我已经sns.catplot使用 seaborn 创建了一个。我的目标是获得带有误差线的条形图。
sns.catplot
我非常感谢任何关于为什么对我的数据框进行排序会导致此问题的回答或评论。
import pandas as pd import matplotlib import seaborn as sns data = {'Parameter': ['$μ_{max}$', '$μ_{max}$', '$μ_{max}$', '$μ_{max}$', '$μ_{max}$', '$m$', '$m$', '$m$', '$m$', '$m$', '$\\alpha_D$', '$\\alpha_D$', '$\\alpha_D$', '$\\alpha_D$', '$\\alpha_D$', '$N_{max}$', '$N_{max}$', '$N_{max}$', '$N_{max}$', '$N_{max}$', '$\\gamma_{cell}$', '$\\gamma_{cell}$', '$\\gamma_{cell}$', '$\\gamma_{cell}$', '$\\gamma_{cell}$', '$K_d$', '$K_d$', '$K_d$', '$K_d$', '$K_d$'], 'Output': ['POC', 'DOC', 'IC', 'Cells', 'Mean', 'POC', 'DOC', 'IC', 'Cells', 'Mean', 'POC', 'DOC', 'IC', 'Cells', 'Mean', 'POC', 'DOC', 'IC', 'Cells', 'Mean', 'POC', 'DOC', 'IC', 'Cells', 'Mean', 'POC', 'DOC', 'IC', 'Cells', 'Mean'], 'Total-effect': [0.9806103414992552, -7.054718234598588e-10, 0.1960778044402512, 0.2537531550865872, 0.3576103250801555, 0.1663846098641205, 1.0851909901687566, 0.2563681021056311, 0.0084168031549801, 0.3790901263233721, 0.0031054085922008, 0.0002724061050653, 0.1659030569337202, 0.2251452993113863, 0.0986065427355931, 0.0340237460462674, 0.3067235088110348, 0.3150260538485233, 0.3349234507482945, 0.24767418986353, 0.1938746960877987, -6.17103884336228e-07, 0.0041542186143554, 0.0032055759222461, 0.050308468380129, 0.0417496162986251, 2.328088857274425e-09, 0.9483137697398172, 0.9881583951740854, 0.4945554458851541], 'First-order': [0.7030107013984165, 2.266962154339895e-19, 0.0062233586910709, 0.001029343445717, 0.1775658508838011, 0.0007896517048184, 0.7264368524472167, 0.0072701545157557, 0.0047752182357577, 0.1848179692258871, -2.123427373989929e-05, 2.395667282242805e-19, 0.0055179953736572, 0.0004377224837127, 0.0014836208959075, -1.509666411558862e-06, 6.068293373049956e-20, 0.0115237519530005, 0.0009532607225978, 0.0031188757522967, 0.0117401346791109, 3.482140934635793e-24, 0.0015109239301033, -2.9803014832201013e-08, 0.0033127572015498, 0.0015795893288074, 3.393882814623132e-17, 0.3451307225252993, 0.4106729024860886, 0.1893458035850488], 'Total Error': [0.0005752772018327, 1.3690325778564916e-09, 0.0033197127516203, 0.0042203628326116, 0.0020288385387743, 0.0007817126652407, 0.074645390474463, 0.0016832816591233, 0.0023529269720789, 0.0198658279427265, 0.0001233951911322, 0.0023340612253369, 0.0029383350061101, 0.003741247467092, 0.0022842597224178, 0.0005740976276596, 0.1017075201238418, 0.0016784578928217, 0.0037270295879161, 0.0269217763080598, 0.0009021103063017, 4.619682769520493e-07, 0.0005201826302926, 0.0005615428740041, 0.0004960744447188, 0.000910170372727, 1.0571905831111963e-09, 0.0029389557787801, 0.0054832440706334, 0.0023330928198327], 'First Error': [0.0024072925459877, 9.366089709991011e-20, 0.0002667351219131, 0.0002702376243862, 0.0007360663230718, 0.0002586411466273, 0.0409234887280223, 0.0005053286335856, 0.0003348751699561, 0.0105055834195478, 2.195881790893627e-05, 8.208495135059976e-20, 0.0001643584459509, 0.0002162523113349, 0.0001006423937987, 0.0001928274220008, 3.4836161809305005e-20, 0.0005126354796536, 0.0005972681850905, 0.0003256827716862, 0.0003252835339205, 5.013811598030501e-24, 3.247452070080876e-05, 8.972262407759052e-08, 8.946194431135658e-05, 0.0001221659592046, 2.8775799201024936e-18, 0.0033817071114312, 0.0058875798799757, 0.0023478632376529]} df = pd.DataFrame(data) # Picks outputs to show show_vars = ["Mean"] err_df = df.melt(id_vars=["Parameter", "Output"], value_vars=["Total Error", "First Error"], var_name="Error").sort_values(by="Parameter") df = df.melt(id_vars=["Parameter", "Output"], value_vars=["Total-effect", "First-order"], var_name="Sobol index", value_name="Value").sort_values(by="Parameter") # Plot grid = sns.catplot(data=df[df["Output"].isin(show_vars)], x="Parameter", y="Value", col="Output", col_wrap=2, hue="Sobol index", kind="bar", aspect=1.8, legend_out=False) grid.set_titles(col_template="Sensitivity with respect to {col_name}") # Add error lines and values for ax, var in zip(grid.axes.ravel(), show_vars): # Value labels for i, c in enumerate(ax.containers): if type(c) == matplotlib.container.BarContainer: ax.bar_label(c, labels=[f'{v.get_height():.2f}' if v.get_height() >= 0.01 else "<0.01" for v in c], label_type='center') # Error bars ticklocs = ax.xaxis.get_majorticklocs() offset = ax.containers[0][0].get_width() / 2 ax.errorbar(x=np.append(ticklocs - offset, ticklocs + offset), y=df[df["Output"] == var]["Value"], yerr=err_df[err_df["Output"] == var]["value"], ecolor='black', linewidth=0, elinewidth=2, capsize=2) # Careful: array order matters # Change title for mean if var == "Mean": ax.set_title("Average sensitivity across outputs") grid.tight_layout()
输出：
我确实尝试通过执行以下操作对选定的数据框进行排序：
y=df[df["Output"] == var].sort_values(by="Parameter")["Value"], yerr=err_df[err_df["Output"] == var].sort_values(by="Parameter")["value"]
尽管数据框中的顺序似乎在各个操作之间得以保留，但情况仍然如此。
matplotlib
默认绘图后端。两个软件包
以不同的方式工作，这使得某些类型的绘图和自定义更容易。
seaborn.barplot
pandas.DataFrame.plot
yerr
请参阅pandas 用户指南：使用误差线绘图
已在python 3.11, pandas 1.5.2, matplotlib 3.6.2,测试seaborn 0.12.1
python 3.11
pandas 1.5.2
matplotlib 3.6.2
seaborn 0.12.1
import matplotlib as mpl import pandas as pd # set the index as the column to be the x-axis df = df.set_index('Parameter') # select the Mean data df_mean = df[df.Output.eq('Mean')] # specify the columns to use for the errors yerr = df_mean[['Total Error', 'First Error']] # the columns must be the same name as the columns used for the data values yerr.columns = ['Total-effect', 'First-order'] # plot the selected data and add the yerr ax = df_mean.plot(kind='bar', y=['Total-effect', 'First-order'], yerr=yerr, rot=0, figsize=(12, 8), title='Average sensitivity across outputs') # iterate through each group of bars for c in ax.containers: # add labels to the bars if type(c) == mpl.container.BarContainer: labels=[f'{h:.2f}' if (h := v.get_height()) >= 0.01 else "<0.01" for v in c] ax.bar_label(c, labels=labels, label_type='center')
