Created
December 30, 2017 09:21
-
-
Save HenrikEckermann/1d334a44f61349ac71f0e235b3443a69 to your computer and use it in GitHub Desktop.
plot mean and error bars with plotnine
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
from plotnine import * | |
#import data | |
bdf = pd.read_csv('http://www.stat.columbia.edu/~gelman/arm/examples/beauty/ProfEvaltnsBeautyPublic.csv') | |
#Rename btystdave to beauty for convenience | |
bdf.columns = ['beauty' if x=='btystdave' else x for x in bdf.columns] | |
bdf.info() | |
#Make categorical vars | |
for col in ['female', 'tenured' ,'blkandwhite']: | |
bdf[col] = pd.Categorical(bdf[col]) | |
#long format | |
bdf_cat_l = pd.melt(bdf[['tenured', 'courseevaluation', 'female', 'blkandwhite']], id_vars = 'courseevaluation') | |
#How are the differences in courseevaluation between the categoricals | |
(ggplot(bdf_cat_l, aes(x='value', y='courseevaluation')) | |
+ geom_jitter(alpha=0.5, width=0.2, color = 'grey') | |
+ stat_summary(fun_data = 'mean_sdl', fun_args = {'mult':1}, geom = 'errorbar') | |
+ stat_summary(fun_y = np.mean, geom = 'point', fill = 'red') | |
+ facet_wrap('~variable')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment