16. 棒棒糖图
棒棒糖图表以一种视觉上令人愉悦的方式提供与有序条形图类似的目的。
# 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
fig, ax = plt.subplots(figsize=(16,10), dpi= 80)
ax.vlines(x=df.index, ymin=0, ymax=df.cty, color='firebrick', alpha=0.7, linewidth=2)
ax.scatter(x=df.index, y=df.cty, s=75, color='firebrick', alpha=0.7)
# Title, Label, Ticks and Ylim
ax.set_title('Lollipop Chart for Highway Mileage', fontdict={'size':22})
ax.set_ylabel('Miles Per Gallon')
ax.set_xticks(df.index)
ax.set_xticklabels(df.manufacturer.str.upper(), rotation=60, fontdict={'horizontalalignment': 'right', 'size':12})
ax.set_ylim(0, 30)
# Annotate
for row in df.itertuples():
ax.text(row.Index, row.cty+.5, s=round(row.cty, 2), horizontalalignment= 'center', verticalalignment='bottom', fontsize=14)
plt.show()
17. 包点图
点图表传达了项目的排名顺序。由于它沿水平轴对齐，因此您可以更容易地看到点彼此之间的距离。
# 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
fig, ax = plt.subplots(figsize=(16,10), dpi= 80)
ax.hlines(y=df.index, xmin=11, xmax=26, color='gray', alpha=0.7, linewidth=1, linestyles='dashdot')
ax.scatter(y=df.index, x=df.cty, s=75, color='firebrick', alpha=0.7)
# Title, Label, Ticks and Ylim
ax.set_title('Dot Plot for Highway Mileage', fontdict={'size':22})
ax.set_xlabel('Miles Per Gallon')
ax.set_yticks(df.index)
ax.set_yticklabels(df.manufacturer.str.title(), fontdict={'horizontalalignment': 'right'})
ax.set_xlim(10, 27)
plt.show()
18. 坡度图
斜率图最适合比较给定人/项目的“之前”和“之后”位置。
import matplotlib.lines as mlines
# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/gdppercap.csv")
left_label = [str(c) + ', '+ str(round(y)) for c, y inzip(df.continent, df['1952'])]
right_label = [str(c) + ', '+ str(round(y)) for c, y inzip(df.continent, df['1957'])]
klass = ['red'if (y1-y2) < 0else'green'for y1, y2 inzip(df['1952'], df['1957'])]
# draw line
# https://stackoverflow.com/questions/36470343/how-to-draw-a-line-with-matplotlib/36479941
def newline(p1, p2, color='black'):
ax = plt.gca()
l = mlines.Line2D([p1[0],p2[0]], [p1[1],p2[1]], color='red'if p1[1]-p2[1] > 0else'green', marker='o', markersize=6)
ax.add_line(l)
return l
fig, ax = plt.subplots(1,1,figsize=(14,14), dpi= 80)
# Vertical Lines
ax.vlines(x=1, ymin=500, ymax=13000, color='black', alpha=0.7, linewidth=1, linestyles='dotted')
ax.vlines(x=3, ymin=500, ymax=13000, color='black', alpha=0.7, linewidth=1, linestyles='dotted')
# Points
ax.scatter(y=df['1952'], x=np.repeat(1, df.shape[0]), s=10, color='black', alpha=0.7)
ax.scatter(y=df['1957'], x=np.repeat(3, df.shape[0]), s=10, color='black', alpha=0.7)
# Line Segmentsand Annotation
for p1, p2, c inzip(df['1952'], df['1957'], df['continent']):
newline([1,p1], [3,p2])
ax.text(1-0.05, p1, c + ', ' + str(round(p1)), horizontalalignment='right', verticalalignment='center', fontdict={'size':14})
ax.text(3+0.05, p2, c + ', ' + str(round(p2)), horizontalalignment='left', verticalalignment='center', fontdict={'size':14})
# 'Before' and 'After' Annotations
ax.text(1-0.05, 13000, 'BEFORE', horizontalalignment='right', verticalalignment='center', fontdict={'size':18, 'weight':700})
ax.text(3+0.05, 13000, 'AFTER', horizontalalignment='left', verticalalignment='center', fontdict={'size':18, 'weight':700})
# Decoration
ax.set_title("Slopechart: Comparing GDP Per Capita between 1952 vs 1957", fontdict={'size':22})
ax.set(xlim=(0,4), ylim=(0,14000), ylabel='Mean GDP Per Capita')
ax.set_xticks([1,3])
ax.set_xticklabels(["1952", "1957"])
plt.yticks(np.arange(500, 13000, 2000), fontsize=12)
# Lighten borders
plt.gca().spines["top"].set_alpha(.0)
plt.gca().spines["bottom"].set_alpha(.0)
plt.gca().spines["right"].set_alpha(.0)
plt.gca().spines["left"].set_alpha(.0)
plt.show()
19. 哑铃图
哑铃图传达各种项目的“前”和“后”位置以及项目的排序。如果您想要将特定项目/计划对不同对象的影响可视化，那么它非常有用。
import matplotlib.lines as mlines
# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/health.csv")
df.sort_values('pct_2014', inplace=True)
df.reset_index(inplace=True)
# Func to draw line segment
defnewline(p1, p2, color='black'):
ax = plt.gca()
l = mlines.Line2D([p1[0],p2[0]], [p1[1],p2[1]], color='skyblue')
ax.add_line(l)
return l
# Figure and Axes
fig, ax = plt.subplots(1,1,figsize=(14,14), facecolor='#f7f7f7', dpi= 80)
# Vertical Lines
ax.vlines(x=.05, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted')
ax.vlines(x=.10, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted')
ax.vlines(x=.15, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted')
ax.vlines(x=.20, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted')
# Points
ax.scatter(y=df['index'], x=df['pct_2013'], s=50, color='#0e668b', alpha=0.7)
ax.scatter(y=df['index'], x=df['pct_2014'], s=50, color='#a3c4dc', alpha=0.7)
# Line Segments
for i, p1, p2 in zip(df['index'], df['pct_2013'], df['pct_2014']):
newline([p1, i], [p2, i])
# Decoration
ax.set_facecolor('#f7f7f7')
ax.set_title("Dumbell Chart: Pct Change - 2013 vs 2014", fontdict={'size':22})
ax.set(xlim=(0,.25), ylim=(-1, 27), ylabel='Mean GDP Per Capita')
ax.set_xticks([.05, .1, .15, .20])
ax.set_xticklabels(['5%', '15%', '20%', '25%'])
ax.set_xticklabels(['5%', '15%', '20%', '25%'])
plt.show()
20. 连续变量的直方图
直方图显示给定变量的频率分布。下面的表示基于分类变量对频率条进行分组，从而更好地了解连续变量和串联变量。
# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")
# Prepare data
x_var = 'displ'
groupby_var = 'class'
df_agg = df.loc[:, [x_var, groupby_var]].groupby(groupby_var)
vals = [df[x_var].values.tolist() for i, df in df_agg]
# Draw
plt.figure(figsize=(16,9), dpi= 80)
colors = [plt.cm.Spectral(i/float(len(vals)-1)) for i inrange(len(vals))]
n, bins, patches = plt.hist(vals, 30, stacked=True, density=False, color=colors[:len(vals)])
# Decoration
plt.legend({group:col forgroup, col inzip(np.unique(df[groupby_var]).tolist(), colors[:len(vals)])})
plt.title(f"Stacked Histogram of ${x_var}$ colored by ${groupby_var}$", fontsize=22)
plt.xlabel(x_var)
plt.ylabel("Frequency")
plt.ylim(0, 25)
plt.xticks(ticks=bins[::3], labels=[round(b,1) for b in bins[::3]])
plt.show()
