Scatter plot colorbar based on datapoint cluster

Question

I am trying to achieve a plot similar to this one:

The color shows the clustering of the datapoints.

My code so far:

import pandas as pd
import readTrc
import matplotlib.pyplot as plt
import numpy as np
import os
import gc

trcpath = 'filename.trc'
datX, datY, m = readTrc.readTrc(trcpath)
srx, sry = pd.Series(datX * 1000), pd.Series(datY * 1000)
df_plot = pd.concat([srx, sry], axis = 1)
df_plot.set_index(0, inplace = True)
fig, ax = plt.subplots()

#Eliminate Noise
df_plot[df_plot < 3] = 0
df = df_plot[df_plot > 3]
df[df < 3] = None
df = df.dropna()

#Plot Parameters
p = np.array(df[1].tolist()[:-1])
p_nach = np.array(df[1].tolist()[1:])
d_t = np.array(pd.Series(df.index).diff().tolist()[1:])

#Graph Limit
graphlim = 101

#Plot
plt.scatter(p, p_nach,
            edgecolors = 'none',
            c = p,
            s = 20,
            cmap=plt.cm.get_cmap('jet'))
plt.xlim(0,graphlim)
plt.ylim(0,graphlim)
plt.xticks(range(0,graphlim,int(graphlim/10)))
plt.yticks(range(0,graphlim,int(graphlim/10)))
plt.colorbar()
plt.grid(zorder = 0, alpha = 0.3)
ax.set_xlabel('p / mV')
ax.set_ylabel('p_nach / mV')

##plt.savefig(dpi = 300)
plt.show()
##plt.close()
##fig.clear()
##gc.collect()

print('Progress... done!')

As you can see, the colorbar does not represent the clustering and instead the place on the x-axis. How do I configure my colorbar to represent the amount of datapoints in an area?

Folder with files: Link

Duplicate of [How can I make a scatter plot colored by density in matplotlib?](https://stackoverflow.com/questions/20105364/how-can-i-make-a-scatter-plot-colored-by-density-in-matplotlib) — ImportanceOfBeingErnest, Jul 23 '19 at 01:17

Trenton McKinney · Answer 1 · 2019-07-25T09:56:46.943

import pandas as pd
import readTrc
import matplotlib.pyplot as plt
import numpy as np
import os
import gc

trcpath = 'filename.trc'
datX, datY, m = readTrc.readTrc(trcpath)

df = pd.DataFrame({'time': datX * 1000, 'volts': datY * 1000})

reduce_noise_df = df[df.volts >= 3.0]

d_t = reduce_noise_df.time.diff()[1:]

p = reduce_noise_df.volts[:-1]

p_nach = reduce_noise_df.volts[1:]

#Graph Limit
graphlim = 41

#Plot
fig, ax = plt.subplots(figsize=(6,6))
plt.scatter(p, p_nach,
            edgecolors = 'none',
            c = d_t,
            s = 20,
            cmap=plt.cm.get_cmap('jet'))
plt.xlim(0, graphlim)
plt.ylim(0, graphlim)
plt.xticks(range(0, graphlim, int(graphlim/10)))
plt.yticks(range(0, graphlim, int(graphlim/10)))
plt.colorbar()
plt.grid(zorder = 0, alpha = 0.3)
ax.set_xlabel('p / mV')
ax.set_ylabel('p_nach / mV')
plt.show()

I began be removing unnecessary code
The main issue was c = p instead of c = d_t.

Plot of waveform from your Le Croy WR640Zi colored by data density

import pandas as pd
import readTrc
import matplotlib.pyplot as plt
import numpy as np
import os
import gc
from scipy.stats import gaussian_kde

trcpath = 'filename.trc'
datX, datY, m = readTrc.readTrc(trcpath)

df = pd.DataFrame({'time': datX * 1000, 'volts': datY * 1000})

reduce_noise_df = df[df.volts >= 3.0]

y = np.array(reduce_noise_df.volts.tolist())
x = np.array(reduce_noise_df.time.tolist())

# Calculate point density
xy = np.vstack([x, y])
z = gaussian_kde(xy)(xy)

# Sort points by density
idx = z.argsort()
x, y, z = x[idx], y[idx], z[idx]

#Plot
fig, ax = plt.subplots(figsize=(6,6))
plt.scatter(x, y,
            edgecolors = 'none',
            c = z,
            s = 20,
            cmap=plt.cm.get_cmap('jet'))
plt.colorbar()
plt.grid(zorder = 0, alpha = 0.3)
ax.set_xlabel('Time (ms)')
ax.set_ylabel('Voltage (mV)')
plt.show()

Scatter plot colorbar based on datapoint cluster

1 Answers1