Related
I currently have a plot like this (consider that data is the dataframe I pasted at the very bottom):
import seaborn as sns
sns.relplot(
data = data,
x = "Threshold",
y = "Value",
kind = "line",
hue="Metric"
).set(xlabel="Threshold")
Which produces:
Now, I want to know how can I annotate a line in this plot, such that it is located between the curves, at the x-Axis value where the distance between curves are maximized. I would also need to annotate text to show the distance value.
It should be something like this:
Here is the pandas dataframe:
Threshold,Metric,Value
0.0,Recall,1.0
0.010101010101010102,Recall,0.9802536231884058
0.020202020202020204,Recall,0.9706521739130435
0.030303030303030304,Recall,0.9621376811594203
0.04040404040404041,Recall,0.9541666666666667
0.05050505050505051,Recall,0.9456521739130435
0.06060606060606061,Recall,0.9322463768115942
0.07070707070707072,Recall,0.9173913043478261
0.08080808080808081,Recall,0.908695652173913
0.09090909090909091,Recall,0.8976449275362319
0.10101010101010102,Recall,0.8813405797101449
0.11111111111111112,Recall,0.8644927536231884
0.12121212121212122,Recall,0.8498188405797101
0.13131313131313133,Recall,0.8358695652173913
0.14141414141414144,Recall,0.818659420289855
0.15151515151515152,Recall,0.7967391304347826
0.16161616161616163,Recall,0.7748188405797102
0.17171717171717174,Recall,0.7521739130434782
0.18181818181818182,Recall,0.7269927536231884
0.19191919191919193,Recall,0.6952898550724638
0.20202020202020204,Recall,0.6704710144927536
0.21212121212121213,Recall,0.648731884057971
0.22222222222222224,Recall,0.6097826086956522
0.23232323232323235,Recall,0.5847826086956521
0.24242424242424243,Recall,0.5521739130434783
0.25252525252525254,Recall,0.5023550724637681
0.26262626262626265,Recall,0.4766304347826087
0.27272727272727276,Recall,0.42047101449275365
0.2828282828282829,Recall,0.3958333333333333
0.29292929292929293,Recall,0.3539855072463768
0.30303030303030304,Recall,0.3327898550724638
0.31313131313131315,Recall,0.3036231884057971
0.32323232323232326,Recall,0.2798913043478261
0.33333333333333337,Recall,0.2371376811594203
0.3434343434343435,Recall,0.22119565217391304
0.3535353535353536,Recall,0.17300724637681159
0.36363636363636365,Recall,0.15996376811594204
0.37373737373737376,Recall,0.13568840579710145
0.38383838383838387,Recall,0.11938405797101449
0.393939393939394,Recall,0.10652173913043478
0.4040404040404041,Recall,0.09891304347826087
0.4141414141414142,Recall,0.08894927536231884
0.42424242424242425,Recall,0.07681159420289856
0.43434343434343436,Recall,0.06557971014492754
0.4444444444444445,Recall,0.05253623188405797
0.4545454545454546,Recall,0.04655797101449275
0.4646464646464647,Recall,0.024456521739130436
0.4747474747474748,Recall,0.019384057971014494
0.48484848484848486,Recall,0.009782608695652175
0.494949494949495,Recall,0.0034420289855072463
0.5050505050505051,Recall,0.002173913043478261
0.5151515151515152,Recall,0.0016304347826086956
0.5252525252525253,Recall,0.0007246376811594203
0.5353535353535354,Recall,0.00018115942028985507
0.5454545454545455,Recall,0.0
0.5555555555555556,Recall,0.0
0.5656565656565657,Recall,0.0
0.5757575757575758,Recall,0.0
0.5858585858585859,Recall,0.0
0.595959595959596,Recall,0.0
0.6060606060606061,Recall,0.0
0.6161616161616162,Recall,0.0
0.6262626262626263,Recall,0.0
0.6363636363636365,Recall,0.0
0.6464646464646465,Recall,0.0
0.6565656565656566,Recall,0.0
0.6666666666666667,Recall,0.0
0.6767676767676768,Recall,0.0
0.686868686868687,Recall,0.0
0.696969696969697,Recall,0.0
0.7070707070707072,Recall,0.0
0.7171717171717172,Recall,0.0
0.7272727272727273,Recall,0.0
0.7373737373737375,Recall,0.0
0.7474747474747475,Recall,0.0
0.7575757575757577,Recall,0.0
0.7676767676767677,Recall,0.0
0.7777777777777778,Recall,0.0
0.787878787878788,Recall,0.0
0.797979797979798,Recall,0.0
0.8080808080808082,Recall,0.0
0.8181818181818182,Recall,0.0
0.8282828282828284,Recall,0.0
0.8383838383838385,Recall,0.0
0.8484848484848485,Recall,0.0
0.8585858585858587,Recall,0.0
0.8686868686868687,Recall,0.0
0.8787878787878789,Recall,0.0
0.888888888888889,Recall,0.0
0.8989898989898991,Recall,0.0
0.9090909090909092,Recall,0.0
0.9191919191919192,Recall,0.0
0.9292929292929294,Recall,0.0
0.9393939393939394,Recall,0.0
0.9494949494949496,Recall,0.0
0.9595959595959597,Recall,0.0
0.9696969696969697,Recall,0.0
0.9797979797979799,Recall,0.0
0.98989898989899,Recall,0.0
1.0,Recall,0.0
0.0,Fall-out,1.0
0.010101010101010102,Fall-out,0.6990465720990212
0.020202020202020204,Fall-out,0.58461408367334
0.030303030303030304,Fall-out,0.516647992727734
0.04040404040404041,Fall-out,0.4643680104855929
0.05050505050505051,Fall-out,0.4172674037587468
0.06060606060606061,Fall-out,0.3796376551170116
0.07070707070707072,Fall-out,0.3507811343889394
0.08080808080808081,Fall-out,0.33186055852694335
0.09090909090909091,Fall-out,0.3152231359533222
0.10101010101010102,Fall-out,0.29964272879098575
0.11111111111111112,Fall-out,0.2855844238208993
0.12121212121212122,Fall-out,0.27161068008371564
0.13131313131313133,Fall-out,0.25719298987379235
0.14141414141414144,Fall-out,0.24338836860241422
0.15151515151515152,Fall-out,0.2312538316808659
0.16161616161616163,Fall-out,0.22026087140350506
0.17171717171717174,Fall-out,0.2083377375642137
0.18181818181818182,Fall-out,0.19694311143056467
0.19191919191919193,Fall-out,0.18402638310466565
0.20202020202020204,Fall-out,0.17440754286197493
0.21212121212121213,Fall-out,0.16548633279073208
0.22222222222222224,Fall-out,0.15278100754709004
0.23232323232323235,Fall-out,0.14292962391391667
0.24242424242424243,Fall-out,0.1317252605542989
0.25252525252525254,Fall-out,0.11555292476164303
0.26262626262626265,Fall-out,0.10612434729298353
0.27272727272727276,Fall-out,0.08902183793839714
0.2828282828282829,Fall-out,0.08331395471745978
0.29292929292929293,Fall-out,0.07232099444009894
0.30303030303030304,Fall-out,0.06735302200706086
0.31313131313131315,Fall-out,0.061454876012092256
0.32323232323232326,Fall-out,0.05665602604485973
0.33333333333333337,Fall-out,0.048982094158932836
0.3434343434343435,Fall-out,0.045641925459273196
0.3535353535353536,Fall-out,0.03748176648415534
0.36363636363636365,Fall-out,0.0341415977844957
0.37373737373737376,Fall-out,0.029321607509037482
0.38383838383838387,Fall-out,0.026996173604211148
0.393939393939394,Fall-out,0.024353635075999407
0.4040404040404041,Fall-out,0.022514428260364035
0.4141414141414142,Fall-out,0.01940680295118703
0.42424242424242425,Fall-out,0.017165930279263473
0.43434343434343436,Fall-out,0.014459970826374648
0.4444444444444445,Fall-out,0.011035240893812233
0.4545454545454546,Fall-out,0.009386296852208105
0.4646464646464647,Fall-out,0.004756569350781135
0.4747474747474748,Fall-out,0.003868676405301989
0.48484848484848486,Fall-out,0.002135171130795087
0.494949494949495,Fall-out,0.0008033317125763693
0.5050505050505051,Fall-out,0.0004228061645138786
0.5151515151515152,Fall-out,0.00031710462338540896
0.5252525252525253,Fall-out,4.228061645138786e-05
0.5353535353535354,Fall-out,0.0
0.5454545454545455,Fall-out,0.0
0.5555555555555556,Fall-out,0.0
0.5656565656565657,Fall-out,0.0
0.5757575757575758,Fall-out,0.0
0.5858585858585859,Fall-out,0.0
0.595959595959596,Fall-out,0.0
0.6060606060606061,Fall-out,0.0
0.6161616161616162,Fall-out,0.0
0.6262626262626263,Fall-out,0.0
0.6363636363636365,Fall-out,0.0
0.6464646464646465,Fall-out,0.0
0.6565656565656566,Fall-out,0.0
0.6666666666666667,Fall-out,0.0
0.6767676767676768,Fall-out,0.0
0.686868686868687,Fall-out,0.0
0.696969696969697,Fall-out,0.0
0.7070707070707072,Fall-out,0.0
0.7171717171717172,Fall-out,0.0
0.7272727272727273,Fall-out,0.0
0.7373737373737375,Fall-out,0.0
0.7474747474747475,Fall-out,0.0
0.7575757575757577,Fall-out,0.0
0.7676767676767677,Fall-out,0.0
0.7777777777777778,Fall-out,0.0
0.787878787878788,Fall-out,0.0
0.797979797979798,Fall-out,0.0
0.8080808080808082,Fall-out,0.0
0.8181818181818182,Fall-out,0.0
0.8282828282828284,Fall-out,0.0
0.8383838383838385,Fall-out,0.0
0.8484848484848485,Fall-out,0.0
0.8585858585858587,Fall-out,0.0
0.8686868686868687,Fall-out,0.0
0.8787878787878789,Fall-out,0.0
0.888888888888889,Fall-out,0.0
0.8989898989898991,Fall-out,0.0
0.9090909090909092,Fall-out,0.0
0.9191919191919192,Fall-out,0.0
0.9292929292929294,Fall-out,0.0
0.9393939393939394,Fall-out,0.0
0.9494949494949496,Fall-out,0.0
0.9595959595959597,Fall-out,0.0
0.9696969696969697,Fall-out,0.0
0.9797979797979799,Fall-out,0.0
0.98989898989899,Fall-out,0.0
1.0,Fall-out,0.0
Use pivot to transform the data from long to wide
Use idxmax to find the x (Threshold) of the max difference between y1 and y2 (Fall-out and Recall)
Use vlines to plot the vertical line at x from y1 to y2
Use annotate to plot the label at the midpoint of y1 and y2
g = sns.relplot(data=data, x='Threshold', y='Value', hue='Metric', kind='line')
# pivot to wide form
p = data.pivot(index='Threshold', columns='Metric', values='Value')
# find x, y1, and y2 corresponding to max difference
diff = p['Fall-out'].sub(p['Recall']).abs()
x = diff.idxmax()
y1, y2 = p.loc[x]
# plot line and label
ax = g.axes.flat[0]
ax.vlines(x, y1, y2, ls='--')
ax.annotate(f'Dist = {diff.loc[x]:.2f}', ha='left', va='center',
xy=(x, 0.5*(y1+y2)), xycoords='data',
xytext=(5, 0), textcoords='offset pixels')
The easiest way which I can think of is to create two separate lists of all values where the metric is Recall and another with all values where metric is Fall-out. This can be easily done using pandas operations as follows (Assuming the dataframe has name df) -
import math
import matplotlib.pyplot as plt
ls_metric = df['Metric'].to_list()
ls_value = df['Value'].to_list()
ls_threshold = df['Threshold'].to_list()
ls_value_recall = []
ls_value_fallout = []
ls_threshold_recall = []
ls_threshold_fallout = []
for i, j, k in zip(ls_metric, ls_value, ls_threshold):
if (i == 'Recall'):
ls_value_recall.append(j)
ls_threshold_recall.append(k)
elif(i == 'Fall-out'):
ls_value_fallout.append(j)
ls_threshold_recall.append(k)
ls_dist = []
for i, j in zip(ls_value_recall, ls_value_fallout):
ls_dist.append(math.abs(i-j))
max_diff = max(ls_dist)
location_of_max_diff = ls_dist.index(max_diff)
value_of_threshold_at_max_diff = ls_threshold_recall[location_of_max_diff]
value_of_recall_at_max_diff = ls_value_recall[location_of_max_diff]
value_of_fallout_at_max_diff = ls_value_fallout[location_of_max_diff]
x_values = [value_of_threshold_at_max_diff, value_of_threshold_at_max_diff]
y_values = [value_of_recall_at_max_diff, value_of_fallout_at_max_diff]
plt.plot(x_values, y_values)
Certain Assumptions - The Threshold Values are the same and same number of readings are present for both metrics which I think is true having had a brief glance at the data but if not I believe it's still pretty easy to modify the code
You can add this plot to your own figure for which the syntax is readily available, now as far as the label for the line is concerned one way to do this is use matplotlib.pyplot.text to add a textbox but with that you'll need to tweak with the location to get the desired location another way to do this would be to add it as a legend only
I try to generate a graph and save an image of the graph in python. Although the "plotting" of the values seems ok and I can get my picture, the scale of the graph is badly shifted.
If you compare the correct graph from tutorial example with my bad graph generated from different dataset, the curves are cut at the bottom to early: Y-axis should start just above the highest values and I should also see the curves for the highest X-values (in my case around 10^3).
But honestly, I think that problem is the scale of the y-axis, but actually do not know what parameteres should I change to fix it. I tried to play with some numbers (see below script), but without any good results.
This is the code for calculation and generation of the graph image:
import numpy as np
hic_data = load_hic_data_from_reads('/home/besy/Hi-C/MOREX/TCC35_parsedV2/TCC35_V2_interaction_filtered.tsv', resolution=100000)
min_diff = 1
max_diff = 500
import matplotlib.pyplot as plt
fig = plt.figure(figsize=(12, 12))
for cnum, c in enumerate(hic_data.chromosomes):
if c in ['ChrUn']:
continue
dist_intr = []
for diff in xrange(min_diff, min((max_diff, 1 + hic_data.chromosomes[c]))):
beg, end = hic_data.section_pos[c]
dist_intr.append([])
for i in xrange(beg, end - diff):
dist_intr[-1].append(hic_data[i, i + diff])
mean_intrp = []
for d in dist_intr:
if len(d):
mean_intrp.append(float(np.nansum(d)) / len(d))
else:
mean_intrp.append(0.0)
xp, yp = range(min_diff, max_diff), mean_intrp
x = []
y = []
for k in xrange(len(xp)):
if yp[k]:
x.append(xp[k])
y.append(yp[k])
l = plt.plot(x, y, '-', label=c, alpha=0.8)
plt.hlines(mean_intrp[2], 3, 5.25 + np.exp(cnum / 4.3), color=l[0].get_color(),
linestyle='--', alpha=0.5)
plt.text(5.25 + np.exp(cnum / 4.3), mean_intrp[2], c, color=l[0].get_color())
plt.plot(3, mean_intrp[2], '+', color=l[0].get_color())
plt.xscale('log')
plt.yscale('log')
plt.ylabel('number of interactions')
plt.xlabel('Distance between bins (in 100 kb bins)')
plt.grid()
plt.ylim(2, 250)
_ = plt.xlim(1, 110)
fig.savefig('/home/besy/Hi-C/MOREX/TCC35_V2_results/filtered/TCC35_V2_decay.png', dpi=fig.dpi)
I think that problem is in scale I need y-axis to start from 10^-1 (0.1), in order to change this I tried this:
min_diff = 0.1
.
.
.
dist_intr = []
for diff in xrange(min_diff, min((max_diff, 0.1 + hic_data.chromosomes[c]))):
.
.
.
plt.ylim((0.1, 20))
But this values return: "integer argument expected, got float"
I also tried to play with:
max_diff, plt.ylim and plt.xlim parameters little bit, but nothing changed to much.
I would like to ask you what parameter/s and how I need change to generate image of the correctly focused graph. Thank you in advance.
I have written some code to graph some data in Python's Matplotlib.
The plot currently:
The code to produce this plot:
groups=['Control','30min','24hour']
cell_lysate_avg=[11887.42595, 4862.429689, 3414.337554]
cell_lysate_sd=[1956.212855, 494.8437915, 525.8556207]
cell_lysate_avg=[i/1000 for i in cell_lysate_avg]
cell_lysate_sd=[i/1000 for i in cell_lysate_sd]
media_avg=[14763.71106,8597.475539,6374.732852]
media_sd=[240.8983759, 167.005365, 256.1374017]
media_avg=[i/1000 for i in media_avg] #to get ng/ml
media_sd=[i/1000 for i in media_sd]
fig, ax = plt.subplots()
index = numpy.arange(len(groups)) #where to put the bars
bar_width=0.45
opacity = 0.5
error_config = {'ecolor': '0.3'}
cell_lysate_plt=plt.bar(index,cell_lysate_avg,bar_width,alpha=opacity,color='black',yerr=cell_lysate_sd,error_kw=error_config,label='Cell Lysates')
media_plt=plt.bar(index+bar_width,media_avg,bar_width,alpha=opacity,color='green',yerr=media_sd,error_kw=error_config,label='Media')
plt.xlabel('Groups',fontsize=15)
plt.ylabel('ng/ml',fontsize=15)
plt.title('\n'.join(wrap('Average Over Biological Repeats for TIMP1 ELISA (n=3)',45)),fontsize=15)
plt.xticks(index + bar_width, groups)
plt.legend()
ax.tick_params(axis='x', labelsize=14)
ax.tick_params(axis='y', labelsize=14)
I have calculated the various two tailed t tests associated with this data and I want to display using standard scientific journal representation - i.e. a line connecting two bars with a star which represents a significance level of (say) >0.05. Can anybody tell me how to do this?
As far as I know there is no standard scientific journal representation for showing significance. The exact way you draw it is a matter of taste. This is probably the reason why matplotlib has no specific function for significance bars (at least to my knowledge). You could just do it manually. E.g:
from matplotlib.markers import TICKDOWN
def significance_bar(start,end,height,displaystring,linewidth = 1.2,markersize = 8,boxpad =0.3,fontsize = 15,color = 'k'):
# draw a line with downticks at the ends
plt.plot([start,end],[height]*2,'-',color = color,lw=linewidth,marker = TICKDOWN,markeredgewidth=linewidth,markersize = markersize)
# draw the text with a bounding box covering up the line
plt.text(0.5*(start+end),height,displaystring,ha = 'center',va='center',bbox=dict(facecolor='1.', edgecolor='none',boxstyle='Square,pad='+str(boxpad)),size = fontsize)
pvals = [0.001,0.1,0.00001]
offset =1
for i,p in enumerate(pvals):
if p>=0.05:
displaystring = r'n.s.'
elif p<0.0001:
displaystring = r'***'
elif p<0.001:
displaystring = r'**'
else:
displaystring = r'*'
height = offset + max(cell_lysate_avg[i],media_avg[i])
bar_centers = index[i] + numpy.array([0.5,1.5])*bar_width
significance_bar(bar_centers[0],bar_centers[1],height,displaystring)
Instead of the stars you could of course also explicitly write p<0.05 or something similar. You can then spend hours fiddling with the parameters until it looks just right.
How can I create a boxplot like the one below, in Python? I want to depict means and confidence bounds only (rather than proportions of IQRs, as in matplotlib boxplot).
I don't have any version constraints, and if your answer has some package dependency that's OK too. Thanks!
Use errorbar instead. Here is a minimal example:
import matplotlib.pyplot as plt
x = [2, 4, 3]
y = [1, 3, 5]
errors = [0.5, 0.25, 0.75]
plt.figure()
plt.errorbar(x, y, xerr=errors, fmt = 'o', color = 'k')
plt.yticks((0, 1, 3, 5, 6), ('', 'x3', 'x2', 'x1',''))
Note that boxplot is not the right approach; the conf_intervals parameter only controls the placement of the notches on the boxes (and we don't want boxes anyway, let alone notched boxes). There is no way to customize the whiskers except as a function of IQR.
Thanks to America, I propose a way to automatize this kind of graph a little bit.
Below an example of code generating 20 arrays from a normal distribution with mean=0.25 and std=0.1.
I used the formula W = t * s / sqrt(n), to calculate the margin of error of the confidence interval, with t the constant from the t distribution (see scipy.stats.t), s the standard deviation and n the number of values in an array.
list_samples=list() # making a list of arrays
for i in range(20):
list.append(np.random.normal(loc=0.25, scale=0.1, size=20))
def W_array(array, conf=0.95): # function that returns W based on the array provided
t = stats.t(df = len(array) - 1).ppf((1 + conf) /2)
W = t * np.std(array, ddof=1) / np.sqrt(len(array))
return W # the error
W_list = list()
mean_list = list()
for i in range(len(list_samples)):
W_list.append(W_array(list_samples[i])) # makes a list of W for each array
mean_list.append(np.mean(list_samples[i])) # same for the means to plot
plt.errorbar(x=mean_list, y=range(len(list_samples)), xerr=W_list, fmt='o', color='k')
plt.axvline(.25, ls='--') # this is only to demonstrate that 95%
# of the 95% CI contain the actual mean
plt.yticks([])
plt.show();
I have a script for plotting astronomical data of redmapping clusters using a csv file. I could get the data points in it and want to plot them using different colors depending on their redshift values: I am binning the dataset into 3 bins (0.1-0.2, 0.2-0.25, 0.25,0.31) based on the redshift.
The problem arises with my code after I distinguish to what bin the datapoint belongs: I want to have 3 labels in the legend corresponding to red, green and blue data points, but this is not happening and I don't know why. I am using plot() instead of scatter() as I also had to do the best fit from the data in the same figure. So everything needs to be in 1 figure.
import numpy as np
import matplotlib.pyplot as py
import csv
z = open("Sheet4CSV.csv","rU")
data = csv.reader(z)
x = []
y = []
ylow = []
yupp = []
xlow = []
xupp = []
redshift = []
for r in data:
x.append(float(r[2]))
y.append(float(r[5]))
xlow.append(float(r[3]))
xupp.append(float(r[4]))
ylow.append(float(r[6]))
yupp.append(float(r[7]))
redshift.append(float(r[1]))
from operator import sub
xerr_l = map(sub,x,xlow)
xerr_u = map(sub,xupp,x)
yerr_l = map(sub,y,ylow)
yerr_u = map(sub,yupp,y)
py.xlabel("$Original\ Tx\ XCS\ pipeline\ Tx\ keV$")
py.ylabel("$Iterative\ Tx\ pipeline\ keV$")
py.xlim(0,12)
py.ylim(0,12)
py.title("Redmapper Clusters comparison of Tx pipelines")
ax1 = py.subplot(111)
##Problem starts here after the previous line##
for p in redshift:
for i in xrange(84):
p=redshift[i]
if 0.1<=p<0.2:
ax1.plot(x[i],y[i],color="b", marker='.', linestyle = " ")#, label = "$z < 0.2$")
exit
if 0.2<=p<0.25:
ax1.plot(x[i],y[i],color="g", marker='.', linestyle = " ")#, label="$0.2 \leq z < 0.25$")
exit
if 0.25<=p<=0.3:
ax1.plot(x[i],y[i],color="r", marker='.', linestyle = " ")#, label="$z \geq 0.25$")
exit
##There seems nothing wrong after this point##
py.errorbar(x,y,yerr=[yerr_l,yerr_u],xerr=[xerr_l,xerr_u], fmt= " ",ecolor='magenta', label="Error bars")
cof = np.polyfit(x,y,1)
p = np.poly1d(cof)
l = np.linspace(0,12,100)
py.plot(l,p(l),"black",label="Best fit")
py.plot([0,15],[0,15],"black", linestyle="dotted", linewidth=2.0, label="line $y=x$")
py.grid()
box = ax1.get_position()
ax1.set_position([box.x1,box.y1,box.width, box.height])
py.legend(loc='center left',bbox_to_anchor=(1,0.5))
py.show()
In the 1st 'for' loop, I have indexed every value 'p' in the list 'redshift' so that bins can be created using 'if' statement. But if I add the labels that are hashed out against each py.plot() inside the 'if' statements, each data point 'i' that gets plotted in the figure as an intersection of (x[i],y[i]) takes the label and my entire legend attains in total 87 labels (including the 3 mentioned in the code at other places)!!!!!!
I essentially need 1 label for each bin...
Please tell me what needs to done after the bins are created and py.plot() commands used...Thanks in advance :-)
Sorry I cannot post my image here due to low reputation!
The data 'appended' for x, y and redshift lists from the csv file are as follows:
x=[5.031,10.599,10.589,8.548,9.089,8.675,3.588,1.244,3.023,8.632,8.953,7.603,7.513,2.917,7.344,7.106,3.889,7.287,3.367,6.839,2.801,2.316,1.328,6.31,6.19,6.329,6.025,5.629,6.123,5.892,5.438,4.398,4.542,4.624,4.501,4.504,5.033,5.068,4.197,2.854,4.784,2.158,4.054,3.124,3.961,4.42,3.853,3.658,1.858,4.537,2.072,3.573,3.041,5.837,3.652,3.209,2.742,2.732,1.312,3.635,2.69,3.32,2.488,2.996,2.269,1.701,3.935,2.015,0.798,2.212,1.672,1.925,3.21,1.979,1.794,2.624,2.027,3.66,1.073,1.007,1.57,0.854,0.619,0.547]
y=[5.255,10.897,11.045,9.125,9.387,17.719,4.025,1.389,4.152,8.703,9.051,8.02,7.774,3.139,7.543,7.224,4.155,7.416,3.905,6.868,2.909,2.658,1.651,6.454,6.252,6.541,6.152,5.647,6.285,6.079,5.489,4.541,4.634,8.851,4.554,4.555,5.559,5.144,5.311,5.839,5.364,3.18,4.352,3.379,4.059,4.575,3.914,5.736,2.304,4.68,3.187,3.756,3.419,9.118,4.595,3.346,3.603,6.313,1.816,4.34,2.732,4.978,2.719,3.761,2.623,2.1,4.956,2.316,4.231,2.831,1.954,2.248,6.573,2.276,2.627,3.85,3.545,25.405,3.996,1.347,1.679,1.435,0.759,0.677]
redshift = [0.12,0.25,0.23,0.23,0.27,0.26,0.12,0.27,0.17,0.18,0.17,0.3,0.23,0.1,0.23,0.29,0.29,0.12,0.13,0.26,0.11,0.24,0.13,0.21,0.17,0.2,0.3,0.29,0.23,0.27,0.25,0.21,0.11,0.15,0.1,0.26,0.23,0.12,0.23,0.26,0.2,0.17,0.22,0.26,0.25,0.12,0.19,0.24,0.18,0.15,0.27,0.14,0.14,0.29,0.29,0.26,0.15,0.29,0.24,0.24,0.23,0.26,0.29,0.22,0.13,0.18,0.24,0.14,0.24,0.24,0.17,0.26,0.29,0.11,0.14,0.26,0.28,0.26,0.28,0.27,0.23,0.26,0.23,0.19]
Working with numerical data like this, you should really consider using a numerical library, like numpy.
The problem in your code arises from processing each record (a coordinate (x,y) and the corresponding value redshift) one at a time. You are calling plot for each point, thereby creating legends for each of those 84 datapoints. You should consider your "bins" as groups of data that belong to the same dataset and process them as such. You could use "logical masks" to distinguish between your "bins", as shown below.
It's also not clear why you call exit after each plotting action.
import numpy as np
import matplotlib.pyplot as plt
x = np.array([5.031,10.599,10.589,8.548,9.089,8.675,3.588,1.244,3.023,8.632,8.953,7.603,7.513,2.917,7.344,7.106,3.889,7.287,3.367,6.839,2.801,2.316,1.328,6.31,6.19,6.329,6.025,5.629,6.123,5.892,5.438,4.398,4.542,4.624,4.501,4.504,5.033,5.068,4.197,2.854,4.784,2.158,4.054,3.124,3.961,4.42,3.853,3.658,1.858,4.537,2.072,3.573,3.041,5.837,3.652,3.209,2.742,2.732,1.312,3.635,2.69,3.32,2.488,2.996,2.269,1.701,3.935,2.015,0.798,2.212,1.672,1.925,3.21,1.979,1.794,2.624,2.027,3.66,1.073,1.007,1.57,0.854,0.619,0.547])
y = np.array([5.255,10.897,11.045,9.125,9.387,17.719,4.025,1.389,4.152,8.703,9.051,8.02,7.774,3.139,7.543,7.224,4.155,7.416,3.905,6.868,2.909,2.658,1.651,6.454,6.252,6.541,6.152,5.647,6.285,6.079,5.489,4.541,4.634,8.851,4.554,4.555,5.559,5.144,5.311,5.839,5.364,3.18,4.352,3.379,4.059,4.575,3.914,5.736,2.304,4.68,3.187,3.756,3.419,9.118,4.595,3.346,3.603,6.313,1.816,4.34,2.732,4.978,2.719,3.761,2.623,2.1,4.956,2.316,4.231,2.831,1.954,2.248,6.573,2.276,2.627,3.85,3.545,25.405,3.996,1.347,1.679,1.435,0.759,0.677])
redshift = np.array([0.12,0.25,0.23,0.23,0.27,0.26,0.12,0.27,0.17,0.18,0.17,0.3,0.23,0.1,0.23,0.29,0.29,0.12,0.13,0.26,0.11,0.24,0.13,0.21,0.17,0.2,0.3,0.29,0.23,0.27,0.25,0.21,0.11,0.15,0.1,0.26,0.23,0.12,0.23,0.26,0.2,0.17,0.22,0.26,0.25,0.12,0.19,0.24,0.18,0.15,0.27,0.14,0.14,0.29,0.29,0.26,0.15,0.29,0.24,0.24,0.23,0.26,0.29,0.22,0.13,0.18,0.24,0.14,0.24,0.24,0.17,0.26,0.29,0.11,0.14,0.26,0.28,0.26,0.28,0.27,0.23,0.26,0.23,0.19])
bin3 = 0.25 <= redshift
bin2 = np.logical_and(0.2 <= redshift, redshift < 0.25)
bin1 = np.logical_and(0.1 <= redshift, redshift < 0.2)
plt.ion()
labels = ("$z < 0.2$", "$0.2 \leq z < 0.25$", "$z \geq 0.25$")
colors = ('r', 'g', 'b')
for bin, label, co in zip( (bin1, bin2, bin3), labels, colors):
plt.plot(x[bin], y[bin], color=co, ls='none', marker='o', label=label)
plt.legend()
plt.show()