I have the following dataframe where it contains the best equipment in operation ranked by 1 to 300 (1 is the best, 300 is the worst) over a few days (df columns)
Equipment 21-03-27 21-03-28 21-03-29 21-03-30 21-03-31 21-04-01 21-04-02
P01-INV-1-1 1 1 1 1 1 2 2
P01-INV-1-2 2 2 4 4 5 1 1
P01-INV-1-3 4 4 3 5 6 10 10
I would like to customize a line plot (example found here) but I'm having some troubles trying to modify the example code provided:
import matplotlib.pyplot as plt
import numpy as np
def energy_rank(data, marker_width=0.1, color='blue'):
y_data = np.repeat(data, 2)
x_data = np.empty_like(y_data)
x_data[0::2] = np.arange(1, len(data)+1) - (marker_width/2)
x_data[1::2] = np.arange(1, len(data)+1) + (marker_width/2)
lines = []
lines.append(plt.Line2D(x_data, y_data, lw=1, linestyle='dashed', color=color))
for x in range(0,len(data)*2, 2):
lines.append(plt.Line2D(x_data[x:x+2], y_data[x:x+2], lw=2, linestyle='solid', color=color))
return lines
data = ranks.head(4).to_numpy() #ranks is the above dataframe
artists = []
for row, color in zip(data, ('red','blue','green','magenta')):
artists.extend(energy_rank(row, color=color))
fig, ax = plt.subplots()
ax.set_xticklabels(ranks.columns) # set X axis to be dataframe columns
ax.set_xticklabels(ax.get_xticklabels(), rotation=35, fontsize = 10)
for artist in artists:
ax.add_artist(artist)
ax.set_ybound([15,0])
ax.set_xbound([.5,8.5])
When using ax.set_xticklabels(ranks.columns), for some reason, it only plots 5 of the 7 days from ranks columns, removing specifically the first and last values. I tried to duplicate those values but this did not work as well. I end up having this below:
In summary, I would like to know if its possible to do 3 customizations:
input all dates from ranks columns on X axis
revert Y axis. ax.set_ybound([15,0]) is not working. It would make more sense to see the graph starting with 0 on top, since 1 is the most important rank to look at
add labels to the end of each line at the last day (last value on X axis). I could add the little window label, but it often gets really messy when you plot more data, so adding just the text at the end of each line would really make it look cleaner
Please let me know if those customizations are impossible to do and any help is really appreciated! Thank you in advance!
To show all the dates, use plt.xticks() and set_xbound to start at 0. To reverse the y axis, use ax.set_ylim(ax.get_ylim()[::-1]). To set the legends the way you described, you can use annotation and set the coordinates of the annotation at your last datapoint for each series.
fig, ax = plt.subplots()
plt.xticks(np.arange(len(ranks.columns)), list(ranks.columns), rotation = 35, fontsize = 10)
plt.xlabel('Date')
plt.ylabel('Rank')
for artist in artists:
ax.add_artist(artist)
ax.set_ybound([0,15])
ax.set_ylim(ax.get_ylim()[::-1])
ax.set_xbound([0,8.5])
ax.annotate('Series 1', xy =(7.1, 2), color = 'red')
ax.annotate('Series 2', xy =(7.1, 1), color = 'blue')
ax.annotate('Series 3', xy =(7.1, 10), color = 'green')
plt.show()
Here is the plot for the three rows of data in your sample dataframe:
If I draw the plot using the following code, it works and I can see all the subplots in a single row. I can specifically break the number of cols into three or two and show them. But I have 30 columns and I wanted to use a loop mechanism so that they are plotted in a grid of say 4x4 sub-plots
regressionCols = ['col_a', 'col_b', 'col_c', 'col_d', 'col_e']
sns.pairplot(numerical_df, x_vars=regressionCols, y_vars='price',height=4, aspect=1, kind='scatter')
plt.show()
The code using loop is below. However, I don't see anything rendered.
nr_rows = 4
nr_cols = 4
li_cat_cols = list(regressionCols)
fig, axs = plt.subplots(nr_rows, nr_cols, figsize=(nr_cols*4,nr_rows*4), squeeze=False)
for r in range(0, nr_rows):
for c in range(0,nr_cols):
i = r*nr_cols+c
if i < len(li_cat_cols):
sns.set(style="darkgrid")
bp=sns.pairplot(numerical_df, x_vars=li_cat_cols[i], y_vars='price',height=4, aspect=1, kind='scatter')
bp.set(xlabel=li_cat_cols[i], ylabel='Price')
plt.tight_layout()
plt.show()
Not sure what I am missing.
I think you didnt connect each of your subplot spaces in a matrix plot to scatter plots generated in a loop.
Maybe this solution with inner pandas plots could be proper for you:
For example,
1.Lets simply define an empty pandas dataframe.
numerical_df = pd.DataFrame([])
2. Create some random features and price depending on them:
numerical_df['A'] = np.random.randn(100)
numerical_df['B'] = np.random.randn(100)*10
numerical_df['C'] = np.random.randn(100)*-10
numerical_df['D'] = np.random.randn(100)*2
numerical_df['E'] = 20*(np.random.randn(100)**2)
numerical_df['F'] = np.random.randn(100)
numerical_df['price'] = 2*numerical_df['A'] +0.5*numerical_df['B'] - 9*numerical_df['C'] + numerical_df['E'] + numerical_df['D']
3. Define number of rows and columns. Create a subplots space with nr_rows and nr_cols.
nr_rows = 2
nr_cols = 4
fig, axes = plt.subplots(nrows=nr_rows, ncols=nr_cols, figsize=(15, 8))
for idx, feature in enumerate(numerical_df.columns[:-1]):
numerical_df.plot(feature, "price", subplots=True,kind="scatter",ax=axes[idx // 4,idx % 4])
4. Enumerate each feature in dataframe and plot a scatterplot with price:
for idx, feature in enumerate(numerical_df.columns[:-1]):
numerical_df.plot(feature, "price", subplots=True,kind="scatter",ax=axes[idx // 4,idx % 4])
where axes[idx // 4, idx % 4] defines the location of each scatterplot in a matrix you create in (3.)
So, we got a matrix plot:
Scatterplot matrix
I am preparing a graph of latency percentile results. This is my pd.DataFrame looks like:
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
result = pd.DataFrame(np.random.randint(133000, size=(5,3)), columns=list('ABC'), index=[99.0, 99.9, 99.99, 99.999, 99.9999])
I am using this function (commented lines are different pyplot methods I have already tried to achieve my goal):
def plot_latency_time_bar(result):
ind = np.arange(4)
means = []
stds = []
for index, row in result.iterrows():
means.append(np.mean([row[0]//1000, row[1]//1000, row[2]//1000]))
stds.append(np .std([row[0]//1000, row[1]//1000, row[2]//1000]))
plt.bar(result.index.values, means, 0.2, yerr=stds, align='center')
plt.xlabel('Percentile')
plt.ylabel('Latency')
plt.xticks(result.index.values)
# plt.xticks(ind, ('99.0', '99.9', '99.99', '99.999', '99.99999'))
# plt.autoscale(enable=False, axis='x', tight=False)
# plt.axis('auto')
# plt.margins(0.8, 0)
# plt.semilogx(basex=5)
plt.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.)
fig = plt.gcf()
fig.set_size_inches(15.5, 10.5)
And here is the figure:
As you can see bars for all percentiles above 99.0 overlaps and are completely unreadable. I would like to set some fixed space between ticks to have a same space between all of them.
Since you're using pandas, you can do all this from within that library:
means = df.mean(axis=1)/1000
stds = df.std(axis=1)/1000
means.plot.bar(yerr=stds, fc='b')
# Make some room for the x-axis tick labels
plt.subplots_adjust(bottom=0.2)
plt.show()
Not wishing to take anything away from xnx's answer (which is the most elegant way to do things given that you're working in pandas, and therefore likely the best answer for you) but the key insight you're missing is that, in matplotlib, the x positions of the data you're plotting and the x tick labels are independent things. If you say:
nominalX = np.arange( 1, 6 ) ** 2
y = np.arange( 1, 6 ) ** 4
positionalX = np.arange(len(y))
plt.bar( positionalX, y ) # graph y against the numbers 1..n
plt.gca().set(xticks=positionalX + 0.4, xticklabels=nominalX) # ...but superficially label the X values as something else
then that's different from tying positions to your nominal X values:
plt.bar( nominalX, y )
Note that I added 0.4 to the x position of the ticks, because that's half the default width of the bars bar( ..., width=0.8 )—so the ticks end up in the middle of the bar.
I am plotting a DataFrame as a scatter graph using this code:
My dataframe somewhat looks like this -
Sector AvgDeg
0 1 52
1 2 52
2 3 52
3 4 54
4 5 52
... ... ...
df.plot.scatter(x='Sector', y='AvgDeg', s=df['AvgDeg'], color='LightBlue',grid=True)
plt.show()
and I'm getting this result:
What I need is to draw every dot with a different color and with the corresponding legend. For example: -blue dot- 'Sector 1', -red dot- 'Sector 2', and so on.
Do you have any idea how to do this? Tks!!
What you have to do is to use a list of the same size as the points in the c parameter of scatter plot.
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF'])
txt = ["text1", "text2", "text3", "text4"]
fig, ax = plt.subplots()
x = np.arange(1, 5)
y = np.arange(1, 5)
#c will change the colors of each point
#s is the size of each point...
#c_map is the color map you want to use
ax.scatter(x, y,s = 40, cmap = cmap_light, c=np.arange(1, 5))
for i, j in enumerate(txt):
#use the below code to display the text for each point
ax.annotate(j, (x[i], y[i]))
plt.show()
What this gives you as a result is -
To assign more different colors for 31 points for example you just gotta change the size...
ax.scatter(x, y,s = 40, cmap = cmap_light, c=np.arange(1, 32))
Similarly you can annotate those points by changing the txt list above.
i would do it this way:
import matplotlib.pyplot as plt
import matplotlib as mpl
mpl.style.use('ggplot')
colorlist = list(mpl.colors.ColorConverter.colors.keys())
ax = df.plot.scatter(x='Sector', y='AvgDeg', s=df.AvgDeg*1.2,
c=(colorlist * len(df))[:len(df)])
df.apply(lambda x: ax.text(x.Sector, x.AvgDeg, 'Sector {}'.format(x.Sector)), axis=1)
plt.show()
Result
I am trying to replicate the following image in matplotlib and it seems barh is my only option. Though it appears that you can't stack barh graphs so I don't know what to do
If you know of a better python library to draw this kind of thing, please let me know.
This is all I could come up with as a start:
import matplotlib.pyplot as plt; plt.rcdefaults()
import numpy as np
import matplotlib.pyplot as plt
people = ('A','B','C','D','E','F','G','H')
y_pos = np.arange(len(people))
bottomdata = 3 + 10 * np.random.rand(len(people))
topdata = 3 + 10 * np.random.rand(len(people))
fig = plt.figure(figsize=(10,8))
ax = fig.add_subplot(111)
ax.barh(y_pos, bottomdata,color='r',align='center')
ax.barh(y_pos, topdata,color='g',align='center')
ax.set_yticks(y_pos)
ax.set_yticklabels(people)
ax.set_xlabel('Distance')
plt.show()
I would then have to add labels individually using ax.text which would be tedious. Ideally I would like to just specify the width of the part to be inserted then it updates the center of that section with a string of my choosing. The labels on the outside (e.g. 3800) I can add myself later, it is mainly the labeling over the bar section itself and creating this stacked method in a nice way I'm having problems with. Can you even specify a 'distance' i.e. span of color in any way?
Edit 2: for more heterogeneous data. (I've left the above method since I find it more usual to work with the same number of records per series)
Answering the two parts of the question:
a) barh returns a container of handles to all the patches that it drew. You can use the coordinates of the patches to aid the text positions.
b) Following these two answers to the question that I noted before (see Horizontal stacked bar chart in Matplotlib), you can stack bar graphs horizontally by setting the 'left' input.
and additionally c) handling data that is less uniform in shape.
Below is one way you could handle data that is less uniform in shape is simply to process each segment independently.
import numpy as np
import matplotlib.pyplot as plt
# some labels for each row
people = ('A','B','C','D','E','F','G','H')
r = len(people)
# how many data points overall (average of 3 per person)
n = r * 3
# which person does each segment belong to?
rows = np.random.randint(0, r, (n,))
# how wide is the segment?
widths = np.random.randint(3,12, n,)
# what label to put on the segment (xrange in py2.7, range for py3)
labels = range(n)
colors ='rgbwmc'
patch_handles = []
fig = plt.figure(figsize=(10,8))
ax = fig.add_subplot(111)
left = np.zeros(r,)
row_counts = np.zeros(r,)
for (r, w, l) in zip(rows, widths, labels):
print r, w, l
patch_handles.append(ax.barh(r, w, align='center', left=left[r],
color=colors[int(row_counts[r]) % len(colors)]))
left[r] += w
row_counts[r] += 1
# we know there is only one patch but could enumerate if expanded
patch = patch_handles[-1][0]
bl = patch.get_xy()
x = 0.5*patch.get_width() + bl[0]
y = 0.5*patch.get_height() + bl[1]
ax.text(x, y, "%d%%" % (l), ha='center',va='center')
y_pos = np.arange(8)
ax.set_yticks(y_pos)
ax.set_yticklabels(people)
ax.set_xlabel('Distance')
plt.show()
Which produces a graph like this , with a different number of segments present in each series.
Note that this is not particularly efficient since each segment used an individual call to ax.barh. There may be more efficient methods (e.g. by padding a matrix with zero-width segments or nan values) but this likely to be problem-specific and is a distinct question.
Edit: updated to answer both parts of the question.
import numpy as np
import matplotlib.pyplot as plt
people = ('A','B','C','D','E','F','G','H')
segments = 4
# generate some multi-dimensional data & arbitrary labels
data = 3 + 10* np.random.rand(segments, len(people))
percentages = (np.random.randint(5,20, (len(people), segments)))
y_pos = np.arange(len(people))
fig = plt.figure(figsize=(10,8))
ax = fig.add_subplot(111)
colors ='rgbwmc'
patch_handles = []
left = np.zeros(len(people)) # left alignment of data starts at zero
for i, d in enumerate(data):
patch_handles.append(ax.barh(y_pos, d,
color=colors[i%len(colors)], align='center',
left=left))
# accumulate the left-hand offsets
left += d
# go through all of the bar segments and annotate
for j in range(len(patch_handles)):
for i, patch in enumerate(patch_handles[j].get_children()):
bl = patch.get_xy()
x = 0.5*patch.get_width() + bl[0]
y = 0.5*patch.get_height() + bl[1]
ax.text(x,y, "%d%%" % (percentages[i,j]), ha='center')
ax.set_yticks(y_pos)
ax.set_yticklabels(people)
ax.set_xlabel('Distance')
plt.show()
You can achieve a result along these lines (note: the percentages I used have nothing to do with the bar widths, as the relationship in the example seems unclear):
See Horizontal stacked bar chart in Matplotlib for some ideas on stacking horizontal bar plots.
Imports and Test DataFrame
Tested in python 3.10, pandas 1.4.2, matplotlib 3.5.1, seaborn 0.11.2
For vertical stacked bars see Stacked Bar Chart with Centered Labels
import pandas as pd
import numpy as np
# create sample data as shown in the OP
np.random.seed(365)
people = ('A','B','C','D','E','F','G','H')
bottomdata = 3 + 10 * np.random.rand(len(people))
topdata = 3 + 10 * np.random.rand(len(people))
# create the dataframe
df = pd.DataFrame({'Female': bottomdata, 'Male': topdata}, index=people)
# display(df)
Female Male
A 12.41 7.42
B 9.42 4.10
C 9.85 7.38
D 8.89 10.53
E 8.44 5.92
F 6.68 11.86
G 10.67 12.97
H 6.05 7.87
Updated with matplotlib v3.4.2
Use matplotlib.pyplot.bar_label
See How to add value labels on a bar chart for additional details and examples with .bar_label.
labels = [f'{v.get_width():.2f}%' if v.get_width() > 0 else '' for v in c ] for python < 3.8, without the assignment expression (:=).
Plotted using pandas.DataFrame.plot with kind='barh'
ax = df.plot(kind='barh', stacked=True, figsize=(8, 6))
for c in ax.containers:
# customize the label to account for cases when there might not be a bar section
labels = [f'{w:.2f}%' if (w := v.get_width()) > 0 else '' for v in c ]
# set the bar label
ax.bar_label(c, labels=labels, label_type='center')
# uncomment and use the next line if there are no nan or 0 length sections; just use fmt to add a % (the previous two lines of code are not needed, in this case)
# ax.bar_label(c, fmt='%.2f%%', label_type='center')
# move the legend
ax.legend(bbox_to_anchor=(1.025, 1), loc='upper left', borderaxespad=0.)
# add labels
ax.set_ylabel("People", fontsize=18)
ax.set_xlabel("Percent", fontsize=18)
plt.show()
Using seaborn
sns.barplot does not have an option for stacked bar plots, however, sns.histplot and sns.displot can be used to create horizontal stacked bars.
seaborn typically requires the dataframe to be in a long, instead of wide, format, so use pandas.DataFrame.melt to reshape the dataframe.
Reshape dataframe
# convert the dataframe to a long form
df = df.reset_index()
df = df.rename(columns={'index': 'People'})
dfm = df.melt(id_vars='People', var_name='Gender', value_name='Percent')
# display(dfm)
People Gender Percent
0 A Female 12.414557
1 B Female 9.416027
2 C Female 9.846105
3 D Female 8.885621
4 E Female 8.438872
5 F Female 6.680709
6 G Female 10.666258
7 H Female 6.050124
8 A Male 7.420860
9 B Male 4.104433
10 C Male 7.383738
11 D Male 10.526158
12 E Male 5.916262
13 F Male 11.857227
14 G Male 12.966913
15 H Male 7.865684
sns.histplot: axes-level plot
fig, axe = plt.subplots(figsize=(8, 6))
sns.histplot(data=dfm, y='People', hue='Gender', discrete=True, weights='Percent', multiple='stack', ax=axe)
# iterate through each set of containers
for c in axe.containers:
# add bar annotations
axe.bar_label(c, fmt='%.2f%%', label_type='center')
axe.set_xlabel('Percent')
plt.show()
sns.displot: figure-level plot
g = sns.displot(data=dfm, y='People', hue='Gender', discrete=True, weights='Percent', multiple='stack', height=6)
# iterate through each facet / supbplot
for axe in g.axes.flat:
# iteate through each set of containers
for c in axe.containers:
# add the bar annotations
axe.bar_label(c, fmt='%.2f%%', label_type='center')
axe.set_xlabel('Percent')
plt.show()
Original Answer - before matplotlib v3.4.2
The easiest way to plot a horizontal or vertical stacked bar, is to load the data into a pandas.DataFrame
This will plot, and annotate correctly, even when all categories ('People'), don't have all segments (e.g. some value is 0 or NaN)
Once the data is in the dataframe:
It's easier to manipulate and analyze
It can be plotted with the matplotlib engine, using:
pandas.DataFrame.plot.barh
label_text = f'{width}' for annotations
pandas.DataFrame.plot.bar
label_text = f'{height}' for annotations
SO: Vertical Stacked Bar Chart with Centered Labels
These methods return a matplotlib.axes.Axes or a numpy.ndarray of them.
Using the .patches method unpacks a list of matplotlib.patches.Rectangle objects, one for each of the sections of the stacked bar.
Each .Rectangle has methods for extracting the various values that define the rectangle.
Each .Rectangle is in order from left the right, and bottom to top, so all the .Rectangle objects, for each level, appear in order, when iterating through .patches.
The labels are made using an f-string, label_text = f'{width:.2f}%', so any additional text can be added as needed.
Plot and Annotate
Plotting the bar, is 1 line, the remainder is annotating the rectangles
# plot the dataframe with 1 line
ax = df.plot.barh(stacked=True, figsize=(8, 6))
# .patches is everything inside of the chart
for rect in ax.patches:
# Find where everything is located
height = rect.get_height()
width = rect.get_width()
x = rect.get_x()
y = rect.get_y()
# The height of the bar is the data value and can be used as the label
label_text = f'{width:.2f}%' # f'{width:.2f}' to format decimal values
# ax.text(x, y, text)
label_x = x + width / 2
label_y = y + height / 2
# only plot labels greater than given width
if width > 0:
ax.text(label_x, label_y, label_text, ha='center', va='center', fontsize=8)
# move the legend
ax.legend(bbox_to_anchor=(1.05, 1), loc='upper left', borderaxespad=0.)
# add labels
ax.set_ylabel("People", fontsize=18)
ax.set_xlabel("Percent", fontsize=18)
plt.show()
Example with Missing Segment
# set one of the dataframe values to 0
df.iloc[4, 1] = 0
Note the annotations are all in the correct location from df.
For this case, the above answers work perfectly. The issue I had, and didn't find a plug-and-play solution online, was that I often have to plot stacked bars in multi-subplot figures, with many values, which tend to have very non-homogenous amplitudes.
(Note: I work usually with pandas dataframes, and matplotlib. I couldn't make the bar_label() method of matplotlib to work all the times.)
So, I just give a kind of ad-hoc, but easily generalizable solution. In this example, I was working with single-row dataframes (for power-exchange monitoring purposes per hour), so, my dataframe (df) had just one row.
(I provide an example figure to show how this can be useful in very densely-packed plots)
[enter image description here][1]
[1]: https://i.stack.imgur.com/9akd8.png
'''
This implementation produces a stacked, horizontal bar plot.
df --> pandas dataframe. Columns are used as the iterator, and only the firs value of each column is used.
waterfall--> bool: if True, apart from the stack-direction, also a perpendicular offset is added.
cyclic_offset_x --> list (of any length) or None: loop through these values to use as x-offset pixels.
cyclic_offset_y --> list (of any length) or None: loop through these values to use as y-offset pixels.
ax --> matplotlib Axes, or None: if None, creates a new axis and figure.
'''
def magic_stacked_bar(df, waterfall=False, cyclic_offset_x=None, cyclic_offset_y=None, ax=None):
if isinstance(cyclic_offset_x, type(None)):
cyclic_offset_x = [0, 0]
if isinstance(cyclic_offset_y, type(None)):
cyclic_offset_y = [0, 0]
ax0 = ax
if isinstance(ax, type(None)):
fig, ax = plt.subplots()
fig.set_size_inches(19, 10)
cycler = 0;
prev = 0 # summation variable to make it stacked
for c in df.columns:
if waterfall:
y = c ; label = "" # bidirectional stack
else:
y = 0; label = c # unidirectional stack
ax.barh(y=y, width=df[c].values[0], height=1, left=prev, label = label)
prev += df[c].values[0] # add to sum-stack
offset_x = cyclic_offset_x[divmod(cycler, len(cyclic_offset_x))[1]]
offset_y = cyclic_offset_y[divmod(cycler, len(cyclic_offset_y))[1]]
ax.annotate(text="{}".format(int(df[c].values[0])), xy=(prev - df[c].values / 2, y),
xytext=(offset_x, offset_y), textcoords='offset pixels',
ha='center', va='top', fontsize=8,
arrowprops=dict(facecolor='black', shrink=0.01, width=0.3, headwidth=0.3),
bbox=dict(boxstyle='round', facecolor='grey', alpha=0.5))
cycler += 1
if not waterfall:
ax.legend() # if waterfall, the index annotates the columns. If
# waterfall ==False, the legend annotates the columns
if isinstance(ax0, type(None)):
ax.set_title("Voi la")
ax.set_xlabel("UltraWatts")
plt.show()
else:
return ax
''' (Sometimes, it is more tedious and requires some custom functions to make the labels look alright.
'''
A, B = 80,80
n_units = df.shape[1]
cyclic_offset_x = -A*np.cos(2*np.pi / (2*n_units) *np.arange(n_units))
cyclic_offset_y = B*np.sin(2*np.pi / (2*n_units) * np.arange(n_units)) + B/2