I'm trying to create an interactive plotly graph from pandas dataframes.
However, I can't get the legends displayed correctly.
Here is a working example:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import plotly.plotly as py
# sign into the plotly api
py.sign_in("***********", "***********")
# create some random dataframes
dates = pd.date_range('1/1/2000', periods=8)
df1 = pd.DataFrame(np.random.randn(8, 1), index=dates, columns=['A'])
df2 = pd.DataFrame(np.random.randn(8, 1), index=dates, columns=['B'])
df1.index.name = 'date'
df2.index.name = 'date'
Now I attempt to plot the dataframes using plotly.
fig, ax = plt.subplots(1,1)
df1.plot(y='A', ax=ax)
df2.plot(y='B', ax=ax)
py.iplot_mpl(fig, filename='random')
Notice there is no legend
Edit:
Based on suggestions below I have added an update dict. Although this does display the legend, it messes up the plot itself:
fig, ax = plt.subplots(1,1)
df1.plot(y='A', ax=ax)
df2.plot(y='B', ax=ax)
update = dict(
layout=dict(
annotations=[dict(text=' ')], # rm erroneous 'A', 'B', ... annotations
showlegend=True # show legend
)
)
py.iplot_mpl(fig, update=update, filename='random')
Edit 2:
Removing the annotations entry from the layout dict results in the plot being displayed correctly, but the legend is not the y column name, but rather the x column name, the index name of the dataframe
fig, ax = plt.subplots(1,1)
df1.plot(y='A', ax=ax)
df2.plot(y='B', ax=ax)
update = dict(
layout=dict(
showlegend=True # show legend
)
)
py.iplot_mpl(fig, update=update, filename='random')
This results in the following plot:
Edit 3:
I have found a way to override the legend text but it seems a bit klunky. Given that I've specified the dataframe column I want to plot:
df1.plot(y='A', ax=ax)
I would have expected that y='A' would result in 'A' being used as the legend label.
It seems this is not the case, and while it is possible to override using the index label, as seen below, it just feels wrong.
Is there a better way to achieve this result?
update = dict(
layout=dict(
showlegend=True,
),
data=[
dict(name='A'),
dict(name='B'),
]
)
py.iplot_mpl(fig, update=update, filename='random')
Legends don't convert well from matplotlib to plotly.
Fortunately, adding a plotly legend to a matplotlib plot is straight forward:
update = dict(
layout=dict(
showlegend=True # show legend
)
)
py.iplot_mpl(fig, update=update)
See the full working ipython notebook here.
For more information, refer to the plotly user guide.
Related
I would like to add a second Y axis to my bar plot bellow, that is the number of citizens in integer:
this graph was made using plotly:
import plotly.express as px
fig = px.bar(df, x="country",y="pourcent_visit",color="city",barmode='group')
# fig.add_hline(y=10)
fig.show()
To my knowledge, there's no direct way to do this. But you can easily build a Plotly Express figure, grab the traces (and data structures) from there and combine them in a figure that allows multiple axes using fig = make_subplots(specs=[[{"secondary_y": True}]]). With no provided data sample, I'll use the built-in dataset px.data.tips() that I'm guessing to a large part resembles the structure of your real world dataset judging by the way you've applied the arguments in px.bar(). Details in the comments, but please don't hesitate to let me know if something is unclear.
Plot:
Complete code:
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
# sample data
df = px.data.tips()
# figure setup with multiple axes
fig = make_subplots(specs=[[{"secondary_y": True}]])
# build plotly express plot
fig2 = px.bar(df, x="day", y="total_bill", color="smoker", barmode="group")
# add traces from plotly express figure to first figure
for t in fig2.select_traces():
fig.add_trace(t, secondary_y = False)
# handle data for secondary axis
df2 = df.groupby('day').agg('sum')#.reset_index()
df2 = df2.reindex(index = df['day'].unique()).reset_index()
#
fig.add_trace(go.Scatter(x = df2['day'], y = df2['size'], mode = 'lines'), secondary_y = True)
# fix layout
fig.update_layout(legend_title_text = 'smoker')
fig.show()
Below you can see my data and facet plot in matplotlib.
import pandas as pd
import numpy as np
pd.set_option('max_columns', None)
import matplotlib.pyplot as plt
import matplotlib as mpl
# Data
data = {
'type_sale': ['g_1','g_2','g_3','g_4','g_5','g_6','g_7','g_8','g_9','g_10'],
'open':[70,20,24,150,80,90,60,90,20,20],
'closed':[30,14,20,10,20,40,10,10,10,10],
}
df = pd.DataFrame(data, columns = ['type_sale',
'open',
'closed',
])
data1 = {
'type_sale': [ 'open','closed'],
'structure':[70,30],
}
df1 = pd.DataFrame(data1, columns = ['type_sale',
'structure',
])
# Ploting
labels = ['open','closed']
fig, axs = plt.subplots(2,2, figsize=(10,8))
plt.subplots_adjust(wspace=0.2, hspace=0.6)
df1.plot(x='type_sale', y='structure',labels=labels,autopct='%1.1f%%',kind='pie', title='Stacked Bar Graph by dataframe',ax=axs[0,0])
df.plot(x='type_sale', kind='bar', stacked=True, title='Stacked Bar Graph by dataframe', ax=axs[0,1])
df.plot(x='type_sale', kind='bar', stacked=True, title='Stacked Bar Graph by dataframe',ax=axs[1,0])
df.plot(x='type_sale', kind='bar', stacked=True,title='Stacked Bar Graph by dataframe', ax=axs[1,1])
plt.suptitle(t='Stacked Bar Graph by dataframe', fontsize=16)
plt.show()
If you compare the first pie plot with others, you can spot a big difference. Namely, the first pie plot is not enclosed with a black line (rectangle), while the other is enclosed.
So can anybody help me with how to solve this problem?
After playing around myself, it seems that this is working, but I think the pie gets stretched, which doesn't look that good.
EDIT
found a better solution with set_adjustable
also two options how you create the piechart, the frame and ticks differ in a bit.
# 1
axs[0,0].pie(df1['structure'],labels=labels,autopct='%1.1f%%',frame=True,radius=10)
axs[0,0].set_title('Stacked Bar Graph by dataframe')
# 2
df1.plot(x='type_sale', y='structure',labels=labels,autopct='%1.1f%%',kind='pie', title='Stacked Bar Graph by dataframe',ax=axs[0,0])
axs[0,0].set_frame_on(True)
axs[0,0].set_adjustable('datalim')
Here is CDF visualization I have:
fig_cdf = px.ecdf(df['Timespan'], color_discrete_sequence=['blue'],ecdfnorm='probability', orientation='h')
fig_cdf.add_hline(y=90, line_width=2, line_color="red", name='90%', visible=True)
fig_cdf.add_hline(y=30, line_width=2, line_color="red", name='75%', visible=True)
fig_cdf.update_layout(width=500, height=500)
The problem here is that i want horizontal lines' names to be visible and appear as 2nd and 3rd legends. For this, I tried to add visible=True. However, it seems not to work. What's wrong?
This is one way of doing it...
Add the two lines to the dataframe as new columns
Use color_discrete_sequence to identify the colors you want
I am using some random dummy data, which you can replace with your data
import plotly.express as px
df = pd.DataFrame({'firstline': random.sample(range(1, 500), 20),'myX' : range(20)}) #My dummy data
#Add the two lines to dataframe
df['90%'] = [90] * 20
df['75%'] = [75] * 20
fig = px.line(df,
y = ['firstline', '90%', '75%'], x= 'myX', color_discrete_sequence=["blue", "red", "red"])
fig.update_layout(legend_title_text='Legend Heading') #Update Legend header if you dont like 'variable'
fig.show()
Output graph
This is my first experience with this graph, but to add it to the legend, you can use the line mode of the scatter plot. So I took the maximum x-axis value used in the first graph and set the legend name Average using the appropriate y-axis value. This example is taken from the official reference.
import plotly.express as px
import plotly.graph_objects as go
df = px.data.tips()
fig = px.ecdf(df, x=["total_bill", "tip"])
xmax = max(fig.data[0]['x'])
#print(xmax)
fig.add_trace(go.Scatter(
x=[0,xmax],
y=[0.6,0.6],
mode='lines',
line_color='red',
name='mean',
showlegend=True
))
fig.show()
I am plotting multiple dataframes as point plot using seaborn. Also I am plotting all the dataframes on the same axis.
How would I add legend to the plot ?
My code takes each of the dataframe and plots it one after another on the same figure.
Each dataframe has same columns
date count
2017-01-01 35
2017-01-02 43
2017-01-03 12
2017-01-04 27
My code :
f, ax = plt.subplots(1, 1, figsize=figsize)
x_col='date'
y_col = 'count'
sns.pointplot(ax=ax,x=x_col,y=y_col,data=df_1,color='blue')
sns.pointplot(ax=ax,x=x_col,y=y_col,data=df_2,color='green')
sns.pointplot(ax=ax,x=x_col,y=y_col,data=df_3,color='red')
This plots 3 lines on the same plot. However the legend is missing. The documentation does not accept label argument .
One workaround that worked was creating a new dataframe and using hue argument.
df_1['region'] = 'A'
df_2['region'] = 'B'
df_3['region'] = 'C'
df = pd.concat([df_1,df_2,df_3])
sns.pointplot(ax=ax,x=x_col,y=y_col,data=df,hue='region')
But I would like to know if there is a way to create a legend for the code that first adds sequentially point plot to the figure and then add a legend.
Sample output :
I would suggest not to use seaborn pointplot for plotting. This makes things unnecessarily complicated.
Instead use matplotlib plot_date. This allows to set labels to the plots and have them automatically put into a legend with ax.legend().
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
import numpy as np
date = pd.date_range("2017-03", freq="M", periods=15)
count = np.random.rand(15,4)
df1 = pd.DataFrame({"date":date, "count" : count[:,0]})
df2 = pd.DataFrame({"date":date, "count" : count[:,1]+0.7})
df3 = pd.DataFrame({"date":date, "count" : count[:,2]+2})
f, ax = plt.subplots(1, 1)
x_col='date'
y_col = 'count'
ax.plot_date(df1.date, df1["count"], color="blue", label="A", linestyle="-")
ax.plot_date(df2.date, df2["count"], color="red", label="B", linestyle="-")
ax.plot_date(df3.date, df3["count"], color="green", label="C", linestyle="-")
ax.legend()
plt.gcf().autofmt_xdate()
plt.show()
In case one is still interested in obtaining the legend for pointplots, here a way to go:
sns.pointplot(ax=ax,x=x_col,y=y_col,data=df1,color='blue')
sns.pointplot(ax=ax,x=x_col,y=y_col,data=df2,color='green')
sns.pointplot(ax=ax,x=x_col,y=y_col,data=df3,color='red')
ax.legend(handles=ax.lines[::len(df1)+1], labels=["A","B","C"])
ax.set_xticklabels([t.get_text().split("T")[0] for t in ax.get_xticklabels()])
plt.gcf().autofmt_xdate()
plt.show()
Old question, but there's an easier way.
sns.pointplot(x=x_col,y=y_col,data=df_1,color='blue')
sns.pointplot(x=x_col,y=y_col,data=df_2,color='green')
sns.pointplot(x=x_col,y=y_col,data=df_3,color='red')
plt.legend(labels=['legendEntry1', 'legendEntry2', 'legendEntry3'])
This lets you add the plots sequentially, and not have to worry about any of the matplotlib crap besides defining the legend items.
I tried using Adam B's answer, however, it didn't work for me. Instead, I found the following workaround for adding legends to pointplots.
import matplotlib.patches as mpatches
red_patch = mpatches.Patch(color='#bb3f3f', label='Label1')
black_patch = mpatches.Patch(color='#000000', label='Label2')
In the pointplots, the color can be specified as mentioned in previous answers. Once these patches corresponding to the different plots are set up,
plt.legend(handles=[red_patch, black_patch])
And the legend ought to appear in the pointplot.
This goes a bit beyond the original question, but also builds on #PSub's response to something more general---I do know some of this is easier in Matplotlib directly, but many of the default styling options for Seaborn are quite nice, so I wanted to work out how you could have more than one legend for a point plot (or other Seaborn plot) without dropping into Matplotlib right at the start.
Here's one solution:
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
# We will need to access some of these matplotlib classes directly
from matplotlib.lines import Line2D # For points and lines
from matplotlib.patches import Patch # For KDE and other plots
from matplotlib.legend import Legend
from matplotlib import cm
# Initialise random number generator
rng = np.random.default_rng(seed=42)
# Generate sample of 25 numbers
n = 25
clusters = []
for c in range(0,3):
# Crude way to get different distributions
# for each cluster
p = rng.integers(low=1, high=6, size=4)
df = pd.DataFrame({
'x': rng.normal(p[0], p[1], n),
'y': rng.normal(p[2], p[3], n),
'name': f"Cluster {c+1}"
})
clusters.append(df)
# Flatten to a single data frame
clusters = pd.concat(clusters)
# Now do the same for data to feed into
# the second (scatter) plot...
n = 8
points = []
for c in range(0,2):
p = rng.integers(low=1, high=6, size=4)
df = pd.DataFrame({
'x': rng.normal(p[0], p[1], n),
'y': rng.normal(p[2], p[3], n),
'name': f"Group {c+1}"
})
points.append(df)
points = pd.concat(points)
# And create the figure
f, ax = plt.subplots(figsize=(8,8))
# The KDE-plot generates a Legend 'as usual'
k = sns.kdeplot(
data=clusters,
x='x', y='y',
hue='name',
shade=True,
thresh=0.05,
n_levels=2,
alpha=0.2,
ax=ax,
)
# Notice that we access this legend via the
# axis to turn off the frame, set the title,
# and adjust the patch alpha level so that
# it closely matches the alpha of the KDE-plot
ax.get_legend().set_frame_on(False)
ax.get_legend().set_title("Clusters")
for lh in ax.get_legend().get_patches():
lh.set_alpha(0.2)
# You would probably want to sort your data
# frame or set the hue and style order in order
# to ensure consistency for your own application
# but this works for demonstration purposes
groups = points.name.unique()
markers = ['o', 'v', 's', 'X', 'D', '<', '>']
colors = cm.get_cmap('Dark2').colors
# Generate the scatterplot: notice that Legend is
# off (otherwise this legend would overwrite the
# first one) and that we're setting the hue, style,
# markers, and palette using the 'name' parameter
# from the data frame and the number of groups in
# the data.
p = sns.scatterplot(
data=points,
x="x",
y="y",
hue='name',
style='name',
markers=markers[:len(groups)],
palette=colors[:len(groups)],
legend=False,
s=30,
alpha=1.0
)
# Here's the 'magic' -- we use zip to link together
# the group name, the color, and the marker style. You
# *cannot* retreive the marker style from the scatterplot
# since that information is lost when rendered as a
# PathCollection (as far as I can tell). Anyway, this allows
# us to loop over each group in the second data frame and
# generate a 'fake' Line2D plot (with zero elements and no
# line-width in our case) that we can add to the legend. If
# you were overlaying a line plot or a second plot that uses
# patches you'd have to tweak this accordingly.
patches = []
for x in zip(groups, colors[:len(groups)], markers[:len(groups)]):
patches.append(Line2D([0],[0], linewidth=0.0, linestyle='',
color=x[1], markerfacecolor=x[1],
marker=x[2], label=x[0], alpha=1.0))
# And add these patches (with their group labels) to the new
# legend item and place it on the plot.
leg = Legend(ax, patches, labels=groups,
loc='upper left', frameon=False, title='Groups')
ax.add_artist(leg);
# Done
plt.show();
Here's the output:
I've been trying to follow this How to make custom legend in matplotlib SO question but I think a few things are getting lost in translation. I used a custom color mapping for the different classes of points in my plot and I want to be able to put a table with those color-label pairs. I stored the info in a dictionary D_color_label and then made 2 parallel lists colors and labels. I tried using it in the ax.legend but it didn't seem to work.
np.random.seed(0)
# Create dataframe
DF_0 = pd.DataFrame(np.random.random((100,2)), columns=["x","y"])
# Label to colors
D_idx_color = {**dict(zip(range(0,25), ["#91FF61"]*25)),
**dict(zip(range(25,50), ["#BA61FF"]*25)),
**dict(zip(range(50,75), ["#916F61"]*25)),
**dict(zip(range(75,100), ["#BAF1FF"]*25))}
D_color_label = {"#91FF61":"label_0",
"#BA61FF":"label_1",
"#916F61":"label_2",
"#BAF1FF":"label_3"}
# Add color column
DF_0["color"] = pd.Series(list(D_idx_color.values()), index=list(D_idx_color.keys()))
# Plot
fig, ax = plt.subplots(figsize=(8,8))
sns.regplot(data=DF_0, x="x", y="y", scatter_kws={"c":DF_0["color"]}, ax=ax)
# Add custom legend
colors = list(set(DF_0["color"]))
labels = [D_color_label[x] for x in set(DF_0["color"])]
# If I do this, I get the following error:
# ax.legend(colors, labels)
# UserWarning: Legend does not support '#BA61FF' instances.
# A proxy artist may be used instead.
According to http://matplotlib.org/users/legend_guide.html you have to put to legend function artists which will be labeled. To use scatter_plot individually you have to group by your data by color and plot every data of one color individually to set its own label for every artist:
import pandas as pd
import numpy as np
import matplotlib.pylab as plt
import seaborn as sns
np.random.seed(0)
# Create dataframe
DF_0 = pd.DataFrame(np.random.random((100, 2)), columns=["x", "y"])
DF_0['color'] = ["#91FF61"]*25 + ["#BA61FF"]*25 + ["#91FF61"]*25 + ["#BA61FF"]*25
#print DF_0
D_color_label = {"#91FF61": "label_0", "#BA61FF": "label_1",
"#916F61": "label_2", "#BAF1FF": "label_3"}
colors = list(DF_0["color"].uniqe())
labels = [D_color_label[x] for x in DF_0["color"].unique()]
ax = sns.regplot(data=DF_0, x="x", y="y", scatter_kws={'c': DF_0['color'], 'zorder':1})
# Make a legend
# groupby and plot points of one color
for i, grp in DF_0.groupby(['color']):
grp.plot(kind='scatter', x='x', y='y', c=i, ax=ax, label=labels[i+1], zorder=0)
ax.legend(loc=2)
plt.show()