add_artist(p2)
plt.show()
