I have a code that create 16 histograms. My problems are:
I think the code is too much repetative and that there are ways to write it shorter.
2.I have 13 fields to create histograms, and as 13 is prime number, I face a problem how to show all of them nicely but without blank plots.
I want to show the distribution but I get only 1 bar, even though I have change dit to 0, 100 and 500 (I have more than 1000 observations).
some columns are float and have too many 0 after the dot and I can't change it.
This is my code:
f, axes = plt.subplots(4, 4, figsize=(20,20), sharex=True)
sns.distplot(data['HR90'], color="skyblue", ax=axes[0,0],bins=500)
sns.distplot(data['HC90'], color="olive", ax=axes[0,1],bins=100)
sns.distplot(data['RD90'], color="gold", ax=axes[0,2],bins=100)
sns.distplot(data['PO90'], color="teal", ax=axes[0,3], bins=100)
sns.distplot(data['PS90'], color="red", ax=axes[1,0], bins=100)
sns.distplot(data['UE90'], color="green", ax=axes[1,1], bins=100)
sns.distplot(data['DV90'], color="blue", ax=axes[1,2], bins=100)
sns.distplot(data['MA90'], color="purple", ax=axes[1,3], bins=100)
sns.distplot(data['POL90'], color="orange", ax=axes[2,0], bins=100)
sns.distplot(data['DNL90'], color="green", ax=axes[2,1], bins=100)
sns.distplot(data['BLK90'], color="pink", ax=axes[2,2], bins=100)
sns.distplot(data['GI89'], color="silver", ax=axes[2,3], bins=100)
sns.distplot(data['FH90'], color="cyan", ax=axes[3,1], bins=100)
and this is the results:
as you can see I have some empty plots and the bins look like one.
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
position = []
for x in range(0, 4):
for y in range (0, 4):
position.append([x, y])
groups = ['PO90', 'HC90', 'RD90', 'HR90', 'PS90', 'UE90', 'DV90', 'MA90', 'POL90', 'DNL90', 'BLK90', 'GI89','FH90']
graph_colors = ["skyblue", "olive", "gold", "teal", "red", "green", "blue", "purple", "orange", "green", "pink", "silver", "cyan"]
graph_bins = [500, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100]
data = pd.DataFrame(np.random.randint(low=0, high=10, size=(100, 13)), columns=groups)
f, axes = plt.subplots(4, 4, figsize=(20,20), sharex=False, sharey=False)
for i in range(0, 13):
sns.distplot(data[groups[i]], color=graph_colors[i], ax=axes[position[i][0], position[i][1]], bins=graph_bins[i])
The plot will look like this:
To get rid of the empty plot, sub plots must be added in a slightly different way, like so:
fig = plt.figure(figsize=(20,20))
# Generating 1st column.
for sp_index in range(1, 14, 4):
ax = fig.add_subplot(4, 4, sp_index)
sns.distplot(data[groups[sp_index-1]], color=graph_colors[sp_index-1], ax=ax, bins=graph_bins[sp_index-1])
# Generating 2nd column.
for sp_index in range(2, 14, 4):
ax = fig.add_subplot(4, 4, sp_index)
sns.distplot(data[groups[sp_index-1]], color=graph_colors[sp_index-1], ax=ax, bins=graph_bins[sp_index-1])
# Generating 3rd column.
for sp_index in range(3, 14, 4):
ax = fig.add_subplot(4, 4, sp_index)
sns.distplot(data[groups[sp_index-1]], color=graph_colors[sp_index-1], ax=ax, bins=graph_bins[sp_index-1])
# Generating 4thcolumn.
for sp_index in range(4, 14, 4):
ax = fig.add_subplot(4, 4, sp_index)
sns.distplot(data[groups[sp_index-1]], color=graph_colors[sp_index-1], ax=ax, bins=graph_bins[sp_index-1])
Then the plot will look like this (N.B. the graphs will look slightly different to the version above, since the data frame values were generated, using np.random.randint function several times, whilst experimenting with the solution):
I found the solution:
I had to change the sharex and sharey :
f, axes = plt.subplots(4, 4, figsize=(60,60), sharex=False, sharey=False)
This way the don't share the same axes and it works
Related
I'm trying to create a scatter plot with 100 data points and three variables: x value, y value, and category. This information is stored in an ndarray.
I can create the scatter plot, but I don't know how to use a different color for each category. I used the following code for the plot, which seems to work fine (although it's not finished):
def my_plot(data, color_map):
f, ax = plt.subplots()
ax.scatter(data.x, data.y, s = 150, edgecolors = "r")
return f
In my function, color_map is a parameter which refers to a dictionary I created to color the different categories (there are four in total). This is the dictionary:
color_map = {"winter":(15, 28, 75), "spring":(92, 57, 32), "summer":(255, 253, 211), "fall":(174, 12, 12)}
What I would like to do is to somehow integrate this color_map in my function so that each dot in my plot receives a different color.
I think this could be done using np.where to create a mask, but I'm not sure how to proceed...
The color values need to be divided by 255 because matplotlib likes them between 0 and 1.
With this dict you can create an array of colors for the categories:
from matplotlib import pyplot as plt
from matplotlib.lines import Line2D
import pandas as pd
import numpy as np
color_map = {"winter": (15, 28, 75), "spring": (92, 57, 32), "summer": (255, 253, 211), "fall": (174, 12, 12)}
color_map = {key: (r / 255, g / 255, b / 255,) for key, (r, g, b) in color_map.items()}
N = 200
data = pd.DataFrame({'x': np.random.uniform(1, 9, N), 'y': np.random.uniform(1, 5, N),
'cat': np.random.choice([*color_map.keys()], N)})
fig, ax = plt.subplots()
ax.scatter(data.x, data.y, s=150, color=[color_map[c] for c in data.cat], ec='r')
handles = [Line2D([], [], marker='o', ls='', color=col, markeredgecolor='r', label=label)
for label, col in color_map.items()]
plt.legend(handles=handles, bbox_to_anchor=[1.02, 1.02], loc='upper left')
plt.tight_layout()
plt.show()
PS: A similar plot can be generated with seaborn, which also automatically adds the corresponding legend. Note that the current version of matplotlib (3.3.1) has a problem with the hue parameter. Normally you would add it as hue='cat' but in this version a workaround via .to_list is needed.
import seaborn as sns
ax = sns.scatterplot(x='x', y='y', hue=data['cat'].to_list(), s=150, palette=color_map, edgecolor='r', data=data)
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()
Ive been struggling with this for a while and figured it was time to come here. Essentially I have two subplots being graphed and they're totally fine except for one thing, the x axis. For some reason one subplot's x-axis is coming out perfectly and the other's is not.
Here is my Code:
## BAR PLOTS
#expected value vs probability of choosing option1
fig,ax = plt.subplots(1, 2, dpi=320)
data.plot(kind='bar', y='value_1', ax=ax[0], color ='red')
data.plot(kind='bar', y='p_1', ax=ax[1], color ='blue')
#ax.set_xlabel("Trials")
#ax.set_ylabel("Value 1 / P_1")
#plt.xticks(np.arange(0, len('value_1')+1, 5), np.arange(0, len('value_1')+1, 5) )
#ticks = range(0, 500, 5)
#labels = ticks
#plt.xticks(ticks, labels)
plt.xticks(np.arange(0, len(data.value_1)+1, 5), np.arange(0, len(data.value_1)+1, 5) )
# plt.xticks(np.arange(0, len(data.p_1)+1, 5), np.arange(0, len(data.p_1)+1, 5) )
#ax.legend(["Value 1, P_1"])
plt.title(' Expected Vs. Probability')
fig.savefig("figure.pdf")
plt.show()
Here is the output:
Try using set_xticks for each ax array:
ax[0].set_xticks(np.arange(0, len(data.value_1)+1, 5))
ax[1].set_xticks(np.arange(0, len(data.value_1)+1, 5))
As you did not provide data I cannot check this, but in principle the set_xticks should work per ax array.
I'm creating a chart with matplotlib, here is my code:
fig = plt.figure(facecolor='#131722',dpi=155, figsize=(8, 4))
ax1 = plt.subplot2grid((1,2), (0,0), facecolor='#131722')
Colors = [['#0400ff', '#FF0000'], ['#09ff00', '#ff8c00']]
for x in List:
Index = List.index(x)
rate_buy = []
total_buy = []
for y in x['data']['bids']:
rate_buy.append(y[0])
total_buy.append(y[1])
rBuys = pd.DataFrame({'buy': rate_buy})
tBuys = pd.DataFrame({'total': total_buy})
ax1.plot(rBuys.buy, tBuys.total, color=Colors[Index][0], linewidth=0.5, alpha=0.8)
ax1.fill_between(rBuys.buy, 0, tBuys.total, facecolor=Colors[Index][0], alpha=1)
And here is the output:
The problem with the current output is that the colors of the two areas are "merging": basically the area BELOW the blue line should be blue, but instead it's green. How can i set it to be blue, for example, like in my example?
Example List data:
[[9665, 0.07062500000000001], [9666, 0.943708], [9667, 5.683787000000001], [9668, 9.802289], [9669, 11.763305], [9670, 14.286004], [9671, 16.180122], [9672, 23.316723000000003], [9673, 30.915156000000003], [9674, 33.44226200000001], [9675, 36.14526200000001], [9676, 45.76024100000001], [9677, 51.85294700000001], [9678, 58.79529300000001], [9679, 59.05322900000001], [9680, 60.27704500000001], [9681, 60.743885000000006], [9682, 66.75103700000001], [9683, 71.86412600000001], [9684, 73.659636], [9685, 78.08502800000001], [9686, 78.19614200000001], [9687, 79.98396400000001], [9688, 90.55855800000002]]
I guess the hint of #JohanC is correct, you are plotting in the wrong order and overlay your previous plots with new ones.
I tried to recreate a small example where total_buy1 > total_buy0, so in order to get the desired result you first have to plot total_buy1
and then total_buy0:
import matplotlib.pyplot as plt
fig, ax = plt.subplots()
Colors = [['#0400ff', '#FF0000'],
['#09ff00', '#ff8c00']]
n = 100
rate_buy = np.linspace(0, 1000, 100)
total_buy0 = np.linspace(0, 300, n)[::-1] + np.random.normal(scale=10, size=n)
total_buy1 = np.linspace(0, 600, n)[::-1] + np.random.normal(scale=10, size=n)
ax.plot(rate_buy, total_buy1, color=Colors[1][1], linewidth=0.5, alpha=0.8)
ax.fill_between(rate_buy, 0, total_buy1, facecolor=Colors[1][0], alpha=1)
ax.plot(rate_buy, total_buy0, color=Colors[0][1], linewidth=0.5, alpha=0.8)
ax.fill_between(rate_buy, 0, total_buy0, facecolor=Colors[0][0], alpha=1)
I noticed that you use Colors[Index][0] for both plotting calls, so the line and the area will not have different colors.
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.