I'm creating a plot consisting of several subplots in matplotlib, like this one:
But for some reason, I get weird Zeros on the y-axis (actually on both sides of the plot):
They don't seem to be ticks, since the ax1.get_yaxis().set_ticks([]) statement does not affect them.
Any ideas why I get these and how I can get rid of them?
import matplotlib.pyplot as plt
from pylab import *
import numpy as np
subplots_adjust(hspace=0.000)
groups = ['01', '03', '05', '07']
for i in range(len(groups)):
x = np.linspace(0, 2*np.pi,400)
y = np.sin(x**2)
ax1 = subplot(len(groups),1,i+1)
ax1.scatter(x, y, s=20, c='b', marker='o')
plt.xlim(xmin=0,xmax=1)
ax1.get_yaxis().set_ticks([])
plt.show()
plt.close()
Thank you for any help!
These are just leftovers from the x ticks at 0.0 and 1.0:
import matplotlib.pyplot as plt
#from pylab import * # don't do it, btw
import numpy as np
groups = ['01' , '03', '05', '07']
fig = plt.figure()
ax = []
for i in range(len(groups)):
ax.append( fig.add_subplot( len(groups), 1, i+1 ) )
fig.subplots_adjust(hspace=0.000)
for i in range(len(groups)):
x = np.linspace(0, 2*np.pi,400)
y = np.sin(x**2)
ax[i] = plt.subplot(len(groups),1,i+1)
ax[i].scatter(x, y, s=20, c='b', marker='o')
ax[i].get_yaxis().set_ticks([])
ax[i].set_xlim([0.001,0.9999]) # <<<<========== here
plt.show()
Related
So this is my code, it's written a little messy and my result is absolutely ridiculous. I have no idea how to fix it.
Also, the seaborn library does not work on my computer in any way.
.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
data=pd.read_csv('Data.csv',encoding="latin1",sep=";",engine="python")
table = data.replace(0, 0.1)
plt.plot(table["RMDM"], table["BSURF"], color="#03012d", marker=".", ls="None", markersize=3, label="")
data['RMDM'] = data['RMDM'].astype(float)
data['BSURF'] = data['BSURF'].astype(float)
fig, ax = plt.subplots()
x=data['BSURF']
y=data['RMDM']
ax.set_yscale('log')
ax.set_xscale('log')
plt.style.use('classic')
plt.xlabel('B_LC')
plt.ylabel('RM/DM')
plt.plot(x,y, 'og')
from scipy.stats import linregress
df = data.loc[(data['RMDM'] >0) & (data['BSURF'] >0)]
stats = linregress(np.log10(df["RMDM"]),np.log10(df["BSURF"]))
m = stats.slope
b = stats.intercept
r = stats.rvalue
x = np.logspace(-1, 5, base=10)
y = (m*x+b)
plt.plot(x, y, c='orange', label="fit")
plt.legend()
#m,c=np.polyfit(x,y,1)
#plt.plot(x,m*x+c)
plt.grid()
plt.show()
lmplot can be used to create a linear line through your data. you correctly used np.log for the linear regression data. keep x in terms of the log.
df['log_col1']=np.log(df['col1'])
sns.lmplot(x='log_col1','y='target', data=df, ci=None)
sns.scatterplot(y='target',x='log_col1',data=df)
plt.show()
I am trying to create a heatmap displaying correlation coefficient values. I'm quite new at this, but the code below would annotate in multiple decimal places, whereas i'm trying to narrow down to 2 d.p.
Does anyone have experience with this?
import pandas_datareader.data as web
import pandas as pd
import datetime as dt
import csv
import matplotlib.pyplot as plt
from matplotlib import style
import numpy as np
import seaborn as sns
style.use('ggplot')
def visualize_data():
df = pd.read_csv('sti_joined.csv')
df.set_index('Date', inplace=True)
df_corr = df.pct_change().corr()
print(df_corr.head())
data = df_corr.values
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
# heatmap = ax.pcolor(data, cmap=plt.cm.get_cmap('RdYlGn'))
heatmap = ax.pcolor(data, cmap=plt.cm.RdYlGn)
fig.colorbar(heatmap)
ax.set_xticks(np.arange(data.shape[0]) + 0.5, minor=False)
ax.set_yticks(np.arange(data.shape[1]) + 0.5, minor=False)
ax.invert_yaxis()
ax.xaxis.tick_top()
for y in range(data.shape[0]):
for x in range(data.shape[1]):
plt.text(x + 0.5, y + 0.5, '%.4f' % data[y, x],
horizontalalignment='center',
verticalalignment='center',
)
column_labels = df_corr.columns
row_labels = df_corr.index
ax.set_xticklabels(column_labels)
ax.set_yticklabels(row_labels)
plt.xticks(rotation=90)
heatmap.set_clim(-1,1)
plt.tight_layout()
plt.show()
visualize_data()
Instead of '%.4f' % data[y, x], you can try using something like
'{0:.2f}'.format(data[y,x])
I would like to plot the same as shown in the picture( but only the red part). The curve is a kernel density estimate based only on the X-values (the y-values are irrelevant and actually all 1,2 or 3. It is here just plotted like this to distinguish between red an blue. I have plotted the scatterplot, but how can I include the kernel density curve on the scatterplot? (the black dotted lines in the curve are just the quartiles and the median).
import seaborn as sns; sns.set()
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib.ticker import MaxNLocator
import matplotlib.pyplot as plt
from scipy.stats import norm
from sklearn.neighbors import KernelDensity
%matplotlib inline
# Change plotting style to ggplot
plt.style.use('ggplot')
from matplotlib.font_manager import FontProperties
X_plot = np.linspace(0, 30, 1000)[:, np.newaxis]
X1 = df[df['Zustandsklasse']==1]['Verweildauer'].values.reshape(-1,1)
X2 = df[df['Zustandsklasse']==2]['Verweildauer'].values.reshape(-1,1)
X3 = df[df['Zustandsklasse']==3]['Verweildauer'].values.reshape(-1,1)
#print(X1)
ax=sns.scatterplot(x="Verweildauer", y="CS_bandwith", data=df, legend="full", alpha=1)
kde=KernelDensity(kernel='gaussian').fit(X1)
log_dens = kde.score_samples(X_plot)
ax.plot(X_plot[:,0], np.exp(log_dens), color ="blue", linestyle="-", label="Gaussian Kernel")
ax.yaxis.set_major_locator(MaxNLocator(integer=True))
ax.invert_yaxis()
plt.ylim(5.5, .5)
ax.set_ylabel("Zustandsklasse")
ax.set_xlabel("Verweildauer in Jahren")
handles, labels = ax.get_legend_handles_labels()
# create the legend again skipping this first entry
leg = ax.legend(handles[1:], labels[1:], loc="lower right", ncol=2, facecolor='silver', fontsize= 7)
ax.set_xticks(np.arange(0, 30, 5))
ax2 = ax.twinx()
#get the ticks at the same heights as the left axis
ax2.set_ylim(ax.get_ylim())
s=[(df["Zustandsklasse"] == t).sum() for t in range(1, 6)]
s.insert(0, 0)
print(s)
ax2.set_yticklabels(s)
ax2.set_ylim(ax.get_ylim())
ax2.set_ylabel("Anzahl Beobachtungen")
ax2.grid(False)
#plt.tight_layout()
plt.show()
Plotting target
Whats is plotted with the code above
It's much easier if you use subplots. Here is an example with seaborn's Titanic dataset:
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()
titanic = sns.load_dataset('titanic')
fig, ax = plt.subplots(nrows=3, sharex=True)
ax[2].set_xlabel('Age')
for i in [1, 2, 3]:
age_i = titanic[titanic['pclass'] == i]['age']
ax[i-1].scatter(age_i, [0] * len(age_i))
sns.kdeplot(age_i, ax=ax[i-1], shade=True, legend=False)
ax[i-1].set_yticks([])
ax[i-1].set_ylim(-0.01)
ax[i-1].set_ylabel('Class ' + str(i))
How can I adjust the whitespace between some subplots? In the example below, let's say I want to eliminate all whitespace between the 1st and 2nd subplots as well as between the 3rd and 4th and increase the space between the 2nd and 3rd?
import matplotlib.pyplot as plt
import numpy as np
# Simple data to display in various forms
x = np.linspace(0, 2 * np.pi, 400)
y = np.sin(x ** 2)
f, ax = plt.subplots(4,figsize=(10,10),sharex=True)
ax[0].plot(x, y)
ax[0].set_title('Panel: A')
ax[1].plot(x, y**2)
ax[2].plot(x, y**3)
ax[2].set_title('Panel: B')
ax[3].plot(x, y**4)
plt.tight_layout()
To keep the solution close to your code you may use create 5 subplots with the middle one being one forth in height of the others and remove that middle plot.
import matplotlib.pyplot as plt
import numpy as np
# Simple data to display in various forms
x = np.linspace(0, 2 * np.pi, 400)
y = np.sin(x ** 2)
f, ax = plt.subplots(5,figsize=(7,7),sharex=True,
gridspec_kw=dict(height_ratios=[4,4,1,4,4], hspace=0))
ax[0].plot(x, y)
ax[0].set_title('Panel: A')
ax[1].plot(x, y**2)
ax[2].remove()
ax[3].plot(x, y**3)
ax[3].set_title('Panel: B')
ax[4].plot(x, y**4)
plt.tight_layout()
plt.show()
You would need to use GridSpec to have different spaces between plots:
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
import numpy as np
# Simple data to display in various forms
x = np.linspace(0, 2 * np.pi, 400)
y = np.sin(x ** 2)
f = plt.figure(figsize=(10,10))
gs0 = gridspec.GridSpec(2, 1)
gs00 = gridspec.GridSpecFromSubplotSpec(2, 1, subplot_spec=gs0[0], hspace=0)
ax0 = f.add_subplot(gs00[0])
ax0.plot(x, y)
ax0.set_title('Panel: A')
ax1 = f.add_subplot(gs00[1], sharex=ax0)
ax1.plot(x, y**2)
gs01 = gridspec.GridSpecFromSubplotSpec(2, 1, subplot_spec=gs0[1], hspace=0)
ax2 = f.add_subplot(gs01[0])
ax2.plot(x, y**3)
ax2.set_title('Panel: B')
ax3 = f.add_subplot(gs01[1], sharex=ax0)
ax3.plot(x, y**4)
plt.show()
I plan to create a figure in matplotlib, with a 3D surface on the left and its corresponding contour map on the right.
I used subplots but it only show the contour map (with blank space for the surface), and a separate figure for the surface.
Is it possible to create these plots in one figure side-by side?
EDIT: The code is as follows:
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import axes3d
import numpy as np
x = np.arange(-5, 5, 0.25)
y = np.arange(-5, 5, 0.25)
x, y = np.meshgrid(x, y)
r = np.sqrt(x**2 + y**2)
z = np.sin(r)
fig, (surf, cmap) = plt.subplots(1, 2)
fig = plt.figure()
surf = fig.gca(projection='3d')
surf.plot_surface(x,y,z)
cmap.contourf(x,y,z,25)
plt.show()
I guess it's hard to use plt.subplots() in order to create a grid of plots with different projections.
So the most straight forward solution is to create each subplot individually with plt.subplot.
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import axes3d
import numpy as np
x = np.arange(-5, 5, 0.25)
y = np.arange(-5, 5, 0.25)
x, y = np.meshgrid(x, y)
r = np.sqrt(x**2 + y**2)
z = np.sin(r)
ax = plt.subplot(121, projection='3d')
ax.plot_surface(x,y,z)
ax2 = plt.subplot(122)
ax2.contourf(x,y,z,25)
plt.show()
Of course one may also use the gridspec capabilities for more sophisticated grid structures.