擅长:python、mysql、java
<pre><code>import pandas as pd
import numpy as np
df = pd.DataFrame({'sheet':['sheet1', 'sheet2', 'sheet3', 'sheet2'],
'tokenized_text':[['efcc', 'fficial', 'billiontwits', 'since', 'covid', 'landed'], ['when', 'people', 'say', 'the', 'fatality', 'rate', 'of', 'coronavirus', 'is'], ['in', 'the', 'coronavirus-induced', 'crisis', 'people', 'are', 'cyvbwx'], ['in', 'the', 'be-induced', 'crisis', 'people', 'are', 'cyvbwx']] })
print(df)
words_collection = ['covid','COVID','Covid-19','pandemic','coronavirus']
# Extract the words from all lines
all_words = []
for index, row in df.iterrows():
all_words.extend(row['tokenized_text'])
# Create a dictionary that maps for each word from `words_collection` the counter it appears
word_to_number_of_occurences = dict()
# Go over the word collection and set it's counter
for word in words_collection:
word_to_number_of_occurences[word] = all_words.count(word)
# {'covid': 1, 'COVID': 0, 'Covid-19': 0, 'pandemic': 0, 'coronavirus': 1}
print(word_to_number_of_occurences)
</code></pre>