Related
I'm prototyping some code to then bring in some more complex time series data (and a lot of it) but can't for the life of me figure out how to get the vector components to animate in the below code. The blue path looks good to start with then disappears on play. And secondly, only the x component displays on play. I've been working mostly off the tutorials on the main plotly site so far, but, as the project builds complexity, my lack of expertise in plotly has let me down. I'm developing in an online Jupyter notebook if someone has any suggestions on how to make my code better. Thanks.
N = 50
vec_x, vec_y, vec_z = [0,0,0]
list_of_lists = []
choice = [-0.2, 0.2]
for i in range(N):
vec_x = vec_x + np.random.choice(choice)
vec_y = vec_y + np.random.choice(choice)
vec_z = vec_z + np.random.choice(choice)
list_of_lists.append([vec_x, vec_y, vec_z])
points = np.array(list_of_lists)
source = points.T
def frameMaker(i):
"""
returns x,y,z dict of currently indexed frame by vector component key
"""
scale = 10
list_of_lists = dict({
"x": [[source[0][i],scale * source[0][i+1]], [source[1][i],source[1][i]], [source[2][i],source[2][i]]],
"y": [[source[0][i],source[0][i]], [source[1][i],scale * source[1][i+1]], [source[2][i], source[2][i]]],
"z": [[source[0][i],source[0][i]], [source[1][i],source[1][i]], [source[2][i], scale * source[2][i+1]]]
})
return list_of_lists
#graphics
plt = go.Figure(
data=[go.Scatter3d(
x=source[0],
y=source[1],
z=source[2],
mode="lines",
line=dict(
color="darkblue",
width=2)),
go.Scatter3d(
x=source[0],
y=source[1],
z=source[2],
mode="lines",
line=dict(
color="darkblue",
width=2))
],
layout =
go.Layout(
title = go.layout.Title(text="Title | Total Frames: "+ str(N)),
scene_aspectmode="cube",
scene = dict(
xaxis = dict(range=[-2,2], nticks=10, autorange=False),
yaxis = dict(range=[-2,2], nticks=10, autorange=False),
zaxis = dict(range=[-2,2], nticks=10, autorange=False)),
updatemenus=[dict(type="buttons",
buttons=[dict(label="Play",
method="animate",
args=[None])])]
),
frames=[go.Frame(
data=[go.Scatter3d(
x = [source[0][k]],
y = [source[1][k]],
z = [source[2][k]],
mode="markers",
marker=dict(color="red",size=10,opacity=0.5)),
go.Scatter3d(
x=frameMaker(k)["x"][0],
y=frameMaker(k)["x"][1],
z=frameMaker(k)["x"][2],
line=dict(color='darkblue',width=2)),
go.Scatter3d(
x=frameMaker(k)["y"][0],
y=frameMaker(k)["y"][1],
z=frameMaker(k)["y"][2],
line=dict(color='#bcbd22',width=2)),
go.Scatter3d(
x=frameMaker(k)["z"][0],
y=frameMaker(k)["z"][1],
z=frameMaker(k)["z"][2],
line=dict(color='#d62728',width=2))],
layout=go.Layout(
title = go.layout.Title(text=str([k+1,list(map(lambda x: round(x,3), source.T[k]))]))
)
) for k in range(N-1)
]
)
plt.show()
Trying to make a choropleth map in plotly using some data I have in a csv file. Have created the following map:
my choromap
This isn't a correct display of the data however. Here is an excerpt of my csv file:
China,2447
...
Trinidad And Tobago,2
Turkey,26
Ukraine,8
United Arab Emirates,97
United States of America,2008
Based on this I'd expected China to appear in a similar colour to that which the US has loaded in, however it looks the same as countries with values of less than 200. Does anyone know what the reason for this is?
Here's my full code for reference:
import pandas as pd
import plotly as py
df = pd.read_csv('app_country_data_minus_uk.csv')
data = [dict(type='choropleth',
locations = df['Country'],
locationmode = 'country names',
z = df['Applications'],
text = df['Country'],
colorbar = {'title':'Apps per country'},
colorscale = 'Jet',
reversescale = False
)]
layout = dict(title='Application Jan-June 2018',
geo = dict(showframe=False,projection={'type':'mercator'}))
choromap = dict(data = data,layout = layout)
red = py.offline.plot(choromap,filename='world.html')
per your comment I would make sure that china is indeed 2447 and not something like 244. I would also follow the plotly documentation although you example code works.
import plotly.plotly as py
import pandas as pd
df = pd.read_csv('app_country_data_minus_uk.csv')
data = [ dict(
type = 'choropleth',
locations = df['Country'],
locationmode = 'country names',
z = df['Applications'],
colorscale = 'Jet',
reversescale = False,
marker = dict(
line = dict (
color = 'rgb(180,180,180)',
width = 0.5
) ),
colorbar = dict(
autotick = False,
tickprefix = '',
title = 'Apps per country'),
) ]
layout = dict(
title = 'app_country_data_minus_uk',
geo = dict(
showframe = True,
showcoastlines = True,
projection = dict(
type = 'Mercator'
)
)
)
fig = dict( data=data, layout=layout )
py.iplot( fig, validate=False, filename='d3-world-map' )
or if you want to plot it offline:
import plotly.plotly as py
import pandas as pd
import plotly
df = pd.read_csv('app_country_data_minus_uk.csv')
data = [ dict(
type = 'choropleth',
locations = df['Country'],
locationmode = 'country names',
z = df['Applications'],
colorscale = 'Jet',
reversescale = False,
marker = dict(
line = dict (
color = 'rgb(180,180,180)',
width = 0.5
) ),
colorbar = dict(
title = 'Apps per country'),
) ]
layout = dict(
title = 'app_country_data_minus_uk',
geo = dict(
showframe = True,
showcoastlines = True,
projection = dict(
type = 'Mercator'
)
)
)
fig = dict( data=data, layout=layout )
plotly.offline.plot(fig,filename='world.html')
If you use iplot you will be able to edit the chart and see the data in plotly to make sure your data looks correct
I have been trying to create a Geoscatter Plot with Plotly where the marker size should indicate the number of customers (row items) in one city (zip_city). I based my code on two templates from the Plotly documentation: United States Bubble Map and the aggregation part Mapping with Aggregates.
I managed to put together a code that does what I want, except for one drawback: when I hover over a bubble, I would like to see the name of the city plus number of customers (the result from the aggregation), so something like Aguadilla: 2. Can you help me on how to do this?
Here is my code (as a beginner with plotly, I am also open to code improvements):
import plotly.offline as pyo
import pandas as pd
df = pd.DataFrame.from_dict({'Customer': [111, 222, 555, 666],
'zip_city': ['Aguadilla', 'Aguadilla', 'Arecibo', 'Wrangell'],
'zip_latitude':[18.498987, 18.498987, 18.449732,56.409507],
'zip_longitude':[-67.13699,-67.13699,-66.69879,-132.33822]})
data = [dict(
type = 'scattergeo',
locationmode = 'USA-states',
lon = df['zip_longitude'],
lat = df['zip_latitude'],
text = df['Customer'],
marker = dict(
size = df['Customer'],
line = dict(width=0.5, color='rgb(40,40,40)'),
sizemode = 'area'
),
transforms = [dict(
type = 'aggregate',
groups = df['zip_city'],
aggregations = [dict(target = df['Customer'], func = 'count', enabled = True)]
)]
)]
layout = dict(title = 'Customers per US City')
fig = dict( data=data, layout=layout )
pyo.plot( fig, validate=False)
Update:
Can I access the result of the transforms argument directly in the data argument to show the number of customers per city?
You can create a list, that will contains what you want and then set text=list in data. Also do not forget specify hoverinfo='text'.
I am updated your code, so try this:
import pandas as pd
import plotly.offline as pyo
df = pd.DataFrame.from_dict({'Customer': [111, 222, 555, 666],
'zip_city': ['Aguadilla', 'Aguadilla', 'Arecibo', 'Wrangell'],
'zip_latitude':[18.498987, 18.498987, 18.449732,56.409507],
'zip_longitude':[-67.13699,-67.13699,-66.69879,-132.33822]})
customer = df['Customer'].tolist()
zipcity = df['zip_city'].tolist()
list = []
for i in range(len(customer)):
k = str(zipcity[i]) + ':' + str(customer[i])
list.append(k)
data = [dict(
type = 'scattergeo',
locationmode = 'USA-states',
lon = df['zip_longitude'],
lat = df['zip_latitude'],
text = list,
hoverinfo = 'text',
marker = dict(
size = df['Customer'],
line = dict(width=0.5, color='rgb(40,40,40)'),
sizemode = 'area'
),
transforms = [dict(
type = 'aggregate',
groups = df['zip_city'],
aggregations = [dict(target = df['Customer'], func = 'count', enabled = True)]
)]
)]
layout = dict(title = 'Customers per US City')
fig = dict(data=data, layout=layout)
pyo.plot(fig, validate=False)
I'm using Plotly's Python interface to generate a network. I've managed to create a network with my desired nodes and edges, and to control the size of the nodes.
I am desperately looking for help on how to do the following:
add node labels
add edge labels according to a list of weights
control the edge line width according to a list of weights
All this without using the "hovering" option, as it has to go in a non-interactive paper. I'd greatly appreciate any help! Plotly's output |
In case this fails, the figure itself |
matrix.csv
This is my code (most is copy-pasted from the Plotly tutorial for Networkx):
import pandas as pd
import plotly.plotly as py
from plotly.graph_objs import *
import networkx as nx
matrix = pd.read_csv("matrix.csv", sep = "\t", index_col = 0, header = 0)
G = nx.DiGraph()
# add nodes:
G.add_nodes_from(matrix.columns)
# add edges:
edge_lst = [(i,j, matrix.loc[i,j])
for i in matrix.index
for j in matrix.columns
if matrix.loc[i,j] != 0]
G.add_weighted_edges_from(edge_lst)
# create node trace:
node_trace = Scatter(x = [], y = [], text = [], mode = 'markers',
marker = Marker(
showscale = True,
colorscale = 'YIGnBu',
reversescale = True,
color = [],
size = [],
colorbar = dict(
thickness = 15,
title = 'Node Connections',
xanchor = 'left',
titleside = 'right'),
line = dict(width = 2)))
# set node positions
pos = nx.spring_layout(G)
for node in G.nodes():
G.node[node]['pos']= pos[node]
for node in G.nodes():
x, y = G.node[node]['pos']
node_trace['x'].append(x)
node_trace['y'].append(y)
# create edge trace:
edge_trace = Scatter(x = [], y = [], text = [],
line = Line(width = [], color = '#888'),
mode = 'lines')
for edge in G.edges():
x0, y0 = G.node[edge[0]]['pos']
x1, y1 = G.node[edge[1]]['pos']
edge_trace['x'] += [x0, x1, None]
edge_trace['y'] += [y0, y1, None]
edge_trace['text'] += str(matrix.loc[edge[0], edge[1]])[:5]
# size nodes by degree
deg_dict = {deg[0]:int(deg[1]) for deg in list(G.degree())}
for node, degree in enumerate(deg_dict):
node_trace['marker']['size'].append(deg_dict[degree] + 20)
fig = Figure(data = Data([edge_trace, node_trace]),
layout = Layout(
title = '<br>AA Substitution Rates',
titlefont = dict(size = 16),
showlegend = True,
margin = dict(b = 20, l = 5, r = 5, t = 40),
annotations = [dict(
text = "sub title text",
showarrow = False,
xref = "paper", yref = "paper",
x = 0.005, y = -0.002)],
xaxis = XAxis(showgrid = False,
zeroline = False,
showticklabels = False),
yaxis = YAxis(showgrid = False,
zeroline = False,
showticklabels = False)))
py.plot(fig, filename = 'networkx')
So
1. The solution to this is relative easy, you create a list with the node ids and you set it in the text attribute of the scatter plot. Then you set the mode as "markers+text" and you're done.
2. This is a little bit more tricky. You have to calculate the middle of each line and create a list of dicts including the line's middle position and weight. Then you add set as the layout's annotation.
3. This is too compicated to be done using plotly IMO. As for now I am calculating the position of each node using networkx spring_layout function. If you'd want to set the width of each line based on its weight you would have to modify the position using a function that takes into account all the markers that each line is attached to.
Bonus I give you the option to color each of the graph's components differently.
Here's a (slightly modified) function I made a while ago that does 1 and 2:
import pandas as pd
import plotly.plotly as py
import plotly.graph_objs as go
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
import networkx as nx
def scatter_plot_2d(G, folderPath, name, savePng = False):
print("Creating scatter plot (2D)...")
Nodes = [comp for comp in nx.connected_components(G)] # Looks for the graph's communities
Edges = G.edges()
edge_weights = nx.get_edge_attributes(G,'weight')
labels = [] # names of the nodes to plot
group = [] # id of the communities
group_cnt = 0
print("Communities | Number of Nodes")
for subgroup in Nodes:
group_cnt += 1
print(" %d | %d" % (group_cnt, len(subgroup)))
for node in subgroup:
labels.append(int(node))
group.append(group_cnt)
labels, group = (list(t) for t in zip(*sorted(zip(labels, group))))
layt = nx.spring_layout(G, dim=2) # Generates the layout of the graph
Xn = [layt[k][0] for k in list(layt.keys())] # x-coordinates of nodes
Yn = [layt[k][1] for k in list(layt.keys())] # y-coordinates
Xe = []
Ye = []
plot_weights = []
for e in Edges:
Xe += [layt[e[0]][0], layt[e[1]][0], None]
Ye += [layt[e[0]][1], layt[e[1]][1], None]
ax = (layt[e[0]][0]+layt[e[1]][0])/2
ay = (layt[e[0]][1]+layt[e[1]][1])/2
plot_weights.append((edge_weights[(e[0], e[1])], ax, ay))
annotations_list =[
dict(
x=plot_weight[1],
y=plot_weight[2],
xref='x',
yref='y',
text=plot_weight[0],
showarrow=True,
arrowhead=7,
ax=plot_weight[1],
ay=plot_weight[2]
)
for plot_weight in plot_weights
]
trace1 = go.Scatter( x=Xe,
y=Ye,
mode='lines',
line=dict(color='rgb(90, 90, 90)', width=1),
hoverinfo='none'
)
trace2 = go.Scatter( x=Xn,
y=Yn,
mode='markers+text',
name='Nodes',
marker=dict(symbol='circle',
size=8,
color=group,
colorscale='Viridis',
line=dict(color='rgb(255,255,255)', width=1)
),
text=labels,
textposition='top center',
hoverinfo='none'
)
xaxis = dict(
backgroundcolor="rgb(200, 200, 230)",
gridcolor="rgb(255, 255, 255)",
showbackground=True,
zerolinecolor="rgb(255, 255, 255)"
)
yaxis = dict(
backgroundcolor="rgb(230, 200,230)",
gridcolor="rgb(255, 255, 255)",
showbackground=True,
zerolinecolor="rgb(255, 255, 255)"
)
layout = go.Layout(
title=name,
width=700,
height=700,
showlegend=False,
plot_bgcolor="rgb(230, 230, 200)",
scene=dict(
xaxis=dict(xaxis),
yaxis=dict(yaxis)
),
margin=dict(
t=100
),
hovermode='closest',
annotations=annotations_list
, )
data = [trace1, trace2]
fig = go.Figure(data=data, layout=layout)
plotDir = folderPath + "/"
print("Plotting..")
if savePng:
plot(fig, filename=plotDir + name + ".html", auto_open=True, image = 'png', image_filename=plotDir + name,
output_type='file', image_width=700, image_height=700, validate=False)
else:
plot(fig, filename=plotDir + name + ".html")
The d3graph library provides the functionalities you want.
pip install d3graph
I downloaded your data and imported it for demonstration:
# Import data
df = pd.read_csv('data.csv', index_col=0)
# Import library
from d3graph import d3graph
# Convert your Pvalues. Note that any edge is set when a value in the matrix is >0. The edge width is however based on this value. A conversion is therefore useful when you work with Pvalues.
df[df.values==0]=1
df = -np.log10(df)
# Increase some distance between edges. Maybe something like this.
df = (np.exp(df)-1)/10
# Make the graph with default settings
d3 = d3graph()
# Make the graph by setting some parameters
d3.graph(df)
# Set edge properties
d3.set_edge_properties(directed=True)
# Set node properties
d3.set_node_properties(color=df.columns.values, size=size, edge_size=10, edge_color='#000000', cmap='Set2')
This will result in an interactive network graph. Two screenshots: one with the default settings and the one with tweaked settings. More examples can be found here.
Trying to use plotly to combine this line graph (that's already stacked):
import plotly
import plotly.graph_objs as plgo
#... Some Code
max = plgo.Scatter(x = day_times_str, y = max_val , name = "Max")
min = plgo.Scatter(x = day_times_str, y = min_val, name = "Min")
layout_opts = plgo.Layout(
xaxis = dict(title = 'xaxis'),
yaxis = dict(title = 'yaxis', rangemode = "tozero"),
)
figure1 = plgo.Figure(
data = [max, min],
layout = layout_opts,
)
and a map that shows location above this line graph...
#Assume geo_coord is a dataframe of coordinates, with columns 'lat', 'long' and 'text'
geo_data = [
plgo.Scattermapbox(
lat = geo_coord['lat'],
lon = geo_coord['lon'],
text = geo_coord['text'],
marker = dict(
color = geo_coord['text'],
size = 12,
),
mode = 'markers'
)
]
geo_layout = plgo.Layout(
autosize=True,
hovermode='closest',
mapbox=dict(
accesstoken= GMapsAPIHelper.MAPBOX_TOKEN, #Constant stored in global object
bearing=0,
pitch=0,
center=dict(
lat=49.04,
lon=-122.7
), #Modify by project details
zoom= 13
),
)
figure2 = dict(data = geo_data, layout = geo_layout)
plotly.offline.plot takes only 1 figure or set of data and I cannot pass in a list for graphing. I have tried using append_trace but because I've defined x and y axes in the line graph layout, this causes an error for the map, as follows:
File "C:\Anaconda2\lib\site-packages\plotly\graph_objs\graph_objs.py", line 934, in append_trace
trace['xaxis'] = ref[0]
TypeError: list indices must be integers, not str
Any help in solving this issue is appreciated.