where is the code?

[jducrocq007]

Hello, your project seems to be very nice, but there is no code implemented here...

I hope there are other ways to do a 2 ways ART ANOVA in Python!

[Palpatineli]

Hi @jducrocq007 thanks for your interest but unfortunately I had abandoned this project 6 years ago and forgot to delete it. I eventually turned to rpy2 to get the result I needed. Here is the function if it may be of any help:

import numpy as np
import pandas as pd
from scipy.stats import mannwhitneyu
from rpy2 import robjects as robj
from rpy2.robjects.packages import importr
from rpy2.robjects import pandas2ri
artool = importr("ARTool")
pandas2ri.activate()

def art_2by2(df: pd.DataFrame, feature: str, group: str):
    feature_wide = df[["Unnamed: 0", feature, "all", "group"]]
    feature_long = feature_wide.melt(id_vars=["Unnamed: 0", "group"], value_vars=[feature, "all"])
    feature_long = feature_long.query(f"group in ('wt', '{group}')")
    feature_long.loc[feature_long["value"] < 0, "value"] = 0
    feature_long["group"] = feature_long["group"].astype("category")
    feature_long["variable"] = feature_long["variable"].astype("category")
    r_df = pandas2ri.py2rpy(feature_long)
    model = artool.art(robj.Formula("value ~ group * variable"), data=r_df)
    anova = robj.r["anova"]
    return anova(model)

[jducrocq007]

Hello,

Ok I see!
Thank you very much for answering anyways and trying to help me, then!

Ok, I will have to see how to install rpy2 with Python 3 and things like that...
What I wanted to do is a Two-Ways ART ANOVA.
I know that to do so, I mostly need to do the Aligned Rank Transform on my data, then I can directly do a standard two-ways ANOVA... Your code would surely help!

[jducrocq007]

Hello, last thing that I ask here...

In addition to the function, could you provide a sample piece of code to use it?

Here are some links that could help others to install rpy2 and ARTTool:

• https://rpy2.github.io/doc/latest/html/introduction.html
• https://joonro.github.io/blog/posts/install-rpy2-windows-10/
• https://cran.r-project.org/web/packages/ARTool/readme/README.html

Thanks a lot!