Plotly 动画气泡图：图中没有数据
Plotly animated bubble chart: no data in the plot
我正在尝试将标准的动画气泡图调整为包含这些列的 csv 文件：
index,country,year,Country code,Total population (Gapminder),Life satisfaction in Cantril Ladder (World Happiness Report 2017),GDP per capita
62,Afghanistan,2008,AFG,29839994.0,3.723589897,1298.14315888
63,Afghanistan,2009,AFG,30577756.0,4.401778221,1531.17399272
64,Afghanistan,2010,AFG,31411743.0,4.75838089,1614.25500126
65,Afghanistan,2011,AFG,32358260.0,3.83171916,1660.73985618
66,Afghanistan,2012,AFG,33397058.0,3.782937527,1839.27357928
67,Afghanistan,2013,AFG,34499915.0,3.572100401,1814.15582533
167,Albania,2007,ALB,3169665.0,4.634251595,8447.88228539
169,Albania,2009,ALB,3192723.0,5.485469818,9524.60981095
170,Albania,2010,ALB,3204284.0,5.268936634,9927.13514733
171,Albania,2011,ALB,3215988.0,5.867421627,10207.7006745
172,Albania,2012,ALB,3227373.0,5.510124207,10369.7616592
173,Albania,2013,ALB,3238316.0,4.550647736,10504.0930888
242,Algeria,2010,DZA,35468208.0,5.46356678,12870.2162376
243,Algeria,2011,DZA,35980193.0,5.317194462,12989.9549601
244,Algeria,2012,DZA,36485828.0,5.604595661,13161.566464
451,Angola,2011,AGO,19618432.0,5.589000702,5911.25433387
452,Angola,2012,AGO,20162517.0,4.360249996,5998.63860099
453,Angola,2013,AGO,20714494.0,3.937106848,6185.0138292
数据点的大小是人口的函数，我将绘制生活满意度与国家 GDP 的函数关系图。我在数据集上做了一些工作：
gdp=pd.read_csv('gdp-vs-happiness.csv')
gdp=gdp.ix[~(gdp['year'] < 2005)]
gdp=gdp.dropna()
dataset = gdp
然后是代码：
years = ['2005','2006', '2007','2008','2009','2010','2011','2012','2013','2014','2015','2016']
# make list of continents
countries = []
for country in dataset['country']:
countries.append(country)
# make figure
figure = {
'data': [],
'layout': {},
'frames': []
}
config = {'scrollzoom': True}
# fill in most of layout
figure['layout']['xaxis'] = {'title': 'GDP per Capita', 'type': 'log'}
figure['layout']['yaxis'] = {'range': [0, 10], 'title': 'Life Satisfaction'}
figure['layout']['hovermode'] = 'closest'
figure['layout']['sliders'] = {
'args': [
'slider.value', {
'duration': 400,
'ease': 'cubic-in-out'
}
],
'initialValue': '2005',
'plotlycommand': 'animate',
'values': years,
'visible': True
}
figure['layout']['updatemenus'] = [
{
'buttons': [
{
'args': [None, {'frame': {'duration': 500, 'redraw': False},
'fromcurrent': True, 'transition': {'duration': 300, 'easing': 'quadratic-in-out'}}],
'label': 'Play',
'method': 'animate'
},
{
'args': [[None], {'frame': {'duration': 0, 'redraw': False}, 'mode': 'immediate',
'transition': {'duration': 0}}],
'label': 'Pause',
'method': 'animate'
}
],
'direction': 'left',
'pad': {'r': 10, 't': 87},
'showactive': False,
'type': 'buttons',
'x': 0.1,
'xanchor': 'right',
'y': 0,
'yanchor': 'top'
}
]
sliders_dict = {
'active': 0,
'yanchor': 'top',
'xanchor': 'left',
'currentvalue': {
'font': {'size': 20},
'prefix': 'Year:',
'visible': True,
'xanchor': 'right'
},
'transition': {'duration': 300, 'easing': 'cubic-in-out'},
'pad': {'b': 10, 't': 50},
'len': 0.9,
'x': 0.1,
'y': 0,
'steps': []
}
# make data
year = 2005
for country in countries:
dataset_by_year = dataset[dataset['year'] == year]
dataset_by_year_and_count = dataset_by_year[dataset_by_year['country'] == country]
data_dict = {
'x': list(dataset_by_year_and_count['GDP per capita']),
'y': list(dataset_by_year_and_count['Life satisfaction in Cantril Ladder (World Happiness Report 2017)']),
'mode': 'markers',
'text': list(dataset_by_year_and_count['country']),
'marker': {
'sizemode': 'area',
'sizeref': 200000,
'size': list(dataset_by_year_and_count['Total population (Gapminder)'])
},
'name': country
}
figure['data'].append(data_dict)
# make frames
for year in years:
frame = {'data': [], 'name': str(year)}
for country in countries:
dataset_by_year = dataset[dataset['year'] == int(year)]
dataset_by_year_and_cont = dataset_by_year[dataset_by_year['country'] == country]
data_dict = {
'x': list(dataset_by_year_and_count['GDP per capita']),
'y': list(dataset_by_year_and_count['Life satisfaction in Cantril Ladder (World Happiness Report 2017)']),
'mode': 'markers',
'text': list(dataset_by_year_and_count['country']),
'marker': {
'sizemode': 'area',
'sizeref': 200000,
'size': list(dataset_by_year_and_count['Total population (Gapminder)'])
},
'name': country
}
frame['data'].append(data_dict)
figure['frames'].append(frame)
slider_step = {'args': [
[year],
{'frame': {'duration': 300, 'redraw': False},
'mode': 'immediate',
'transition': {'duration': 300}}
],
'label': year,
'method': 'animate'}
sliders_dict['steps'].append(slider_step)
figure['layout']['sliders'] = [sliders_dict]
iplot(figure, config=config)
这里的问题是我得到一个完全没有数据的空图（滑块、布局、轴标签动画正在运行），并且没有出现错误。所以老实说，我不知道问题出在哪里。显然和脚本中的数据构建有关，但我不知道具体是什么。
我使用了您提供的示例数据并对其进行了处理，我遇到了一些问题并在每一行中添加了我的评论，评论部分指出了主要原因，但您可以通过以下方式交叉检查我的代码你的，得到你需要的
代码：
from plotly.offline import init_notebook_mode, iplot
from IPython.display import display, HTML
import pandas as pd
init_notebook_mode(connected=True)
url = 'testing.csv'
dataset = pd.read_csv(url)
# instead of hardcoding you can use unique() function to get the years present in the file, then convert to list and sort based on years
# years = dataset['year'].unique().tolist()
# years.sort()
years = ['2007','2008','2009','2010','2011','2012','2013'] # try to provide years that contain data in the data set
# make list of continents
countries = []
for country in dataset['country'].unique():
countries.append(country)
# make figure
figure = {
'data': [],
'layout': {},
'frames': []
}
config = {'scrollzoom': True}
# fill in most of layout
# there is a small ranging issue, where some points go out of the plot so try this code if you notice it
#figure['layout']['xaxis'] = {'title': 'GDP per Capita', 'autorange': False, 'range': [int(dataset['GDP per capita'].min()), int(dataset['GDP per capita'].max())]} #was not set properly
#figure['layout']['yaxis'] = {'title': 'Life Expectancy', 'autorange': False,
# 'range': [int(dataset['Life satisfaction in Cantril Ladder (World Happiness Report 2017)'].min()),
# int(dataset['Life satisfaction in Cantril Ladder (World Happiness Report 2017)'].max())]} #was not set properly
figure['layout']['xaxis'] = {'title': 'GDP per Capita', 'type': 'log', 'autorange': True} #was not set properly
figure['layout']['yaxis'] = {'title': 'Life Expectancy', 'autorange': True} #was not set properly
figure['layout']['hovermode'] = 'closest'
figure['layout']['showlegend'] = True
figure['layout']['sliders'] = {
'args': [
'slider.value', {
'duration': 400,
'ease': 'cubic-in-out'
}
],
'initialValue': '2007',
'plotlycommand': 'animate',
'values': years,
'visible': True
}
figure['layout']['updatemenus'] = [
{
'buttons': [
{
'args': [None, {'frame': {'duration': 500, 'redraw': False},
'fromcurrent': True, 'transition': {'duration': 300, 'easing': 'quadratic-in-out'}}],
'label': 'Play',
'method': 'animate'
},
{
'args': [[None], {'frame': {'duration': 0, 'redraw': False}, 'mode': 'immediate',
'transition': {'duration': 0}}],
'label': 'Pause',
'method': 'animate'
}
],
'direction': 'left',
'pad': {'r': 10, 't': 87},
'showactive': False,
'type': 'buttons',
'x': 0.1,
'xanchor': 'right',
'y': 0,
'yanchor': 'top'
}
]
sliders_dict = {
'active': 0,
'yanchor': 'top',
'xanchor': 'left',
'currentvalue': {
'font': {'size': 20},
'prefix': 'Year:',
'visible': True,
'xanchor': 'right'
},
'transition': {'duration': 300, 'easing': 'cubic-in-out'},
'pad': {'b': 10, 't': 50},
'len': 0.9,
'x': 0.1,
'y': 0,
'steps': []
}
# make data - here you need to specify the year being used as starting point, important to change
year = 2007
for country in countries:
dataset_by_year = dataset[dataset['year'] == year]
dataset_by_year_and_cont=dataset_by_year[dataset_by_year['country'] == country]
data_dict = {
'x': list(dataset_by_year_and_cont['GDP per capita']),
'y': list(dataset_by_year_and_cont['Life satisfaction in Cantril Ladder (World Happiness Report 2017)']),
'mode': 'markers',
'text': [country], # since there is only one country we do not need to provide the list for text -
#Suggestion: No need to have this
'marker': {
'sizemode': 'area',
'sizeref': 200000,
'size': list(dataset_by_year_and_cont['Total population (Gapminder)'])
},
'name': country
}
figure['data'].append(data_dict)
# make frames
for year in years:
frame = {'data': [], 'name': str(year)}
dataset_by_year = dataset[dataset['year'] == int(year)] # here this has been moved because if the country
# is not present for that particular year there is no need to plot those traces
for country in dataset_by_year['country']:
dataset_by_year_and_cont=dataset_by_year[dataset_by_year['country'] == country]
data_dict = {
'x': list(dataset_by_year_and_cont['GDP per capita']),
'y': list(dataset_by_year_and_cont['Life satisfaction in Cantril Ladder (World Happiness Report 2017)']),
'mode': 'markers',
'text': [country], # since there is only one country we do not need to provide the list for text -
#Suggestion: No need to have this
'marker': {
'sizemode': 'area',
'sizeref': 200000,
'size': list(dataset_by_year_and_cont['Total population (Gapminder)'])
},
'name': country,
'type': 'scatter',
'showlegend': True
}
frame['data'].append(data_dict)
figure['frames'].append(frame) #this block was indented and should not have been.
slider_step = {'args': [
[year],
{'frame': {'duration': 300, 'redraw': False},
'mode': 'immediate',
'transition': {'duration': 300}}
],
'label': year,
'method': 'animate'}
sliders_dict['steps'].append(slider_step)
figure['layout']['sliders'] = [sliders_dict]
iplot(figure, config=config)
输出：
我正在尝试将标准的动画气泡图调整为包含这些列的 csv 文件：
index,country,year,Country code,Total population (Gapminder),Life satisfaction in Cantril Ladder (World Happiness Report 2017),GDP per capita
62,Afghanistan,2008,AFG,29839994.0,3.723589897,1298.14315888
63,Afghanistan,2009,AFG,30577756.0,4.401778221,1531.17399272
64,Afghanistan,2010,AFG,31411743.0,4.75838089,1614.25500126
65,Afghanistan,2011,AFG,32358260.0,3.83171916,1660.73985618
66,Afghanistan,2012,AFG,33397058.0,3.782937527,1839.27357928
67,Afghanistan,2013,AFG,34499915.0,3.572100401,1814.15582533
167,Albania,2007,ALB,3169665.0,4.634251595,8447.88228539
169,Albania,2009,ALB,3192723.0,5.485469818,9524.60981095
170,Albania,2010,ALB,3204284.0,5.268936634,9927.13514733
171,Albania,2011,ALB,3215988.0,5.867421627,10207.7006745
172,Albania,2012,ALB,3227373.0,5.510124207,10369.7616592
173,Albania,2013,ALB,3238316.0,4.550647736,10504.0930888
242,Algeria,2010,DZA,35468208.0,5.46356678,12870.2162376
243,Algeria,2011,DZA,35980193.0,5.317194462,12989.9549601
244,Algeria,2012,DZA,36485828.0,5.604595661,13161.566464
451,Angola,2011,AGO,19618432.0,5.589000702,5911.25433387
452,Angola,2012,AGO,20162517.0,4.360249996,5998.63860099
453,Angola,2013,AGO,20714494.0,3.937106848,6185.0138292
数据点的大小是人口的函数，我将绘制生活满意度与国家 GDP 的函数关系图。我在数据集上做了一些工作：
gdp=pd.read_csv('gdp-vs-happiness.csv')
gdp=gdp.ix[~(gdp['year'] < 2005)]
gdp=gdp.dropna()
dataset = gdp
然后是代码：
years = ['2005','2006', '2007','2008','2009','2010','2011','2012','2013','2014','2015','2016']
# make list of continents
countries = []
for country in dataset['country']:
countries.append(country)
# make figure
figure = {
'data': [],
'layout': {},
'frames': []
}
config = {'scrollzoom': True}
# fill in most of layout
figure['layout']['xaxis'] = {'title': 'GDP per Capita', 'type': 'log'}
figure['layout']['yaxis'] = {'range': [0, 10], 'title': 'Life Satisfaction'}
figure['layout']['hovermode'] = 'closest'
figure['layout']['sliders'] = {
'args': [
'slider.value', {
'duration': 400,
'ease': 'cubic-in-out'
}
],
'initialValue': '2005',
'plotlycommand': 'animate',
'values': years,
'visible': True
}
figure['layout']['updatemenus'] = [
{
'buttons': [
{
'args': [None, {'frame': {'duration': 500, 'redraw': False},
'fromcurrent': True, 'transition': {'duration': 300, 'easing': 'quadratic-in-out'}}],
'label': 'Play',
'method': 'animate'
},
{
'args': [[None], {'frame': {'duration': 0, 'redraw': False}, 'mode': 'immediate',
'transition': {'duration': 0}}],
'label': 'Pause',
'method': 'animate'
}
],
'direction': 'left',
'pad': {'r': 10, 't': 87},
'showactive': False,
'type': 'buttons',
'x': 0.1,
'xanchor': 'right',
'y': 0,
'yanchor': 'top'
}
]
sliders_dict = {
'active': 0,
'yanchor': 'top',
'xanchor': 'left',
'currentvalue': {
'font': {'size': 20},
'prefix': 'Year:',
'visible': True,
'xanchor': 'right'
},
'transition': {'duration': 300, 'easing': 'cubic-in-out'},
'pad': {'b': 10, 't': 50},
'len': 0.9,
'x': 0.1,
'y': 0,
'steps': []
}
# make data
year = 2005
for country in countries:
dataset_by_year = dataset[dataset['year'] == year]
dataset_by_year_and_count = dataset_by_year[dataset_by_year['country'] == country]
data_dict = {
'x': list(dataset_by_year_and_count['GDP per capita']),
'y': list(dataset_by_year_and_count['Life satisfaction in Cantril Ladder (World Happiness Report 2017)']),
'mode': 'markers',
'text': list(dataset_by_year_and_count['country']),
'marker': {
'sizemode': 'area',
'sizeref': 200000,
'size': list(dataset_by_year_and_count['Total population (Gapminder)'])
},
'name': country
}
figure['data'].append(data_dict)
# make frames
for year in years:
frame = {'data': [], 'name': str(year)}
for country in countries:
dataset_by_year = dataset[dataset['year'] == int(year)]
dataset_by_year_and_cont = dataset_by_year[dataset_by_year['country'] == country]
data_dict = {
'x': list(dataset_by_year_and_count['GDP per capita']),
'y': list(dataset_by_year_and_count['Life satisfaction in Cantril Ladder (World Happiness Report 2017)']),
'mode': 'markers',
'text': list(dataset_by_year_and_count['country']),
'marker': {
'sizemode': 'area',
'sizeref': 200000,
'size': list(dataset_by_year_and_count['Total population (Gapminder)'])
},
'name': country
}
frame['data'].append(data_dict)
figure['frames'].append(frame)
slider_step = {'args': [
[year],
{'frame': {'duration': 300, 'redraw': False},
'mode': 'immediate',
'transition': {'duration': 300}}
],
'label': year,
'method': 'animate'}
sliders_dict['steps'].append(slider_step)
figure['layout']['sliders'] = [sliders_dict]
iplot(figure, config=config)
这里的问题是我得到一个完全没有数据的空图（滑块、布局、轴标签动画正在运行），并且没有出现错误。所以老实说，我不知道问题出在哪里。显然和脚本中的数据构建有关，但我不知道具体是什么。
我使用了您提供的示例数据并对其进行了处理，我遇到了一些问题并在每一行中添加了我的评论，评论部分指出了主要原因，但您可以通过以下方式交叉检查我的代码你的，得到你需要的
代码：
from plotly.offline import init_notebook_mode, iplot
from IPython.display import display, HTML
import pandas as pd
init_notebook_mode(connected=True)
url = 'testing.csv'
dataset = pd.read_csv(url)
# instead of hardcoding you can use unique() function to get the years present in the file, then convert to list and sort based on years
# years = dataset['year'].unique().tolist()
# years.sort()
years = ['2007','2008','2009','2010','2011','2012','2013'] # try to provide years that contain data in the data set
# make list of continents
countries = []
for country in dataset['country'].unique():
countries.append(country)
# make figure
figure = {
'data': [],
'layout': {},
'frames': []
}
config = {'scrollzoom': True}
# fill in most of layout
# there is a small ranging issue, where some points go out of the plot so try this code if you notice it
#figure['layout']['xaxis'] = {'title': 'GDP per Capita', 'autorange': False, 'range': [int(dataset['GDP per capita'].min()), int(dataset['GDP per capita'].max())]} #was not set properly
#figure['layout']['yaxis'] = {'title': 'Life Expectancy', 'autorange': False,
# 'range': [int(dataset['Life satisfaction in Cantril Ladder (World Happiness Report 2017)'].min()),
# int(dataset['Life satisfaction in Cantril Ladder (World Happiness Report 2017)'].max())]} #was not set properly
figure['layout']['xaxis'] = {'title': 'GDP per Capita', 'type': 'log', 'autorange': True} #was not set properly
figure['layout']['yaxis'] = {'title': 'Life Expectancy', 'autorange': True} #was not set properly
figure['layout']['hovermode'] = 'closest'
figure['layout']['showlegend'] = True
figure['layout']['sliders'] = {
'args': [
'slider.value', {
'duration': 400,
'ease': 'cubic-in-out'
}
],
'initialValue': '2007',
'plotlycommand': 'animate',
'values': years,
'visible': True
}
figure['layout']['updatemenus'] = [
{
'buttons': [
{
'args': [None, {'frame': {'duration': 500, 'redraw': False},
'fromcurrent': True, 'transition': {'duration': 300, 'easing': 'quadratic-in-out'}}],
'label': 'Play',
'method': 'animate'
},
{
'args': [[None], {'frame': {'duration': 0, 'redraw': False}, 'mode': 'immediate',
'transition': {'duration': 0}}],
'label': 'Pause',
'method': 'animate'
}
],
'direction': 'left',
'pad': {'r': 10, 't': 87},
'showactive': False,
'type': 'buttons',
'x': 0.1,
'xanchor': 'right',
'y': 0,
'yanchor': 'top'
}
]
sliders_dict = {
'active': 0,
'yanchor': 'top',
'xanchor': 'left',
'currentvalue': {
'font': {'size': 20},
'prefix': 'Year:',
'visible': True,
'xanchor': 'right'
},
'transition': {'duration': 300, 'easing': 'cubic-in-out'},
'pad': {'b': 10, 't': 50},
'len': 0.9,
'x': 0.1,
'y': 0,
'steps': []
}
# make data - here you need to specify the year being used as starting point, important to change
year = 2007
for country in countries:
dataset_by_year = dataset[dataset['year'] == year]
dataset_by_year_and_cont=dataset_by_year[dataset_by_year['country'] == country]
data_dict = {
'x': list(dataset_by_year_and_cont['GDP per capita']),
'y': list(dataset_by_year_and_cont['Life satisfaction in Cantril Ladder (World Happiness Report 2017)']),
'mode': 'markers',
'text': [country], # since there is only one country we do not need to provide the list for text -
#Suggestion: No need to have this
'marker': {
'sizemode': 'area',
'sizeref': 200000,
'size': list(dataset_by_year_and_cont['Total population (Gapminder)'])
},
'name': country
}
figure['data'].append(data_dict)
# make frames
for year in years:
frame = {'data': [], 'name': str(year)}
dataset_by_year = dataset[dataset['year'] == int(year)] # here this has been moved because if the country
# is not present for that particular year there is no need to plot those traces
for country in dataset_by_year['country']:
dataset_by_year_and_cont=dataset_by_year[dataset_by_year['country'] == country]
data_dict = {
'x': list(dataset_by_year_and_cont['GDP per capita']),
'y': list(dataset_by_year_and_cont['Life satisfaction in Cantril Ladder (World Happiness Report 2017)']),
'mode': 'markers',
'text': [country], # since there is only one country we do not need to provide the list for text -
#Suggestion: No need to have this
'marker': {
'sizemode': 'area',
'sizeref': 200000,
'size': list(dataset_by_year_and_cont['Total population (Gapminder)'])
},
'name': country,
'type': 'scatter',
'showlegend': True
}
frame['data'].append(data_dict)
figure['frames'].append(frame) #this block was indented and should not have been.
slider_step = {'args': [
[year],
{'frame': {'duration': 300, 'redraw': False},
'mode': 'immediate',
'transition': {'duration': 300}}
],
'label': year,
'method': 'animate'}
sliders_dict['steps'].append(slider_step)
figure['layout']['sliders'] = [sliders_dict]
iplot(figure, config=config)
输出：