I have 5 txt files which contain data give me the effect of increasing heat on my samples and I want plot them in a vertical stacked graph, Where the final figure is 5 vertical stacked chart sharing the same X-axis and each line in a separate one to reveal the difference between them.
I wrote this code:
import glob
import pandas as pd
import matplotlib.axes._axes as axes
import matplotlib.pyplot as plt
input_files = glob.glob('01-input/RR_*.txt')
for file in input_files:
data = pd.read_csv(file, header=None, delimiter="\t").values
x = data[:,0]
y = data[:,1]
plt.subplot(2, 1, 1)
plt.plot(x, y, linewidth=2, linestyle=':')
plt.tight_layout()
plt.xlabel('x-axis')
plt.ylabel('y-axis')
But the result is only one graph containing all the lines:
I want to get the following chart:
import matplotlib.pyplot as plt
import numpy as np
# just a dummy data
x = np.linspace(0, 2700, 50)
all_data = [np.sin(x), np.cos(x), x**0.3, x**0.4, x**0.5]
n = len(all_data)
n_rows = n
n_cols = 1
fig, ax = plt.subplots(n_rows, n_cols) # each element in "ax" is a axes
for i, y in enumerate(all_data):
ax[i].plot(x, y, linewidth=2, linestyle=':')
ax[i].set_ylabel('y-axis')
# You can to use a list of y-labels. Example:
# my_labels = ['y1', 'y2', 'y3', 'y4', 'y5']
# ax[i].set_ylabel(my_labels[i])
# The "my_labels" lenght must be "n" too
plt.xlabel('x-axis') # add xlabel at last axes
plt.tight_layout()
Related
I have dataframe like this:
df_meshX_min_select = pd.DataFrame({
'Number of Elements' : [5674, 8810,13366,19751,36491],
'Time (a)' : [42.14, 51.14, 55.64, 55.14, 56.64],
'Different Result(Temperature)' : [0.083849, 0.057309, 0.055333, 0.060516, 0.035343]})
and I tried to combine bar plot (number of elements Vs Different result) and line plot (Number of elements Vs Time) in the same figure, but I found the following problem like this:
it seems that x_value doesn't match when combining 2 plots, but if you see the data frame, the x value is exactly the same value.
My expectation is combining these 2 plots into 1 figure:
and this is the code that I made:
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
df_meshX_min_select = pd.DataFrame({
'Number of Elements' : [5674, 8810,13366,19751,36491],
'Time (a)' : [42.14, 51.14, 55.64, 55.14, 56.64],
'Different Result(Temperature)' : [0.083849, 0.057309, 0.055333, 0.060516, 0.035343]})
x1= df_meshX_min_select["Number of Elements"]
t1= df_meshX_min_select["Time (a)"]
T1= df_meshX_min_select["Different Result(Temperature)"]
#Create combo chart
fig, ax1 = plt.subplots(figsize=(10,6))
color = 'tab:green'
#bar plot creation
ax1.set_title('Mesh Analysis', fontsize=16)
ax1.set_xlabel('Number of elements', fontsize=16)
ax1.set_ylabel('Different Result(Temperature)', fontsize=16)
ax1 = sns.barplot(x='Number of Elements', y='Different Result(Temperature)', data = df_meshX_min_select)
ax1.tick_params(axis='y')
#specify we want to share the same x-axis
ax2 = ax1.twinx()
color = 'tab:red'
#line plot creation
ax2.set_ylabel('Time (a)', fontsize=16)
ax2 = sns.lineplot(x='Number of Elements', y='Time (a)', data = df_meshX_min_select, sort=False, color=color, ax=ax2)
ax2.tick_params(axis='y', color=color)
#show plot
plt.show()
Anyone can help me, please?
Seaborn and pandas use a categorical x-axis for bar plots (internally numbered 0,1,2,...) and floating-point numbers for a line plot. Note that your x-values aren't evenly spaced, so either the bars would have weird distances between them, or wouldn't align with the x-values from the line plot.
Here is a solution using standard matplotlib to combine both graphs.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
df_meshx_min_select = pd.DataFrame({
'number of elements': [5674, 8810, 13366, 19751, 36491],
'time (a)': [42.14, 51.14, 55.64, 55.14, 56.64],
'different result(temperature)': [0.083849, 0.057309, 0.055333, 0.060516, 0.035343]})
x1 = df_meshx_min_select["number of elements"]
t1 = df_meshx_min_select["time (a)"]
d1 = df_meshx_min_select["different result(temperature)"]
fig, ax1 = plt.subplots(figsize=(10, 6))
color = 'limegreen'
ax1.set_title('mesh analysis', fontsize=16)
ax1.set_xlabel('number of elements', fontsize=16)
ax1.set_ylabel('different result(temperature)', fontsize=16, color=color)
ax1.bar(x1, height=d1, width=2000, color=color)
ax1.tick_params(axis='y', colors=color)
ax2 = ax1.twinx() # share the x-axis, new y-axis
color = 'crimson'
ax2.set_ylabel('time (a)', fontsize=16, color=color)
ax2.plot(x1, t1, color=color)
ax2.tick_params(axis='y', colors=color)
plt.show()
I was plotting a boxplot with a lineplot and I had the same problem even my two x-axes are identical, so I solved converting my x-axis feature to type string:
df_meshX_min_select['Number of Elements'] = df_meshX_min_select['Number of Elements'].astype('string')
This way the plot works using seaborn:
So currently learning how to import data and work with it in matplotlib and I am having trouble even tho I have the exact code from the book.
This is what the plot looks like, but my question is how can I get it where there is no white space between the start and the end of the x-axis.
Here is the code:
import csv
from matplotlib import pyplot as plt
from datetime import datetime
# Get dates and high temperatures from file.
filename = 'sitka_weather_07-2014.csv'
with open(filename) as f:
reader = csv.reader(f)
header_row = next(reader)
#for index, column_header in enumerate(header_row):
#print(index, column_header)
dates, highs = [], []
for row in reader:
current_date = datetime.strptime(row[0], "%Y-%m-%d")
dates.append(current_date)
high = int(row[1])
highs.append(high)
# Plot data.
fig = plt.figure(dpi=128, figsize=(10,6))
plt.plot(dates, highs, c='red')
# Format plot.
plt.title("Daily high temperatures, July 2014", fontsize=24)
plt.xlabel('', fontsize=16)
fig.autofmt_xdate()
plt.ylabel("Temperature (F)", fontsize=16)
plt.tick_params(axis='both', which='major', labelsize=16)
plt.show()
There is an automatic margin set at the edges, which ensures the data to be nicely fitting within the axis spines. In this case such a margin is probably desired on the y axis. By default it is set to 0.05 in units of axis span.
To set the margin to 0 on the x axis, use
plt.margins(x=0)
or
ax.margins(x=0)
depending on the context. Also see the documentation.
In case you want to get rid of the margin in the whole script, you can use
plt.rcParams['axes.xmargin'] = 0
at the beginning of your script (same for y of course). If you want to get rid of the margin entirely and forever, you might want to change the according line in the matplotlib rc file:
axes.xmargin : 0
axes.ymargin : 0
Example
import seaborn as sns
import matplotlib.pyplot as plt
tips = sns.load_dataset('tips')
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
tips.plot(ax=ax1, title='Default Margin')
tips.plot(ax=ax2, title='Margins: x=0')
ax2.margins(x=0)
Alternatively, use plt.xlim(..) or ax.set_xlim(..) to manually set the limits of the axes such that there is no white space left.
If you only want to remove the margin on one side but not the other, e.g. remove the margin from the right but not from the left, you can use set_xlim() on a matplotlib axes object.
import seaborn as sns
import matplotlib.pyplot as plt
import math
max_x_value = 100
x_values = [i for i in range (1, max_x_value + 1)]
y_values = [math.log(i) for i in x_values]
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
sn.lineplot(ax=ax1, x=x_values, y=y_values)
sn.lineplot(ax=ax2, x=x_values, y=y_values)
ax2.set_xlim(-5, max_x_value) # tune the -5 to your needs
I'm using seaborn in Python 3.5. Taking the example joy plot from the gallery, modified slightly to save the figure:
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
sns.set(style="white", rc={"axes.facecolor": (0, 0, 0, 0)})
# Create the data
rs = np.random.RandomState(1979)
x = rs.randn(500)
g = np.tile(list("ABCDEFGHIJ"), 50)
df = pd.DataFrame(dict(x=x, g=g))
m = df.g.map(ord)
df["x"] += m
# Initialize the FacetGrid object
pal = sns.cubehelix_palette(10, rot=-.25, light=.7)
g = sns.FacetGrid(df, row="g", hue="g", aspect=15, size=.5, palette=pal)
# Draw the densities in a few steps
g.map(sns.kdeplot, "x", clip_on=False, shade=True, alpha=1, lw=1.5, bw=.2)
g.map(sns.kdeplot, "x", clip_on=False, color="w", lw=2, bw=.2)
g.map(plt.axhline, y=0, lw=2, clip_on=False)
# Define and use a simple function to label the plot in axes coordinates
def label(x, color, label):
ax = plt.gca()
ax.text(0, .2, label, fontweight="bold", color=color,
ha="left", va="center", transform=ax.transAxes)
g.map(label, "x")
# Set the subplots to overlap
g.fig.subplots_adjust(hspace=-.25)
# Remove axes details that don't play will with overlap
g.set_titles("")
g.set(yticks=[])
g.despine(bottom=True, left=True)
plt.savefig('tmp.png')
There is a slight visual defect, namely the KDEs do not quite fill all the way to the top. This is most visible in rows B, G, H and J:
Any idea what's causing this?
Is there a way to specify in Seaborn or Matplotlib the color increments of heat-map color scale. For instance, for data-frame that contains normalized values between 0-1, to specify 100,discrete, color increments so each value is distinguished from other values?
Thank you in advance
There are two principle approaches to discetize a heatmap into n colors:
Supply the data rounded to the n values.
Use a discrete colormap.
The following code shows those two options.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
x, y = np.meshgrid(range(15),range(6))
v = np.random.rand(len(x.flatten()))
df = pd.DataFrame({"x":x.flatten(), "y":y.flatten(),"value":v})
df = df.pivot(index="y", columns="x", values="value")
n = 4.
fig, (ax0, ax, ax2) = plt.subplots(nrows=3)
### original
im0 = ax0.imshow(df.values, cmap="viridis", vmin=0, vmax=1)
ax0.set_title("original")
### Discretize array
arr = np.floor(df.values * n)/n
im = ax.imshow(arr, cmap="viridis", vmin=0, vmax=1)
ax.set_title("discretize values")
### Discretize colormap
cmap = plt.cm.get_cmap("viridis", n)
im2 = ax2.imshow(df.values, cmap=cmap, vmin=0, vmax=1 )
ax2.set_title("discretize colormap")
#colorbars
fig.colorbar(im0, ax=ax0)
fig.colorbar(im, ax=ax)
fig.colorbar(im2, ax=ax2, ticks=np.arange(0,1,1./n), )
plt.tight_layout()
plt.show()
With the following code I create four histograms:
import numpy as np
import pandas as pd
data = pd.DataFrame(np.random.normal((1, 2, 3 , 4), size=(100, 4)))
data.hist(bins=10)
I want the histograms to look like this:
I know how to make it one graph at the time, see here
But how can I do it for multiple histograms without specifying each single one? Ideally I could use 'pd.scatter_matrix'.
Plot each histogram seperately and do the fit to each histogram as in the example you linked or take a look at the hist api example here. Essentially what should be done is
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.mlab as mlab
fig = plt.figure()
ax1 = fig.add_subplot(221)
ax2 = fig.add_subplot(222)
ax3 = fig.add_subplot(223)
ax4 = fig.add_subplot(224)
for ax in [ax1, ax2, ax3, ax4]:
n, bins, patches = ax.hist(**your_data_here**, 50, normed=1, facecolor='green', alpha=0.75)
bincenters = 0.5*(bins[1:]+bins[:-1])
y = mlab.normpdf( bincenters, mu, sigma)
l = ax.plot(bincenters, y, 'r--', linewidth=1)
plt.show()