I have the following data frame:

dic_projects = {
                'Proyectos' :['A','B','C', 'D','E','F','G'],
                'Impacto'   :[188,57,358,24, None, None,24],
                'Viabilidad':[2.15,2.05,2.28,2.33, 1.6, 1.91, 2.15]
                }
df = pd.DataFrame(dic_projects)

And I would like to use a scatter plot with seaborn

sns.regplot(x=df['Viabilidad'], y=df['Impacto'], ci=False, fit_reg=False)
for i in range(df.shape[0]):
    plt.text(x=df['Impacto'][i] 0.3, y=df['Viabilidad'][i] 0.3, s=df['Proyectos'][i], 
             fontdict=dict(color='red',size=5),
             bbox=dict(facecolor='yellow',alpha=0.5))
plt.title('Impacto-Viabilidad, proyectos plazas') 
plt.xlabel('Viabilidad') 
plt.ylabel('Impacto ($)') 
plt.show()

But I get the ValueError: Image size pixels is too large. Thanks in advance.

CodePudding user response：

Is this what you want?

import pandas as pd
import matplotlib.pyplot as plt
dic_projects = {
                'Proyectos' :['A','B','C', 'D','E','F','G'],
                'Impacto'   :[188,57,358,24, None, None,24],
                'Viabilidad':[2.15,2.05,2.28,2.33, 1.6, 1.91, 2.15]
                }
df = pd.DataFrame(dic_projects)
plt.figure(figsize=(8,8))
plt.plot(df['Impacto'], df['Viabilidad'], '--o')
for i in range(df.shape[0]):
    plt.text(x=df['Impacto'][i], y=df['Viabilidad'][i], s=df['Proyectos'][i], 
             fontdict=dict(color='red',size=11),
             bbox=dict(facecolor='yellow',alpha=0.5))
plt.title('Impacto-Viabilidad, proyectos plazas') 
plt.xlabel('Viabilidad') 
plt.ylabel('Impacto ($)') 
plt.show()

CodePudding user response：

There are 3 problems:

• x and y are switched between the call to sns.regplot and to plt.text()
• plotting the text needs a test to filter out NaNs.
• the distance of 0.3 is too high in the x-direction

Apart from that, the margins could be enlarged a bit to fit all the texts.

import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
import pandas as pd

dic_projects = {'Proyectos': ['A', 'B', 'C', 'D', 'E', 'F', 'G'],
                'Impacto': [188, 57, 358, 24, None, None, 24],
                'Viabilidad': [2.15, 2.05, 2.28, 2.33, 1.6, 1.91, 2.15]}
df = pd.DataFrame(dic_projects)

ax = sns.regplot(x=df['Viabilidad'], y=df['Impacto'], ci=False, fit_reg=False)
for i in range(df.shape[0]):
    print(i, df['Impacto'][i], df['Viabilidad'][i])
    if not (np.isnan(df['Impacto'][i]) or np.isnan(df['Viabilidad'][i])):
        print('>', df['Impacto'][i], df['Viabilidad'][i], df['Proyectos'][i])
        ax.text(x=df['Viabilidad'][i]   0.01, y=df['Impacto'][i]   0.3, s=df['Proyectos'][i],
                fontdict=dict(color='red', size=5), va='bottom',
                bbox=dict(facecolor='yellow', alpha=0.5))
ax.set_title('Impacto-Viabilidad, proyectos plazas')
ax.set_xlabel('Viabilidad')
ax.set_ylabel('Impacto ($)')
ax.margins(x=0.1, y=0.1) # increase margins
plt.show()