I have a 3D scatter plot which was produced using the following code
import seaborn as sns
import numpy as np
from matplotlib import pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from matplotlib.colors import ListedColormap
# Create an example dataframe
data = {'th': [1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2],
'pdvalue': [0.5, 0.5, 0.5, 0.5, 0.2,0.2,0.2,0.2,0.3,0.3,0.4,0.1,1,1.1,3,1],
'my_val': [1.2,3.2,4,5.1,1,2,5.1,1,2,4,1,3,6,6,2,3],
'name':['a','b','c','d','a','b','c','d','a','b','c','d','a','b','c','d']}
df = pd.DataFrame(data)
# convert unique str into unique int
order_dict = {k: i for i, k in enumerate ( df ['name'])}
df ['name_int'] = df ['name'].map ( order_dict )
data_np=df.to_numpy()
# generate data
x = data_np[:,0]
y = data_np[:,1]
z = data_np[:,2]
# axes instance
fig = plt.figure(figsize=(10,6))
ax = Axes3D(fig)
# get colormap from seaborn
cmap = ListedColormap(sns.color_palette("husl", 256).as_hex())
# plot
sc = ax.scatter(x, y, z, s=40, c=data_np[:,4], marker='o', cmap=cmap, alpha=1)
ax.set_xlabel('th')
ax.set_ylabel('pdvalue')
ax.set_zlabel('my_val')
# legend
plt.legend(*sc.legend_elements(), bbox_to_anchor=(1.05, 1), loc=2)
plt.show()
and this produce
In the above, I had to convert the name into integer type as the para c of the ax.scatter only accept number. As a result, the legend was map according thenumeric value instead of the original name.
May I know how to have the legend in term of name instead of the numerical representation?
The code can be simplified making use of pandas to do conversions and selections. By drawing the scatter plot for each 'name' separately, they each can be given a label for the legend.
Here is the adapted code:
import seaborn as sns
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
# Create an example dataframe
data = {'th': [1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2],
'pdvalue': [0.5, 0.5, 0.5, 0.5, 0.2, 0.2, 0.2, 0.2, 0.3, 0.3, 0.4, 0.1, 1, 1.1, 3, 1],
'my_val': [1.2, 3.2, 4, 5.1, 1, 2, 5.1, 1, 2, 4, 1, 3, 6, 6, 2, 3],
'name': ['a', 'b', 'c', 'd', 'a', 'b', 'c', 'd', 'a', 'b', 'c', 'd', 'a', 'b', 'c', 'd']}
df = pd.DataFrame(data)
# axes instance
fig = plt.figure(figsize=(10, 6))
ax = Axes3D(fig, auto_add_to_figure=False)
fig.add_axes(ax)
# find all the unique labels in the 'name' column
labels = np.unique(df['name'])
# get palette from seaborn
palette = sns.color_palette("husl", len(labels))
# plot
for label, color in zip(labels, palette):
df1 = df[df['name'] == label]
ax.scatter(df1['th'], df1['pdvalue'], df1['my_val'],
s=40, marker='o', color=color, alpha=1, label=label)
ax.set_xlabel('th')
ax.set_ylabel('pdvalue')
ax.set_zlabel('my_val')
# legend
plt.legend(bbox_to_anchor=(1.05, 1), loc=2)
plt.show()
Related
I made a mock-up version of my dataset to illustrate my problem.
I have a graph like this:
import pandas as pd
import matplotlib.pyplot as plt
data = {'x': [0, 1, 2, 3],
'y': [3, 2, 1, 0],
'cat1': ['A', 'B', 'A', 'B'],
'cat2': ['f', 'g', 'h', 'i']}
df = pd.DataFrame(data)
colors = {'A':'tab:red',
'B':'tab:blue'}
markers = {'f':"o",
'g':"v",
'h':"s",
'i':"+"}
fig, ax = plt.subplots()
for i in range(df.shape[0]):
ax.scatter(df.loc[i,'x'],
df.loc[i,'y'],
color=colors[df.loc[i,'cat1']],
marker=markers[df.loc[i,'cat2']],
label = df.loc[i, 'cat2'])
ax.legend()
But I'm looking for a legend like this:
Could anyone give me some tips on how to solve this? Also, it would be better if the legend in the final plot were in a box outside the plot, on the right side.
To add additional lines (A,B), rearrange the order and move the legend outside the graph, these are the steps you can follow after plotting.
Create a custom legend entries for the new entries and existing one using Line2D
Plot the legend and use bbox_to_anchor to move the legend to where you need it. You can adjust the coordinates within bbox if you want to move the position
Adjust the labels for A, B as these are only text (no marker) so that align horizontally to the middle (you can adjust set_position() if you want to move it further to the left/right
Code
import pandas as pd
import matplotlib.pyplot as plt
data = {'x': [0, 1, 2, 3],
'y': [3, 2, 1, 0],
'cat1': ['A', 'B', 'A', 'B'],
'cat2': ['f', 'g', 'h', 'i']}
df = pd.DataFrame(data)
colors = {'A':'tab:red',
'B':'tab:blue'}
markers = {'f':"o",
'h':"s",
'g':"v",
'i':"+"}
fig, ax = plt.subplots()
for i in range(df.shape[0]):
ax.scatter(df.loc[i,'x'], df.loc[i,'y'],
color=colors[df.loc[i,'cat1']],
marker=markers[df.loc[i,'cat2']],
label = df.loc[i, 'cat2']
## Create legend handle entries for each of the items
from matplotlib.lines import Line2D
title = Line2D([0], [0], linestyle="none", marker="")
f = Line2D([0], [0], linestyle="none", marker="o", markersize=10, markeredgecolor='tab:red', markerfacecolor="tab:red")
g = Line2D([0], [0], linestyle="none", marker="v", markersize=10, markeredgecolor='tab:blue', markerfacecolor="tab:blue")
h = Line2D([0], [0], linestyle="none", marker="s", markersize=10, markeredgecolor='tab:red', markerfacecolor="tab:red")
i = Line2D([0], [0], linestyle="none", marker="+", markersize=10, markeredgecolor='tab:blue', markerfacecolor="tab:blue")
## Plot in order you want, bbox to set legend box outside
leg=ax.legend((title, f, h, title, g, i), ('A', 'f', 'h', 'B', 'g','i'), bbox_to_anchor=(1.16, 1.03))
## Adjust position of A and B so that they are in middle
for item, label in zip(leg.legendHandles, leg.texts):
if label._text in ['A', 'B']:
width=item.get_window_extent(fig.canvas.get_renderer()).width
label.set_ha('left')
label.set_position((-width/2,0)) ## Adjust here to move left/right
Plot
I am new in python programming. I can simply plot the input data shown in the figure with my code but how can I plot the time series data as mention in the figure. Any code and suggestions will be thankful.
My code is:
import matplotlib.pyplot as plt
import numpy as np
y_values = [5, 5, 1, 1, 5, 5, 1, 1, 5, 1, 1]
x_values = np.arange(30, 331, 30)
plt.figure()
plt.plot(x_values,y_values,"-x")
plt.show()
Although there is a way to draw a series of rectangular shapes, we used a general method and used horizontal bar charts. We added a list for the values in the bar chart and stacked the values. Class label names and class titles are now supported as annotations. You can try various other parameters.
import matplotlib.pyplot as plt
import numpy as np
y = [5]*11
y_values = [5, 5, 1, 1, 5, 5, 1, 1, 5, 1, 1]
x_values = np.arange(30, 331, 30)
fig, ax = plt.subplots(figsize=(12,1))
ax.barh(y=0, height=1.0, edgecolor='k', width=y[0], label='Time Interval')
for i in range(len(y)):
if y_values[i] == 5:
color = 'y'
else:
color = 'm'
ax.barh(y=0, left=sum(y[:i]), height=1.0, width=y[i], color=color, edgecolor='k', label='Time Interval')
for s in ['top','bottom','left','right']:
ax.spines[s].set_visible(False)
for i,(p,t) in enumerate(zip(y, y_values)):
ax.text(y=0.6, x=2.5+p*i, s=str(t))
ax.text(-0.08, 1, 'Class', transform=ax.transAxes)
ax.set_xticks([])
ax.set_yticks([])
ax.set_ylabel('Time Interval', rotation=0, labelpad=40, loc='center')
plt.show()
Try:
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
y_values = ['class', 5, 5, 1, 1, 5, 5, 1, 1, 5, 1, 1]
x_values = np.arange(30, 331, 30)
x_values = np.concatenate((['Time'],x_values))
df = pd.DataFrame(data={'class': y_values, 'Time': x_values})
colors = {5: 'gold', 1: 'darkviolet'}
df['colors'] = df['class'].map(colors)
df['colors'].fillna('white', inplace=True)
df['Time'].iloc[1:] = ''
print(df)
fig, ax =plt.subplots(1,1)
ax.axis('tight')
ax.axis('off')
data = df.T.values
colors = [data[2].tolist()]
table = ax.table(cellText=[data[1].tolist()], colLabels=data[0].tolist(),loc="center", cellColours=colors)
table.set_fontsize(14)
for i in range(len(data[0])):
table[0, i].visible_edges = ''
table[1, 0].visible_edges = ''
table.scale(1.5, 1.5)
plt.show()
I want to plot a seaborn.swarmplot with categories (hue) represented as markers, while the color of the scatterplots defines the value of an additional column.
I found this great answer to be quite similar, but instead I'd like to add another column to my dataframe, let's call it cat for a categoric variable, which is set as hue='cat' while the colormap is defined via the column c. Instead of colored categories, I want the categories to be marked with markers, f.i. markers=['x', 'o', 'd']. I adapted the above mentioned answer to implement at least the colormap to depend on c but to be also mapped by the category, but the setting a marker for each category still fails:
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.colorbar
import matplotlib.colors
import matplotlib.cm
from mpl_toolkits.axes_grid1 import make_axes_locatable
import seaborn as sns
# dataframe
df = pd.DataFrame(
data={'a': [1, 4, 5, 6, 3, 4, 5, 6],
'c': [12, 35, 12, 46, 78, 45, 34, 70],
'cat': [0, 1, 1, 1, 0, 1, 0, 1],
'key': [1, 2, 2, 1, 1, 2, 1, 2]}
)
# Create a matplotlib colormap from the sns seagreen color palette
cmap = sns.light_palette("seagreen", reverse=False, as_cmap=True)
# Normalize to the range of possible values from df["c"]
norm = matplotlib.colors.Normalize(vmin=df["c"].min(), vmax=df["c"].max())
# create a color dictionary (value in c : color from colormap)
colors = {}
for cat, cval in zip(df['cat'], df["c"]):
colors.update({'{0}-{1}'.format(cat, cval) : cmap(norm(cval))})
# save cat-col key as new reformed cat col:
df['cat-color'] = list(colors.keys())
fig = plt.figure(figsize=(5,2.8))
# plot the swarmplot with the colors dictionary as palette
m = sns.swarmplot(x='key', y='a', hue="cat-color", s=12, data=df,
palette=colors, markers=['x', 'o', 'd'])
## create colorbar ##
divider = make_axes_locatable(plt.gca())
ax_cb = divider.new_horizontal(size="5%", pad=0.05)
fig.add_axes(ax_cb)
cb1 = matplotlib.colorbar.ColorbarBase(
ax_cb, cmap=cmap, norm=norm, orientation='vertical')
plt.show()
Any idea how to integrate the markers and how to make the color only dependent on c and not on cat?
I also found this answer which deals with markers, but I can't see any way to combine it to have markers and colors independently.
I'm creating a stacked horizontal bar graph with 3 segments using the code below:
import matplotlib.pyplot as plt
import numpy as np
def create_stacked_hbar(data):
fig, ax = plt.subplots(figsize=(10, 10))
ylabels = list(data.keys())
labels = ['a', 'b', 'c', 'd', 'e', 'f']
c = []
v = []
for key, val in data.items():
c.append(key)
v.append(val)
v = np.array(v)
print(v)
plt.barh(range(len(c)), v[:,0], width=1, color='red',
edgecolor='w',linewidth=2, tick_label=ylabels, label=labels[0])
plt.barh(range(len(c)), v[:,1], width=1, left=v[:,0], color='orange',
edgecolor='w', linewidth=2, label=labels[1])
plt.barh(range(len(c)), v[:,2], width=1, left=(v[:,0]+v[:,1]), color='yellow',
edgecolor='w', linewidth=2, label=labels[2])
for p in ax.patches:
left, bottom, width, height = p.get_bbox().bounds
if width != 0.0:
ax.annotate(str(int(width)), xy=(left+width/2, bottom+height/2),
ha='center', va='center', size = 12)
plt.legend(bbox_to_anchor=(0, -0.15), loc=3, prop={'size': 14}, frameon=False)
plt.yticks(np.arange(len(ylabels)), ylabels)
plt.show()
data = {'A': [8, 7, 2], 'B': [0, 2, 0],
'C': [3, 2, 4], 'D': [0, 4, 0],
'E': [0, 1, 1], 'F': [0, 1, 0],
'G': [0, 0, 0]}
create_stacked_hbar(data)
The issue is that in attempting to set width = 1 in the bars throws a type error:
TypeError: <lambda>() got multiple values for argument 'width'
removing width allows to the code to work, but I do need to increase the width of the bars in the chart. I suspect this has to do with the annotation code I use in this case. Does anyone have any suggestions on getting around this?
Also note I am unable to use the "dataframe.plot.barh(data, stacked=True)" method via pandas to generate this chart.
You are making a horizontal bar plot, the width parameter corresponds to the data, so in your example you are passing both v[:,0] and 1 as width. If you are trying to specify the height because you do not desire whitespace between the bars you need to set height=1, consider this example:
import numpy as np
import matplotlib.pyplot as plt
# Seeded for reproducing
np.random.seed(1)
v1 = abs(np.random.randn(10))
v2 = abs(np.random.randn(10))
v3 = abs(np.random.randn(10))
c = range(10)
plt.title("Sample bar plot")
plt.barh(c, v1, height=1, alpha=0.8, color='r')
plt.barh(c, v2, height=1, left=v1, alpha=0.8, color='b')
plt.barh(c, v3, height=1, left=v1+v2, alpha=0.8, color='g')
plt.show()
This will give you
Where removing the height=1 specification would give you
I'm looking to make a colorbar like plot, like so:
but with a controllable color, for example I have the following x and y arrays:
x = [0,1,2,4,7,8]
y = [1,2,1,3,4,5]
Then I would have a colorbar like the above picture, but when y=1, it would color red, y=2: green, y=3: blue, y=4:black, etc.
Here is the python code that I modified from matplotlib's gallery:
from matplotlib import pyplot
import matplotlib as mpl
fig = pyplot.figure(figsize=(8,1))
ax2 = fig.add_axes([0.05, 0.25, 0.9, 0.5])
cmap = mpl.cm.Accent
norm = mpl.colors.Normalize(vmin=5, vmax=10)
bounds = [1, 2, 4, 7, 8]
norm = mpl.colors.BoundaryNorm(bounds, cmap.N)
cb2 = mpl.colorbar.ColorbarBase(ax2, cmap=cmap,
norm=norm,
boundaries=[0]+bounds+[13],
ticks=bounds, # optional
spacing='proportional',
orientation='horizontal')
After adapting your code I managed to obtain something like you described.
In this case the colormap is generated using ListedColormap and I added the yellow color for y=5.
It is important to notice that while calculating the BoundaryNorm I am using the intervals that contain the values you described for y.
from matplotlib import pyplot,colors
import matplotlib as mpl
fig = pyplot.figure(figsize=(8,1))
ax2 = fig.add_axes([0.05, 0.25, 0.9, 0.5])
cmap = colors.ListedColormap(['r', 'g', 'b', 'k','y'])
bounds = [0, 1, 2, 4, 7, 8, 13]
yVals = [ 1, 2, 1, 3, 4, 5]
cBounds = [i+0.5 for i in range(6)]
norm = mpl.colors.BoundaryNorm(cBounds, cmap.N)
cb2 = mpl.colorbar.ColorbarBase(ax2, cmap=cmap,
norm=norm,
values=yVals,
boundaries=bounds,
ticks=bounds[1:-1], # optional
spacing='proportional',
orientation='horizontal')
-- Edited 14 of Jan (mrcl) --
Alternatively, you can use pcolormesh to plot your colormap and have a colorbar as your legend, such as in the example below.
from pylab import *
from matplotlib import pyplot,colors
import matplotlib as mpl
fig = pyplot.figure(figsize=(8,1.5))
ax1 = fig.add_axes([0.05, 0.25, 0.82, 0.5])
cmap = colors.ListedColormap(['r', 'g', 'b', 'k','y'])
xBounds = array([0, 1, 2, 4, 7, 8, 13])
yBounds = array([0, 1])
Vals = array([[ 1, 2, 1, 3, 4, 5]])
cBounds = [i+0.5 for i in arange(amax(Vals)+1)]
norm = mpl.colors.BoundaryNorm(cBounds, cmap.N)
c = ax1.pcolormesh(xBounds,yBounds,Vals,cmap=cmap,norm=norm)
ax1.set_xticks(xBounds[1:-1])
ax1.set_yticks([])
ax1.set_xlim(xBounds[0],xBounds[-1])
ax1.set_ylim(yBounds[0],yBounds[-1])
ax2 = fig.add_axes([0.9, 0.25, 0.05, 0.5])
colorbar(c,cax=ax2,ticks=arange(amax(Vals))+1)
Hope it helps.
Cheers
Well, I sort of tinkering with other ways:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cmx
import matplotlib.colors as colors
close('all')
def ColorPlot(x,y):
figure()
jet = plt.get_cmap('jet')
cNorm = colors.Normalize(vmin=min(y), vmax=max(y))
scalarMap = cmx.ScalarMappable(norm=cNorm, cmap=jet)
if len(x) == len(y):
x.insert(0,0)
for kk in range(len(x)-1):
colorVal = scalarMap.to_rgba(y[kk])
plt.axvspan(x[kk], x[kk+1], facecolor=colorVal,
alpha=0.5,label=colorVal)
plt.yticks([])
plt.xticks(x)
xlim([x[0],x[-1]])
plt.show()
x = [1,3,5,6,10,12]
y = [1,3,4,1,4,3]
ColorPlot(x,y)