Adding labels in x y scatter plot with seaborn

Thanks to the 2 other answers, here is a function scatter_text that makes it possible to reuse these plots several times.

import seaborn as sns
import matplotlib.pyplot as plt

def scatter_text(x, y, text_column, data, title, xlabel, ylabel):
    """Scatter plot with country codes on the x y coordinates
       Based on this answer: https://stackoverflow.com/a/54789170/2641825"""
    # Create the scatter plot
    p1 = sns.scatterplot(x, y, data=data, size = 8, legend=False)
    # Add text besides each point
    for line in range(0,data.shape[0]):
         p1.text(data[x][line]+0.01, data[y][line], 
                 data[text_column][line], horizontalalignment='left', 
                 size='medium', color='black', weight='semibold')
    # Set title and axis labels
    plt.title(title)
    plt.xlabel(xlabel)
    plt.ylabel(ylabel)
    return p1

Use the function as follows:

df_iris=sns.load_dataset("iris") 
plt.figure(figsize=(20,10))
scatter_text('sepal_length', 'sepal_width', 'species',
             data = df_iris, 
             title = 'Iris sepals', 
             xlabel = 'Sepal Length (cm)',
             ylabel = 'Sepal Width (cm)')

See also this answer on how to have a function that returns a plot: https://stackoverflow.com/a/43926055/2641825


One way you can do this is as follows:

import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
%matplotlib inline

df_iris=sns.load_dataset("iris") 

ax = sns.lmplot('sepal_length', # Horizontal axis
           'sepal_width', # Vertical axis
           data=df_iris, # Data source
           fit_reg=False, # Don't fix a regression line
           size = 10,
           aspect =2 ) # size and dimension

plt.title('Example Plot')
# Set x-axis label
plt.xlabel('Sepal Length')
# Set y-axis label
plt.ylabel('Sepal Width')


def label_point(x, y, val, ax):
    a = pd.concat({'x': x, 'y': y, 'val': val}, axis=1)
    for i, point in a.iterrows():
        ax.text(point['x']+.02, point['y'], str(point['val']))

label_point(df_iris.sepal_length, df_iris.sepal_width, df_iris.species, plt.gca())  

enter image description here


Here's a more up-to-date answer that doesn't suffer from the string issue described in the comments.

import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

df_iris=sns.load_dataset("iris") 

plt.figure(figsize=(20,10))
p1 = sns.scatterplot('sepal_length', # Horizontal axis
       'sepal_width', # Vertical axis
       data=df_iris, # Data source
       size = 8,
       legend=False)  

for line in range(0,df_iris.shape[0]):
     p1.text(df_iris.sepal_length[line]+0.01, df_iris.sepal_width[line], 
     df_iris.species[line], horizontalalignment='left', 
     size='medium', color='black', weight='semibold')

plt.title('Example Plot')
# Set x-axis label
plt.xlabel('Sepal Length')
# Set y-axis label
plt.ylabel('Sepal Width')

enter image description here