I'm building a visualization with Python.
There I'd like to visualize fuel stops and the fuel costs of my car. Furthermore, car washes and their costs should be visualized as well as repairs. The fuel costs and laundry costs should have a higher bar depending on the costs. I created the visualization below to describe the concepts.
How to create such a visualization with matplotlib?
This is the visualization being built:
Yes, this kind of visualization is perfectly possible with matplotlib. To store the data, numpy arrays are usually very handy.
Here is some code to get you started:
import matplotlib.pyplot as plt
import numpy as np
refuel_km = np.array([0, 505.4, 1070, 1690])
refuel_cost = np.array([40.1, 50, 63, 55])
carwash_km = np.array([302.0, 605.4, 901, 1331, 1788.2])
carwash_cost = np.array([35.0, 40.0, 35.0, 35.0, 35.0])
repair_km = np.array([788.0, 1605.4])
repair_cost = np.array([135.0, 74.5])
fig, ax = plt.subplots(figsize=(12,3))
plt.scatter(refuel_km, np.full_like(refuel_km, 0), marker='o', s=100, color='lime', edgecolors='black', zorder=3, label='refuel')
plt.bar(refuel_km, refuel_cost, bottom=15, color='lime', ec='black', width=20, label='refuel cost')
plt.scatter(carwash_km, np.full_like(carwash_km, 0), marker='d', s=100, color='tomato', edgecolors='black', zorder=3, label='car wash')
plt.bar(carwash_km, -carwash_cost, bottom=-15, color='tomato', ec='black', width=20, label='car wash cost')
plt.scatter(repair_km, np.full_like(repair_km, 0), marker='^', s=100, color='lightblue', edgecolors='black', zorder=3, label='car repair')
#plt.bar(repair_km, -repair_cost, bottom=-15, color='lightblue', ec='black', width=20)
ax.spines['bottom'].set_position('zero')
ax.spines['top'].set_color('none')
ax.spines['right'].set_color('none')
ax.spines['left'].set_color('none')
ax.tick_params(axis='x', length=20)
ax.set_yticks([]) # turn off the yticks
_, xmax = ax.get_xlim()
ymin, ymax = ax.get_ylim()
ax.set_xlim(-15, xmax)
ax.set_ylim(ymin, ymax+25) # make room for the legend
ax.text(xmax, -5, "km", ha='right', va='top', size=14)
plt.legend(ncol=5, loc='upper left')
plt.tight_layout()
plt.show()
Related
please see the result graph image below.
I wish to remove only one major grid line at y-axis value of 10 (Blue horizontal line), and keep all other grid lines.
Is there a way to do that?
plt.rcParams['font.family'] = 'Arial'
fig, ax = plt.subplots(figsize=(14.78, 9.84))
plt.xlim(0, 105)
plt.ylim(0, 10)
ax.xaxis.set_minor_locator(AutoMinorLocator(2))
ax.yaxis.set_minor_locator(AutoMinorLocator(2))
ax.spines['bottom'].set_linewidth(1.5)
ax.spines['left'].set_linewidth(1.5)
ax.spines['top'].set_linewidth(0)
ax.spines['right'].set_linewidth(0)
# Grid setting
plt.grid(True, color='#0100FF', which="major", ls="-")
plt.grid(True, color='#0BC904', which="minor", ls="-")
plt.xlabel("Indicator Amplitude, %FSH", fontsize=28, labelpad=15)
plt.ylabel("Function Generator Output, V", fontsize=28, labelpad=15)
# Axis setting
plt.tick_params(which="major", labelsize=22, length=10, pad=10, width=1.5)
plt.tick_params(which="minor", length=8, width=1.5)
# Plot scatter & line
plt.plot(FSH_axis, x_value[2:], color='black', marker='^', linewidth=1.5, markersize=8, label="40 dB")
plt.plot(FSH_axis, y_value[2:], color='red', marker='o', linewidth=1.5, markersize=8, label="60 dB")
plt.plot(FSH_axis, z_value[2:], color='blue', marker='v', linewidth=1.5, markersize=8, label="80 dB")
plt.legend(loc=(1 / 16, 58 / 90), ncol=1, fontsize=20, frameon=True, framealpha=1, edgecolor="black")
plt.show()
We can catch all gridlines with get_ygridlines(), then access individual gridlines as Line2D objects to modify them:
from matplotlib import pyplot as plt
from matplotlib.ticker import AutoMinorLocator
plt.rcParams['font.family'] = 'Arial'
fig, ax = plt.subplots(figsize=(14.78, 9.84))
plt.xlim(0, 105)
plt.ylim(0, 10)
ax.xaxis.set_minor_locator(AutoMinorLocator(2))
ax.yaxis.set_minor_locator(AutoMinorLocator(2))
ax.spines['bottom'].set_linewidth(1.5)
ax.spines['left'].set_linewidth(1.5)
ax.spines['top'].set_linewidth(0)
ax.spines['right'].set_linewidth(0)
# Grid setting
plt.grid(True, color='#0100FF', which="major", ls="-")
plt.grid(True, color='#0BC904', which="minor", ls="-")
#this part is added
#set the last horizontal gridline invisible
ygridlines = ax.get_ygridlines()
gridline_of_interest = ygridlines[-1]
gridline_of_interest.set_visible(False)
plt.xlabel("Indicator Amplitude, %FSH", fontsize=28, labelpad=15)
plt.ylabel("Function Generator Output, V", fontsize=28, labelpad=15)
# Axis setting
plt.tick_params(which="major", labelsize=22, length=10, pad=10, width=1.5)
plt.tick_params(which="minor", length=8, width=1.5)
# Plot scatter & line
FSH_axis = [10, 40, 100]
plt.plot(FSH_axis, [1, 3, 2], color='black', marker='^', linewidth=1.5, markersize=8, label="40 dB")
plt.plot(FSH_axis, [2, 2, 3], color='red', marker='o', linewidth=1.5, markersize=8, label="60 dB")
plt.plot(FSH_axis, [2, 1, 1], color='blue', marker='v', linewidth=1.5, markersize=8, label="80 dB")
plt.legend(loc=(1 / 16, 58 / 90), ncol=1, fontsize=20, frameon=True, framealpha=1, edgecolor="black")
plt.show()
Sample output:
Of course, the corresponding get_xgridlines() also exists.
I Darw a graph with mutliple axix, have several questios:
why the left y-axsis is not satrting from zero. (I mean the zero point
is not at the begining of the y-axix).
I only want major grid for the x-axis (a major grid line for each week) but the code add a mjor
grid for the y-axix also.
How can i add minor grid for y-axix (the red one (ax2))
i want to change the color for the x-axis labels (Dates) color to black
import matplotlib.pyplot as plt
Hits= pd.read_excel("stackoverflow_example.xlsx", sheet_name="data")
fig=plt.figure(figsize=(20,10))
ax=fig.add_subplot(111, label="1")
ax2=fig.add_subplot(111, label="2", frame_on=False)
ax.bar(Hits['Date'], Hits['Total'], width=0.35, color="b" )
ax.set_ylabel('Hits', color="b",size=16)
ax.yaxis.set_label_position('right')
ax.tick_params(axis='y', colors="b")
ax.tick_params(axis='x', colors="b", rotation=45)
ax.yaxis.tick_right()
ax2.plot(Hits['weeks'], Hits['Cases'], linewidth= 3.5, color="Red")
ax2.set_ylabel("Cases", color="Red",size=16)
ax2.tick_params(axis='y', colors="Red", size=16)
ax2.xaxis.set_ticks_position('top')
major_ticks = np.arange(0, 10, 1)
ax.set_xticks(major_ticks)
ax.grid(which='major', alpha=0.5)
plt.show()
My data
[
Graph:
If you want to start from zero, you can do that with 'ax2.set_ylim()'. After that, you can specify the axes for the grid. If the color is black, you can set color='k'.
import matplotlib.pyplot as plt
fig=plt.figure(figsize=(20,10))
ax=fig.add_subplot(111, label="1")
ax2=fig.add_subplot(111, label="2", frame_on=False)
ax.bar(Hits['Date'], Hits['Total'], width=0.35, color="b" )
ax.set_ylabel('Hits', color="b",size=16)
ax.yaxis.set_label_position('right')
ax.tick_params(axis='y', colors="b")
ax.tick_params(axis='x', colors="k", rotation=45)
ax.yaxis.tick_right()
ax2.plot(Hits['weeks'], Hits['Cases'], linewidth= 3.5, color="Red")
ax2.set_ylabel("Cases", color="Red",size=16)
ax2.tick_params(axis='y', colors="Red", size=16)
ax2.xaxis.set_ticks_position('top')
ax2.set_ylim(0,62) # update
major_ticks = np.arange(0, 10, 1)
ax.set_xticks(major_ticks)
ax.grid(which='major', axis='x', alpha=0.5) #update
ax2.grid(which='major', axis='y', alpha=0.5) # update
plt.show()
I have tried a number of different things to fix my chart, from zorder on the plots to plt.rcParams.
I feel that this is such a simple problem but I just dont know where I have gone wrong. As you can see the bottom annotation in cyan blue is unreadable and mashed with the y label.
Ideally, the annotation sits over the y label to a point where text inside annotation is readable.
If possible just for the annotation to sit on top and still overlay the y label..something like this
Any help on this would be greatly appreciated.
ax = df.plot(x=df.columns[0], y=df.columns[1], legend=False, zorder=0, linewidth=1)
y1 =df.loc[:, df.columns[2]].tail(1)
y2= df.loc[:, df.columns[1]].tail(1)
colors = plt.rcParams["axes.prop_cycle"].by_key()["color"]
print(colors)
for var in (y1, y2):
plt.annotate('%0.2f' % var.max(), xy=(1, var.max()), zorder=1, xytext=(8, 0),
xycoords=('axes fraction', 'data'),
textcoords='offset points',
bbox=dict(boxstyle="round", fc=colors[0], ec=colors[0],))
ax2 = ax.twinx()
df.plot(x=df.columns[0], y=df.columns[2], ax=ax2, legend=False, color='#fa8174', zorder=0,linewidth=1)
ax.figure.legend(prop=subtitle_font)
ax.grid(True, color="white",alpha=0.2)
pack = [df.columns[1], df.columns[2], freq[0]]
plt.text(0.01, 0.95,'{0} v {1} - ({2})'.format(df.columns[1], df.columns[2], freq[0]),
horizontalalignment='left',
verticalalignment='center',
transform = ax.transAxes,
zorder=10,
fontproperties=subtitle_font)
ax.text(0.01,0.02,"Sources: FRED, Quandl, #Paul92s",
color="white",fontsize=10,
horizontalalignment='left',
transform = ax.transAxes,
verticalalignment='center',
zorder=20,
fontproperties=subtitle_font)
ax.xaxis.set_major_locator(matplotlib.dates.YearLocator())
ax.xaxis.set_minor_locator(matplotlib.dates.MonthLocator((4,7,10)))
ax.xaxis.set_major_formatter(matplotlib.dates.DateFormatter("%Y"))
ax.xaxis.set_minor_formatter(ticker.NullFormatter()) # matplotlib.dates.DateFormatter("%m")
plt.setp(ax.get_xticklabels(), rotation=0, ha="center", zorder=-1)
plt.setp(ax2.get_yticklabels(), rotation=0, zorder=-1)
plt.setp(ax.get_yticklabels(), rotation=0, zorder=-1)
plt.gcf().set_size_inches(14,7)
ax.set_xlabel('Data as of; {0}'.format(df['Date'].max().strftime("%B %d, %Y")), fontproperties=subtitle_font)
y1 =df.loc[:, df.columns[2]].tail(1)
y2= df.loc[:, df.columns[1]].tail(1)
for var in (y1, y2):
plt.annotate('%0.2f' % var.max(), xy=(1, var.max()), zorder=1,xytext=(8, 0),
xycoords=('axes fraction', 'data'),
textcoords='offset points',
bbox=dict(boxstyle="round", fc="#fa8174", ec="#fa8174"))
plt.title('{0}'.format("FRED Velocity of M2 Money Stock v Trade Weighted U.S. Dollar Index: Broad"),fontproperties=heading_font)
ax.texts.append(ax.texts.pop())
ax.set_facecolor('#181818')
ax.figure.set_facecolor('#181818')
plt.rcParams['axes.axisbelow'] = True
I don't figure out why zorder doesn't work, but you can directly set the label style of tick labels:
import matplotlib.pyplot as plt
import numpy as np
from numpy.random import rand
import matplotlib.patches as mpatches
fig, ax = plt.subplots(1, 1)
ax.plot(rand(100), '^', color='r')
for label in ax.get_xticklabels():
label.set_bbox(dict(facecolor='orange'))
ax1 = ax.twinx()
ax1.plot(rand(100), 'o', color='b')
index_to_add_bbox = [2, 4]
ax1_labels = ax1.get_yticklabels()
for i in index_to_add_bbox:
ax1_labels[i].set_bbox(dict(boxstyle='Circle', facecolor='orange'))
plt.show()
I have two plots in Matplotlib that I would like to merge. They have different axes and scales. Here is the code for each of them.
Electrical Power Plot:
#Case Study: Curtailment
from matplotlib import pyplot as plt
%matplotlib inline
load = [0, 250, 250, 250, 250, 250, 665, 2500, 2500, 2500, 2500, 2500,0,2500, 2366, 250, 250, 373, 2500,0, 2500, 0, 2500,250, 0]
hours = list(range(25)) # [0, 1, 2, ... 22, 23, 24]
labels = [f'{h:02d}:00' for h in hours] # ["00:00", "01:00", ... "23:00", "24:00"]
fig = plt.figure(linewidth=1, figsize=(9, 5))
ax = plt.gca()
ax.plot(hours, load, color="goldenrod",drawstyle="steps-post", linewidth=3) # <- drawstyle argument.
ax.set_xlabel("Time of day", fontsize=14, labelpad=8)
ax.set_ylabel("Electrical power in W", fontsize=14, labelpad=8)
ax.set_xlim(0, 24)
ax.set_ylim(0, 3000)
plt.xticks(hours, labels=labels, rotation=90)
plt.grid(axis='y', alpha=.4)
ax.tick_params(axis='both', which='major', labelsize=14)
# (Optional) ax.legend(loc='center left', bbox_to_anchor=(0.03, 1.15), fontsize = 14, ncol=3)
plt.tight_layout() # This must be called last, after all elements (plot and legend) are ready.
plt.savefig('CS_Curtailment_ElectricalLoad.png', edgecolor='black', dpi=400, bbox_inches='tight')
plt.show()
Temperature Plot:
#Case Study: Curtailment
from matplotlib import pyplot as plt
%matplotlib inline
temperature = [
21.00,
21.02,
20.96,
20.85,
20.68,
20.46,
20.40,
20.56,
20.77,
21.06,
21.41,
21.79,
21.10,
21.57,
22.00,
21.47,
20.92,
20.46,
20.92,
20.31,
20.77,
20.35,
20.90,
21.00,
21.00
]
hours = list(range(25)) # [0, 1, 2, ... 22, 23, 24]
labels = [f'{h:02d}:00' for h in hours] # ["00:00", "01:00", ... "23:00", "24:00"]
fig = plt.figure(linewidth=1, figsize=(9, 5))
ax = plt.gca()
ax.plot(hours, temperature, color="red", linewidth=3) # <- drawstyle argument.
ax.set_xlabel("Time of day", fontsize=14, labelpad=8)
ax.set_ylabel("Temperature in °C", fontsize=14, labelpad=8)
ax.set_xlim(0, 24)
ax.set_ylim(20, 22.5)
plt.xticks(hours, labels=labels, rotation=90)
plt.grid(axis='y', alpha=.4)
ax.tick_params(axis='both', which='major', labelsize=14)
# (Optional) ax.legend(loc='center left', bbox_to_anchor=(0.03, 1.15), fontsize = 14, ncol=3)
plt.tight_layout() # This must be called last, after all elements (plot and legend) are ready.
plt.savefig('CS_Curtailment_Temperature.png', edgecolor='black', dpi=400, bbox_inches='tight')
plt.show()
I would like to have the electrical power axis on the left (first plot) and the temperature axis on the right (second plot). Of course the two plots have similar x-axis values.
Can you do this with Matplotlib?
I'd appreciate every comment.
Yes this can be done in matplotlib to do so, first generate the first ax (electrical power) and then instantiate the second axes
ax.plot(hours, load, color="goldenrod",drawstyle="steps-post", linewidth=3)
# ...
#generate the second instance
ax2 = ax.twinx()
ax2.plot(hours, temperature, color="red", linewidth=3)
# ... set additional configuration for ax2
Both axes will share the same x-axes and the same fig, so make sure that before showing the plot to tight the layout, otherwise y-label might be clipped.
fig.tight_layout()
plt.show()
EDIT:
To handle both axes at the same time, you need to use the figure object, so use it to save them to a png and set the legend. legend() method need to receive the labels which you can set manually of on each ax.plot( ..., label='<label>')
get the current figure before plt.show()
Set the legend using the figure object.
Save the image using the figure object.
Show the image.
The code:
fig = plt.gcf()
fig.legend(loc='center left', bbox_to_anchor=(0.15, 1.07), fontsize=14, ncol=3)
fig.savefig('CS_Curtailment_CombinedDiagram.png',
edgecolor='black', dpi=400, bbox_inches='tight')
plt.show()
How do we draw an average line (horizontal) for a histogram in using matplotlib?
Right now, I'm able to draw the histogram without any issues.
Here is the code I'm using:
## necessary variables
ind = np.arange(N) # the x locations for the groups
width = 0.2 # the width of the bars
plt.tick_params(axis='both', which='major', labelsize=30)
plt.tick_params(axis='both', which='minor', labelsize=30)
ax2 = ax.twinx()
## the bars
rects1 = ax.bar(ind, PAAE1, width,
color='0.2',
error_kw=dict(elinewidth=2,ecolor='red'),
label='PAAE1')
rects2 = ax.bar(ind+width, PAAE2, width,
color='0.3',
error_kw=dict(elinewidth=2,ecolor='black'),
label='PAAE2')
rects3 = ax2.bar(ind+width+width, AAE1, width,
color='0.4',
error_kw=dict(elinewidth=2,ecolor='red'),
label='AAE1')
rects4 = ax2.bar(ind+3*width, AAE2, width,
color='0.5',
error_kw=dict(elinewidth=2,ecolor='black'),
label='AAE3')
maxi = max(dataset[2])
maxi1 = max(dataset[4])
f_max = max(maxi, maxi1)
lns = [rects1,rects2,rects3,rects4]
labs = [l.get_label() for l in lns]
ax.legend(lns, labs, loc='upper center', ncol=4)
# axes and labels
ax.set_xlim(-width,len(ind)+width)
ax.set_ylim(0, 100)
ax.set_ylabel('PAAE', fontsize=25)
ax2.set_ylim(0, f_max+500)
ax2.set_ylabel('AAE (mW)', fontsize=25)
xTickMarks = dataset[0]
ax.set_xticks(ind+width)
xtickNames = ax.set_xticklabels(xTickMarks)
plt.setp(xtickNames, rotation=90, fontsize=25)
I want to plot the average line for PAAE 1, 2 and AAE 1, 2.
What should I be using to plot the average line?
If you'd like a vertical line to denote the mean use axvline(x_value). This will place a vertical line that always spans the full (or specified fraction of) y-axis. There's also axhline for horizontal lines.
In other works, you might have something like this:
ax.axvline(data1.mean(), color='blue', linewidth=2)
ax.axvline(data2.mean(), color='green', linewidth=2)
As a more complete, but unnecessarily complex example (most of this is nicely annotating the means with curved arrows):
import numpy as np
import matplotlib.pyplot as plt
data1 = np.random.normal(0, 1, 1000)
data2 = np.random.normal(-2, 1.5, 1000)
fig, ax = plt.subplots()
bins = np.linspace(-10, 5, 50)
ax.hist(data1, bins=bins, color='blue', label='Dataset 1',
alpha=0.5, histtype='stepfilled')
ax.hist(data2, bins=bins, color='green', label='Dataset 2',
alpha=0.5, histtype='stepfilled')
ax.axvline(data1.mean(), color='blue', linewidth=2)
ax.axvline(data2.mean(), color='green', linewidth=2)
# Add arrows annotating the means:
for dat, xoff in zip([data1, data2], [15, -15]):
x0 = dat.mean()
align = 'left' if xoff > 0 else 'right'
ax.annotate('Mean: {:0.2f}'.format(x0), xy=(x0, 1), xytext=(xoff, 15),
xycoords=('data', 'axes fraction'), textcoords='offset points',
horizontalalignment=align, verticalalignment='center',
arrowprops=dict(arrowstyle='-|>', fc='black', shrinkA=0, shrinkB=0,
connectionstyle='angle,angleA=0,angleB=90,rad=10'),
)
ax.legend(loc='upper left')
ax.margins(0.05)
plt.show()