new feature request - automatically fit multiple variables about distfit HOT 2 OPEN

import numpy as np
import pandas as pd
import re
from distfit import distfit
from joblib import Parallel, delayed
import collections
pd.options.display.max_columns = 100

# Numeric-only data from here (sign-in required):  
# https://www.kaggle.com/datasets/fedesoriano/company-bankruptcy-prediction/download?datasetVersionNumber=2

#----------------------------------------------------------------------------------
#Clean up column names and lower memory.
#----------------------------------------------------------------------------------
df = pd.read_csv("./data.csv")
for c in df.columns:  #clean up column names
    no_beg_end_spaces = c.strip()
    result = re.sub(r"\s+", "_", no_beg_end_spaces)
    df.rename(columns={c : result}, inplace=True)

print('df shape:', df.shape)
display(df.tail(3))

for c in df.columns:
    df[c] = pd.to_numeric(df[c], downcast='float')


#----------------------------------------------------------------------------------
#Use joblib to run distfit on CPU cores in parallel.
#----------------------------------------------------------------------------------
chunks = np.array_split(df, len(df.columns), axis=1)  #chunks are one column due to univariate constraint.
display(chunks[0].head())
display(chunks[1].head())

def get_distfit(series):
    try:        
        result = dfit.fit_transform(series.values, verbose=30)
        return result['model']['name']
    except:
        return 'ERROR'
    
dfit = distfit()
with Parallel(n_jobs=-2, prefer="processes") as parallel:
    results = parallel(delayed(get_distfit)(chunk) for chunk in chunks)

display(list(zip(df.columns, results))[0:5])  #show best distribution by column
display(sorted(collections.Counter(results).items(), key=lambda x:x[1], reverse=True))


#----------------------------------------------------------------------------------
#Get best distribution one column at a time (slower than parallel run).
#----------------------------------------------------------------------------------
sequential_outputs = []
for chunk in chunks:
    sequential_outputs.append(get_distfit(chunk))
display(list(zip(df.columns, sequential_outputs))[0:5])  #show best distribution by column
display(sorted(collections.Counter(sequential_outputs).items(), key=lambda x:x[1], reverse=True))