Related
I try to produce a plot and want to automatically add text (in this case is percentage) to each circle in correspond to each y axis types. Any help would be very helpful.
# import libraries
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
# Make some data
index=['Stream flow',
'Soil moisture',
'Water indices',
'Others',
'Temperature',
'Precipitation',
'Vegetative indices']
value=[2.13, 6.38, 10.64, 12.77, 17.73, 21.99, 28.37]
# create dataframe
percentages = pd.Series(value,index=index)
df = pd.DataFrame({'percentage' : percentages})
df = df.sort_values(by='percentage')
# we first need a numeric placeholder for the y axis
my_range=list(range(1,len(df.index)+1))
fig, ax = plt.subplots(figsize=(15,8))
# create for each expense type an horizontal line that starts at x = 0 with the length
plt.hlines(y=my_range, xmin=0, xmax=df['percentage']-0.5, color='black', alpha=0.8, linewidth=1)
# create for each expense type a dot at the level of the expense percentage value
line=plt.plot(df['percentage'], my_range, "o", markersize=30, color='#fd8c00', alpha=0.6, linewidth=0.3)
# set labels
ax.set_xlabel('Percentage', fontsize=15)
ax.set_ylabel('')
# set axis
ax.tick_params(axis='both', which='major', labelsize=14)
plt.yticks(my_range, df.index)
ax.set_xlim(0,30)
You can use matplotlib.axes.Axes.text:
x_space = 0.4
y_space = 0.05
fontsize = 7
for y_i, val in enumerate(value, 1):
ax.text(x = val - x_space, y = y_i - y_space, s = f'{val}%', fontsize = fontsize)
You have to adjust x_space, y_space and fontsize in order to fit properly the text within the circles.
Complete code
# import libraries
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
# Make some data
index=['Stream flow',
'Soil moisture',
'Water indices',
'Others',
'Temperature',
'Precipitation',
'Vegetative indices']
value=[2.13, 6.38, 10.64, 12.77, 17.73, 21.99, 28.37]
# create dataframe
percentages = pd.Series(value,index=index)
df = pd.DataFrame({'percentage' : percentages})
df = df.sort_values(by='percentage')
# we first need a numeric placeholder for the y axis
my_range=list(range(1,len(df.index)+1))
fig, ax = plt.subplots(figsize=(15,8))
# create for each expense type an horizontal line that starts at x = 0 with the length
plt.hlines(y=my_range, xmin=0, xmax=df['percentage']-0.5, color='black', alpha=0.8, linewidth=1)
# create for each expense type a dot at the level of the expense percentage value
line=plt.plot(df['percentage'], my_range, "o", markersize=30, color='#fd8c00', alpha=0.6, linewidth=0.3)
# set labels
ax.set_xlabel('Percentage', fontsize=15)
ax.set_ylabel('')
# set axis
ax.tick_params(axis='both', which='major', labelsize=14)
plt.yticks(my_range, df.index)
ax.set_xlim(0,30)
x_space = 0.4
y_space = 0.05
for y_i, val in enumerate(value, 1):
ax.text(x = val - x_space, y = y_i - y_space, s = f'{val:>5.2f}%', fontsize = 7)
plt.show()
Same code as above, but with increased circle radius and font, in order to improve readability.
# import libraries
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
# Make some data
index=['Stream flow',
'Soil moisture',
'Water indices',
'Others',
'Temperature',
'Precipitation',
'Vegetative indices']
value=[2.13, 6.38, 10.64, 12.77, 17.73, 21.99, 28.37]
# create dataframe
percentages = pd.Series(value,index=index)
df = pd.DataFrame({'percentage' : percentages})
df = df.sort_values(by='percentage')
# we first need a numeric placeholder for the y axis
my_range=list(range(1,len(df.index)+1))
fig, ax = plt.subplots(figsize=(15,8))
# create for each expense type an horizontal line that starts at x = 0 with the length
plt.hlines(y=my_range, xmin=0, xmax=df['percentage']-0.85, color='black', alpha=0.8, linewidth=1)
# create for each expense type a dot at the level of the expense percentage value
line=plt.plot(df['percentage'], my_range, "o", markersize=50, color='#fd8c00', alpha=0.6, linewidth=0.3)
# set labels
ax.set_xlabel('Percentage', fontsize=15)
ax.set_ylabel('')
# set axis
ax.tick_params(axis='both', which='major', labelsize=14)
plt.yticks(my_range, df.index)
ax.set_xlim(0,30)
ax.set_ylim(0, len(value) + 1)
x_space = 0.75
y_space = 0.06
fontsize = 12
for y_i, val in enumerate(value, 1):
ax.text(x = val - x_space, y = y_i - y_space, s = f'{val:>5.2f}%', fontsize = fontsize)
plt.show()
Even better, you can use matplotlib.axes.Axes.annotate to get rid of x_space and y_space:
fontsize = 12
for y_i, x_i in enumerate(value, 1):
ax.annotate(f'{x_i:>5.2f}%', xy = (x_i, y_i), xytext = (0, 0), textcoords = 'offset points', ha = 'center', va = 'center', fontsize = fontsize)
You still have to adjust the fontsize to properly fit the radius of the circles.
I'm using this code to plot my data in boxplot:
import matplotlib.pyplot as plt
import numpy as np
from matplotlib.patches import Polygon
random_dists = ['Overlap', 'Non overlap', ]
Overlap= [6,6,5,1,3,4,4,3]
non_overlap= [1,2,6,6,1,3,3,3,3,3,5,2,2]
data = [
Overlap,
non_overlap
]
fig, ax1 = plt.subplots(figsize=(6, 6))
fig.canvas.set_window_title('A Boxplot Example')
fig.subplots_adjust(left=0.075, right=0.95, top=0.9, bottom=0.25)
# bp = ax1.boxplot(data, notch=0, sym='+', vert=1, whis=1.5)
bp = ax1.boxplot(data)
plt.setp(bp['boxes'], color='black')
plt.setp(bp['whiskers'], color='black')
plt.setp(bp['fliers'], color='red', marker='+')
# Add a horizontal grid to the plot, but make it very light in color
# so we can use it for reading data values but not be distracting
ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey',
alpha=0.5)
# Hide these grid behind plot objects
ax1.set_axisbelow(True)
ax1.set_title('overlap and non_overlap against mRS')
# ax1.set_xlabel('Distribution')
# ax1.set_ylabel('Value')
# Now fill the boxes with desired colors
box_colors = ['darkkhaki', 'royalblue']
num_boxes = len(data)
medians = np.empty(num_boxes)
for i in range(num_boxes):
box = bp['boxes'][i]
boxX = []
boxY = []
for j in range(5):
boxX.append(box.get_xdata()[j])
boxY.append(box.get_ydata()[j])
box_coords = np.column_stack([boxX, boxY])
# Alternate between Dark Khaki and Royal Blue
ax1.add_patch(Polygon(box_coords, facecolor=box_colors[i % 2]))
# Now draw the median lines back over what we just filled in
med = bp['medians'][i]
medianX = []
medianY = []
for j in range(2):
medianX.append(med.get_xdata()[j])
medianY.append(med.get_ydata()[j])
ax1.plot(medianX, medianY, 'k')
medians[i] = medianY[0]
# Finally, overplot the sample averages, with horizontal alignment
# in the center of each box
ax1.plot(np.average(med.get_xdata()), np.average(data[i]),
color='w', marker='*', markeredgecolor='k')
# Set the axes ranges and axes labels
ax1.set_xlim(0.5, num_boxes + 0.5)
top = 10 #y-axis
bottom = 0 #y-axis
ax1.set_ylim(bottom, top)
ax1.set_xticklabels(np.repeat(random_dists, 1),
rotation=45, fontsize=8)
pos = np.arange(num_boxes) + 1
# Finally, add a basic legend
fig.text(0.80, 0.08, 'Overlap',
backgroundcolor=box_colors[0], color='black', weight='roman',
size='x-small')
fig.text(0.80, 0.045, 'Non overlap',
backgroundcolor=box_colors[1],
color='white', weight='roman', size='x-small')
fig.text(0.80, 0.015, '*', color='white', backgroundcolor='silver',
weight='roman', size='medium')
fig.text(0.815, 0.013, ' Average Value', color='black', weight='roman',
size='x-small')
plt.show()
What i need is overlap the data into it as a scatter plot just like the picture from this link
I really try hard to use the code on the link and try to search on overstack to find a solution but i'm not that good in coding, also i try using seaborn library but i always get an error that: 'list' object has no attribute 'get' and couldn't fix it
so please any one can help ()
The current version of plt.boxplot() allows plotting most of these elements standard.
Means will be drawn if showmeans is set to True. Its properties can be controlled via the meanprops dictionary. When setting patch_artist=True, instead of just the outline, a filled box will be drawn, boxprops controls how they look.
To draw the scatter plot on top, just call ax1.scatter. The x-positions can be jittered randomly via i + np.random.uniform(-0.4, 0.4). To force them on top of boxplot, their z-order can be changed.
As the fliers are also part of the scatter data, it probably makes sense to leave them out (showfliers=False).
To create a legend, you can collect handles to all desired elements and pass them to ax1.legend(). Note that your boxplots already get labels in the x-axis, so having them also in the legend might be a bit superfluous.
import matplotlib.pyplot as plt
import numpy as np
random_dist_names = ['Overlap', 'Non overlap']
overlap = [6, 6, 5, 1, 3, 4, 4, 3]
non_overlap = [1, 2, 6, 6, 1, 3, 3, 3, 3, 3, 5, 2, 2]
data = [overlap, non_overlap]
fig, ax1 = plt.subplots(figsize=(6, 6))
fig.canvas.set_window_title('A Boxplot Example')
fig.subplots_adjust(left=0.075, right=0.95, top=0.9, bottom=0.25)
box_colors = ['darkkhaki', 'royalblue']
scatter_colors = ['purple', 'crimson']
legend_handles = []
for i, (values, box_color, scatter_color) in enumerate(zip(data, box_colors, scatter_colors), start=1):
bp = ax1.boxplot(values, positions=[i], showmeans=True, patch_artist=True, showfliers=False,
boxprops={'edgecolor': 'black', 'facecolor': box_color},
whiskerprops={'color': 'black'}, # flierprops={'color': 'red', 'marker': '+'},
medianprops={'color': 'lime', 'linewidth': 2, 'linestyle': ':'},
meanprops={'markerfacecolor': 'w', 'marker': '*', 'markeredgecolor': 'k', 'markersize': 10})
if i == 1:
legend_handles.append(bp['means'][0])
legend_handles.append(bp['boxes'][0])
ax1.scatter(i + np.random.uniform(-0.4, 0.4, len(values)), values, color=scatter_color, alpha=0.5, zorder=3)
ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
ax1.set_axisbelow(True)
ax1.set_title('overlap and non_overlap against mRS')
ax1.set_xlim(0.5, len(data) + 0.5)
ax1.set_ylim(ymin=0)
ax1.set_xticklabels(random_dist_names, rotation=0, fontsize=8)
ax1.legend(legend_handles, ['Mean'] + random_dist_names, bbox_to_anchor=[1, -0.1], loc='upper right')
plt.show()
Note that you have very few data points, and they all have integer values, which makes the red dots appear in horizontal lines.
PS: To create something similar with Seaborn, the data has to be organized more similar to a pandas dataframe. Such a dataframe would have one column with all the values, and one column with the category.
The legend can be created more automatically. To also get the means into the legend, a label has to be assigned to the mean via meanprops={..., 'label': 'Mean'}. Unfortunately, this creates one legend entry for every box. These can be skipped by first getting all the legend entries with ax.get_legend_handles_labels() and taking subarrays of the handles and labels.
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
random_dist_names = ['Overlap', 'Non overlap']
overlap = [6, 6, 5, 1, 3, 4, 4, 3]
non_overlap = [1, 2, 6, 6, 1, 3, 3, 3, 3, 3, 5, 2, 2]
data_names = np.repeat(random_dist_names, [len(overlap), len(non_overlap)])
data_values = np.concatenate([overlap, non_overlap])
ax = sns.boxplot(x=data_names, y=data_values, hue=data_names, palette=['darkkhaki', 'royalblue'],
dodge=False, showfliers=False, showmeans=True,
meanprops={'markerfacecolor': 'w', 'marker': '*', 'markeredgecolor': 'k', 'markersize': 10, 'label': 'Mean'})
sns.stripplot(x=data_names, y=data_values, color='red', alpha=0.4)
handles, labels = ax.get_legend_handles_labels()
skip_pos = len(random_dist_names) - 1
ax.legend(handles[skip_pos:], labels[skip_pos:], bbox_to_anchor=(1.02, -0.05), loc='upper right')
plt.tight_layout()
plt.show()
i have test data like:
d = {'Year':[2015,2016,2017,2018,2019,2020],
'Average Temperature, C':[15, 16, 14, 13, 17, 17],
'Precipitation':[1,2,3,4,5,6]}
so my df is df = pd.DataFrame(data=d)
then i'm want to visualize this in Temperature meaning, so
fig, ax = plt.subplots()
fig.set_size_inches(11.7,8.27)
sns.barplot(x='Year', y='Average Temperature, C', data=df, ax=ax)
sns.despine()
i can do this as well with Precipitation meaning
fig, ax = plt.subplots()
fig.set_size_inches(11.7,8.27)
sns.barplot(x='Year', y='Precipitation', data=df, ax=ax)
sns.despine()
i want to unite this grapics in first image and give all of plots text from Precipitation so this should be looks like
There seems to be a solution here
Seaborn Barplot - Displaying Values (Found this after I posted my following answer)
But this is one another way to do it.
df = {'Year':[2015,2016,2017,2018,2019,2020],
'Average Temperature, C':[15, 16, 14, 13, 17, 17],
'Precipitation':[1,2,3,4,5,6]}
import matplotlib.pyplot as plt
fig, ax = plt.subplots()
fig.set_size_inches(11.7,8.27)
rects =ax.bar(x=df['Year'],height=df['Average Temperature, C'])
def autolabel(rects, pvalue, xpos='center',):
"""
Attach a text label above each bar in *rects*, displaying its height.
*xpos* indicates which side to place the text w.r.t. the center of
the bar. It can be one of the following {'center', 'right', 'left'}.
"""
xpos = xpos.lower() # normalize the case of the parameter
ha = {'center': 'center', 'right': 'left', 'left': 'right'}
offset = {'center': 0.5, 'right': 0.57, 'left': 0.43} # x_txt = x + w*off
for i, rect in enumerate(rects):
height = rect.get_height()
ax.text(rect.get_x() + rect.get_width()*offset[xpos], 1.01*height,
'{}'.format(pvalue[i]), ha=ha[xpos], va='bottom')
autolabel(rects,df['Precipitation'], "left")
which results in
How to plot multiple bars in matplotlib, when I tried to call the bar function multiple times, they overlap and as seen the below figure the highest value red can be seen only.
How can I plot the multiple bars with dates on the x-axes?
So far, I tried this:
import matplotlib.pyplot as plt
import datetime
x = [
datetime.datetime(2011, 1, 4, 0, 0),
datetime.datetime(2011, 1, 5, 0, 0),
datetime.datetime(2011, 1, 6, 0, 0)
]
y = [4, 9, 2]
z = [1, 2, 3]
k = [11, 12, 13]
ax = plt.subplot(111)
ax.bar(x, y, width=0.5, color='b', align='center')
ax.bar(x, z, width=0.5, color='g', align='center')
ax.bar(x, k, width=0.5, color='r', align='center')
ax.xaxis_date()
plt.show()
I got this:
The results should be something like, but with the dates are on the x-axes and bars are next to each other:
import matplotlib.pyplot as plt
from matplotlib.dates import date2num
import datetime
x = [
datetime.datetime(2011, 1, 4, 0, 0),
datetime.datetime(2011, 1, 5, 0, 0),
datetime.datetime(2011, 1, 6, 0, 0)
]
x = date2num(x)
y = [4, 9, 2]
z = [1, 2, 3]
k = [11, 12, 13]
ax = plt.subplot(111)
ax.bar(x-0.2, y, width=0.2, color='b', align='center')
ax.bar(x, z, width=0.2, color='g', align='center')
ax.bar(x+0.2, k, width=0.2, color='r', align='center')
ax.xaxis_date()
plt.show()
I don't know what's the "y values are also overlapping" means, does the following code solve your problem?
ax = plt.subplot(111)
w = 0.3
ax.bar(x-w, y, width=w, color='b', align='center')
ax.bar(x, z, width=w, color='g', align='center')
ax.bar(x+w, k, width=w, color='r', align='center')
ax.xaxis_date()
ax.autoscale(tight=True)
plt.show()
The trouble with using dates as x-values, is that if you want a bar chart like in your second picture, they are going to be wrong. You should either use a stacked bar chart (colours on top of each other) or group by date (a "fake" date on the x-axis, basically just grouping the data points).
import numpy as np
import matplotlib.pyplot as plt
N = 3
ind = np.arange(N) # the x locations for the groups
width = 0.27 # the width of the bars
fig = plt.figure()
ax = fig.add_subplot(111)
yvals = [4, 9, 2]
rects1 = ax.bar(ind, yvals, width, color='r')
zvals = [1,2,3]
rects2 = ax.bar(ind+width, zvals, width, color='g')
kvals = [11,12,13]
rects3 = ax.bar(ind+width*2, kvals, width, color='b')
ax.set_ylabel('Scores')
ax.set_xticks(ind+width)
ax.set_xticklabels( ('2011-Jan-4', '2011-Jan-5', '2011-Jan-6') )
ax.legend( (rects1[0], rects2[0], rects3[0]), ('y', 'z', 'k') )
def autolabel(rects):
for rect in rects:
h = rect.get_height()
ax.text(rect.get_x()+rect.get_width()/2., 1.05*h, '%d'%int(h),
ha='center', va='bottom')
autolabel(rects1)
autolabel(rects2)
autolabel(rects3)
plt.show()
after looking for a similar solution and not finding anything flexible enough, I decided to write my own function for it. It allows you to have as many bars per group as you wish and specify both the width of a group as well as the individual widths of the bars within the groups.
Enjoy:
from matplotlib import pyplot as plt
def bar_plot(ax, data, colors=None, total_width=0.8, single_width=1, legend=True):
"""Draws a bar plot with multiple bars per data point.
Parameters
----------
ax : matplotlib.pyplot.axis
The axis we want to draw our plot on.
data: dictionary
A dictionary containing the data we want to plot. Keys are the names of the
data, the items is a list of the values.
Example:
data = {
"x":[1,2,3],
"y":[1,2,3],
"z":[1,2,3],
}
colors : array-like, optional
A list of colors which are used for the bars. If None, the colors
will be the standard matplotlib color cyle. (default: None)
total_width : float, optional, default: 0.8
The width of a bar group. 0.8 means that 80% of the x-axis is covered
by bars and 20% will be spaces between the bars.
single_width: float, optional, default: 1
The relative width of a single bar within a group. 1 means the bars
will touch eachother within a group, values less than 1 will make
these bars thinner.
legend: bool, optional, default: True
If this is set to true, a legend will be added to the axis.
"""
# Check if colors where provided, otherwhise use the default color cycle
if colors is None:
colors = plt.rcParams['axes.prop_cycle'].by_key()['color']
# Number of bars per group
n_bars = len(data)
# The width of a single bar
bar_width = total_width / n_bars
# List containing handles for the drawn bars, used for the legend
bars = []
# Iterate over all data
for i, (name, values) in enumerate(data.items()):
# The offset in x direction of that bar
x_offset = (i - n_bars / 2) * bar_width + bar_width / 2
# Draw a bar for every value of that type
for x, y in enumerate(values):
bar = ax.bar(x + x_offset, y, width=bar_width * single_width, color=colors[i % len(colors)])
# Add a handle to the last drawn bar, which we'll need for the legend
bars.append(bar[0])
# Draw legend if we need
if legend:
ax.legend(bars, data.keys())
if __name__ == "__main__":
# Usage example:
data = {
"a": [1, 2, 3, 2, 1],
"b": [2, 3, 4, 3, 1],
"c": [3, 2, 1, 4, 2],
"d": [5, 9, 2, 1, 8],
"e": [1, 3, 2, 2, 3],
"f": [4, 3, 1, 1, 4],
}
fig, ax = plt.subplots()
bar_plot(ax, data, total_width=.8, single_width=.9)
plt.show()
Output:
I know that this is about matplotlib, but using pandas and seaborn can save you a lot of time:
df = pd.DataFrame(zip(x*3, ["y"]*3+["z"]*3+["k"]*3, y+z+k), columns=["time", "kind", "data"])
plt.figure(figsize=(10, 6))
sns.barplot(x="time", hue="kind", y="data", data=df)
plt.show()
Given the existing answers, the easiest solution, given the data in the OP, is load the data into a dataframe and plot with pandas.DataFrame.plot.
Load the value lists into pandas with a dict, and specify x as the index. The index will automatically be set as the x-axis, and the columns will be plotted as the bars.
pandas.DataFrame.plot uses matplotlib as the default backend.
See How to add value labels on a bar chart for thorough details about using .bar_label.
Tested in python 3.8.11, pandas 1.3.2, matplotlib 3.4.3
import pandas as pd
# using the existing lists from the OP, create the dataframe
df = pd.DataFrame(data={'y': y, 'z': z, 'k': k}, index=x)
# since there's no time component and x was a datetime dtype, set the index to be just the date
df.index = df.index.date
# display(df)
y z k
2011-01-04 4 1 11
2011-01-05 9 2 12
2011-01-06 2 3 13
# plot bars or kind='barh' for horizontal bars; adjust figsize accordingly
ax = df.plot(kind='bar', rot=0, xlabel='Date', ylabel='Value', title='My Plot', figsize=(6, 4))
# add some labels
for c in ax.containers:
# set the bar label
ax.bar_label(c, fmt='%.0f', label_type='edge')
# add a little space at the top of the plot for the annotation
ax.margins(y=0.1)
# move the legend out of the plot
ax.legend(title='Columns', bbox_to_anchor=(1, 1.02), loc='upper left')
Horizontal bars for when there are more columns
ax = df.plot(kind='barh', ylabel='Date', title='My Plot', figsize=(5, 4))
ax.set(xlabel='Value')
for c in ax.containers:
# set the bar label
ax.bar_label(c, fmt='%.0f', label_type='edge')
ax.margins(x=0.1)
# move the legend out of the plot
ax.legend(title='Columns', bbox_to_anchor=(1, 1.02), loc='upper left')
I modified pascscha's solution extending the interface, hopefully this helps someone else! Key features:
Variable number of entries per bar group
Customizable colors
Handling of x ticks
Fully customizable bar labels on top of bars
def bar_plot(ax, data, group_stretch=0.8, bar_stretch=0.95,
legend=True, x_labels=True, label_fontsize=8,
colors=None, barlabel_offset=1,
bar_labeler=lambda k, i, s: str(round(s, 3))):
"""
Draws a bar plot with multiple bars per data point.
:param dict data: The data we want to plot, wher keys are the names of each
bar group, and items is a list of bar values for the corresponding group.
:param float group_stretch: 1 means groups occupy the most (largest groups
touch side to side if they have equal number of bars).
:param float bar_stretch: If 1, bars within a group will touch side to side.
:param bool x_labels: If true, x-axis will contain labels with the group
names given at data, centered at the bar group.
:param int label_fontsize: Font size for the label on top of each bar.
:param float barlabel_offset: Distance, in y-values, between the top of the
bar and its label.
:param function bar_labeler: If not None, must be a functor with signature
``f(group_name, i, scalar)->str``, where each scalar is the entry found at
data[group_name][i]. When given, returns a label to put on the top of each
bar. Otherwise no labels on top of bars.
"""
sorted_data = list(sorted(data.items(), key=lambda elt: elt[0]))
sorted_k, sorted_v = zip(*sorted_data)
max_n_bars = max(len(v) for v in data.values())
group_centers = np.cumsum([max_n_bars
for _ in sorted_data]) - (max_n_bars / 2)
bar_offset = (1 - bar_stretch) / 2
bars = defaultdict(list)
#
if colors is None:
colors = {g_name: [f"C{i}" for _ in values]
for i, (g_name, values) in enumerate(data.items())}
#
for g_i, ((g_name, vals), g_center) in enumerate(zip(sorted_data,
group_centers)):
n_bars = len(vals)
group_beg = g_center - (n_bars / 2) + (bar_stretch / 2)
for val_i, val in enumerate(vals):
bar = ax.bar(group_beg + val_i + bar_offset,
height=val, width=bar_stretch,
color=colors[g_name][val_i])[0]
bars[g_name].append(bar)
if bar_labeler is not None:
x_pos = bar.get_x() + (bar.get_width() / 2.0)
y_pos = val + barlabel_offset
barlbl = bar_labeler(g_name, val_i, val)
ax.text(x_pos, y_pos, barlbl, ha="center", va="bottom",
fontsize=label_fontsize)
if legend:
ax.legend([bars[k][0] for k in sorted_k], sorted_k)
#
ax.set_xticks(group_centers)
if x_labels:
ax.set_xticklabels(sorted_k)
else:
ax.set_xticklabels()
return bars, group_centers
Sample run:
fig, ax = plt.subplots()
data = {"Foo": [1, 2, 3, 4], "Zap": [0.1, 0.2], "Quack": [6], "Bar": [1.1, 2.2, 3.3, 4.4, 5.5]}
bar_plot(ax, data, group_stretch=0.8, bar_stretch=0.95, legend=True,
labels=True, label_fontsize=8, barlabel_offset=0.05,
bar_labeler=lambda k, i, s: str(round(s, 3)))
fig.show()
I did this solution: if you want plot more than one plot in one figure, make sure before plotting next plots you have set right matplotlib.pyplot.hold(True)
to able adding another plots.
Concerning the datetime values on the X axis, a solution using the alignment of bars works for me. When you create another bar plot with matplotlib.pyplot.bar(), just use align='edge|center' and set width='+|-distance'.
When you set all bars (plots) right, you will see the bars fine.
How to plot multiple bars in matplotlib, when I tried to call the bar function multiple times, they overlap and as seen the below figure the highest value red can be seen only.
How can I plot the multiple bars with dates on the x-axes?
So far, I tried this:
import matplotlib.pyplot as plt
import datetime
x = [
datetime.datetime(2011, 1, 4, 0, 0),
datetime.datetime(2011, 1, 5, 0, 0),
datetime.datetime(2011, 1, 6, 0, 0)
]
y = [4, 9, 2]
z = [1, 2, 3]
k = [11, 12, 13]
ax = plt.subplot(111)
ax.bar(x, y, width=0.5, color='b', align='center')
ax.bar(x, z, width=0.5, color='g', align='center')
ax.bar(x, k, width=0.5, color='r', align='center')
ax.xaxis_date()
plt.show()
I got this:
The results should be something like, but with the dates are on the x-axes and bars are next to each other:
import matplotlib.pyplot as plt
from matplotlib.dates import date2num
import datetime
x = [
datetime.datetime(2011, 1, 4, 0, 0),
datetime.datetime(2011, 1, 5, 0, 0),
datetime.datetime(2011, 1, 6, 0, 0)
]
x = date2num(x)
y = [4, 9, 2]
z = [1, 2, 3]
k = [11, 12, 13]
ax = plt.subplot(111)
ax.bar(x-0.2, y, width=0.2, color='b', align='center')
ax.bar(x, z, width=0.2, color='g', align='center')
ax.bar(x+0.2, k, width=0.2, color='r', align='center')
ax.xaxis_date()
plt.show()
I don't know what's the "y values are also overlapping" means, does the following code solve your problem?
ax = plt.subplot(111)
w = 0.3
ax.bar(x-w, y, width=w, color='b', align='center')
ax.bar(x, z, width=w, color='g', align='center')
ax.bar(x+w, k, width=w, color='r', align='center')
ax.xaxis_date()
ax.autoscale(tight=True)
plt.show()
The trouble with using dates as x-values, is that if you want a bar chart like in your second picture, they are going to be wrong. You should either use a stacked bar chart (colours on top of each other) or group by date (a "fake" date on the x-axis, basically just grouping the data points).
import numpy as np
import matplotlib.pyplot as plt
N = 3
ind = np.arange(N) # the x locations for the groups
width = 0.27 # the width of the bars
fig = plt.figure()
ax = fig.add_subplot(111)
yvals = [4, 9, 2]
rects1 = ax.bar(ind, yvals, width, color='r')
zvals = [1,2,3]
rects2 = ax.bar(ind+width, zvals, width, color='g')
kvals = [11,12,13]
rects3 = ax.bar(ind+width*2, kvals, width, color='b')
ax.set_ylabel('Scores')
ax.set_xticks(ind+width)
ax.set_xticklabels( ('2011-Jan-4', '2011-Jan-5', '2011-Jan-6') )
ax.legend( (rects1[0], rects2[0], rects3[0]), ('y', 'z', 'k') )
def autolabel(rects):
for rect in rects:
h = rect.get_height()
ax.text(rect.get_x()+rect.get_width()/2., 1.05*h, '%d'%int(h),
ha='center', va='bottom')
autolabel(rects1)
autolabel(rects2)
autolabel(rects3)
plt.show()
after looking for a similar solution and not finding anything flexible enough, I decided to write my own function for it. It allows you to have as many bars per group as you wish and specify both the width of a group as well as the individual widths of the bars within the groups.
Enjoy:
from matplotlib import pyplot as plt
def bar_plot(ax, data, colors=None, total_width=0.8, single_width=1, legend=True):
"""Draws a bar plot with multiple bars per data point.
Parameters
----------
ax : matplotlib.pyplot.axis
The axis we want to draw our plot on.
data: dictionary
A dictionary containing the data we want to plot. Keys are the names of the
data, the items is a list of the values.
Example:
data = {
"x":[1,2,3],
"y":[1,2,3],
"z":[1,2,3],
}
colors : array-like, optional
A list of colors which are used for the bars. If None, the colors
will be the standard matplotlib color cyle. (default: None)
total_width : float, optional, default: 0.8
The width of a bar group. 0.8 means that 80% of the x-axis is covered
by bars and 20% will be spaces between the bars.
single_width: float, optional, default: 1
The relative width of a single bar within a group. 1 means the bars
will touch eachother within a group, values less than 1 will make
these bars thinner.
legend: bool, optional, default: True
If this is set to true, a legend will be added to the axis.
"""
# Check if colors where provided, otherwhise use the default color cycle
if colors is None:
colors = plt.rcParams['axes.prop_cycle'].by_key()['color']
# Number of bars per group
n_bars = len(data)
# The width of a single bar
bar_width = total_width / n_bars
# List containing handles for the drawn bars, used for the legend
bars = []
# Iterate over all data
for i, (name, values) in enumerate(data.items()):
# The offset in x direction of that bar
x_offset = (i - n_bars / 2) * bar_width + bar_width / 2
# Draw a bar for every value of that type
for x, y in enumerate(values):
bar = ax.bar(x + x_offset, y, width=bar_width * single_width, color=colors[i % len(colors)])
# Add a handle to the last drawn bar, which we'll need for the legend
bars.append(bar[0])
# Draw legend if we need
if legend:
ax.legend(bars, data.keys())
if __name__ == "__main__":
# Usage example:
data = {
"a": [1, 2, 3, 2, 1],
"b": [2, 3, 4, 3, 1],
"c": [3, 2, 1, 4, 2],
"d": [5, 9, 2, 1, 8],
"e": [1, 3, 2, 2, 3],
"f": [4, 3, 1, 1, 4],
}
fig, ax = plt.subplots()
bar_plot(ax, data, total_width=.8, single_width=.9)
plt.show()
Output:
I know that this is about matplotlib, but using pandas and seaborn can save you a lot of time:
df = pd.DataFrame(zip(x*3, ["y"]*3+["z"]*3+["k"]*3, y+z+k), columns=["time", "kind", "data"])
plt.figure(figsize=(10, 6))
sns.barplot(x="time", hue="kind", y="data", data=df)
plt.show()
Given the existing answers, the easiest solution, given the data in the OP, is load the data into a dataframe and plot with pandas.DataFrame.plot.
Load the value lists into pandas with a dict, and specify x as the index. The index will automatically be set as the x-axis, and the columns will be plotted as the bars.
pandas.DataFrame.plot uses matplotlib as the default backend.
See How to add value labels on a bar chart for thorough details about using .bar_label.
Tested in python 3.8.11, pandas 1.3.2, matplotlib 3.4.3
import pandas as pd
# using the existing lists from the OP, create the dataframe
df = pd.DataFrame(data={'y': y, 'z': z, 'k': k}, index=x)
# since there's no time component and x was a datetime dtype, set the index to be just the date
df.index = df.index.date
# display(df)
y z k
2011-01-04 4 1 11
2011-01-05 9 2 12
2011-01-06 2 3 13
# plot bars or kind='barh' for horizontal bars; adjust figsize accordingly
ax = df.plot(kind='bar', rot=0, xlabel='Date', ylabel='Value', title='My Plot', figsize=(6, 4))
# add some labels
for c in ax.containers:
# set the bar label
ax.bar_label(c, fmt='%.0f', label_type='edge')
# add a little space at the top of the plot for the annotation
ax.margins(y=0.1)
# move the legend out of the plot
ax.legend(title='Columns', bbox_to_anchor=(1, 1.02), loc='upper left')
Horizontal bars for when there are more columns
ax = df.plot(kind='barh', ylabel='Date', title='My Plot', figsize=(5, 4))
ax.set(xlabel='Value')
for c in ax.containers:
# set the bar label
ax.bar_label(c, fmt='%.0f', label_type='edge')
ax.margins(x=0.1)
# move the legend out of the plot
ax.legend(title='Columns', bbox_to_anchor=(1, 1.02), loc='upper left')
I modified pascscha's solution extending the interface, hopefully this helps someone else! Key features:
Variable number of entries per bar group
Customizable colors
Handling of x ticks
Fully customizable bar labels on top of bars
def bar_plot(ax, data, group_stretch=0.8, bar_stretch=0.95,
legend=True, x_labels=True, label_fontsize=8,
colors=None, barlabel_offset=1,
bar_labeler=lambda k, i, s: str(round(s, 3))):
"""
Draws a bar plot with multiple bars per data point.
:param dict data: The data we want to plot, wher keys are the names of each
bar group, and items is a list of bar values for the corresponding group.
:param float group_stretch: 1 means groups occupy the most (largest groups
touch side to side if they have equal number of bars).
:param float bar_stretch: If 1, bars within a group will touch side to side.
:param bool x_labels: If true, x-axis will contain labels with the group
names given at data, centered at the bar group.
:param int label_fontsize: Font size for the label on top of each bar.
:param float barlabel_offset: Distance, in y-values, between the top of the
bar and its label.
:param function bar_labeler: If not None, must be a functor with signature
``f(group_name, i, scalar)->str``, where each scalar is the entry found at
data[group_name][i]. When given, returns a label to put on the top of each
bar. Otherwise no labels on top of bars.
"""
sorted_data = list(sorted(data.items(), key=lambda elt: elt[0]))
sorted_k, sorted_v = zip(*sorted_data)
max_n_bars = max(len(v) for v in data.values())
group_centers = np.cumsum([max_n_bars
for _ in sorted_data]) - (max_n_bars / 2)
bar_offset = (1 - bar_stretch) / 2
bars = defaultdict(list)
#
if colors is None:
colors = {g_name: [f"C{i}" for _ in values]
for i, (g_name, values) in enumerate(data.items())}
#
for g_i, ((g_name, vals), g_center) in enumerate(zip(sorted_data,
group_centers)):
n_bars = len(vals)
group_beg = g_center - (n_bars / 2) + (bar_stretch / 2)
for val_i, val in enumerate(vals):
bar = ax.bar(group_beg + val_i + bar_offset,
height=val, width=bar_stretch,
color=colors[g_name][val_i])[0]
bars[g_name].append(bar)
if bar_labeler is not None:
x_pos = bar.get_x() + (bar.get_width() / 2.0)
y_pos = val + barlabel_offset
barlbl = bar_labeler(g_name, val_i, val)
ax.text(x_pos, y_pos, barlbl, ha="center", va="bottom",
fontsize=label_fontsize)
if legend:
ax.legend([bars[k][0] for k in sorted_k], sorted_k)
#
ax.set_xticks(group_centers)
if x_labels:
ax.set_xticklabels(sorted_k)
else:
ax.set_xticklabels()
return bars, group_centers
Sample run:
fig, ax = plt.subplots()
data = {"Foo": [1, 2, 3, 4], "Zap": [0.1, 0.2], "Quack": [6], "Bar": [1.1, 2.2, 3.3, 4.4, 5.5]}
bar_plot(ax, data, group_stretch=0.8, bar_stretch=0.95, legend=True,
labels=True, label_fontsize=8, barlabel_offset=0.05,
bar_labeler=lambda k, i, s: str(round(s, 3)))
fig.show()
I did this solution: if you want plot more than one plot in one figure, make sure before plotting next plots you have set right matplotlib.pyplot.hold(True)
to able adding another plots.
Concerning the datetime values on the X axis, a solution using the alignment of bars works for me. When you create another bar plot with matplotlib.pyplot.bar(), just use align='edge|center' and set width='+|-distance'.
When you set all bars (plots) right, you will see the bars fine.