I am trying to change the range of my x-axis on my plot. The code for my plot looks like this:
dataset.plot(x='Date', y='Amount', label='Actual')
plt.plot(z, y_pred, label='Predicted')
plt.title('Graph')
plt.xlabel('Date')
plt.ylabel('Amount')
plt.xticks(x, x, rotation='90')
plt.legend()
plt.show()
My graph:
I am trying to stop the graph up till the last point on the orange line.
I have tried using:
axes = plt.gca()
axes.set_xlim([xmin,xmax])
But it creates an empty plot instead. Thank you!
I think in your plot you should be using: 'axes.set_xlim([min(z),max(z)])'.
import pandas as pd
import numpy as np
df_actual = pd.DataFrame(np.random.randint(0,20,size=(20, 1)), columns=['Amount'])
df_actual['Date'] = df.index
x_predicted = range(0,10)
y_predicted = np.random.uniform(0, 20, 10)
df_actual.plot(x='Date', y='Amount', label='Actual')
plt.plot(x_predicted, y_predicted, label='Predicted')
axes = plt.gca()
axes.set_xlim([min(x_predicted),max(x_predicted)])
Related
I'm using the following dummy code for generating a 3D plot.
import random
from matplotlib import pyplot as plt
random.seed(0)
D = [[random.random() for x in range(3)] for y in range(1000)]
df = pd.DataFrame(D,columns=['Feature_1','Feature_2','Feature_3'])
predictions = [random.randint(0,4) for x in range(1000)]
df['predictions'] = predictions
plt.rcParams["figure.figsize"]=(10,10)
plt.rcParams['legend.fontsize'] = 10
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure()
ax = Axes3D(fig)
ax.scatter(df['Feature_1'],df['Feature_2'],df['Feature_3'], c=df['predictions'], s =150,cmap='rainbow')
ax.legend(loc = 'upper left')
ax.set_xlabel('Feature_1',fontsize=20,labelpad=10)
ax.set_ylabel('Feature_2', fontsize=20, rotation=150,labelpad=10)
ax.set_zlabel('Feature_3', fontsize=20, rotation=60,labelpad=15)
plt.show()
I'm using as marker color the column predictions, and i would like for each element of that column to appear in the legend but it does not.
Here's a screenshot of the resulting plot
You forgot to put a label handle into the scatter function. If you replace your scatter call with the following line, a legend will show up:
ax.scatter(
df['Feature_1'], df['Feature_2'], df['Feature_3'],
c=df['predictions'], s=150, cmap='rainbow', label='Dummy data'
)
Or to show the predictions classes as labels:
scatter = ax.scatter(df['Feature_1'], df['Feature_2'], df['Feature_3'],
c=df['predictions'], s=150, cmap='rainbow')
legend1 = ax.legend(*scatter.legend_elements(),
loc="upper left", title="Classes")
ax.add_artist(legend1)
MWE:
I would like the title position same as in the graph :
Here is my code :
import matplotlib.pyplot as plt
import numpy as np
import random
fig, ax = plt.subplots()
x = random.sample(range(256),200)
y = random.sample(range(256),200)
cor=np.corrcoef(x,y)
plt.scatter(x,y, color='b', s=5, marker=".")
#plt.scatter(x,y, label='skitscat', color='b', s=5, marker=".")
ax.set_xlim(0,300)
ax.set_ylim(0,300)
plt.xlabel('x')
plt.ylabel('y')
plt.title('Correlation Coefficient: %f'%cor[0][1])
#plt.legend()
fig.savefig('plot.png', dpi=fig.dpi)
#plt.show()
But this gives :
How do I fix this title position?
assign two corresponded value to X and Y axis. notice! to have title inside graph, values should be in (0,1) interval. you can see a sample code here:
import matplotlib. pyplot as plt
A= [2,1,4,5]; B = [3,2,-2,1]
plt.scatter(A,B)
plt.title("title", x=0.9, y=0.9)
plt.xlabel("x-axis")
plt.ylabel("y-axis")
plt.show()
It will be unnecessarily complicated to move the title at some arbitrary position inside the axes.
Instead one would rather create a text at the desired position.
import matplotlib.pyplot as plt
import numpy as np
fig, ax = plt.subplots()
x = np.random.randint(256,size=200)
y = np.random.randint(256,size=200)
cor=np.corrcoef(x,y)
ax.scatter(x,y, color='b', s=5, marker=".")
ax.set_xlim(0,300)
ax.set_ylim(0,300)
ax.set_xlabel('x')
ax.set_ylabel('y')
ax.text(0.9, 0.9, 'Correlation Coefficient: %f'%cor[0][1],
transform=ax.transAxes, ha="right")
plt.show()
I've got a Pandas dataframe named clean which contains a column v for which I would like to draw a histogram and superimpose a density plot. I know I can plot one under the other this way:
import pandas as pd
import matplotlib.pyplot as plt
Maxv=200
plt.subplot(211)
plt.hist(clean['v'],bins=40, range=(0, Maxv), color='g')
plt.ylabel("Number")
plt.subplot(212)
ax=clean['v'].plot(kind='density')
ax.set_xlim(0, Maxv)
plt.xlabel("Orbital velocity (km/s)")
ax.get_yaxis().set_visible(False)
But when I try to superimpose, y scales doesn't match (and I loose y axis ticks and labels):
yhist, xhist, _hist = plt.hist(clean['v'],bins=40, range=(0, Maxv), color='g')
plt.ylabel("Number")
ax=clean['v'].plot(kind='density') #I would like to insert here a normalization to max(yhist)/max(ax)
ax.set_xlim(0, Maxv)
plt.xlabel("Orbital velocity (km/s)")
ax.get_yaxis().set_visible(False)
Some hint? (Additional question: how can I change the width of density smoothing?)
Based on your code, this should work:
ax = clean.v.plot(kind='hist', bins=40, normed=True)
clean.v.plot(kind='kde', ax=ax, secondary_y=True)
ax.set(xlim=[0, Maxv])
You might not even need the secondary_y anymore.
No I try this:
ax = clean.v.plot(kind='hist', bins=40, range=(0, Maxv))
clean.v.plot(kind='kde', ax=ax, secondary_y=True)
But the range part doesn't work, and ther's still the left y-axis problem
Seaborn makes this easy
import seaborn as sns
sns.distplot(df['numeric_column'],bins=25)
I have two graphs to where both have the same x-axis, but with different y-axis scalings.
The plot with regular axes is the data with a trend line depicting a decay while the y semi-log scaling depicts the accuracy of the fit.
fig1 = plt.figure(figsize=(15,6))
ax1 = fig1.add_subplot(111)
# Plot of the decay model
ax1.plot(FreqTime1,DecayCount1, '.', color='mediumaquamarine')
# Plot of the optimized fit
ax1.plot(x1, y1M, '-k', label='Fitting Function: $f(t) = %.3f e^{%.3f\t} \
%+.3f$' % (aR1,kR1,bR1))
ax1.set_xlabel('Time (sec)')
ax1.set_ylabel('Count')
ax1.set_title('Run 1 of Cesium-137 Decay')
# Allows me to change scales
# ax1.set_yscale('log')
ax1.legend(bbox_to_anchor=(1.0, 1.0), prop={'size':15}, fancybox=True, shadow=True)
Now, i'm trying to figure out to implement both close together like the examples supplied by this link
http://matplotlib.org/examples/pylab_examples/subplots_demo.html
In particular, this one
When looking at the code for the example, i'm a bit confused on how to implant 3 things:
1) Scaling the axes differently
2) Keeping the figure size the same for the exponential decay graph but having a the line graph have a smaller y size and same x size.
For example:
3) Keeping the label of the function to appear in just only the decay graph.
Any help would be most appreciated.
Look at the code and comments in it:
import matplotlib.pyplot as plt
import numpy as np
from matplotlib import gridspec
# Simple data to display in various forms
x = np.linspace(0, 2 * np.pi, 400)
y = np.sin(x ** 2)
fig = plt.figure()
# set height ratios for subplots
gs = gridspec.GridSpec(2, 1, height_ratios=[2, 1])
# the first subplot
ax0 = plt.subplot(gs[0])
# log scale for axis Y of the first subplot
ax0.set_yscale("log")
line0, = ax0.plot(x, y, color='r')
# the second subplot
# shared axis X
ax1 = plt.subplot(gs[1], sharex = ax0)
line1, = ax1.plot(x, y, color='b', linestyle='--')
plt.setp(ax0.get_xticklabels(), visible=False)
# remove last tick label for the second subplot
yticks = ax1.yaxis.get_major_ticks()
yticks[-1].label1.set_visible(False)
# put legend on first subplot
ax0.legend((line0, line1), ('red line', 'blue line'), loc='lower left')
# remove vertical gap between subplots
plt.subplots_adjust(hspace=.0)
plt.show()
Here is my solution:
import numpy as np
import matplotlib.pyplot as plt
x = np.linspace(0, 2 * np.pi, 400)
y = np.sin(x ** 2)
fig, (ax1,ax2) = plt.subplots(nrows=2, sharex=True, subplot_kw=dict(frameon=False)) # frameon=False removes frames
plt.subplots_adjust(hspace=.0)
ax1.grid()
ax2.grid()
ax1.plot(x, y, color='r')
ax2.plot(x, y, color='b', linestyle='--')
One more option is seaborn.FacetGrid but this requires Seaborn and Pandas libraries.
Here are some adaptions to show how the code could work to add a combined legend when plotting a pandas dataframe. ax=ax0 can be used to plot on a given ax and ax0.get_legend_handles_labels() gets the information for the legend.
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
dates = pd.date_range('20210101', periods=100, freq='D')
df0 = pd.DataFrame({'x': np.random.normal(0.1, 1, 100).cumsum(),
'y': np.random.normal(0.3, 1, 100).cumsum()}, index=dates)
df1 = pd.DataFrame({'z': np.random.normal(0.2, 1, 100).cumsum()}, index=dates)
fig, (ax0, ax1) = plt.subplots(nrows=2, sharex=True, gridspec_kw={'height_ratios': [2, 1], 'hspace': 0})
df0.plot(ax=ax0, color=['dodgerblue', 'crimson'], legend=False)
df1.plot(ax=ax1, color='limegreen', legend=False)
# put legend on first subplot
handles0, labels0 = ax0.get_legend_handles_labels()
handles1, labels1 = ax1.get_legend_handles_labels()
ax0.legend(handles=handles0 + handles1, labels=labels0 + labels1)
# remove last tick label for the second subplot
yticks = ax1.get_yticklabels()
yticks[-1].set_visible(False)
plt.tight_layout()
plt.show()
In my code, I take the logarithm of two data series and plot them. I would like to change each tick value of the x-axis by raising it to the power of e (anti-log of natural logarithm).
In other words. I want to graph the logarithms of both series but have x-axis in levels.
Here is the code that I'm using.
from pylab import scatter
import pylab
import matplotlib.pyplot as plt
import pandas as pd
from pandas import Series, DataFrame
import numpy as np
file_name = '/Users/joedanger/Desktop/Python/scatter_python.csv'
data = DataFrame(pd.read_csv(file_name))
y = np.log(data['o_value'], dtype='float64')
x = np.log(data['time_diff_day'], dtype='float64')
fig = plt.figure()
plt.scatter(x, y, c='blue', alpha=0.05, edgecolors='none')
fig.suptitle('test title', fontsize=20)
plt.xlabel('time_diff_day', fontsize=18)
plt.ylabel('o_value', fontsize=16)
plt.xticks([-8,-7,-6,-5,-4,-3,-2,-1,0,1,2,3,4])
plt.grid(True)
pylab.show()
let matplotlib take the log for you:
fig = plt.figure()
ax = plt.gca()
ax.scatter(data['o_value'] ,data['time_diff_day'] , c='blue', alpha=0.05, edgecolors='none')
ax.set_yscale('log')
ax.set_xscale('log')
If you are using all the same size and color markers, it is faster to use plot
fig = plt.figure()
ax = plt.gca()
ax.plot(data['o_value'] ,data['time_diff_day'], 'o', c='blue', alpha=0.05, markeredgecolor='none')
ax.set_yscale('log')
ax.set_xscale('log')
The accepted answer is a bit out of date. At least pandas 0.25 natively supports log axes:
# logarithmic X
df.plot.scatter(..., logx=True)
# logarithmic Y
df.plot.scatter(..., logy=True)
# both
df.plot.scatter(..., loglog=True)