如何在 Plotly 中为折线图添加 95% 的置信区间？
How to add 95% confidence interval for a line chart in Plotly?
我有本福德测试结果，test_show
Expected Counts Found Dif AbsDif Z_score
Sec_Dig
0 0.119679 4318 0.080052 -0.039627 0.039627 28.347781
1 0.113890 2323 0.043066 -0.070824 0.070824 51.771489
2 0.108821 1348 0.024991 -0.083831 0.083831 62.513122
3 0.104330 1298 0.024064 -0.080266 0.080266 60.975864
4 0.100308 3060 0.056730 -0.043579 0.043579 33.683738
5 0.096677 6580 0.121987 0.025310 0.025310 19.884178
6 0.093375 10092 0.187097 0.093722 0.093722 74.804141
7 0.090352 9847 0.182555 0.092203 0.092203 74.687841
8 0.087570 8439 0.156452 0.068882 0.068882 56.587749
9 0.084997 6635 0.123007 0.038010 0.038010 31.646817
我正在尝试使用 Plotly 绘制 Benford 结果，如下所示，
这是我目前试过的代码
import plotly.graph_objects as go
fig = go.Figure()
fig.add_trace(go.Bar(x=test_show.index,
y=test_show.Found,
name='Found',
marker_color='rgb(55, 83, 109)',
# color="color"
))
fig.add_trace(go.Scatter(x=test_show.index,
y=test_show.Expected,
mode='lines+markers',
name='Expected'
))
fig.update_layout(
title='Benfords Law',
xaxis=dict(
title='Digits',
tickmode='linear',
titlefont_size=16,
tickfont_size=14),
yaxis=dict(
title='% Percentage',
titlefont_size=16,
tickfont_size=14,
),
legend=dict(
x=0,
y=1.0,
bgcolor='rgba(255, 255, 255, 0)',
bordercolor='rgba(255, 255, 255, 0)'
))
fig.show()
如何为 test_show["Expected"] 添加置信区间？
从 Python 3.8 开始，您可以使用 NormalDist to calculate a confidence interval as explained in detail here。通过对该方法稍作调整，您可以使用两个 go.Scatter() 跟踪将其包含在 fig.add_traces() 的设置中，然后像这样为最后一个跟踪设置 fill='tonexty', fillcolor = 'rgba(255, 0, 0, 0.2)')：
CI = confidence_interval(df.Expected, 0.95)
fig.add_traces([go.Scatter(x = df.index, y = df['Expected']+CI,
mode = 'lines', line_color = 'rgba(0,0,0,0)',
showlegend = False),
go.Scatter(x = df.index, y = df['Expected']-CI,
mode = 'lines', line_color = 'rgba(0,0,0,0)',
name = '95% confidence interval',
fill='tonexty', fillcolor = 'rgba(255, 0, 0, 0.2)')])
请注意，此方法从非常有限的 df.Expected 系列计算置信区间。这可能不是您想要在这里做的。因此，让我知道这个初步建议对您的效果如何，然后我们可以从那里开始。
情节
完整代码：
import plotly.graph_objects as go
import pandas as pd
from statistics import NormalDist
def confidence_interval(data, confidence=0.95):
dist = NormalDist.from_samples(data)
z = NormalDist().inv_cdf((1 + confidence) / 2.)
h = dist.stdev * z / ((len(data) - 1) ** .5)
return h
df = pd.DataFrame({'Expected': {0: 0.119679,
1: 0.11389,
2: 0.108821,
3: 0.10432999999999999,
4: 0.10030800000000001,
5: 0.096677,
6: 0.093375,
7: 0.090352,
8: 0.08757000000000001,
9: 0.084997},
'Counts': {0: 4318,
1: 2323,
2: 1348,
3: 1298,
4: 3060,
5: 6580,
6: 10092,
7: 9847,
8: 8439,
9: 6635},
'Found': {0: 0.080052,
1: 0.043066,
2: 0.024991,
3: 0.024064,
4: 0.056729999999999996,
5: 0.12198699999999998,
6: 0.187097,
7: 0.182555,
8: 0.156452,
9: 0.12300699999999999},
'Dif': {0: -0.039626999999999996,
1: -0.070824,
2: -0.08383099999999999,
3: -0.08026599999999999,
4: -0.043579,
5: 0.02531,
6: 0.093722,
7: 0.092203,
8: 0.068882,
9: 0.03801},
'AbsDif': {0: 0.039626999999999996,
1: 0.070824,
2: 0.08383099999999999,
3: 0.08026599999999999,
4: 0.043579,
5: 0.02531,
6: 0.093722,
7: 0.092203,
8: 0.068882,
9: 0.03801},
'Z_scoreSec_Dig': {0: 28.347781,
1: 51.771489,
2: 62.513121999999996,
3: 60.975864,
4: 33.683738,
5: 19.884178,
6: 74.804141,
7: 74.687841,
8: 56.587749,
9: 31.646817}})
test_show = df
fig = go.Figure()
fig.add_trace(go.Bar(x=test_show.index,
y=test_show.Found,
name='Found',
marker_color='rgb(55, 83, 109)',
# color="color"
))
fig.add_trace(go.Scatter(x=test_show.index,
y=test_show.Expected,
mode='lines+markers',
name='Expected'
))
fig.update_layout(
title='Benfords Law',
xaxis=dict(
title='Digits',
tickmode='linear',
titlefont_size=16,
tickfont_size=14),
yaxis=dict(
title='% Percentage',
titlefont_size=16,
tickfont_size=14,
),
legend=dict(
x=0,
y=1.0,
bgcolor='rgba(255, 255, 255, 0)',
bordercolor='rgba(255, 255, 255, 0)'
))
CI = confidence_interval(df.Expected, 0.95)
fig.add_traces([go.Scatter(x = df.index, y = df['Expected']+CI,
mode = 'lines', line_color = 'rgba(0,0,0,0)',
showlegend = False),
go.Scatter(x = df.index, y = df['Expected']-CI,
mode = 'lines', line_color = 'rgba(0,0,0,0)',
name = '95% confidence interval',
fill='tonexty', fillcolor = 'rgba(255, 0, 0, 0.2)')])
fig.show()
我有本福德测试结果，test_show
Expected Counts Found Dif AbsDif Z_score
Sec_Dig
0 0.119679 4318 0.080052 -0.039627 0.039627 28.347781
1 0.113890 2323 0.043066 -0.070824 0.070824 51.771489
2 0.108821 1348 0.024991 -0.083831 0.083831 62.513122
3 0.104330 1298 0.024064 -0.080266 0.080266 60.975864
4 0.100308 3060 0.056730 -0.043579 0.043579 33.683738
5 0.096677 6580 0.121987 0.025310 0.025310 19.884178
6 0.093375 10092 0.187097 0.093722 0.093722 74.804141
7 0.090352 9847 0.182555 0.092203 0.092203 74.687841
8 0.087570 8439 0.156452 0.068882 0.068882 56.587749
9 0.084997 6635 0.123007 0.038010 0.038010 31.646817
我正在尝试使用 Plotly 绘制 Benford 结果，如下所示，
这是我目前试过的代码
import plotly.graph_objects as go
fig = go.Figure()
fig.add_trace(go.Bar(x=test_show.index,
y=test_show.Found,
name='Found',
marker_color='rgb(55, 83, 109)',
# color="color"
))
fig.add_trace(go.Scatter(x=test_show.index,
y=test_show.Expected,
mode='lines+markers',
name='Expected'
))
fig.update_layout(
title='Benfords Law',
xaxis=dict(
title='Digits',
tickmode='linear',
titlefont_size=16,
tickfont_size=14),
yaxis=dict(
title='% Percentage',
titlefont_size=16,
tickfont_size=14,
),
legend=dict(
x=0,
y=1.0,
bgcolor='rgba(255, 255, 255, 0)',
bordercolor='rgba(255, 255, 255, 0)'
))
fig.show()
如何为 test_show["Expected"] 添加置信区间？
从 Python 3.8 开始，您可以使用 NormalDist to calculate a confidence interval as explained in detail here。通过对该方法稍作调整，您可以使用两个 go.Scatter() 跟踪将其包含在 fig.add_traces() 的设置中，然后像这样为最后一个跟踪设置 fill='tonexty', fillcolor = 'rgba(255, 0, 0, 0.2)')：
CI = confidence_interval(df.Expected, 0.95)
fig.add_traces([go.Scatter(x = df.index, y = df['Expected']+CI,
mode = 'lines', line_color = 'rgba(0,0,0,0)',
showlegend = False),
go.Scatter(x = df.index, y = df['Expected']-CI,
mode = 'lines', line_color = 'rgba(0,0,0,0)',
name = '95% confidence interval',
fill='tonexty', fillcolor = 'rgba(255, 0, 0, 0.2)')])
请注意，此方法从非常有限的 df.Expected 系列计算置信区间。这可能不是您想要在这里做的。因此，让我知道这个初步建议对您的效果如何，然后我们可以从那里开始。
情节
完整代码：
import plotly.graph_objects as go
import pandas as pd
from statistics import NormalDist
def confidence_interval(data, confidence=0.95):
dist = NormalDist.from_samples(data)
z = NormalDist().inv_cdf((1 + confidence) / 2.)
h = dist.stdev * z / ((len(data) - 1) ** .5)
return h
df = pd.DataFrame({'Expected': {0: 0.119679,
1: 0.11389,
2: 0.108821,
3: 0.10432999999999999,
4: 0.10030800000000001,
5: 0.096677,
6: 0.093375,
7: 0.090352,
8: 0.08757000000000001,
9: 0.084997},
'Counts': {0: 4318,
1: 2323,
2: 1348,
3: 1298,
4: 3060,
5: 6580,
6: 10092,
7: 9847,
8: 8439,
9: 6635},
'Found': {0: 0.080052,
1: 0.043066,
2: 0.024991,
3: 0.024064,
4: 0.056729999999999996,
5: 0.12198699999999998,
6: 0.187097,
7: 0.182555,
8: 0.156452,
9: 0.12300699999999999},
'Dif': {0: -0.039626999999999996,
1: -0.070824,
2: -0.08383099999999999,
3: -0.08026599999999999,
4: -0.043579,
5: 0.02531,
6: 0.093722,
7: 0.092203,
8: 0.068882,
9: 0.03801},
'AbsDif': {0: 0.039626999999999996,
1: 0.070824,
2: 0.08383099999999999,
3: 0.08026599999999999,
4: 0.043579,
5: 0.02531,
6: 0.093722,
7: 0.092203,
8: 0.068882,
9: 0.03801},
'Z_scoreSec_Dig': {0: 28.347781,
1: 51.771489,
2: 62.513121999999996,
3: 60.975864,
4: 33.683738,
5: 19.884178,
6: 74.804141,
7: 74.687841,
8: 56.587749,
9: 31.646817}})
test_show = df
fig = go.Figure()
fig.add_trace(go.Bar(x=test_show.index,
y=test_show.Found,
name='Found',
marker_color='rgb(55, 83, 109)',
# color="color"
))
fig.add_trace(go.Scatter(x=test_show.index,
y=test_show.Expected,
mode='lines+markers',
name='Expected'
))
fig.update_layout(
title='Benfords Law',
xaxis=dict(
title='Digits',
tickmode='linear',
titlefont_size=16,
tickfont_size=14),
yaxis=dict(
title='% Percentage',
titlefont_size=16,
tickfont_size=14,
),
legend=dict(
x=0,
y=1.0,
bgcolor='rgba(255, 255, 255, 0)',
bordercolor='rgba(255, 255, 255, 0)'
))
CI = confidence_interval(df.Expected, 0.95)
fig.add_traces([go.Scatter(x = df.index, y = df['Expected']+CI,
mode = 'lines', line_color = 'rgba(0,0,0,0)',
showlegend = False),
go.Scatter(x = df.index, y = df['Expected']-CI,
mode = 'lines', line_color = 'rgba(0,0,0,0)',
name = '95% confidence interval',
fill='tonexty', fillcolor = 'rgba(255, 0, 0, 0.2)')])
fig.show()