I'm trying to duplicate my y axis so that it appears on both the left and the right side of my graph (same scale on each side). I believe the correct way to do this is through the twiny method, but cannot get my head round it. Here is my current code:
import matplotlib as mpl
mpl.use('Agg')
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
def bar(data_df,
colour_df=None,
method='default',
ret_obj=False):
height = len(data_df.columns)*4
width = len(data_df.index)/4
ind = np.arange(len(data_df.index))
dat = data_df[data_df.columns[0]]
bar_width = 0.85
fig, ax = plt.subplots(figsize=(width,height))
ax1 = ax.bar(ind,dat,bar_width,color='y',log=True)
ax2 = ax1.twiny()
ax.tick_params(bottom='off', top='off', left='on', right='on')
plt.xticks(np.arange(len(data_df.index)) + bar_width,
data_df.index, rotation=67,ha='right')
ylab = 'Region Length (base pairs, log10)'
figname = 'bar' + method + '.png'
if ret_obj==False:
fig.savefig(figname,bbox_inches='tight',dpi=250)
print "Output figure:", figname
plt.close()
if ret_obj==True:
return fig
Which returns the following error when passed a dataframe:
AttributeError: 'BarContainer' object has no attribute 'twiny'
Having looked into it a bit further I believe that using the host/parasite methods would also work, but I'm a bit lost how I could fit it into my current code. Advice would be gratefully appreciated!
You don't have to use twiny in this case. It suffices to draw the labels on all sides:
bars = ax.bar(ind,dat,bar_width,color='y',log=True)
ax.tick_params(axis='both', which='both', labelbottom=True, labeltop=True,
labelleft=True, labelright=True)
I get following result with dummy data:
df = pd.DataFrame({"a": np.logspace(1,10,20)})
bar(df)
Related
I usually don't ask questions on this platform, but I have a problem that quite bugs me.
Context
I have a function that plots data from a dataframe that has stockdata. It all works perfectly except for the fact that a second, empty window shows next to the actual graph whenever I execute this function. (image)
Here is all the relevant code, I'd be very grateful if some smart people could help me.
def plot(self):
plt.clf()
plt.cla()
colors = Colors()
data = self.getStockData()
if data.empty:
return
data.index = [TimeData.fromTimestamp(x) for x in data.index]
current, previous = data.iloc[-1, 1], data.iloc[0, 1]
percentage = (current / previous - 1) * 100
# Create a table
color = colors.decideColorPct(percentage)
# Create the table
fig = plt.figure(edgecolor=colors.NEUTRAL_COLOR)
fig.patch.set_facecolor(colors.BACKGROUND_COLOR)
plt.plot(data.close, color=color)
plt.title(self.__str2__(), color=colors.NEUTRAL_COLOR)
plt.ylabel("Share price in $", color=colors.NEUTRAL_COLOR)
plt.xlabel("Date", color=colors.NEUTRAL_COLOR)
ax = plt.gca()
ax.xaxis.set_major_formatter(plt_dates.DateFormatter('%Y/%m/%d %H:%M'))
ax.set_xticks([data.index[0], data.index[-1]])
ax.set_facecolor(colors.BACKGROUND_COLOR)
ax.tick_params(color=colors.NEUTRAL_COLOR, labelcolor=colors.NEUTRAL_COLOR)
for spine in ax.spines.values():
spine.set_edgecolor(colors.NEUTRAL_COLOR)
ax.yaxis.grid(True, color=colors.NEUTRAL_COLOR, linestyle=(0, (5, 10)), linewidth=.5)
plt.show()
Some notes:
Matplotlib never gets used in the program before this.
The data is standardized and consists of the following columns: open, low, high, close, volume.
The index of the dataframe exists of timestamps, which gets converted to an index of datetime objects at the following line: data.index = [TimeData.fromTimestamp(x) for x in data.index]
Remove plt.clf() and plt.cla() because it automatically creates window for plot when you don't have this window.
And later fig = plt.figure() creates new window which it uses to display your plot.
Minimal code for test
import matplotlib.pyplot as plt
import pandas as pd
data = pd.DataFrame({'x': [1,2,3], 'y': [2,3,1]})
#plt.clf()
#plt.cla()
fig = plt.figure()
plt.plot(data)
ax = plt.gca()
plt.show()
Hi I'm trying to plot a pointplot and scatterplot on one graph with the same dataset so I can see the individual points that make up the pointplot.
Here is the code I am using:
xlPath = r'path to data here'
df = pd.concat(pd.read_excel(xlPath, sheet_name=None),ignore_index=True)
sns.pointplot(data=df, x='ID', y='HM (N/mm2)', palette='bright', capsize=0.15, alpha=0.5, ci=95, join=True, hue='Layer')
sns.scatterplot(data=df, x='ID', y='HM (N/mm2)')
plt.show()
When I plot, for some reason the points from the scatterplot are offsetting one ID spot right on the x-axis. When I plot the scatter or the point plot separately, they each are in the correct ID spot. Why would plotting them on the same plot cause the scatterplot to offset one right?
Edit: Tried to make the ID column categorical, but that didn't work either.
Seaborn's pointplot creates a categorical x-axis while here the scatterplot uses a numerical x-axis.
Explicitly making the x-values categorical: df['ID'] = pd.Categorical(df['ID']), isn't sufficient, as the scatterplot still sees numbers. Changing the values to strings does the trick. To get them in the correct order, sorting might be necessary.
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
# first create some test data
df = pd.DataFrame({'ID': np.random.choice(np.arange(1, 49), 500),
'HM (N/mm2)': np.random.uniform(1, 10, 500)})
df['Layer'] = ((df['ID'] - 1) // 6) % 4 + 1
df['HM (N/mm2)'] += df['Layer'] * 8
df['Layer'] = df['Layer'].map(lambda s: f'Layer {s}')
# sort the values and convert the 'ID's to strings
df = df.sort_values('ID')
df['ID'] = df['ID'].astype(str)
fig, ax = plt.subplots(figsize=(12, 4))
sns.pointplot(data=df, x='ID', y='HM (N/mm2)', palette='bright',
capsize=0.15, alpha=0.5, ci=95, join=True, hue='Layer', ax=ax)
sns.scatterplot(data=df, x='ID', y='HM (N/mm2)', color='purple', ax=ax)
ax.margins(x=0.02)
plt.tight_layout()
plt.show()
Updated question and code!
Probably, the tips dataset is not the best example to use, however my issue is reproduced in it, i.e. we see that both point and bar plots share the same Y
I need to combine line and bar plots on one chart. To do this I used seaborn and the following code:
tips = sns.load_dataset('tips')
g = sns.FacetGrid(tips, hue='sex', col='sex', size=4, aspect=2.1, sharey=False, sharex=False)
g = g.map(sns.pointplot, 'day', 'tip', ci=0)
g = g.map(sns.barplot, 'day', 'total_bill', ci=0)
g.set_xticklabels(rotation=45, fontsize=9)
g.set_xticklabels(rotation=45, fontsize=9)
plt.show()
Here is the result:
Everything is okay except the fact that one Y axis is used for both bars and lines on each facetgrid object. I am new to seaborn and currently cannot find a solution. Tried to add "sharey=False" to this line of code
> `g.map(sns.pointplot, 'date', 'worthusdcount')`
however it didn't help.
Any solutions on how to add second Y axis would be appreciated
Here's an example where you apply a custom mapping function to the dataframe of interest. Within the function, you can call plt.gca() to get the current axis at the facet being currently plotted in FacetGrid. Once you have the axis, twinx() can be called just like you would in plain old matplotlib plotting.
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns
def facetgrid_two_axes(*args, **kwargs):
data = kwargs.pop('data')
dual_axis = kwargs.pop('dual_axis')
alpha = kwargs.pop('alpha', 0.2)
kwargs.pop('color')
ax = plt.gca()
if dual_axis:
ax2 = ax.twinx()
ax2.set_ylabel('Second Axis!')
ax.plot(data['x'],data['y1'], **kwargs, color='red',alpha=alpha)
if dual_axis:
ax2.bar(df['x'],df['y2'], **kwargs, color='blue',alpha=alpha)
df = pd.DataFrame()
df['x'] = np.arange(1,5,1)
df['y1'] = 1 / df['x']
df['y2'] = df['x'] * 100
df['facet'] = 'foo'
df2 = df.copy()
df2['facet'] = 'bar'
df3 = pd.concat([df,df2])
win_plot = sns.FacetGrid(df3, col='facet', size=6)
(win_plot.map_dataframe(facetgrid_two_axes, dual_axis=True)
.set_axis_labels("X", "First Y-axis"))
plt.show()
This isn't the prettiest plot as you might want to adjust the presence of the second y-axis' label, the spacing between plots, etc. but the code suffices to show how to plot two series of differing magnitudes within FacetGrids.
Is there any possibility to do a bar plot without y-(x-)axis? In presentations all redundant informations have to be erased, so I would like to begin to delete the axis. I did not see helpful informations in the matplotlib documentation. Maybe you have better solutions than pyplot..?
Edit: I would like to have lines around the bars except the axis at the bottom. Is this possible
#!/usr/bin/env python
import matplotlib.pyplot as plt
ind = (1,2,3)
width = 0.8
fig = plt.figure(1)
p1 = plt.bar(ind,ind)
# plt.show()
fig.savefig("test.svg")
Edit: I did not see using plt.show()
that there is still the yaxis without ticks.
To make the axes not visible, try something like
import matplotlib.pyplot as plt
ind = (1,2,3)
width = 0.8
fig,a = plt.subplots()
p1 = a.bar(ind,ind)
a.xaxis.set_visible(False)
a.yaxis.set_visible(False)
plt.show()
Is this what you meant?
Here is the code I used at the end. It is not minimal anymore. Maybe it helps.
import matplotlib.pyplot as plt
import numpy as np
def adjust_spines(ax,spines):
for loc, spine in ax.spines.items():
if loc in spines:
spine.set_smart_bounds(True)
else:
spine.set_color('none') # don't draw spine
# turn off ticks where there is no spine
if 'left' in spines:
ax.yaxis.set_ticks_position('left')
else:
# no yaxis ticks
ax.yaxis.set_ticks([])
def nbar(samples, data, err, bWidth=0.4, bSafe=True, svgName='out'):
fig,a = plt.subplots(frameon=False)
if len(data)!=len(samples):
print("length(data) must be equal to length(samples)!")
return
ticks = np.arange(len(data))
p1 = plt.bar(ticks, data, bWidth, yerr=err)
plt.xticks(ticks+bWidth/2., samples )
adjust_spines(a,['bottom'])
a.xaxis.tick_bottom()
if bSafe:
fig.savefig(svgName+".svg")
samples = ('Sample1', 'Sample2','Sample3')
qyss = (91, 44, 59)
qysserr = (1,5,4)
nbar(samples,qyss,qysserr,svgName="test")
Thx to all contributors.
I want to create a bar chart of two series (say 'A' and 'B') contained in a Pandas dataframe. If I wanted to just plot them using a different y-axis, I can use secondary_y:
df = pd.DataFrame(np.random.uniform(size=10).reshape(5,2),columns=['A','B'])
df['A'] = df['A'] * 100
df.plot(secondary_y=['A'])
but if I want to create bar graphs, the equivalent command is ignored (it doesn't put different scales on the y-axis), so the bars from 'A' are so big that the bars from 'B' are cannot be distinguished:
df.plot(kind='bar',secondary_y=['A'])
How can I do this in pandas directly? or how would you create such graph?
I'm using pandas 0.10.1 and matplotlib version 1.2.1.
Don't think pandas graphing supports this. Did some manual matplotlib code.. you can tweak it further
import pylab as pl
fig = pl.figure()
ax1 = pl.subplot(111,ylabel='A')
#ax2 = gcf().add_axes(ax1.get_position(), sharex=ax1, frameon=False, ylabel='axes2')
ax2 =ax1.twinx()
ax2.set_ylabel('B')
ax1.bar(df.index,df.A.values, width =0.4, color ='g', align = 'center')
ax2.bar(df.index,df.B.values, width = 0.4, color='r', align = 'edge')
ax1.legend(['A'], loc = 'upper left')
ax2.legend(['B'], loc = 'upper right')
fig.show()
I am sure there are ways to force the one bar further tweak it. move bars further apart, one slightly transparent etc.
Ok, I had the same problem recently and even if it's an old question, I think that I can give an answer for this problem, in case if someone else lost his mind with this. Joop gave the bases of the thing to do, and it's easy when you only have (for exemple) two columns in your dataframe, but it becomes really nasty when you have a different numbers of columns for the two axis, due to the fact that you need to play with the position argument of the pandas plot() function. In my exemple I use seaborn but it's optionnal :
import pandas as pd
import seaborn as sns
import pylab as plt
import numpy as np
df1 = pd.DataFrame(np.array([[i*99 for i in range(11)]]).transpose(), columns = ["100"], index = [i for i in range(11)])
df2 = pd.DataFrame(np.array([[i for i in range(11)], [i*2 for i in range(11)]]).transpose(), columns = ["1", "2"], index = [i for i in range(11)])
fig, ax = plt.subplots()
ax2 = ax.twinx()
# we must define the length of each column.
df1_len = len(df1.columns.values)
df2_len = len(df2.columns.values)
column_width = 0.8 / (df1_len + df2_len)
# we calculate the position of each column in the plot. This value is based on the position definition :
# Specify relative alignments for bar plot layout. From 0 (left/bottom-end) to 1 (right/top-end). Default is 0.5 (center)
# http://pandas.pydata.org/pandas-docs/dev/generated/pandas.DataFrame.plot.html
df1_posi = 0.5 + (df2_len/float(df1_len)) * 0.5
df2_posi = 0.5 - (df1_len/float(df2_len)) * 0.5
# In order to have nice color, I use the default color palette of seaborn
df1.plot(kind='bar', ax=ax, width=column_width*df1_len, color=sns.color_palette()[:df1_len], position=df1_posi)
df2.plot(kind='bar', ax=ax2, width=column_width*df2_len, color=sns.color_palette()[df1_len:df1_len+df2_len], position=df2_posi)
ax.legend(loc="upper left")
# Pandas add line at x = 0 for each dataframe.
ax.lines[0].set_visible(False)
ax2.lines[0].set_visible(False)
# Specific to seaborn, we have to remove the background line
ax2.grid(b=False, axis='both')
# We need to add some space, the xlim don't manage the new positions
column_length = (ax2.get_xlim()[1] - abs(ax2.get_xlim()[0])) / float(len(df1.index))
ax2.set_xlim([ax2.get_xlim()[0] - column_length, ax2.get_xlim()[1] + column_length])
fig.patch.set_facecolor('white')
plt.show()
And the result : http://i.stack.imgur.com/LZjK8.png
I didn't test every possibilities but it looks like it works fine whatever the number of columns in each dataframe you use.