split string array by regex spliter, counter value frequency

split_and_counter_hitter.py

import pandas as pd
def conlusion_hitter_df(arr):
    conclusion_counter = {}
    def per_item(ac, item):
        v = item
        if v not in ac:
            ac[v] = 0
        ac[v] = ac[v] + 1
        return ac
    conclusion_counter = reduce(per_item, arr, conclusion_counter)
    df = pd.DataFrame.from_items(map(lambda x:(x[0], [x[1]]), conclusion_counter.items(),) )
    df = df.transpose()
    return df.sort_values(by=0, ascending=False)

def flatten_array(array):
    def f(ac, arr):
        if(isinstance(arr, list)):
            ac.extend(arr)
        return ac
    return reduce(f ,array, [] )

arr = flatten_array(obj_all.values())

import re
spliters = [
    r'\d:',
    *list('，;'),
]
def apply_string_spilters(spliters, array):
    array = [*array]
    for spliter in spliters:
        for i in range(len(array)):
            array[i] =  re.split(spliter, array[i])
        array = flatten_array(array)
    return array

def filter_nonempty_string(array):
    array = [*array]
    return list(filter(lambda x:isinstance(x, str) and len(x)>0, array))

def apply_rules_on_array(arr):
    arr = [*arr]
    
    arr = apply_string_spilters(spliters, arr)

    arr = list(map(lambda x:x.strip(), arr))

    arr = filter_nonempty_string(arr)

    arr = list(filter(lambda x:'？' not in x, arr))

    arr = list(filter(lambda x:'?' not in x, arr))
    
    return arr

conlusion_hitter_df( arr ).to_excel('counter_apply_spliter.xlsx')

arr = apply_rules_on_array(arr)

conlusion_hitter_df( arr ).to_excel('counter_apply_spliter.xlsx')