I made a line plot chart for years 1960-2014 using seaborn but the xticks aren't correct. I want only intervals to appear (like 1960, 1970, 1980, etc).How do i adjust the xticks? I tried rotating it but it didn't seem to work. Here is my code:
#plot figure using sns
g=sns.relplot(x="Year", y="Indicator_Value",
data=Emissions_C_df,
kind="line",
style="Indicator_Name",
hue="Indicator_Name",
)
plt.show()
You can use a MaxNLocator from matplotlib.ticker for the major ticks (decades) and manually set specific minor ticks with a FixedLocator.
import seaborn as sns
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.ticker import FixedLocator, MaxNLocator
a = np.arange(50)
d = {'Year': 1953+a, 'Indicator_Value': a}
df = pd.DataFrame(data=d)
g = sns.relplot(x="Year", y="Indicator_Value",
data=df,
kind="line")
ax = plt.gca()
ax.xaxis.set_major_locator(MaxNLocator(steps=[10]))
ax.xaxis.set_minor_locator(FixedLocator(range(1960,1970)))
plt.show()
Related
I have three columns of data. They are too large to generate meshgrids from. So e.g. in order to generate a surface plot from the data, I use a method like so
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib import cm
from mpl_toolkits.mplot3d import Axes3D
x, y, z = np.loadtxt('data_file', unpack=True)
df = pd.DataFrame({'x':x, 'y':y, 'z':z})
fig = plt.figure()
ax = Axes3D(fig)
surf = ax.plot_trisurf(df.x, df.y, df.z, cmap=cm.jet, linewidth=0.05)
fig.colorbar(surf, shrink=0.5, aspect=5)
plt.show()
Is there a similar alternative to plot_trisurf for contours?
import pandas as pd
import seaborn as sns
from matplotlib import pyplot as plt
import matplotlib.pyplot as plt
sns.set(style="darkgrid")
df = pd.read_csv('Leap_Static_trials.csv')
Length = sns.swarmplot(x='name', y= 'length', data= df, color = 'green')
Width = sns.swarmplot(x='name', y= 'width', data= df, color = 'red')
plt.legend(labels=['Length','Width'])
plt.show()
From my dataset df I am plotting the length and width of the fingers taken from Leap Motion Controller. I am unable to change the legend to include the second color (red) which signifies the width.
Please find the attached figure as well. Your help is much appreciated. :)
Adding the parameter label= to a plot command usually creates the legend handles and labels automatically. In this case, seaborn creates handles for each column (so 5 of each). A trick is to create the legend with only the first and the last of the handles and the labels.
import pandas as pd
import seaborn as sns
from matplotlib import pyplot as plt
import matplotlib.pyplot as plt
sns.set(style="darkgrid")
N = 100
# df = pd.read_csv('Leap_Static_trials.csv')
names = list('abcde')
ax = plt.gca()
df = pd.DataFrame({'name': np.random.choice(names, N),
'length': np.random.normal(50, 0.7, N),
'width': np.random.normal(20, 0.5, N)})
Length = sns.swarmplot(x='name', y='length', data=df, color='green', label='Length', order=names, ax=ax)
Width = sns.swarmplot(x='name', y='width', data=df, color='red', label='Width', ax=ax)
handles, labels = ax.get_legend_handles_labels()
plt.legend([handles[0], handles[-1]], [labels[0], labels[-1]])
plt.show()
I tried to plot a graph for energies of 4 nodes using line graph but I'm not able to identify which line represent which node ID(1,2,3 or 4)
My csv looks something like this :
Time,Source,Destination,Bits,Energy
0,1,2,288,9.9999856
1058,1,2,288,9.9999856
1140,2,1,96,9.9999808
1958,2,3,96,9.9999952
2024,2,1,96,9.9999808
2051,2,3,288,9.999966399
3063,2,3,288,9.9999808
3126,3,2,96,9.999976
3127,2,1,288,9.9999664
3946,3,2,96,9.999961599
8340,1,2,288,9.999952
9418,1,2,288,9.999947199
9479,2,1,96,9.999942399
10299,2,3,96,9.9999712
10365,2,1,96,9.9999472
10758,2,3,288,9.999927999
11770,2,3,288,9.9999568
11832,3,2,96,9.999951999
11842,2,1,288,9.9999328
Code :
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
df = pd.read_csv('DS1.csv')
for Energy,data in df.groupby('Source'):
plt.plot(data['Time'], data['Energy'])
plt.legend(data['Source'])
#print(data)
plt.xlabel('Time')
plt.ylabel('Energy')
plt.legend()
plt.show()
I actually want to plot source,energy vs Time for all sources(1 to 4)
You need to set the label.
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
df = pd.read_csv('DS1.csv')
for Energy, data in df.groupby('Source'):
plt.plot(data['Time'], data['Energy'], label=Energy)
#print(data)
plt.xlabel('Time')
plt.ylabel('Energy')
plt.legend()
plt.show()
Hi here is a sample code with 6 dimensional dataset.
import matplotlib.pyplot as plt
from matplotlib import cm
from matplotlib.ticker import LinearLocator, FormatStrFormatter
from mpl_toolkits.mplot3d import Axes3D
import numpy as np
import pandas as pd
import seaborn as sns
def f(a,b,c,d,e):
return a*b*c*d*e/1e14
# characteristics
a=np.arange(1000,11000,1000)
b=np.arange(45,100,10)
c=np.arange(10000,60000,5000)
d=np.arange(1,6,.5)*1000
e=np.array([1,2])
gr=np.array(np.meshgrid(a,b,c,d,e)).T.reshape(-1,5)
cost=np.array([f(*j) for j in gr])
df=pd.DataFrame(np.column_stack([gr,cost]),columns=['a','b','c','d','e','cost'])
I would like to look into possible trends in the data. For example i would like to know the effect of "a" on "cost" either while keeping the rest of the columns constant or not etc. Is there a better way of gaining insight from the data than this;
fig = plt.figure(figsize=[10,8])
ax = Axes3D(fig)
temp=df[(df.a==4000) & (df.d==1000)]
ax.plot_trisurf(temp.b, temp.c, temp.cost, cmap=cm.jet, linewidth=0.2)
ax.set_xlabel('b', fontsize=16)
ax.set_ylabel('c', fontsize=16)
ax.set_zlabel('cost', fontsize=16)
I have also tried these but not clear what they mean. For example, in this case shouldn't all correlation values be equal in the heat map for cost-variable pairs?
# Various visualizaiton methods
#a)
f, ax = plt.subplots(figsize=(10, 6))
corr = df.corr()
hm = sns.heatmap(round(corr,2), annot=True, ax=ax, cmap="coolwarm",fmt='.2f',
linewidths=.05)
f.subplots_adjust(top=0.93)
#b)
pd.plotting.scatter_matrix(df, alpha=0.2, figsize=(16, 16))
can you please tell me how to plot the graph for csv data.
csv file have x,y,depth,color values i want to plot the depth and color for x and y axis,i goggled many times but i didn't find anything properly.so please guide me how to plot the graph for that values?
this is i tried :
from matplotlib import pyplot as plt
from matplotlib import style
import pandas as pd
data=pd.read_csv("Tunnel.csv",names=['x','y','z','color'])
data1 =data[data.z==0]
print (data1)
# plt.plot(data[data.x],data[data.y])
plt.ylabel('yaxis')
plt.xlabel('xaxis')
plt.title('Tunnel 2d')
plt.show()
my data is given bellow
I'm assuming that you want the first two columns to be used as plot axis and columns 3 and 4 as plot data.
from matplotlib import pyplot as plt
import pandas as pd
data = pd.read_csv("Tunnel.csv")
x = stats[stats.columns[2]]
y = stats[stats.columns[3]]
xlab = list(stats)[0] #x-axis label
ylab = list(stats)[1] #y-axis label
fig, pli = plt.subplots()
pli.show()
#Assuming it's a line graph that you want to plot
line, = pli.plot(x, y, color='g', linewidth=5, label='depth vs color')
plt.xlabel(xlab)
plt.ylabel(ylab)
plt.title(title)
fig.savefig('./Directory/Graph.png')
I am assuming that you want the color and depth as text annotations.
import stuff
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
create the df
dep=list(np.random.randint(0,100,10))
col=list(np.random.randint(0,100,10))
y=[int(x/3)+1 for x in range(0,10)]
x=list(range(0,10))
my_df=pd.DataFrame({'x':x,'y':y,'colour':col,'depth':dep})
create the annotate column
my_df['my_text']='c= '+my_df.colour.astype(str)+','+'d= '+my_df.depth.astype(str)
plot it
plt.figure(figsize=(20,10))
plt.plot(my_df.x,my_df.y,'o')
for i, txt in enumerate(my_df['my_text']):
plt.annotate(txt, (x[i],y[i]), size=10, xytext=(0,0), ha='left', textcoords='offset points', bbox=dict(facecolor='none', edgecolor='red'))
plt.ylabel('yaxis')
plt.xlabel('xaxis')
plt.title('Tunnel 2d')
plt.show()
Result