calculate top 20 most frequent words on 57235 * 30 excel sheet

gist.py

import pandas as pd
import numpy
df= pd.read_excel('dwfef.xlsx')

arr = df.to_numpy().flatten() #convert 2dimentional dataframe to 1dimentional list
arr = arr[~pd.isnull(arr)] # remove 'nan' - empty strings
striper = lambda t: str(t.strip())
arr = np.array([striper(xi) for xi in arr]).astype(str) # remove whitespaces before and after each word
unique_elements, counts_elements = np.unique(arr, return_counts=True)

zipped = list(zip(unique_elements, counts_elements))
zipped.sort(key = lambda t: -t[1]) #reverse sort them
print(zipped[0:20])