Currently I have the following code
import matplotlib.pyplot as plt
import pandas as pd
from pandas.plotting import scatter_matrix
df= pd.read_csv(file, sep=',')
colors = list('r' if i==1 else 'b' for i in df['class']) # class is either 1 or 0
plt.figure()
scatter_matrix(df, color=colors )
plt.show()
It shows the following output
But in this plot on diagonals, instead of simple histogram I want to show stacked histogram like the following such that for class '1' it is red and for '0' it is blue
Please guide me how can I do this ?
The use of seaborn is probably highly beneficial for plotting a scatter matrix kind of plot. However, I do not know how to plot a stacked histogram easily into the diagonal of a PairGrid in seaborn.
As the question anyways asks for matplotlib, the following is a solution using pandas and matplotlib. Unfortunately it will require to do a lot of stuff by hand. The following would be an example (note that seaborn is only imported to get some data since the question did not provide any).
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# seaborn import just needed to get some data
import seaborn as sns
df = sns.load_dataset("iris")
n_hist = 10
category = "species"
columns = ["sepal_length","sepal_width","petal_length","petal_width"]
mi = df[columns].values.min()
ma = df[columns].values.max()
hist_bins = np.linspace(mi, ma, n_hist)
fig, axes = plt.subplots(nrows=len(columns), ncols=len(columns),
sharex="col")
for i,row in enumerate(columns):
for j,col in enumerate(columns):
ax= axes[i,j]
if i == j:
# diagonal
mi = df[col].values.min()
ma = df[col].values.max()
hist_bins = np.linspace(mi, ma, n_hist)
def hist(x):
h, e = np.histogram(x.dropna()[col], bins=hist_bins)
return pd.Series(h, e[:-1])
b = df[[col,category]].groupby(category).apply(hist).T
values = np.cumsum(b.values, axis=1)
for k in range(len(b.columns)):
if k == 0:
ax.bar(b.index, values[:,k], width=np.diff(hist_bins)[0])
else:
ax.bar(b.index, values[:,k], width=np.diff(hist_bins)[0],
bottom=values[:,k-1])
else:
# offdiagonal
for (n,cat) in df.groupby(category):
ax.scatter(cat[col],cat[row], s = 5,label=n, )
ax.set_xlabel(col)
ax.set_ylabel(row)
#ax.legend()
plt.tight_layout()
plt.show()
Sample code
import seaborn as sns
sns.set(style="ticks")
df = sns.load_dataset("iris")
sns.pairplot(df, hue="species")
Related
I want to plot my dataframe (df) as a bar plot based on the time columns, where each bar represents the value counts() for each letter that appears in the column.
Expected output
.
date,00:00:00,01:00:00,02:00:00,03:00:00,04:00:00
2002-02-01,Y,Y,U,N,N
2002-02-02,U,N,N,N,N
2002-02-03,N,N,N,N,N
2002-02-04,N,N,N,N,N
2002-02-05,N,N,N,N,N
When I select individual time columns, I can do as below
import pandas as pd
import numpy as np
from datetime import datetime
import matplotlib.pyplot as plt
df = pd.read_csv('df.csv')
df = df['04:00:00'].value_counts()
df.plot(kind='bar')
plt.show()
How can I plot all the columns on the same bar plot as shown on the expected output.
One possible solution is:
pd.DataFrame({t: df[t].value_counts() for t in df.columns if t != "date"}).T.plot.bar()
Here is an approach via seaborn's catplot:
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
from io import StringIO
df_str = '''date,00:00:00,01:00:00,02:00:00,03:00:00,04:00:00
2002-02-01,Y,Y,U,N,N
2002-02-02,U,N,N,N,N
2002-02-03,N,N,N,N,N
2002-02-04,N,N,N,N,N
2002-02-05,N,N,N,N,N'''
df = pd.read_csv(StringIO(df_str))
df_long = df.set_index('date').melt(var_name='hour', value_name='kind')
g = sns.catplot(kind='count', data=df_long, x='kind', palette='mako',
col='hour', col_wrap=5, height=3, aspect=0.5)
for ax in g.axes.flat:
ax.set_xlabel(ax.get_title()) # use the title as xlabel
ax.grid(True, axis='y')
ax.set_title('')
if len(ax.get_ylabel()) == 0:
sns.despine(ax=ax, left=True) # remove left axis for interior subplots
ax.tick_params(axis='y', size=0)
plt.tight_layout()
plt.show()
I am not able to make a x,y histogram or bar plot (horizontal), based on the below example data. Can anyone help in this!
import matplotlib.pyplot as plt
import pandas as pd
# data
a = [3850., 3900., 3950., 4000., 4050., 4100., 4150., 4200.]
b = [2.7000e+03, 6.9300e+04, 1.6920e+05, 2.7360e+05, 5.5620e+05,5.8950e+05, 4.5630e+05, 6.1020e+05]
df = pd.DataFrame({'altitude' : a, 'area' : b})
df
plt.hist(df.area, bins= df.altitude, orientation='horizontal')
plt.show()
I am expecting a such figure from this data
I have the following code where I am trying to plot a bar plot in seaborn. (This is a sample data and both x and y variables are continuous variables).
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
xvar = [1,2,2,3,4,5,6,8]
yvar = [3,6,-4,4,2,0.5,-1,0.5]
year = [2010,2011,2012,2010,2011,2012,2010,2011]
df = pd.DataFrame()
df['xvar'] = xvar
df['yvar']=yvar
df['year']=year
df
sns.set_style('whitegrid')
fig,ax=plt.subplots()
fig.set_size_inches(10,5)
sns.barplot(data=df,x='xvar',y='yvar',hue='year',lw=0,dodge=False)
It results in the following plot:
Two questions here:
I want to be able to plot the two bars on 2 side by side and not overlapped the way they are now.
For the x-labels, in the original data, I have alot of them. Is there a way I can set xticks to a specific frequency? for instance, in the chart above only I only want to see 1,3 and 6 for x-labels.
Note: If I set dodge = True then the lines become very thin with the original data.
For the first question, get the patches in the bar chart and modify the width of the target patch. It also shifts the position of the x-axis to represent the alignment.
The second question can be done by using slices to set up a list or a manually created list in a specific order.
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
xvar = [1,2,2,3,4,5,6,8]
yvar = [3,6,-4,4,2,0.5,-1,0.5]
year = [2010,2011,2012,2010,2011,2012,2010,2011]
df = pd.DataFrame({'xvar':xvar,'yvar':yvar,'year':year})
fig,ax = plt.subplots(figsize=(10,5))
sns.set_style('whitegrid')
g = sns.barplot(data=df, x='xvar', y='yvar', hue='year', lw=0, dodge=False)
for idx,patch in enumerate(ax.patches):
current_width = patch.get_width()
current_pos = patch.get_x()
if idx == 8 or idx == 15:
patch.set_width(current_width/2)
if idx == 15:
patch.set_x(current_pos+(current_width/2))
ax.set_xticklabels([1,'',3,'','',6,''])
plt.show()
I would like create an plot with to display the last value on line. But i can not create the plot with the last value on chart. Do you have an idea for to resolve my problem, thanks you !
Input :
DataFrame
Plot
Output :
Cross = Last Value In columns
Output Final
# import eikon as ek
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
import os
import seaborn as sns; sns.set()
import pylab
from scipy import *
from pylab import *
fichier = "P:/GESTION_RPSE/GES - Gestion Epargne Salariale/Dvp Python/Florian/Absolute
Performance/PLOT.csv"
df = pd.read_csv(fichier)
df = df.drop(columns=['Unnamed: 0'])
# sns.set()
plt.figure(figsize=(16, 10))
df = df.melt('Date', var_name='Company', value_name='Value')
#palette = sns.color_palette("husl",12)
ax = sns.lineplot(x="Date", y="Value", hue='Company', data=df).set_title("LaLaLa")
plt.show()
Do you just want to put an 'X' at the end of your lines?
If so, you could pass markerevery=[-1] to the call to lineplot(). However there are a few caveats:
You have to use style= instead of hue= otherwise, there are no markers drawn
Filled markers work better than unfilled markers (like "x"). You can just use markers=True to use the default markers, or pass a list markers=['s','d','o',etc...]
code:
fmri = sns.load_dataset("fmri")
fig, ax = plt.subplots()
ax = sns.lineplot(x="timepoint", y="signal",
style="event", data=fmri, ci=None, markers=True, markevery=[-1], markersize=10)
I'm trying to create a scatterplot of a dataset with point coloring based on different categorical columns. Seaborn works well here for one plot:
fg = sns.FacetGrid(data=plot_data, hue='col_1')
fg.map(plt.scatter, 'x_data', 'y_data', **kws).add_legend()
plt.show()
I then want to display the same data, but with hue='col_2' and hue='col_3'. It works fine if I just make 3 plots, but I'm really hoping to find a way to have them all appear as subplots in one figure. Unfortunately, I haven't found any way to change the hue from one plot to the next. I know there are plotting APIs that allow for an axis keyword, thereby letting you pop it into a matplotlib figure, but I haven't found one that simultaneously allows you to set 'ax=' and 'hue='. Any ideas?
Thanks in advance!
Edit:
Here's some sample code to illustrate the idea
xx = np.random.rand(10,2)
cat1 = np.array(['cat','dog','dog','dog','cat','hamster','cat','cat','hamster','dog'])
cat2 = np.array(['blond','brown','brown','black','black','blond','blond','blond','brown','blond'])
d = {'x':xx[:,0], 'y':xx[:,1], 'pet':cat1, 'hair':cat2}
df = pd.DataFrame(data=d)
sns.set(style='ticks')
fg = sns.FacetGrid(data=df, hue='pet', size=5)
fg.map(plt.scatter, 'x', 'y').add_legend()
fg = sns.FacetGrid(data=df, hue='hair', size=5)
fg.map(plt.scatter, 'x', 'y').add_legend()
plt.show()
This plots what I want, but in two windows. The color scheme is set in the first plot by grouping by 'pet', and in the second plot by 'hair'. Is there any way to do this on one plot?
In order to plot 3 scatterplots with different colors for each, you may create 3 axes in matplotlib and plot a scatter to each axes.
import pandas as pd
import numpy as np; np.random.seed(42)
import matplotlib.pyplot as plt
df = pd.DataFrame(np.random.rand(10,5),
columns=["x", "y", "col1", "col2", "col3"])
fig, axes = plt.subplots(nrows=3)
for ax, col in zip(axes, df.columns[2:]):
ax.scatter(df.x, df.y, c=df[col])
plt.show()
For categorical data it is often easier to plot several scatter plots, one per category.
import pandas as pd
import numpy as np; np.random.seed(42)
import matplotlib.pyplot as plt
import seaborn as sns
xx = np.random.rand(10,2)
cat1 = np.array(['cat','dog','dog','dog','cat','hamster','cat','cat','hamster','dog'])
cat2 = np.array(['blond','brown','brown','black','black','blond','blond','blond','brown','blond'])
d = {'x':xx[:,0], 'y':xx[:,1], 'pet':cat1, 'hair':cat2}
df = pd.DataFrame(data=d)
cols = ['pet',"hair"]
fig, axes = plt.subplots(nrows=len(cols ))
for ax,col in zip(axes,cols):
for n, group in df.groupby(col):
ax.scatter(group.x,group.y, label=n)
ax.legend()
plt.show()
You may surely use a FacetGrid, if you really want, but that requires a different data format of the DataFrame.
import pandas as pd
import numpy as np; np.random.seed(42)
import matplotlib.pyplot as plt
import seaborn as sns
xx = np.random.rand(10,2)
cat1 = np.array(['cat','dog','dog','dog','cat','hamster','cat','cat','hamster','dog'])
cat2 = np.array(['blond','brown','brown','black','black','blond','blond','blond','brown','blond'])
d = {'x':xx[:,0], 'y':xx[:,1], 'pet':cat1, 'hair':cat2}
df = pd.DataFrame(data=d)
df2 = pd.melt(df, id_vars=['x','y'], value_name='category', var_name="kind")
fg = sns.FacetGrid(data=df2, row="kind",hue='category', size=3)
fg.map(plt.scatter, 'x', 'y').add_legend()