I try to plot a bar graph with a pre-defined number of grid lines like below. However, once I plot it, some yticklabels (A_2,A_3,etc) have not shown (only A_1, A_5, A_9,A_13,A_17 shown). I want to keep all ytick labels, but the gridline should be the same as x axis. Do you have any ideas to fix it?
import matplotlib.pyplot as plt
import numpy as np
mdict={"Column1":["A_"+str(i) for i in range(1,21)],"Value":[i for i in range(1,21)]}
# Create a dataframe
df=pd.DataFrame(mdict)
# Set plot params
fig, ax = plt.subplots(figsize=(12,8))
ax.barh(df.Column1,df.Value, color="darkgray",edgecolor="black", linewidth=0.5)
ax.set_xlabel("Numbers", fontsize=15)
# ax.set_yticklabels(list(df_cor.Country.values.tolist()), fontsize=15)
major_ticks_top=np.linspace(0,20,6)
minor_ticks_top=np.linspace(0,20,6)
ax.set_xticks(major_ticks_top)
ax.set_yticks(minor_ticks_top)
ax.grid(alpha=0.2,color="black")
plt.show()
I wouldn't explicitly set the ticks and labels but modify the output matplotlib generates:
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib.ticker import MultipleLocator
mdict={"Column1":["A_"+str(i) for i in range(1,21)],"Value":[i for i in range(1,21)]}
df=pd.DataFrame(mdict)
fig, ax = plt.subplots(figsize=(12,8))
ax.barh(df.Column1, df.Value, color="darkgray", edgecolor="black", linewidth=0.5)
ax.set_xlabel("Numbers", fontsize=15)
#set every fourth tick
n=4
ax.xaxis.set_major_locator(MultipleLocator(n))
ax.grid(alpha=0.2,color="black")
#remove unwanted gridlines on the y-axis
ygrd_lines = ax.get_ygridlines()
[grd_line.set_visible(False) for i, grd_line in enumerate(ygrd_lines) if i%n]
plt.show()
Sample output:
Methods used:
MultipleLocator() setting ticks at defined intervals
.get_ygridlines returning gridlines as a list of Line2D objects for further modification
Related
I have dataframe like this:
df_meshX_min_select = pd.DataFrame({
'Number of Elements' : [5674, 8810,13366,19751,36491],
'Time (a)' : [42.14, 51.14, 55.64, 55.14, 56.64],
'Different Result(Temperature)' : [0.083849, 0.057309, 0.055333, 0.060516, 0.035343]})
and I tried to combine bar plot (number of elements Vs Different result) and line plot (Number of elements Vs Time) in the same figure, but I found the following problem like this:
it seems that x_value doesn't match when combining 2 plots, but if you see the data frame, the x value is exactly the same value.
My expectation is combining these 2 plots into 1 figure:
and this is the code that I made:
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
df_meshX_min_select = pd.DataFrame({
'Number of Elements' : [5674, 8810,13366,19751,36491],
'Time (a)' : [42.14, 51.14, 55.64, 55.14, 56.64],
'Different Result(Temperature)' : [0.083849, 0.057309, 0.055333, 0.060516, 0.035343]})
x1= df_meshX_min_select["Number of Elements"]
t1= df_meshX_min_select["Time (a)"]
T1= df_meshX_min_select["Different Result(Temperature)"]
#Create combo chart
fig, ax1 = plt.subplots(figsize=(10,6))
color = 'tab:green'
#bar plot creation
ax1.set_title('Mesh Analysis', fontsize=16)
ax1.set_xlabel('Number of elements', fontsize=16)
ax1.set_ylabel('Different Result(Temperature)', fontsize=16)
ax1 = sns.barplot(x='Number of Elements', y='Different Result(Temperature)', data = df_meshX_min_select)
ax1.tick_params(axis='y')
#specify we want to share the same x-axis
ax2 = ax1.twinx()
color = 'tab:red'
#line plot creation
ax2.set_ylabel('Time (a)', fontsize=16)
ax2 = sns.lineplot(x='Number of Elements', y='Time (a)', data = df_meshX_min_select, sort=False, color=color, ax=ax2)
ax2.tick_params(axis='y', color=color)
#show plot
plt.show()
Anyone can help me, please?
Seaborn and pandas use a categorical x-axis for bar plots (internally numbered 0,1,2,...) and floating-point numbers for a line plot. Note that your x-values aren't evenly spaced, so either the bars would have weird distances between them, or wouldn't align with the x-values from the line plot.
Here is a solution using standard matplotlib to combine both graphs.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
df_meshx_min_select = pd.DataFrame({
'number of elements': [5674, 8810, 13366, 19751, 36491],
'time (a)': [42.14, 51.14, 55.64, 55.14, 56.64],
'different result(temperature)': [0.083849, 0.057309, 0.055333, 0.060516, 0.035343]})
x1 = df_meshx_min_select["number of elements"]
t1 = df_meshx_min_select["time (a)"]
d1 = df_meshx_min_select["different result(temperature)"]
fig, ax1 = plt.subplots(figsize=(10, 6))
color = 'limegreen'
ax1.set_title('mesh analysis', fontsize=16)
ax1.set_xlabel('number of elements', fontsize=16)
ax1.set_ylabel('different result(temperature)', fontsize=16, color=color)
ax1.bar(x1, height=d1, width=2000, color=color)
ax1.tick_params(axis='y', colors=color)
ax2 = ax1.twinx() # share the x-axis, new y-axis
color = 'crimson'
ax2.set_ylabel('time (a)', fontsize=16, color=color)
ax2.plot(x1, t1, color=color)
ax2.tick_params(axis='y', colors=color)
plt.show()
I was plotting a boxplot with a lineplot and I had the same problem even my two x-axes are identical, so I solved converting my x-axis feature to type string:
df_meshX_min_select['Number of Elements'] = df_meshX_min_select['Number of Elements'].astype('string')
This way the plot works using seaborn:
I am using matplotlib to plot a pie chart. I have added a legend to the chart. However, i would like to add a "Total" to the legend, to sum up the values of all the other categories. Hence the value of "Total" would not be a part of the pie chart, and would only be shown in the legend. Is it possible for me to do that? Thank you.
You can create 2 legends. On the second one, you can create/manipulate symbol/text/title as you want. Here is a runnable code that you can try.
from matplotlib import pyplot as plt
import matplotlib.patches as mpatches
import numpy as np
fig = plt.figure()
ax = fig.add_axes([0,0,1,1])
ax.axis('equal')
langs = ['C', 'C++', 'Java', 'Python', 'PHP']
students = [23,17,35,29,12]
ax.pie(students, labels = langs,autopct='%1.2f%%')
# first legend
lgn = plt.legend()
ax = plt.gca().add_artist(lgn)
# second legend
gold_patch = mpatches.Patch(color='gold', label='Total= 9999') # use your description text here
second_legend = plt.legend(handles=[gold_patch], loc=1, \
bbox_to_anchor=(0.5, 0.35, 0.55, 0.35)) # adjust location of legend here
second_legend.set_frame_on(False) # use True/False as needed
second_legend.set_title("Other categories")
plt.show()
The output plot:
I am using subplots in a function which is using a slider widget inputs to calculate some stuff and plotting results.
I want to turn on the grid for all subplots of ax1. But somehow jupternotebooks only turns it on only on the last plot...
import numpy as np
from matplotlib import pyplot as plt
import ipywidgets as widgets
from IPython.html.widgets import interact
%matplotlib inline
## Plot
fig, ax1 = plt.subplots(6,2)
plt.subplots_adjust(right = 2, top = 8 )
# Show the major grid lines with dark grey lines
plt.grid(b=True, which='major', color='#666666', linestyle='-')
# Show the minor grid lines with very faint and almost transparent grey lines
plt.minorticks_on()
plt.grid(b=True, which='minor', color='#999999', linestyle='-', alpha=0.2)
## Giergeschwindigkeit über v und ay
ax1[0,0].plot(v_ms, omega)
ax1[0,0].set_ylabel('Giergeschwindigkeit [rad/s]')
ax1[0,0].set_xlabel('Geschwindigkeit [m/s]')
ax1[0,0].set_title('Giergeschwindigkeit über Geschwindigkeit')
# ... more subplots
plt.show()
It looks like this:
And can you explain to me why in my case
ax1.grid()
throws an error?
AttributeError: 'numpy.ndarray' object has no attribute 'grid'
This is because plt will only operate on the last-created axes object.
And the reason you're getting that error is that ax1 is a numpy n-dimensional array, not an axes object.
You can do this to iterate over the numpy n-dimensional array to create the grids:
for row in axes:
for ax in row:
ax.grid(b=True, which='major', color='#666666', linestyle='-')
ax.minorticks_on()
ax.grid(b=True, which='minor', color='#999999', linestyle='-',alpha=0.2)
Result (without plt.subplots_adjust()):
You can set grid for every ax object, so in your case you should set like this:
ax1[0,0].grid()
ax1[0,1].grid()
So currently learning how to import data and work with it in matplotlib and I am having trouble even tho I have the exact code from the book.
This is what the plot looks like, but my question is how can I get it where there is no white space between the start and the end of the x-axis.
Here is the code:
import csv
from matplotlib import pyplot as plt
from datetime import datetime
# Get dates and high temperatures from file.
filename = 'sitka_weather_07-2014.csv'
with open(filename) as f:
reader = csv.reader(f)
header_row = next(reader)
#for index, column_header in enumerate(header_row):
#print(index, column_header)
dates, highs = [], []
for row in reader:
current_date = datetime.strptime(row[0], "%Y-%m-%d")
dates.append(current_date)
high = int(row[1])
highs.append(high)
# Plot data.
fig = plt.figure(dpi=128, figsize=(10,6))
plt.plot(dates, highs, c='red')
# Format plot.
plt.title("Daily high temperatures, July 2014", fontsize=24)
plt.xlabel('', fontsize=16)
fig.autofmt_xdate()
plt.ylabel("Temperature (F)", fontsize=16)
plt.tick_params(axis='both', which='major', labelsize=16)
plt.show()
There is an automatic margin set at the edges, which ensures the data to be nicely fitting within the axis spines. In this case such a margin is probably desired on the y axis. By default it is set to 0.05 in units of axis span.
To set the margin to 0 on the x axis, use
plt.margins(x=0)
or
ax.margins(x=0)
depending on the context. Also see the documentation.
In case you want to get rid of the margin in the whole script, you can use
plt.rcParams['axes.xmargin'] = 0
at the beginning of your script (same for y of course). If you want to get rid of the margin entirely and forever, you might want to change the according line in the matplotlib rc file:
axes.xmargin : 0
axes.ymargin : 0
Example
import seaborn as sns
import matplotlib.pyplot as plt
tips = sns.load_dataset('tips')
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
tips.plot(ax=ax1, title='Default Margin')
tips.plot(ax=ax2, title='Margins: x=0')
ax2.margins(x=0)
Alternatively, use plt.xlim(..) or ax.set_xlim(..) to manually set the limits of the axes such that there is no white space left.
If you only want to remove the margin on one side but not the other, e.g. remove the margin from the right but not from the left, you can use set_xlim() on a matplotlib axes object.
import seaborn as sns
import matplotlib.pyplot as plt
import math
max_x_value = 100
x_values = [i for i in range (1, max_x_value + 1)]
y_values = [math.log(i) for i in x_values]
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
sn.lineplot(ax=ax1, x=x_values, y=y_values)
sn.lineplot(ax=ax2, x=x_values, y=y_values)
ax2.set_xlim(-5, max_x_value) # tune the -5 to your needs
Given the shape file available here: I know can produce the basic map that I need with county labels and even some points on the map (see below). The issue I'm having is that I cannot seem to control the size of the figure with figsize.
Here's what I have:
import geopandas as gpd
import matplotlib.pyplot as plt
%matplotlib inline
figsize=5,5
fig = plt.figure(figsize=(figsize),dpi=300)
shpfileshpfile=r'Y:\HQ\TH\Groups\NR\PSPD\Input\US_Counties\cb_2015_us_county_20m.shp'
c=gpd.read_file(shpfile)
c=c.loc[c['GEOID'].isin(['26161','26093','26049','26091','26075','26125','26163','26099','26115','26065'])]
c['coords'] = c['geometry'].apply(lambda x: x.representative_point().coords[:])
c['coords'] = [coords[0] for coords in c['coords']]
ax=c.plot()
#Control some attributes regarding the axis (for the plot above)
ax.spines['top'].set_visible(False);ax.spines['bottom'].set_visible(False);ax.spines['left'].set_visible(False);ax.spines['right'].set_visible(False)
ax.tick_params(axis='y',which='both',left='off',right='off',color='none',labelcolor='none')
ax.tick_params(axis='x',which='both',top='off',bottom='off',color='none',labelcolor='none')
for idx, row in c.iterrows():
ax.annotate(s=row['NAME'], xy=row['coords'],
horizontalalignment='center')
lat2=[42.5,42.3]
lon2=[-84,-83.5]
#Add another plot...
ax.plot(lon2,lat2,alpha=1,marker='o',linestyle='none',markeredgecolor='none',markersize=15,color='white')
plt.show()
As you can see, I opted to call the plots by the axis name because I need to control attributes of the axis, such as tick_params. I'm not sure if there is a better approach. This seems like a "no-brainer" but I can't seem to figure out why I can't control the figure size.
Thanks in advance!
I just had to do the following:
Use fig, ax = plt.subplots(1, 1, figsize = (figsize))
2.use the ax=ax argument in c.plot()
import geopandas as gpd
import matplotlib.pyplot as plt
%matplotlib inline
figsize=5,5
#fig = plt.figure(figsize=(figsize),dpi=300)
#ax = fig.add_subplot(111)
fig, ax = plt.subplots(1, 1, figsize = (figsize))
shpfileshpfile=r'Y:\HQ\TH\Groups\NR\PSPD\Input\US_Counties\cb_2015_us_county_20m.shp'
c=gpd.read_file(shpfile)
c=c.loc[c['GEOID'].isin(['26161','26093','26049','26091','26075','26125','26163','26099','26115','26065'])]
c['coords'] = c['geometry'].apply(lambda x: x.representative_point().coords[:])
c['coords'] = [coords[0] for coords in c['coords']]
c.plot(ax=ax)
ax.spines['top'].set_visible(False);ax.spines['bottom'].set_visible(False);ax.spines['left'].set_visible(False);ax.spines['right'].set_visible(False)
ax.tick_params(axis='y',which='both',left='off',right='off',color='none',labelcolor='none')
ax.tick_params(axis='x',which='both',top='off',bottom='off',color='none',labelcolor='none')
for idx, row in c.iterrows():
ax.annotate(s=row['NAME'], xy=row['coords'],
horizontalalignment='center')
lat2=[42.5,42.3]
lon2=[-84,-83.5]
ax.plot(lon2,lat2,alpha=1,marker='o',linestyle='none',markeredgecolor='none',markersize=15,color='white')