Related
I have a dataset that is a list of lists.
Each list is a category to be plotted as a box plot.
Each list has a list of up to 9 components to be plotted into subplots.
The functions I am using is below was based on this answer. I pulled it out of my work and added some mock data. Should be a minimal example below.
neonDict = {
0:0, 1:1, 2:2, 3:3, 4:4, 5:5, 6:6, 7:7, 8:8
}
import matplotlib as mpl
import matplotlib.pyplot as plt
def coloredBoxPlot(axis, data,edgeColor,fillColor):
bp = axis.boxplot(data,vert=False,patch_artist=True)
for element in ['boxes', 'whiskers', 'fliers', 'means', 'medians', 'caps']:
plt.setp(bp[element], color=edgeColor)
for patch in bp['boxes']:
patch.set(facecolor=fillColor)
return bp
def plotCalStats(data, prefix='Channel', savedir=None,colors=['#00597c','#a8005c','#00aeea','#007d50','#400080','#e07800'] ):
csize = mpl.rcParams['figure.figsize']
cdpi = mpl.rcParams['figure.dpi']
mpl.rcParams['figure.figsize'] = (12,8)
mpl.rcParams['figure.dpi'] = 1080
pkdata = []
labels = []
lstyles = []
fg, ax = plt.subplots(3,3)
for pk in range(len(neonDict)):
px = pk // 3
py = pk % 3
ax[px,py].set_xlabel('Max Pixel')
ax[px,py].set_ylabel('')
ax[px,py].set_title(str(neonDict[pk]) + ' nm')
pkdata.append([])
for cat in range(len(data)):
bp = ''
for acal in data[cat]:
for apeak in acal.peaks:
pkdata[apeak].append(acal.peaks[apeak][0])
for pk in range(9):
px = pk // 3
py = pk % 3
bp = coloredBoxPlot(ax[px,py], pkdata[pk], colors[cat], '#ffffff')
if len(data[cat]) > 0:
#print(colors[cat])
#print(bp['boxes'][0].get_edgecolor())
labels.append(prefix+' '+str(cat))
lstyles.append(bp['boxes'][0])
fg.legend(lstyles,labels)
fg.suptitle('Calibration Summary by '+prefix)
fg.tight_layout()
if savedir is not None:
plt.savefig(savedir + 'Boxplots.png')
plt.show()
mpl.rcParams['figure.figsize'] = csize
mpl.rcParams['figure.dpi'] = cdpi
return
class acal:
def __init__(self):
self.peaks = {}
for x in range(9):
self.peaks[x] = (np.random.randint(20*x,20*(x+1)),)
mockData = [[acal() for y in range(100)] for x in range(6)]
#Some unused channels
mockData[2] = []
mockData[3] = []
mockData[4] = []
plotCalStats(mockData)
So the issue is that the plot colors do not match the legend. Even if I restrict the data to only add a label if data exists (ensuring thus there is no issue with calling boxplots with an empty data set and not getting an appropriate PathPatch.
The printouts verify the colors are correctly stored in the PathPatch. (I can add my digits -> hex converter) if that is questioned.
Attached is the output. One can see I get a purple box but no purple in the legend. Purple is the 4th category which is empty.
Any ideas why the labels don't match the actual style? Thanks much!
EDITS:
To address question on 'confusing'.
I have six categories of data, each category is coming from a single event. Each event has 9 components. I want to compare all events, for each individual component, for each category on a single plot as shown below.
Each subplot is a individual component comprised from the series of data for each categorical (Channel).
So the link I have provided, (like I said, is adapted from) shows how to create a single box plot on one axis for 2 data sets. I've basically done the same thing for 6 data sets on 9 axis, where 3 data sets are empty (but don't have to be, I did it to illustrate the issue. If I have all 6 data sets there, how can you tell the colors are messed up?????)
Regarding the alpha:
The alphas are always 'ff' when giving only RGB data to matplotlib. If I call get_edgecolors, it will return a tuple (RGBA) where A = 1.0.
See commented out print statement.
EDIT2:
If I restrict it down to a single category, it makes the box plot view less confusing.
Single Example (see how box plot color is orange, figure says it's blue)
All colors off
Feel like this used to work....
Uncertain how the error presented as it did, but the issue has to do with reformatting the data before creating the box plot.
By removing pkdata.append([]) during the creation of the subplots before looping the categories and adding:
pkdata = [[],[],[],[],[],[],[],[],[]] during each iteration of the category loop fixed the issue. The former was sending in all previous channel data...
Output is now better. Full sol attached.
Likely, since the plot uses data from pkdata, the empty channel (data[cat]) plotted previous data (from data[cat-1]) as that was still in pkdata (actually, all previous data[cat] was still in pkdata) which was then plotted. I only check data[cat] for data on each loop to add to the legend. The legend was set up for channels 0,1,5, for example.. but we saw data for channel: 0 as 0, 0+1 as 1, 0+1 as 2, 0+1 as 3, 0+1 as 4, 0+1+5 as 5... thus channel 4 (purple) had data to plot but wasn't added to the legend. Giving the impression of 'misaligned' legends but rather unlegend data...
The single channel data is actually all 6 channels overlapping, the final channel 5 color being orange, overlapping all previous, namely the original channel 0 data to whom the data belongs and was properly added to the legend.
neonDict = {
0:0, 1:1, 2:2, 3:3, 4:4, 5:5, 6:6, 7:7, 8:8
}
import matplotlib as mpl
import matplotlib.pyplot as plt
def getHex(r,g,b,a=1.0):
colors = [int(r * 255 ),int(g * 255 ),int(b * 255 ),int(a * 255) ]
s = '#'
for x in range(4):
cs = hex(colors[x])
if len(cs) == 3:
cs = cs + '0'
s += cs.replace('0x','')
return s
def getRGB(colstr):
try:
a = ''
r = int(colstr[1:3],16) / 255
g = int(colstr[3:5],16) / 255
b = int(colstr[5:7],16) / 255
if len (colstr) == 7:
a = 1.0
else:
a = int(colstr[7:],16) / 255
return (r,g,b,a)
except Exception as e:
print(e)
raise e
return
def compareHexColors(col1,col2):
try:
## ASSUME #RBG or #RBGA
## If less than 7, append the ff for the colors
if len(col1) < 9:
col1 += 'ff'
if len(col2) < 9:
col2 += 'ff'
return col1.lower() == col2.lower()
except Exception as e:
raise e
return False
def coloredBoxPlot(axis, data,edgeColor,fillColor):
bp = axis.boxplot(data,vert=False,patch_artist=True)
for element in ['boxes', 'whiskers', 'fliers', 'means', 'medians', 'caps']:
plt.setp(bp[element], color=edgeColor)
for patch in bp['boxes']:
patch.set(facecolor=fillColor)
return bp
def plotCalStats(data, prefix='Channel', savedir=None,colors=['#00597c','#a8005c','#00aeea','#007d50','#400080','#e07800'] ):
csize = mpl.rcParams['figure.figsize']
cdpi = mpl.rcParams['figure.dpi']
mpl.rcParams['figure.figsize'] = (12,8)
mpl.rcParams['figure.dpi'] = 1080
pkdata = []
labels = []
lstyles = []
fg, ax = plt.subplots(3,3)
for pk in range(len(neonDict)):
px = pk // 3
py = pk % 3
ax[px,py].set_xlabel('Max Pixel')
ax[px,py].set_ylabel('')
ax[px,py].set_title(str(neonDict[pk]) + ' nm')
for cat in range(len(data)):
bp = ''
pkdata = [[],[],[],[],[],[],[],[],[]]
for acal in data[cat]:
for apeak in acal.peaks:
pkdata[apeak].append(acal.peaks[apeak][0])
for pk in range(9):
px = pk // 3
py = pk % 3
bp = coloredBoxPlot(ax[px,py], pkdata[pk], colors[cat], '#ffffff')
if len(data[cat]) > 0:
print(compareHexColors(colors[cat],getHex(*bp['boxes'][0].get_edgecolor())))
labels.append(prefix+' '+str(cat))
lstyles.append(bp['boxes'][0])
fg.legend(lstyles,labels)
fg.suptitle('Calibration Summary by '+prefix)
fg.tight_layout()
if savedir is not None:
plt.savefig(savedir + 'Boxplots.png')
plt.show()
mpl.rcParams['figure.figsize'] = csize
mpl.rcParams['figure.dpi'] = cdpi
return
class acal:
def __init__(self,center):
self.peaks = {}
for x in range(9):
self.peaks[x] = [10*x + (center) + (np.random.randint(10)-1)/2.0,0,0]
mockData = [[acal(x) for y in range(1000)] for x in range(6)]
#Some unused channels
mockData[2] = []
mockData[3] = []
mockData[4] = []
plotCalStats(mockData)
I have a data frame like the below:
Every row represents a person. They stay at 3 different locations for some time given on the dataframe. The first few people don't stay at location1 but they "born" at location2. The rest of them stay at every locations (3 locations).
I would like to animate every person at the given X, Y coordinates given on the data frame and represent them as dots or any other shape. Here is the flow:
Every person should appear at the first given location (location1) at the given time. Their color should be blue at this state.
Stay at location1 until location2_time and then appear at location2. Their color should be red at this state.
Stay at location2 until location3_time and then appear at location3. Their color should be red at this state.
Stay at location3 for 3 seconds and disappear forever.
There can be several people on the visual at the same time. How can I do that?
There are some good answers on the below links. However, on these solutions, points don't disappear.
How can i make points of a python plot appear over time?
How to animate a scatter plot?
The following is an implementation with python-ffmpeg, pandas, matplotlib, and seaborn. You can find output video on my YouTube channel (link is unlisted).
Each frame with figures is saved directly to memory. New figures are generated only when the state of the population changes (person appears/moves/disappears).
You should definetely separate this code into smaller chunks if you are using this in a Python package:
from numpy.random import RandomState, SeedSequence
from numpy.random import MT19937
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
import ffmpeg
RESOLUTION = (12.8, 7.2) # * 100 pixels
NUMBER_OF_FRAMES = 900
class VideoWriter:
# Courtesy of https://github.com/kylemcdonald/python-utils/blob/master/ffmpeg.py
def __init__(
self,
filename,
video_codec="libx265",
fps=15,
in_pix_fmt="rgb24",
out_pix_fmt="yuv420p",
input_args=None,
output_args=None,
):
self.filename = filename
self.process = None
self.input_args = {} if input_args is None else input_args
self.output_args = {} if output_args is None else output_args
self.input_args["r"] = self.input_args["framerate"] = fps
self.input_args["pix_fmt"] = in_pix_fmt
self.output_args["pix_fmt"] = out_pix_fmt
self.output_args["vcodec"] = video_codec
def add(self, frame):
if self.process is None:
height, width = frame.shape[:2]
self.process = (
ffmpeg.input(
"pipe:",
format="rawvideo",
s="{}x{}".format(width, height),
**self.input_args,
)
.filter("crop", "iw-mod(iw,2)", "ih-mod(ih,2)")
.output(self.filename, **self.output_args)
.global_args("-loglevel", "quiet")
.overwrite_output()
.run_async(pipe_stdin=True)
)
conv = frame.astype(np.uint8).tobytes()
self.process.stdin.write(conv)
def close(self):
if self.process is None:
return
self.process.stdin.close()
self.process.wait()
def figure_to_array(figure):
"""adapted from: https://stackoverflow.com/questions/21939658/"""
figure.canvas.draw()
buf = figure.canvas.tostring_rgb()
n_cols, n_rows = figure.canvas.get_width_height()
return np.frombuffer(buf, dtype=np.uint8).reshape(n_rows, n_cols, 3)
# Generate data for the figure
rs1 = RandomState(MT19937(SeedSequence(123456789)))
time_1 = np.round(rs1.rand(232) * NUMBER_OF_FRAMES).astype(np.int16)
time_2 = time_1 + np.round(rs1.rand(232) * (NUMBER_OF_FRAMES - time_1)).astype(np.int16)
time_3 = time_2 + np.round(rs1.rand(232) * (NUMBER_OF_FRAMES - time_2)).astype(np.int16)
loc_1_x, loc_1_y, loc_2_x, loc_2_y, loc_3_x, loc_3_y = np.round(rs1.rand(6, 232) * 100, 1)
df = pd.DataFrame({
"loc_1_time": time_1,
"loc_1_x": loc_1_x,
"loc_1_y": loc_1_y,
"loc_2_time": time_2,
"loc_2_x": loc_2_x,
"loc_2_y": loc_2_y,
"loc_3_time": time_3,
"loc_3_x": loc_3_x,
"loc_3_y": loc_3_y,
})
"""The stack answer starts here"""
# Add extra column for disappear time
df["disappear_time"] = df["loc_3_time"] + 3
all_times = df[["loc_1_time", "loc_2_time", "loc_3_time", "disappear_time"]]
change_times = np.unique(all_times)
# Prepare ticks for plotting the figure across frames
x_values = df[["loc_1_x", "loc_2_x", "loc_3_x"]].values.flatten()
x_ticks = np.array(np.linspace(x_values.min(), x_values.max(), 6), dtype=np.uint8)
y_values = df[["loc_1_y", "loc_2_y", "loc_3_y"]].values.flatten()
y_ticks = np.array(np.round(np.linspace(y_values.min(), y_values.max(), 6)), dtype=np.uint8)
sns.set_theme(style="whitegrid")
video_writer = VideoWriter("endermen.mp4")
if 0 not in change_times:
# Generate empty figure if no person arrive at t=0
fig, ax = plt.subplots(figsize=RESOLUTION)
ax.set_xticklabels(x_ticks)
ax.set_yticklabels(y_ticks)
ax.set_title("People movement. T=0")
video_writer.add(figure_to_array(fig))
loop_range = range(1, NUMBER_OF_FRAMES)
else:
loop_range = range(NUMBER_OF_FRAMES)
palette = sns.color_palette("tab10") # Returns three colors from the palette (we have three groups)
animation_data_df = pd.DataFrame(columns=["x", "y", "location", "index"])
for frame_idx in loop_range:
if frame_idx in change_times:
plt.close("all")
# Get person who appears/moves/disappears
indexes, loc_nums = np.where(all_times == frame_idx)
loc_nums += 1
for i, loc in zip(indexes, loc_nums):
if loc != 4:
x, y = df[[f"loc_{loc}_x", f"loc_{loc}_y"]].iloc[i]
if loc == 1: # location_1
animation_data_df = animation_data_df.append(
{"x": x, "y": y, "location": loc, "index": i},
ignore_index=True
)
else:
data_index = np.where(animation_data_df["index"] == i)[0][0]
if loc in (2, 3): # location_2 or 3
animation_data_df.loc[[data_index], :] = x, y, loc, i
elif loc == 4: # Disappear
animation_data_df.iloc[data_index] = np.nan
current_palette_size = np.sum(~np.isnan(np.unique(animation_data_df["location"])))
fig, ax = plt.subplots(figsize=RESOLUTION)
sns.scatterplot(
x="x", y="y", hue="location", data=animation_data_df, ax=ax, palette=palette[:current_palette_size]
)
ax.set_xticks(x_ticks)
ax.set_xticklabels(x_ticks)
ax.set_yticks(y_ticks)
ax.set_yticklabels(y_ticks)
ax.legend(loc="center left", bbox_to_anchor=(1, 0.5))
ax.set_title(f"People movement. T={frame_idx}")
video_writer.add(figure_to_array(fig))
video_writer.close()
Edit: There was a bug in which location_3 wasn't removed after 3 seconds. Fixed now.
Modifying the code from this question to only include the positions you want automatically removes the old ones if the old position isn't included in the new ones. This doesn't change if you want to animate by time or iterations or anything else. I have opted to use iterations here since it's easier and I don't know how you are handling your dataset. The code does have one bug though, the last point (or points if they last the same amount of time) remaining won't disappear, this can be solved easily if you don't want to draw anything again, if you do though for exaple in case you there is a gap in the data with no people and then the data resumes I haven't found any workarounds
import math
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.animation import FuncAnimation
#The t0,t1,t2,t3 are the times (in iterations) that the position changes
#If t0 is None then the person will never be displayed
people = [
# t0 x1 y1 t1 x2 y2 t2 x3 y3 t4
[ 0, 1, 0.1, 1, 2, 0.2, 2, 3, 0.3, 3],
[ 2, None, None, None, 2, 1, 3, 4, 1, 7],
[ 2, float("NaN"), float("NaN"), float("NaN"), 2, 0.8, 4, 4, 0.8, 10],
]
fig = plt.figure()
plt.xlim(0, 5)
plt.ylim(0, 1)
graph = plt.scatter([], [])
def animate(i):
points = []
colors = []
for person in people:
if person[0] is None or math.isnan(person[0]) or i < person[0]:
continue
# Position 1
elif person[3] is not None and not (math.isnan(person[3])) and i <= person[3]:
new_point = [person[1], person[2]]
color = "b"
# Position 2
elif person[6] is not None and not (math.isnan(person[6])) and i <= person[6]:
new_point = [person[4], person[5]]
color = "r"
# Position 3
elif person[9] is not None and not (math.isnan(person[9])) and i <= person[9]:
new_point = [person[7], person[8]]
color = "r"
else:
people.remove(person)
new_point = []
if new_point != []:
points.append(new_point)
colors.append(color)
if points != []:
graph.set_offsets(points)
graph.set_facecolors(colors)
else:
# You can use graph.remove() to fix the last point not disappiring but you won't be able to plot anything after that
# graph.remove()
pass
return graph
ani = FuncAnimation(fig, animate, repeat=False, interval=500)
plt.show()
I want to have the legend of the plot shown with the value in a list. But what I get is the element index but not the value itself. I dont know how to fix it. I'm referring to the plt.plot line. Thanks for the help.
import matplotlib.pyplot as plt
import numpy as np
x = np.random.random(1000)
y = np.random.random(1000)
n = len(x)
d_ij = []
for i in range(n):
for j in range(i+1,n):
a = np.sqrt((x[i]-x[j])**2+(y[i]-y[j])**2)
d_ij.append(a)
epsilon = np.linspace(0.01,1,num=10)
sigma = np.linspace(0.01,1,num=10)
def lj_pot(epsi,sig,d):
result = []
for i in range(len(d)):
a = 4*epsi*((sig/d[i])**12-(sig/d[i])**6)
result.append(a)
return result
for i in range(len(epsilon)):
for j in range(len(sigma)):
a = epsilon[i]
b = sigma[j]
plt.cla()
plt.ylim([-1.5, 1.5])
plt.xlim([0, 2])
plt.plot(sorted(d_ij),lj_pot(epsilon[i],sigma[j],sorted(d_ij)),label = 'epsilon = %d, sigma =%d' %(a,b))
plt.legend()
plt.savefig("epsilon_%d_sigma_%d.png" % (i,j))
plt.show()
Your code is a bit unpythonic, so I tried to clean it up to the best of my knowledge. numpy.random.random and numpy.random.uniform(0, 1) are basically the same, however, the latter also allows you to pass the shape of the return array that you would like to have, in this case an array with 1000 rows and two columns (1000, 2). I then use some magic to assign the two colums of the return array to x and y in the same line, respectively.
numpy.hypot does as the name suggests and calculates the hypothenuse of x and y. It can also do that for each entry of arrays with the same size, saving you the for loops, which you should try to aviod in Python since they are pretty slow.
You used plt for all your plotting, which is fine as long as you only have one figure, but I would recommend to be as explicit as possible, according to one of Python's key notions:
explicit is better than implicit.
I recommend you read through this guide, in particular the section called 'Stateful Versus Stateless Approaches'. I changed your commands accordingly.
It is also very unpythonic to loop over items of a list using the index of the item in the list like you did (for i in range(len(list)): item = list[i]). You can just reference the item directly (for item in list:).
Lastly I changed your formatted strings to the more convenient f-strings. Have a read here.
import matplotlib.pyplot as plt
import numpy as np
def pot(epsi, sig, d):
result = 4*epsi*((sig/d)**12 - (sig/d)**6)
return result
# I am not sure why you would create the independent variable this way,
# maybe you are simulating something. In that case, the code below is
# simpler than your version and should achieve the same.
# x, y = zip(*np.random.uniform(0, 1, (1000, 2)))
# d = np.array(sorted(np.hypot(x, y)))
# If you only want to plot your pot function then creating the value range
# like this is just fine.
d = np.linspace(0.001, 1, 1000)
epsilons = sigmas = np.linspace(0.01, 1, num=10)
fig, ax = plt.subplots()
ax.set_xlim([0, 2])
ax.set_ylim([-1.5, 1.5])
line = None
for epsilon in epsilons:
for sigma in sigmas:
if line is None:
line = ax.plot(
d, pot(epsilon, sigma, d),
label=f'epsilon = {epsilon}, sigma = {sigma}'
)[0]
fig.legend()
else:
line.set_data(d, pot(epsilon, sigma, d))
# plt.savefig(f"epsilon_{epsilon}_sigma_{sigma}.png")
fig.show()
I'm making a plot to compare band structure calculations from two different methods. This means plotting multiple lines for each set of data. I want to have a set of widgets that controls each set of data separately. The code below works if I only plot one set of data, but I can't get the widgets to work properly for two sets of data.
#!/usr/bin/env python3
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.widgets import Slider, TextBox
#cols = ['blue', 'red', 'green', 'purple']
cols = ['#3f54bf','#c14142','#59bf3f','#b83fbf']
finam = ['wan_band.dat','wan_band.pwx.dat']
#finam = ['wan_band.dat'] # this works
lbot = len(finam)*0.09 + 0.06
fig, ax = plt.subplots()
plt.subplots_adjust(bottom=lbot)
ax.margins(x=0) # lines go to the edge of the horizontal axes
def setlines(lines, txbx1, txbx2):
''' turn lines on/off based on text box values '''
try:
mn = int(txbx1) - 1
mx = int(txbx2) - 1
for ib in range(len(lines)):
if (ib<mn) or (ib>mx):
lines[ib].set_visible(False)
else :
lines[ib].set_visible(True)
plt.draw()
except ValueError as err:
print('Invalid range')
#end def setlines(cnt, lines, txbx1, txbx2):
def alphalines(lines, valin):
''' set lines' opacity '''
maxval = int('ff',16)
maxval = hex(int(valin*maxval))[2:]
for ib in range(bcnt):
lines[ib].set_color(cols[cnt]+maxval)
plt.draw()
#end def alphalines(lines, valtxt):
lines = [0]*len(finam) # 2d list to hold Line2Ds
txbox1 = [0]*len(finam) # list of Lo Band TextBoxes
txbox2 = [0]*len(finam) # lsit of Hi Band TextBoxes
alslid = [0]*len(finam) # list of Line Opacity Sliders
for cnt, fnam in enumerate(finam):
ptcnt = 0 # point count
fid = open(fnam, 'r')
fiit = iter(fid)
for line in fiit:
if line.strip() == '' :
break
ptcnt += 1
fid.close()
bandat_raw = np.loadtxt(fnam)
bcnt = int(np.round((bandat_raw.shape[0] / (ptcnt))))
print(ptcnt)
print(bcnt)
# get views of the raw data that are easier to work with
kbandat = bandat_raw[:ptcnt,0] # k point length along path
ebandat = bandat_raw.reshape((bcnt,ptcnt,2))[:,:,1] # band energy # k-points
lines[cnt] = [0]*bcnt # point this list element to another list
for ib in range(bcnt):
#l, = plt.plot(kbandat, ebandat[ib], c=cols[cnt],lw=1.0)
l, = ax.plot(kbandat, ebandat[ib], c=cols[cnt],lw=1.0)
lines[cnt][ib] = l
y0 = 0.03 + 0.07*cnt
bxht = 0.035
axbox1 = plt.axes([0.03, y0, 0.08, bxht]) # x0, y0, width, height
axbox2 = plt.axes([0.13, y0, 0.08, bxht])
txbox1[cnt] = TextBox(axbox1, '', initial=str(1))
txbox2[cnt] = TextBox(axbox2, '', initial=str(bcnt))
txbox1[cnt].on_submit( lambda x: setlines(lines[cnt], x, txbox2[cnt].text) )
txbox2[cnt].on_submit( lambda x: setlines(lines[cnt], txbox1[cnt].text, x) )
axalpha = plt.axes([0.25, y0, 0.65, bxht])
alslid[cnt] = Slider(axalpha, '', 0.1, 1.0, valinit=1.0)
salpha = alslid[cnt]
alslid[cnt].on_changed( lambda x: alphalines(lines[cnt], x) )
#end for cnt, fnam in enumerate(finam):
plt.text(0.01, 1.2, 'Lo Band', transform=axbox1.transAxes)
plt.text(0.01, 1.2, 'Hi Band', transform=axbox2.transAxes)
plt.text(0.01, 1.2, 'Line Opacity', transform=axalpha.transAxes)
plt.show()
All the widgets only control the last data set plotted instead of the individual data sets I tried to associate with each widget. Here is a sample output:
Here the bottom slider should be changing the blue lines' opacity, but instead it changes the red lines' opacity. Originally the variables txbox1, txbox2, and alslid were not lists. I changed them to lists though to ensure they weren't garbage collected but it didn't change anything.
Here is the test data set1 and set2 I've been using. They should be saved as files 'wan_band.dat' and 'wan_band.pwx.dat' as per the hard coded list finam in the code.
I figured it out, using a lambda to partially execute some functions with an iterator value meant they were always being evaluated with the last value of the iterator. Switching to functools.partial fixed the issue.
I can draw a boxplot from data:
import numpy as np
import matplotlib.pyplot as plt
data = np.random.rand(100)
plt.boxplot(data)
Then, the box will range from the 25th-percentile to 75th-percentile, and the whisker will range from the smallest value to the largest value between (25th-percentile - 1.5*IQR, 75th-percentile + 1.5*IQR), where the IQR denotes the inter-quartile range. (Of course, the value 1.5 is customizable).
Now I want to know the values used in the boxplot, i.e. the median, upper and lower quartile, the upper whisker end point and the lower whisker end point. While the former three are easy to obtain by using np.median() and np.percentile(), the end point of the whiskers will require some verbose coding:
median = np.median(data)
upper_quartile = np.percentile(data, 75)
lower_quartile = np.percentile(data, 25)
iqr = upper_quartile - lower_quartile
upper_whisker = data[data<=upper_quartile+1.5*iqr].max()
lower_whisker = data[data>=lower_quartile-1.5*iqr].min()
I was wondering, while this is acceptable, would there be a neater way to do this? It seems that the values should be ready to pull-out from the boxplot, as it's already drawn.
Why do you want to do so? what you are doing is already pretty direct.
Yeah, if you want to fetch them for the plot, when the plot is already made, simply use the get_ydata() method.
B = plt.boxplot(data)
[item.get_ydata() for item in B['whiskers']]
It returns an array of the shape (2,) for each whiskers, the second element is the value we want:
[item.get_ydata()[1] for item in B['whiskers']]
I've had this recently and have written a function to extract the boxplot values from the boxplot as a pandas dataframe.
The function is:
def get_box_plot_data(labels, bp):
rows_list = []
for i in range(len(labels)):
dict1 = {}
dict1['label'] = labels[i]
dict1['lower_whisker'] = bp['whiskers'][i*2].get_ydata()[1]
dict1['lower_quartile'] = bp['boxes'][i].get_ydata()[1]
dict1['median'] = bp['medians'][i].get_ydata()[1]
dict1['upper_quartile'] = bp['boxes'][i].get_ydata()[2]
dict1['upper_whisker'] = bp['whiskers'][(i*2)+1].get_ydata()[1]
rows_list.append(dict1)
return pd.DataFrame(rows_list)
And is called by passing an array of labels (the ones that you would pass to the boxplot plotting function) and the data returned by the boxplot function itself.
For example:
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
def get_box_plot_data(labels, bp):
rows_list = []
for i in range(len(labels)):
dict1 = {}
dict1['label'] = labels[i]
dict1['lower_whisker'] = bp['whiskers'][i*2].get_ydata()[1]
dict1['lower_quartile'] = bp['boxes'][i].get_ydata()[1]
dict1['median'] = bp['medians'][i].get_ydata()[1]
dict1['upper_quartile'] = bp['boxes'][i].get_ydata()[2]
dict1['upper_whisker'] = bp['whiskers'][(i*2)+1].get_ydata()[1]
rows_list.append(dict1)
return pd.DataFrame(rows_list)
data1 = np.random.normal(loc = 0, scale = 1, size = 1000)
data2 = np.random.normal(loc = 5, scale = 1, size = 1000)
data3 = np.random.normal(loc = 10, scale = 1, size = 1000)
labels = ['data1', 'data2', 'data3']
bp = plt.boxplot([data1, data2, data3], labels=labels)
print(get_box_plot_data(labels, bp))
plt.show()
Outputs the following from get_box_plot_data:
label lower_whisker lower_quartile median upper_quartile upper_whisker
0 data1 -2.491652 -0.587869 0.047543 0.696750 2.559301
1 data2 2.351567 4.310068 4.984103 5.665910 7.489808
2 data3 7.227794 9.278931 9.947674 10.661581 12.733275
And produces the following plot:
upper_whisker = data[data<=upper_quartile+1.5*iqr].max()
lower_whisker = data[data>=lower_quartile-1.5*iqr].min()
equal to
upper_whisker = data.max()
lower_whisker = data.min()
if you just want to get the real data points in the dataset. But statistically speaking, the whisker values are upper_quantile+1.5IQR and lower_quantile-1.5IQR