Labeling stacked histogram bins with frequency of only one of the stacks - python

I've made a histogram of some data. It represents a bunch of stars, some of which have been observed, others of which have not. The white space represents the ones not observed. I would like to make it so that above the bins where there is white space, it would label the amount of white counts in those bins, but ignore the green and orange. If above the bins is complex, then below them is fine as well. Wherever is simplest. Here's the plot and the code:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
from matplotlib import font_manager
# hfont = {'fontname':'Computer Modern'}
filename = ("master.kkids.obslist")
datadata = np.loadtxt(filename,skiprows=14,dtype=str)
x = datadata[:,7]
y = datadata[:,8]
u = datadata[:,18]
v = datadata[:,19]
z = datadata[:,20]
yesGEM = (v == "Y") & (u == "GemN")
yesDCT = (v == "Y") & (u == "DCT")
no = (v == "N")
x1 = x.astype(float)
y1 = y.astype(float)
x2 = x1*24/360
colors = ['green', 'orange', 'white']
labels = ['GemN','DCT','Not Observed']
plt.xlim(0,24)
plt.hist((x2[yesGEM],x2[yesDCT],x2[no]), 24, label=labels, color=colors, histtype='bar', stacked=True)
plt.legend(fancybox=True,shadow=True)
plt.ylabel('Frequency')
plt.xlabel('Right Ascension (h)')
plt.savefig('kkids.hist.png')

The general pattern can be to loop on your x axis, for each stack check if there is a 'Not Observed', if so, fetch the values of GemN + DCT + (Not Observed / 2) for this observation, then use these two values as x and y to plot the desired text (i.e the value of not observed) using plt.text(x, y, text).
So if y understand correctly your dataset, i guess something like this should do the job :
# Get the returned arrays from plt.hist, they contain stacked frequencies
phist = plt.hist((x2[yesGEM],x2[yesDCT],x2[no]), 24, label=labels,
color=colors, histtype='bar', stacked=True)
plt.legend(fancybox=True,shadow=True)
plt.ylabel('Frequency')
plt.xlabel('Right Ascension (h)')
# Reshape the frequencies values :
stack_plots = \
np.concatenate(phist[0]).reshape(len(labels), len(phist[0][0])).T
for nb_x, stack in enumerate(stack_plots):
# 'stack' is an array with the frequency of [GEM, DCT + GEM, CDT + GEM + NO]
if stack[2] - stack[1] != 0: # If there is Not Observed..
# Compute the coords for the text :
x_text = nb_x
y_text = stack[1] + (stack[2] - stack[1]) / 2
# And plot it:
plt.text(x_text, y_text, round(stack[2] - stack[1]), verticalalignment='center')

Related

Colored gradient on multiple lines from a csv in 3D plot?

Disclaimer: I'm a total newb to this, 2nd day so pls bear with me, thank you in advance!
So, I managed to get my 3D plot to have multiple lines, but I would like to give them some color gradients. I've managed to get it onto one example line, but I cannot convert it to my own plots.
My plots come from a .csv
I followed this question for the gradients: https://stackoverflow.com/a/8505774/20387853 (Answer by Yann) but I can't seem to understand how to merge the two for i in range bits (one from my old code with the new code) (if it even can be?)
I also dont understand ax.plot(x[i:i+2],y[i:i+2]) so I couldn't adjust this like I thought I could.
SO ATM i have two scripts
Script 1 - in which I'm trying to merge my two data sets.
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import sys
import pandas
points = pandas.read_csv('D:Documents\PYTHON_FILES/test3d.csv')
def highResPoints(x,y,factor=10):
# r is the distance spanned between pairs of points
r = [0]
for i in range(1,len(x)):
dx = x[i]-x[i-1]
dy = y[i]-y[i-1]
r.append(np.sqrt(dx*dx+dy*dy))
r = np.array(r)
# rtot is a cumulative sum of r, it's used to save time
rtot = []
for i in range(len(r)):
rtot.append(r[0:i].sum())
rtot.append(r.sum())
dr = rtot[-1]/(NPOINTS*RESFACT-1)
xmod=[x[0]]
ymod=[y[0]]
rPos = 0 # current point on walk along data
rcount = 1
while rPos < r.sum():
x1,x2 = x[rcount-1],x[rcount]
y1,y2 = y[rcount-1],y[rcount]
dpos = rPos-rtot[rcount]
theta = np.arctan2((x2-x1),(y2-y1))
rx = np.sin(theta)*dpos+x1
ry = np.cos(theta)*dpos+y1
xmod.append(rx)
ymod.append(ry)
rPos+=dr
while rPos > rtot[rcount+1]:
rPos = rtot[rcount+1]
rcount+=1
if rcount>rtot[-1]:
break
return xmod,ymod
#CONSTANTS
NPOINTS = 10
COLOR='red'
RESFACT=10
MAP='winter' # choose carefully, or color transitions will not appear smoooth
cm = plt.get_cmap(MAP)
################ These are old data sets, just to use for this example
x = points['x'].values
y = points['y'].values
z = points['z'].values
x2 = points['x2'].values
y2 = points['y2'].values
z2 = points['z2'].values
fig = plt.figure()
#ax1 = fig.add_subplot(111,projection='3d') # regular resolution color map
ax = fig.add_subplot(111, projection='3d')
ax.plot(x, y, z, c='red',marker='v', linewidth=1.0, markersize=2)
ax.plot(x2, y2, z2, c='blue', marker='o', linewidth=1.0, markersize=2)
ax.set_prop_cycle(color=[cm(1.*i/(NPOINTS-1)) for i in range(NPOINTS-1)])
for i in range(NPOINTS-1):
#ax1.plot(x[i:i+2],y[i:i+2])
ax.plot(x[i:i+2],y[i:i+2])
########################The part I want to merge in
#for i in range(1, 5):
#if i == 1: i = '' #x is your first value not x1
#ax.plot(points[f"x{i}"], points[f"y{i}"], points[f"z{i}"], c='red', marker='o', linewidth=1.0, markersize=2)
#########################
fig.savefig('colorgradienttest.png')
plt.show()
[Link to Image]
I want to make the blue and red lines have a color gradient like the example 3rd line (markers are not important)
Script 2 - to which I want to apply the gradient (the one with the .csv)
from mpl_toolkits.mplot3d import Axes3D
import sys
import matplotlib.pyplot as plt
import pandas
import numpy as np
points = pandas.read_csv('D:Documents\PYTHON_FILES/test3d.csv')
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
#OPTION 1 - not sure why this isn't working for me so Im not using it yet
#for idx in range(29):
# suffix = '' if idx == 0 else str(idx + 1) # ranges start at 0
# x = points[f"x{suffix}"].values
# y = points[f"y{suffix}"].values
# z = points[f"z{suffix}"].values
#ax.plot(x, y, z, c='red', marker='o', linewidth=1.0, markersize=2)
#OPTION 2 - current approach <<<<<<<<<<<<<<<< want to apply gradient to this segment
for i in range(1, 5):
if i == 1: i = '' #x is your first value not x1
ax.plot(points[f"x{i}"], points[f"y{i}"], points[f"z{i}"], c='red', marker='o', linewidth=1.0, markersize=2)
plt.show()

Create a plot in pyplot with several different y-axis scale [duplicate]

Two and three dimensional data can be viewed relatively straight-forwardly using traditional plot types. Even with four dimensional data, we can often find a way to display the data. Dimensions above four, though, become increasingly difficult to display. Fortunately, parallel coordinates plots provide a mechanism for viewing results with higher dimensions.
Several plotting packages provide parallel coordinates plots, such as Matlab, R, VTK type 1 and VTK type 2, but I don't see how to create one using Matplotlib.
Is there a built-in parallel coordinates plot in Matplotlib? I certainly don't see one in the gallery.
If there is no built-in-type, is it possible to build a parallel coordinates plot using standard features of Matplotlib?
Edit:
Based on the answer provided by Zhenya below, I developed the following generalization that supports an arbitrary number of axes. Following the plot style of the example I posted in the original question above, each axis gets its own scale. I accomplished this by normalizing the data at each axis point and making the axes have a range of 0 to 1. I then go back and apply labels to each tick-mark that give the correct value at that intercept.
The function works by accepting an iterable of data sets. Each data set is considered a set of points where each point lies on a different axis. The example in __main__ grabs random numbers for each axis in two sets of 30 lines. The lines are random within ranges that cause clustering of lines; a behavior I wanted to verify.
This solution isn't as good as a built-in solution since you have odd mouse behavior and I'm faking the data ranges through labels, but until Matplotlib adds a built-in solution, it's acceptable.
#!/usr/bin/python
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
def parallel_coordinates(data_sets, style=None):
dims = len(data_sets[0])
x = range(dims)
fig, axes = plt.subplots(1, dims-1, sharey=False)
if style is None:
style = ['r-']*len(data_sets)
# Calculate the limits on the data
min_max_range = list()
for m in zip(*data_sets):
mn = min(m)
mx = max(m)
if mn == mx:
mn -= 0.5
mx = mn + 1.
r = float(mx - mn)
min_max_range.append((mn, mx, r))
# Normalize the data sets
norm_data_sets = list()
for ds in data_sets:
nds = [(value - min_max_range[dimension][0]) /
min_max_range[dimension][2]
for dimension,value in enumerate(ds)]
norm_data_sets.append(nds)
data_sets = norm_data_sets
# Plot the datasets on all the subplots
for i, ax in enumerate(axes):
for dsi, d in enumerate(data_sets):
ax.plot(x, d, style[dsi])
ax.set_xlim([x[i], x[i+1]])
# Set the x axis ticks
for dimension, (axx,xx) in enumerate(zip(axes, x[:-1])):
axx.xaxis.set_major_locator(ticker.FixedLocator([xx]))
ticks = len(axx.get_yticklabels())
labels = list()
step = min_max_range[dimension][2] / (ticks - 1)
mn = min_max_range[dimension][0]
for i in xrange(ticks):
v = mn + i*step
labels.append('%4.2f' % v)
axx.set_yticklabels(labels)
# Move the final axis' ticks to the right-hand side
axx = plt.twinx(axes[-1])
dimension += 1
axx.xaxis.set_major_locator(ticker.FixedLocator([x[-2], x[-1]]))
ticks = len(axx.get_yticklabels())
step = min_max_range[dimension][2] / (ticks - 1)
mn = min_max_range[dimension][0]
labels = ['%4.2f' % (mn + i*step) for i in xrange(ticks)]
axx.set_yticklabels(labels)
# Stack the subplots
plt.subplots_adjust(wspace=0)
return plt
if __name__ == '__main__':
import random
base = [0, 0, 5, 5, 0]
scale = [1.5, 2., 1.0, 2., 2.]
data = [[base[x] + random.uniform(0., 1.)*scale[x]
for x in xrange(5)] for y in xrange(30)]
colors = ['r'] * 30
base = [3, 6, 0, 1, 3]
scale = [1.5, 2., 2.5, 2., 2.]
data.extend([[base[x] + random.uniform(0., 1.)*scale[x]
for x in xrange(5)] for y in xrange(30)])
colors.extend(['b'] * 30)
parallel_coordinates(data, style=colors).show()
Edit 2:
Here is an example of what comes out of the above code when plotting Fisher's Iris data. It isn't quite as nice as the reference image from Wikipedia, but it is passable if all you have is Matplotlib and you need multi-dimensional plots.
pandas has a parallel coordinates wrapper:
import pandas
import matplotlib.pyplot as plt
from pandas.tools.plotting import parallel_coordinates
data = pandas.read_csv(r'C:\Python27\Lib\site-packages\pandas\tests\data\iris.csv', sep=',')
parallel_coordinates(data, 'Name')
plt.show()
Source code, how they made it: plotting.py#L494
When answering a related question, I worked out a version using only one subplot (so it can be easily fit together with other plots) and optionally using cubic bezier curves to connect the points. The plot adjusts itself to the desired number of axes.
import matplotlib.pyplot as plt
from matplotlib.path import Path
import matplotlib.patches as patches
import numpy as np
fig, host = plt.subplots()
# create some dummy data
ynames = ['P1', 'P2', 'P3', 'P4', 'P5']
N1, N2, N3 = 10, 5, 8
N = N1 + N2 + N3
category = np.concatenate([np.full(N1, 1), np.full(N2, 2), np.full(N3, 3)])
y1 = np.random.uniform(0, 10, N) + 7 * category
y2 = np.sin(np.random.uniform(0, np.pi, N)) ** category
y3 = np.random.binomial(300, 1 - category / 10, N)
y4 = np.random.binomial(200, (category / 6) ** 1/3, N)
y5 = np.random.uniform(0, 800, N)
# organize the data
ys = np.dstack([y1, y2, y3, y4, y5])[0]
ymins = ys.min(axis=0)
ymaxs = ys.max(axis=0)
dys = ymaxs - ymins
ymins -= dys * 0.05 # add 5% padding below and above
ymaxs += dys * 0.05
dys = ymaxs - ymins
# transform all data to be compatible with the main axis
zs = np.zeros_like(ys)
zs[:, 0] = ys[:, 0]
zs[:, 1:] = (ys[:, 1:] - ymins[1:]) / dys[1:] * dys[0] + ymins[0]
axes = [host] + [host.twinx() for i in range(ys.shape[1] - 1)]
for i, ax in enumerate(axes):
ax.set_ylim(ymins[i], ymaxs[i])
ax.spines['top'].set_visible(False)
ax.spines['bottom'].set_visible(False)
if ax != host:
ax.spines['left'].set_visible(False)
ax.yaxis.set_ticks_position('right')
ax.spines["right"].set_position(("axes", i / (ys.shape[1] - 1)))
host.set_xlim(0, ys.shape[1] - 1)
host.set_xticks(range(ys.shape[1]))
host.set_xticklabels(ynames, fontsize=14)
host.tick_params(axis='x', which='major', pad=7)
host.spines['right'].set_visible(False)
host.xaxis.tick_top()
host.set_title('Parallel Coordinates Plot', fontsize=18)
colors = plt.cm.tab10.colors
for j in range(N):
# to just draw straight lines between the axes:
# host.plot(range(ys.shape[1]), zs[j,:], c=colors[(category[j] - 1) % len(colors) ])
# create bezier curves
# for each axis, there will a control vertex at the point itself, one at 1/3rd towards the previous and one
# at one third towards the next axis; the first and last axis have one less control vertex
# x-coordinate of the control vertices: at each integer (for the axes) and two inbetween
# y-coordinate: repeat every point three times, except the first and last only twice
verts = list(zip([x for x in np.linspace(0, len(ys) - 1, len(ys) * 3 - 2, endpoint=True)],
np.repeat(zs[j, :], 3)[1:-1]))
# for x,y in verts: host.plot(x, y, 'go') # to show the control points of the beziers
codes = [Path.MOVETO] + [Path.CURVE4 for _ in range(len(verts) - 1)]
path = Path(verts, codes)
patch = patches.PathPatch(path, facecolor='none', lw=1, edgecolor=colors[category[j] - 1])
host.add_patch(patch)
plt.tight_layout()
plt.show()
Here's similar code for the iris data set. The second axis is reversed to avoid some crossing lines.
import matplotlib.pyplot as plt
from matplotlib.path import Path
import matplotlib.patches as patches
import numpy as np
from sklearn import datasets
iris = datasets.load_iris()
ynames = iris.feature_names
ys = iris.data
ymins = ys.min(axis=0)
ymaxs = ys.max(axis=0)
dys = ymaxs - ymins
ymins -= dys * 0.05 # add 5% padding below and above
ymaxs += dys * 0.05
ymaxs[1], ymins[1] = ymins[1], ymaxs[1] # reverse axis 1 to have less crossings
dys = ymaxs - ymins
# transform all data to be compatible with the main axis
zs = np.zeros_like(ys)
zs[:, 0] = ys[:, 0]
zs[:, 1:] = (ys[:, 1:] - ymins[1:]) / dys[1:] * dys[0] + ymins[0]
fig, host = plt.subplots(figsize=(10,4))
axes = [host] + [host.twinx() for i in range(ys.shape[1] - 1)]
for i, ax in enumerate(axes):
ax.set_ylim(ymins[i], ymaxs[i])
ax.spines['top'].set_visible(False)
ax.spines['bottom'].set_visible(False)
if ax != host:
ax.spines['left'].set_visible(False)
ax.yaxis.set_ticks_position('right')
ax.spines["right"].set_position(("axes", i / (ys.shape[1] - 1)))
host.set_xlim(0, ys.shape[1] - 1)
host.set_xticks(range(ys.shape[1]))
host.set_xticklabels(ynames, fontsize=14)
host.tick_params(axis='x', which='major', pad=7)
host.spines['right'].set_visible(False)
host.xaxis.tick_top()
host.set_title('Parallel Coordinates Plot — Iris', fontsize=18, pad=12)
colors = plt.cm.Set2.colors
legend_handles = [None for _ in iris.target_names]
for j in range(ys.shape[0]):
# create bezier curves
verts = list(zip([x for x in np.linspace(0, len(ys) - 1, len(ys) * 3 - 2, endpoint=True)],
np.repeat(zs[j, :], 3)[1:-1]))
codes = [Path.MOVETO] + [Path.CURVE4 for _ in range(len(verts) - 1)]
path = Path(verts, codes)
patch = patches.PathPatch(path, facecolor='none', lw=2, alpha=0.7, edgecolor=colors[iris.target[j]])
legend_handles[iris.target[j]] = patch
host.add_patch(patch)
host.legend(legend_handles, iris.target_names,
loc='lower center', bbox_to_anchor=(0.5, -0.18),
ncol=len(iris.target_names), fancybox=True, shadow=True)
plt.tight_layout()
plt.show()
I'm sure there is a better way of doing it, but here's a quick-and-dirty one (a really dirty one):
#!/usr/bin/python
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
#vectors to plot: 4D for this example
y1=[1,2.3,8.0,2.5]
y2=[1.5,1.7,2.2,2.9]
x=[1,2,3,8] # spines
fig,(ax,ax2,ax3) = plt.subplots(1, 3, sharey=False)
# plot the same on all the subplots
ax.plot(x,y1,'r-', x,y2,'b-')
ax2.plot(x,y1,'r-', x,y2,'b-')
ax3.plot(x,y1,'r-', x,y2,'b-')
# now zoom in each of the subplots
ax.set_xlim([ x[0],x[1]])
ax2.set_xlim([ x[1],x[2]])
ax3.set_xlim([ x[2],x[3]])
# set the x axis ticks
for axx,xx in zip([ax,ax2,ax3],x[:-1]):
axx.xaxis.set_major_locator(ticker.FixedLocator([xx]))
ax3.xaxis.set_major_locator(ticker.FixedLocator([x[-2],x[-1]])) # the last one
# EDIT: add the labels to the rightmost spine
for tick in ax3.yaxis.get_major_ticks():
tick.label2On=True
# stack the subplots together
plt.subplots_adjust(wspace=0)
plt.show()
This is essentially based on a (much nicer) one by Joe Kingon, Python/Matplotlib - Is there a way to make a discontinuous axis?. You might also want to have a look at the other answer to the same question.
In this example I don't even attempt at scaling the vertical scales, since it depends on what exactly you are trying to achieve.
EDIT: Here is the result
When using pandas (like suggested by theta), there is no way to scale the axes independently.
The reason you can't find the different vertical axes is because there aren't any. Our parallel coordinates is "faking" the other two axes by just drawing a vertical line and some labels.
https://github.com/pydata/pandas/issues/7083#issuecomment-74253671
I've adapted the #JohanC code to a pandas dataframe and expanded it to also work with categorical variables. The code needs more improving, like being able to put also a numerical variable as the first one in the dataframe, but I think it is nice for now.
# Paths:
path_data = "data/"
# Packages:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.colors import LinearSegmentedColormap
from matplotlib.path import Path
import matplotlib.patches as patches
from functools import reduce
# Display options:
pd.set_option("display.width", 1200)
pd.set_option("display.max_columns", 300)
pd.set_option("display.max_rows", 300)
# Dataset:
df = pd.read_csv(path_data + "nasa_exoplanets.csv")
df_varnames = pd.read_csv(path_data + "nasa_exoplanets_var_names.csv")
# Variables (the first variable must be categoric):
my_vars = ["discoverymethod", "pl_orbper", "st_teff", "disc_locale", "sy_gaiamag"]
my_vars_names = reduce(pd.DataFrame.append,
map(lambda i: df_varnames[df_varnames["var"] == i], my_vars))
my_vars_names = my_vars_names["var_name"].values.tolist()
# Adapt the data:
df = df.loc[df["pl_letter"] == "d"]
df_plot = df[my_vars]
df_plot = df_plot.dropna()
df_plot = df_plot.reset_index(drop = True)
# Convert to numeric matrix:
ym = []
dics_vars = []
for v, var in enumerate(my_vars):
if df_plot[var].dtype.kind not in ["i", "u", "f"]:
dic_var = dict([(val, c) for c, val in enumerate(df_plot[var].unique())])
dics_vars += [dic_var]
ym += [[dic_var[i] for i in df_plot[var].tolist()]]
else:
ym += [df_plot[var].tolist()]
ym = np.array(ym).T
# Padding:
ymins = ym.min(axis = 0)
ymaxs = ym.max(axis = 0)
dys = ymaxs - ymins
ymins -= dys*0.05
ymaxs += dys*0.05
# Reverse some axes for better visual:
axes_to_reverse = [0, 1]
for a in axes_to_reverse:
ymaxs[a], ymins[a] = ymins[a], ymaxs[a]
dys = ymaxs - ymins
# Adjust to the main axis:
zs = np.zeros_like(ym)
zs[:, 0] = ym[:, 0]
zs[:, 1:] = (ym[:, 1:] - ymins[1:])/dys[1:]*dys[0] + ymins[0]
# Colors:
n_levels = len(dics_vars[0])
my_colors = ["#F41E1E", "#F4951E", "#F4F01E", "#4EF41E", "#1EF4DC", "#1E3CF4", "#F41EF3"]
cmap = LinearSegmentedColormap.from_list("my_palette", my_colors)
my_palette = [cmap(i/n_levels) for i in np.array(range(n_levels))]
# Plot:
fig, host_ax = plt.subplots(
figsize = (20, 10),
tight_layout = True
)
# Make the axes:
axes = [host_ax] + [host_ax.twinx() for i in range(ym.shape[1] - 1)]
dic_count = 0
for i, ax in enumerate(axes):
ax.set_ylim(
bottom = ymins[i],
top = ymaxs[i]
)
ax.spines.top.set_visible(False)
ax.spines.bottom.set_visible(False)
ax.ticklabel_format(style = 'plain')
if ax != host_ax:
ax.spines.left.set_visible(False)
ax.yaxis.set_ticks_position("right")
ax.spines.right.set_position(
(
"axes",
i/(ym.shape[1] - 1)
)
)
if df_plot.iloc[:, i].dtype.kind not in ["i", "u", "f"]:
dic_var_i = dics_vars[dic_count]
ax.set_yticks(
range(len(dic_var_i))
)
ax.set_yticklabels(
[key_val for key_val in dics_vars[dic_count].keys()]
)
dic_count += 1
host_ax.set_xlim(
left = 0,
right = ym.shape[1] - 1
)
host_ax.set_xticks(
range(ym.shape[1])
)
host_ax.set_xticklabels(
my_vars_names,
fontsize = 14
)
host_ax.tick_params(
axis = "x",
which = "major",
pad = 7
)
# Make the curves:
host_ax.spines.right.set_visible(False)
host_ax.xaxis.tick_top()
for j in range(ym.shape[0]):
verts = list(zip([x for x in np.linspace(0, len(ym) - 1, len(ym)*3 - 2,
endpoint = True)],
np.repeat(zs[j, :], 3)[1: -1]))
codes = [Path.MOVETO] + [Path.CURVE4 for _ in range(len(verts) - 1)]
path = Path(verts, codes)
color_first_cat_var = my_palette[dics_vars[0][df_plot.iloc[j, 0]]]
patch = patches.PathPatch(
path,
facecolor = "none",
lw = 2,
alpha = 0.7,
edgecolor = color_first_cat_var
)
host_ax.add_patch(patch)
plotly has a nice interactive solution called parallel_coordinates which works just fine:
import plotly.express as px
df = px.data.iris()
fig = px.parallel_coordinates(df, color="species_id", labels={"species_id": "Species",
"sepal_width": "Sepal Width", "sepal_length": "Sepal Length",
"petal_width": "Petal Width", "petal_length": "Petal Length", },
color_continuous_scale=px.colors.diverging.Tealrose,
color_continuous_midpoint=2)
fig.show()
I want to plug a beta-released parallel coordinate plotting package called Paxplot which is based on Matplotlib. It uses similar underlying logic to the other answers and extends functionality while maintaining clean usage.
The documentation provides examples of basic usage, advanced usage, and usage with Pandas. As per the figure provided in the original question, I have provided a solution that plots the iris dataset:
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import load_iris
import paxplot
# Import data
iris = load_iris(as_frame=True)
df = pd.DataFrame(
data=np.c_[iris['data'], iris['target']],
columns=iris['feature_names'] + ['target']
)
cols = df.columns
# Create figure
paxfig = paxplot.pax_parallel(n_axes=len(cols))
paxfig.plot(df.to_numpy())
# Add labels
paxfig.set_labels(cols)
# Set ticks
paxfig.set_ticks(
ax_idx=-1,
ticks=[0, 1, 2],
labels=iris.target_names
)
# Add colorbar
color_col = 0
paxfig.add_colorbar(
ax_idx=color_col,
cmap='viridis',
colorbar_kwargs={'label': cols[color_col]}
)
plt.show()
For full disclosure, I created Paxplot and have been developing and maintaining it with some friends. Definitely feel free to reach out if you are interested in contributing!
Best example I've seen thus far is this one
https://python.g-node.org/python-summerschool-2013/_media/wiki/datavis/olympics_vis.py
See the normalised_coordinates function. Not super fast, but works from what I've tried.
normalised_coordinates(['VAL_1', 'VAL_2', 'VAL_3'], np.array([[1230.23, 1500000, 12453.03], [930.23, 140000, 12453.03], [130.23, 120000, 1243.03]]), [1, 2, 1])
Still far from perfect but it works and is relatively short:
import numpy as np
import matplotlib.pyplot as plt
def plot_parallel(data,labels):
data=np.array(data)
x=list(range(len(data[0])))
fig, axis = plt.subplots(1, len(data[0])-1, sharey=False)
for d in data:
for i, a in enumerate(axis):
temp=d[i:i+2].copy()
temp[1]=(temp[1]-np.min(data[:,i+1]))*(np.max(data[:,i])-np.min(data[:,i]))/(np.max(data[:,i+1])-np.min(data[:,i+1]))+np.min(data[:,i])
a.plot(x[i:i+2], temp)
for i, a in enumerate(axis):
a.set_xlim([x[i], x[i+1]])
a.set_xticks([x[i], x[i+1]])
a.set_xticklabels([labels[i], labels[i+1]], minor=False, rotation=45)
a.set_ylim([np.min(data[:,i]),np.max(data[:,i])])
plt.subplots_adjust(wspace=0)
plt.show()
This is a version using TensorBoard, if not strictly need matplotlib figure.
I'm looking around for something works like Visualize the results in TensorBoard's HParams plugin result. Here is a wrapped function just plotting ignoring training in that tutorial, using TensorBoard. The logic is using metrics_name specified key as metrics, using other columns as HParams. For any other detail, refer original tutorial.
import os
import json
import pandas as pd
import numpy as np
import tensorflow as tf
from tensorboard.plugins.hparams import api as hp
def tensorboard_parallel_coordinates_plot(dataframe, metrics_name, metrics_display_name=None, skip_columns=[], log_dir='logs/hparam_tuning'):
skip_columns = skip_columns + [metrics_name]
to_hp_discrete = lambda column: hp.HParam(column, hp.Discrete(np.unique(dataframe[column].values).tolist()))
hp_params_dict = {column: to_hp_discrete(column) for column in dataframe.columns if column not in skip_columns}
if dataframe[metrics_name].values.dtype == 'object': # Not numeric
metrics_map = {ii: id for id, ii in enumerate(np.unique(dataframe[metrics_name]))}
description = json.dumps(metrics_map)
else:
metrics_map, description = None, None
METRICS = metrics_name if metrics_display_name is None else metrics_display_name
with tf.summary.create_file_writer(log_dir).as_default():
metrics = [hp.Metric(METRICS, display_name=METRICS, description=description)]
hp.hparams_config(hparams=list(hp_params_dict.values()), metrics=metrics)
for id in dataframe.index:
log = dataframe.iloc[id]
hparams = {hp_unit: log[column] for column, hp_unit in hp_params_dict.items()}
print({hp_unit.name: hparams[hp_unit] for hp_unit in hparams})
run_dir = os.path.join(log_dir, 'run-%d' % id)
with tf.summary.create_file_writer(run_dir).as_default():
hp.hparams(hparams) # record the values used in this trial
metric_item = log[metrics_name] if metrics_map is None else metrics_map[log[metrics_name]]
tf.summary.scalar(METRICS, metric_item, step=1)
print()
if metrics_map is not None:
print("metrics_map:", metrics_map)
print("Start tensorboard by: tensorboard --logdir {}".format(log_dir))
Plotting test:
aa = pd.read_csv('https://raw.github.com/pandas-dev/pandas/main/pandas/tests/io/data/csv/iris.csv')
tensorboard_parallel_coordinates_plot(aa, metrics_name="Name", log_dir="logs/iris")
# metrics_map: {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
# Start tensorboard by: tensorboard --logdir logs/iris
!tensorboard --logdir logs/iris
# TensorBoard 2.8.0 at http://localhost:6006/ (Press CTRL+C to quit)
Open tesnorboard link, default http://localhost:6006/, go to HPARAMS -> PARALLEL COORDINATES VIEW will show the result:
TensorBoard result is interactive. But this is designed for plotting model hyper parameters tuning results, so I think it's not friendly for plotting large dataset.
You have to clean saved data manually if plotting new data in same log_dir directory.
It seems the final metrics item has to be numeric, while other axes don't have to.
fake_data = {
"optimizer": ["sgd", "adam", "adam", "lamb", "lamb", "lamb", "lamb"],
"weight_decay": [0.1, 0.1, 0.2, 0.1, 0.2, 0.2, 0.3],
"rescale_mode": ["tf", "tf", "tf", "tf", "tf", "torch", "torch"],
"accuracy": [78.5, 78.2, 78.8, 79.2, 79.3, 79.5, 79.6],
}
aa = pd.DataFrame(fake_data)
tensorboard_parallel_coordinates_plot(aa, "accuracy", log_dir="logs/fake")
# Start tensorboard by: tensorboard --logdir logs/fake
!tensorboard --logdir logs/fake
# TensorBoard 2.8.0 at http://localhost:6006/ (Press CTRL+C to quit)

Why is my line clipping in matplotlib?

I am trying to draw a series of lines. The lines are all the same length, and randomly switch colors for a random length (blue to orange). I am drawing the lines in blue and then overlaying orange on top. You can see from my picture there are clipped parts of the lines where it is grey. I cannot figure out why this is happening. Also related I believe is that my labels are not moving to a left alignment like they should. Any help is greatly appreciated.
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.lines as mlines
import random
plt.close('all')
fig, ax = plt.subplots(figsize=(15,11))
def label(xy, text):
y = xy[1] - 2
ax.text(xy[0], y, text, ha="left", family='sans-serif', size=14)
def draw_chromosome(start, stop, y, color):
x = np.array([start, stop])
y = np.array([y, y])
line = mlines.Line2D(x , y, lw=10., color=color)
ax.add_line(line)
x = 50
y = 100
chr = 1
for i in range(22):
draw_chromosome(x, 120, y, "#1C2F4D")
j = 0
while j < 120:
print j
length = 1
if random.randint(1, 100) > 90:
length = random.randint(1, 120-j)
draw_chromosome(j, j+length, y, "#FA9B00")
j = j+length+1
label([x, y], "Chromosome%i" % chr)
y -= 3
chr += 1
plt.axis('equal')
plt.axis('off')
plt.tight_layout()
plt.show()
You're only drawing the blue background from x = 50 to x = 120.
Replace this line:
draw_chromosome(x, 120, y, "#1C2F4D")
with this:
draw_chromosome(0, 120, y, "#1C2F4D")
To draw the blue line all the way across.
Alternately, if you also want to move your labels to the left, you can just set x=0 instead of setting it to 50.
I suggest using LineCollection for this. Below is a little helper function I wrote based on the example at http://matplotlib.org/examples/pylab_examples/multicolored_line.html (it looks long, but there is a lot of comments + docstrings)
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.collections import LineCollection
from matplotlib.colors import ListedColormap, BoundaryNorm
from matplotlib.ticker import NullLocator
from collections import OrderedDict
def binary_state_lines(ax, chrom_data, xmin=0, xmax=120,
delta_y=3,
off_color = "#1C2F4D",
on_color = "#FA9B00"):
"""
Draw a whole bunch of chromosomes
Parameters
----------
ax : Axes
The axes to draw stuff to
chrom_data : OrderedDict
The chromosome data as a dict, key on the label with a list of pairs
of where the data is 'on'. Data is plotted top-down
xmin, xmax : float, optional
The minimum and maximum limits for the x values
delta_y : float, optional
The spacing between lines
off_color, on_color : color, optional
The colors to use for the the on/off state
Returns
-------
collections : dict
dictionary of the collections added keyed on the label
"""
# base offset
y_val = 0
# make the color map and norm
cmap = ListedColormap([off_color, on_color])
norm = BoundaryNorm([0, 0.5, 1], cmap.N)
# sort out where the text should be
txt_x = (xmax + xmin) / 2
# dictionary to hold the returned artists
ret = dict()
# loop over the input data draw each collection
for label, data in chrom_data.items():
# increment the y offset
y_val += delta_y
# turn the high windows on to alternating
# high/low regions
x = np.asarray(data).ravel()
# assign the high/low state to each one
state = np.mod(1 + np.arange(len(x)), 2)
# deal with boundary conditions to be off
# at start/end
if x[0] > xmin:
x = np.r_[xmin, x]
state = np.r_[0, state]
if x[-1] < xmax:
x = np.r_[x, xmax]
state = np.r_[state, 0]
# make the matching y values
y = np.ones(len(x)) * y_val
# call helper function to create the collection
coll = draw_segments(ax, x, y, state,
cmap, norm)
ret[label] = coll
# set up the axes limits
ax.set_xlim(xmin, xmax)
ax.set_ylim(0, y_val + delta_y)
# turn off x-ticks
ax.xaxis.set_major_locator(NullLocator())
# make the y-ticks be labeled as per the input
ax.yaxis.set_ticks((1 + np.arange(len(chrom_data))) * delta_y)
ax.yaxis.set_ticklabels(list(chrom_data.keys()))
# invert so that the first data is at the top
ax.invert_yaxis()
# turn off the frame and patch
ax.set_frame_on(False)
# return the added artists
return ret
def draw_segments(ax, x, y, state, cmap, norm, lw=10):
"""
helper function to turn boundary edges into the input LineCollection
expects.
Parameters
----------
ax : Axes
The axes to draw to
x, y, state : array
The x edges, the y values and the state of each region
cmap : matplotlib.colors.Colormap
The color map to use
norm : matplotlib.ticker.Norm
The norm to use with the color map
lw : float, optional
The width of the lines
"""
points = np.array([x, y]).T.reshape(-1, 1, 2)
segments = np.concatenate([points[:-1], points[1:]], axis=1)
lc = LineCollection(segments, cmap=cmap, norm=norm)
lc.set_array(state)
lc.set_linewidth(lw)
ax.add_collection(lc)
return lc
An example:
synthetic_data = OrderedDict()
for j in range(21):
key = 'data {:02d}'.format(j)
synthetic_data[key] = np.cumsum(np.random.randint(1, 10, 20)).reshape(-1, 2)
fig, ax = plt.subplots(tight_layout=True)
binary_state_lines(ax, synthetic_data, xmax=120)
plt.show()
Separating the plotting logic from everything else will make your code easier to maintain and more reusable.
I also took the liberty of moving your labels from between the lines (where they can be ambiguous) to the yaxis tick labels.

Matplotlib: pcolor() does not plot last row and column?

It seems that PCOLOR is chopping off the last row and column of my data set. Printing the shape of zi below reveals that it is (22,22), as I expect, but an area of 21 squares by 21 squares is shown... Any idea why the last row and column are not being plotted?
def pcolor_probs(x,y,z, x_str, y_str, t_str):
xi = np.arange(min(x),max(x)+1, 1)
yi = np.arange(min(y),max(y)+1, 1)
zi = griddata(x,y,z,xi,yi)
print np.shape(xi),np.shape(yi),np.shape(zi)
# fix NANs
zi = np.asarray(zi)
for i in range(len(zi)):
for j in range(len(zi[i])):
print i,j
if isnan(float(zi[i][j])):
zi[i][j] = 0
# plot
f = figure()
ax = f.add_subplot(111)
pc_plot = ax.pcolor(zi, cmap = cm.coolwarm, shading = 'faceted', alpha = 0.75)
# pc_plot = ax.contourf(zi, 20, cmap = cm.coolwarm, alpha = 0.75)
ax.set_xticks(np.arange(zi.shape[0])+0.5, minor=False)
ax.set_yticks(np.arange(zi.shape[1])+0.5, minor=False)
ax.set_xticklabels(np.arange(len(xi)))
ax.set_yticklabels(np.arange(len(yi)))
ax.set_xlim(min(x), max(x))
ax.set_ylim(min(y), max(y))
ax.set_xlabel(x_str)
ax.set_ylabel(y_str)
ax.set_title(t_str)
f.colorbar(pc_plot)
f.set_tight_layout(True)
font = {'family' : 'serif','weight' : 'regular','size' : 12}
matplotlib.rc('font', **font)
show()
Let's make it even more simple,
X = np.random.rand(10,10)
pcolor(X)
show()
Produces,
A bit late, but just providing an X and Y arguments whose shape is larger by just 1 (in both directions) will display the entire array.
Something like the example bellow:
import numpy as np
import matplotlib.pyplot as plt
#define the space limits:
horizontal_min = -2.
horizontal_max = 2.
horizontal_step = 0.1
vertical_min = -1.
vertical_max = 1.
vertical_step = 0.2
# create the arrays
nx = (horizontal_max - horizontal_min) / horizontal_step
ny = ( vertical_max - vertical_min ) / vertical_step
Z = np.zeros((nx,ny))
Y,X = np.meshgrid(np.arange(vertical_min,
vertical_max+vertical_step, # THIS LINE...
vertical_step),
np.arange(horizontal_min,
horizontal_max+horizontal_step, # ...& THIS LINE
horizontal_step)
)
Y2,X2 = np.meshgrid(np.arange(vertical_min,
vertical_max, # THIS LINE...
vertical_step),
np.arange(horizontal_min,
horizontal_max, # ...& THIS LINE
horizontal_step)
)
# populate the data array (Z)
i = 0
if nx > ny:
while i < ny:
Z[i,i] = i+1
Z[nx-i-1,i] = -i-1
i += 1
else:
while i < ny:
Z[i,i] = i+1
Z[i,ny-i-1] = -i-1
i += 1
# make the graph
fig,axes = plt.subplots(2,1)
pc_plot1 = axes[0].pcolor(X, Y, Z)
axes[0].set_title('X.shape == Y.shape != Z.shape')
pc_plot2 = axes[1].pcolor(X2, Y2, Z)
axes[1].set_title('X.shape == Y.shape == Z.shape')
for ax in axes:
ax.axis('equal')
ax.set_xlim(horizontal_min, horizontal_max)
ax.set_ylim(vertical_min, vertical_max)
fig.tight_layout()
fig.show()
Notice the lines marked with THIS LINE. What they mean is that:
>>> print X.shape,Y.shape,Z.shape
(41, 11) (41, 11) (40, 10)
(For the given example)
Just a small note, using Y,X = np.meshgrid... replaces having to transpose Z (see official documentation).
The reason is that pcolor counts points on vertices. There are, in fact, 22 and 10 vertices. Use imshow(...,extent[]) instead.

Inline labels in Matplotlib

In Matplotlib, it's not too tough to make a legend (example_legend(), below), but I think it's better style to put labels right on the curves being plotted (as in example_inline(), below). This can be very fiddly, because I have to specify coordinates by hand, and, if I re-format the plot, I probably have to reposition the labels. Is there a way to automatically generate labels on curves in Matplotlib? Bonus points for being able to orient the text at an angle corresponding to the angle of the curve.
import numpy as np
import matplotlib.pyplot as plt
def example_legend():
plt.clf()
x = np.linspace(0, 1, 101)
y1 = np.sin(x * np.pi / 2)
y2 = np.cos(x * np.pi / 2)
plt.plot(x, y1, label='sin')
plt.plot(x, y2, label='cos')
plt.legend()
def example_inline():
plt.clf()
x = np.linspace(0, 1, 101)
y1 = np.sin(x * np.pi / 2)
y2 = np.cos(x * np.pi / 2)
plt.plot(x, y1, label='sin')
plt.plot(x, y2, label='cos')
plt.text(0.08, 0.2, 'sin')
plt.text(0.9, 0.2, 'cos')
Update: User cphyc has kindly created a Github repository for the code in this answer (see here), and bundled the code into a package which may be installed using pip install matplotlib-label-lines.
Pretty Picture:
In matplotlib it's pretty easy to label contour plots (either automatically or by manually placing labels with mouse clicks). There does not (yet) appear to be any equivalent capability to label data series in this fashion! There may be some semantic reason for not including this feature which I am missing.
Regardless, I have written the following module which takes any allows for semi-automatic plot labelling. It requires only numpy and a couple of functions from the standard math library.
Description
The default behaviour of the labelLines function is to space the labels evenly along the x axis (automatically placing at the correct y-value of course). If you want you can just pass an array of the x co-ordinates of each of the labels. You can even tweak the location of one label (as shown in the bottom right plot) and space the rest evenly if you like.
In addition, the label_lines function does not account for the lines which have not had a label assigned in the plot command (or more accurately if the label contains '_line').
Keyword arguments passed to labelLines or labelLine are passed on to the text function call (some keyword arguments are set if the calling code chooses not to specify).
Issues
Annotation bounding boxes sometimes interfere undesirably with other curves. As shown by the 1 and 10 annotations in the top left plot. I'm not even sure this can be avoided.
It would be nice to specify a y position instead sometimes.
It's still an iterative process to get annotations in the right location
It only works when the x-axis values are floats
Gotchas
By default, the labelLines function assumes that all data series span the range specified by the axis limits. Take a look at the blue curve in the top left plot of the pretty picture. If there were only data available for the x range 0.5-1 then then we couldn't possibly place a label at the desired location (which is a little less than 0.2). See this question for a particularly nasty example. Right now, the code does not intelligently identify this scenario and re-arrange the labels, however there is a reasonable workaround. The labelLines function takes the xvals argument; a list of x-values specified by the user instead of the default linear distribution across the width. So the user can decide which x-values to use for the label placement of each data series.
Also, I believe this is the first answer to complete the bonus objective of aligning the labels with the curve they're on. :)
label_lines.py:
from math import atan2,degrees
import numpy as np
#Label line with line2D label data
def labelLine(line,x,label=None,align=True,**kwargs):
ax = line.axes
xdata = line.get_xdata()
ydata = line.get_ydata()
if (x < xdata[0]) or (x > xdata[-1]):
print('x label location is outside data range!')
return
#Find corresponding y co-ordinate and angle of the line
ip = 1
for i in range(len(xdata)):
if x < xdata[i]:
ip = i
break
y = ydata[ip-1] + (ydata[ip]-ydata[ip-1])*(x-xdata[ip-1])/(xdata[ip]-xdata[ip-1])
if not label:
label = line.get_label()
if align:
#Compute the slope
dx = xdata[ip] - xdata[ip-1]
dy = ydata[ip] - ydata[ip-1]
ang = degrees(atan2(dy,dx))
#Transform to screen co-ordinates
pt = np.array([x,y]).reshape((1,2))
trans_angle = ax.transData.transform_angles(np.array((ang,)),pt)[0]
else:
trans_angle = 0
#Set a bunch of keyword arguments
if 'color' not in kwargs:
kwargs['color'] = line.get_color()
if ('horizontalalignment' not in kwargs) and ('ha' not in kwargs):
kwargs['ha'] = 'center'
if ('verticalalignment' not in kwargs) and ('va' not in kwargs):
kwargs['va'] = 'center'
if 'backgroundcolor' not in kwargs:
kwargs['backgroundcolor'] = ax.get_facecolor()
if 'clip_on' not in kwargs:
kwargs['clip_on'] = True
if 'zorder' not in kwargs:
kwargs['zorder'] = 2.5
ax.text(x,y,label,rotation=trans_angle,**kwargs)
def labelLines(lines,align=True,xvals=None,**kwargs):
ax = lines[0].axes
labLines = []
labels = []
#Take only the lines which have labels other than the default ones
for line in lines:
label = line.get_label()
if "_line" not in label:
labLines.append(line)
labels.append(label)
if xvals is None:
xmin,xmax = ax.get_xlim()
xvals = np.linspace(xmin,xmax,len(labLines)+2)[1:-1]
for line,x,label in zip(labLines,xvals,labels):
labelLine(line,x,label,align,**kwargs)
Test code to generate the pretty picture above:
from matplotlib import pyplot as plt
from scipy.stats import loglaplace,chi2
from labellines import *
X = np.linspace(0,1,500)
A = [1,2,5,10,20]
funcs = [np.arctan,np.sin,loglaplace(4).pdf,chi2(5).pdf]
plt.subplot(221)
for a in A:
plt.plot(X,np.arctan(a*X),label=str(a))
labelLines(plt.gca().get_lines(),zorder=2.5)
plt.subplot(222)
for a in A:
plt.plot(X,np.sin(a*X),label=str(a))
labelLines(plt.gca().get_lines(),align=False,fontsize=14)
plt.subplot(223)
for a in A:
plt.plot(X,loglaplace(4).pdf(a*X),label=str(a))
xvals = [0.8,0.55,0.22,0.104,0.045]
labelLines(plt.gca().get_lines(),align=False,xvals=xvals,color='k')
plt.subplot(224)
for a in A:
plt.plot(X,chi2(5).pdf(a*X),label=str(a))
lines = plt.gca().get_lines()
l1=lines[-1]
labelLine(l1,0.6,label=r'$Re=${}'.format(l1.get_label()),ha='left',va='bottom',align = False)
labelLines(lines[:-1],align=False)
plt.show()
#Jan Kuiken's answer is certainly well-thought and thorough, but there are some caveats:
it does not work in all cases
it requires a fair amount of extra code
it may vary considerably from one plot to the next
A much simpler approach is to annotate the last point of each plot. The point can also be circled, for emphasis. This can be accomplished with one extra line:
import matplotlib.pyplot as plt
for i, (x, y) in enumerate(samples):
plt.plot(x, y)
plt.text(x[-1], y[-1], f'sample {i}')
A variant would be to use the method matplotlib.axes.Axes.annotate.
Nice question, a while ago I've experimented a bit with this, but haven't used it a lot because it's still not bulletproof. I divided the plot area into a 32x32 grid and calculated a 'potential field' for the best position of a label for each line according the following rules:
white space is a good place for a label
Label should be near corresponding line
Label should be away from the other lines
The code was something like this:
import matplotlib.pyplot as plt
import numpy as np
from scipy import ndimage
def my_legend(axis = None):
if axis == None:
axis = plt.gca()
N = 32
Nlines = len(axis.lines)
print Nlines
xmin, xmax = axis.get_xlim()
ymin, ymax = axis.get_ylim()
# the 'point of presence' matrix
pop = np.zeros((Nlines, N, N), dtype=np.float)
for l in range(Nlines):
# get xy data and scale it to the NxN squares
xy = axis.lines[l].get_xydata()
xy = (xy - [xmin,ymin]) / ([xmax-xmin, ymax-ymin]) * N
xy = xy.astype(np.int32)
# mask stuff outside plot
mask = (xy[:,0] >= 0) & (xy[:,0] < N) & (xy[:,1] >= 0) & (xy[:,1] < N)
xy = xy[mask]
# add to pop
for p in xy:
pop[l][tuple(p)] = 1.0
# find whitespace, nice place for labels
ws = 1.0 - (np.sum(pop, axis=0) > 0) * 1.0
# don't use the borders
ws[:,0] = 0
ws[:,N-1] = 0
ws[0,:] = 0
ws[N-1,:] = 0
# blur the pop's
for l in range(Nlines):
pop[l] = ndimage.gaussian_filter(pop[l], sigma=N/5)
for l in range(Nlines):
# positive weights for current line, negative weight for others....
w = -0.3 * np.ones(Nlines, dtype=np.float)
w[l] = 0.5
# calculate a field
p = ws + np.sum(w[:, np.newaxis, np.newaxis] * pop, axis=0)
plt.figure()
plt.imshow(p, interpolation='nearest')
plt.title(axis.lines[l].get_label())
pos = np.argmax(p) # note, argmax flattens the array first
best_x, best_y = (pos / N, pos % N)
x = xmin + (xmax-xmin) * best_x / N
y = ymin + (ymax-ymin) * best_y / N
axis.text(x, y, axis.lines[l].get_label(),
horizontalalignment='center',
verticalalignment='center')
plt.close('all')
x = np.linspace(0, 1, 101)
y1 = np.sin(x * np.pi / 2)
y2 = np.cos(x * np.pi / 2)
y3 = x * x
plt.plot(x, y1, 'b', label='blue')
plt.plot(x, y2, 'r', label='red')
plt.plot(x, y3, 'g', label='green')
my_legend()
plt.show()
And the resulting plot:
matplotx (which I wrote) has line_labels() which plots the labels to the right of the lines. It's also smart enough to avoid overlaps when too many lines are concentrated in one spot. (See stargraph for examples.) It does that by solving a particular non-negative-least-squares problem on the target positions of the labels. Anyway, in many cases where there's no overlap to begin with, such as the example below, that's not even necessary.
import matplotlib.pyplot as plt
import matplotx
import numpy as np
# create data
rng = np.random.default_rng(0)
offsets = [1.0, 1.50, 1.60]
labels = ["no balancing", "CRV-27", "CRV-27*"]
x0 = np.linspace(0.0, 3.0, 100)
y = [offset * x0 / (x0 + 1) + 0.1 * rng.random(len(x0)) for offset in offsets]
# plot
with plt.style.context(matplotx.styles.dufte):
for yy, label in zip(y, labels):
plt.plot(x0, yy, label=label)
plt.xlabel("distance [m]")
matplotx.ylabel_top("voltage [V]") # move ylabel to the top, rotate
matplotx.line_labels() # line labels to the right
plt.show()
# plt.savefig("out.png", bbox_inches="tight")
A simpler approach like the one Ioannis Filippidis do :
import matplotlib.pyplot as plt
import numpy as np
# evenly sampled time at 200ms intervals
tMin=-1 ;tMax=10
t = np.arange(tMin, tMax, 0.1)
# red dashes, blue points default
plt.plot(t, 22*t, 'r--', t, t**2, 'b')
factor=3/4 ;offset=20 # text position in view
textPosition=[(tMax+tMin)*factor,22*(tMax+tMin)*factor]
plt.text(textPosition[0],textPosition[1]+offset,'22 t',color='red',fontsize=20)
textPosition=[(tMax+tMin)*factor,((tMax+tMin)*factor)**2+20]
plt.text(textPosition[0],textPosition[1]+offset, 't^2', bbox=dict(facecolor='blue', alpha=0.5),fontsize=20)
plt.show()
code python 3 on sageCell

Categories

Resources