How to Automatically Build Stopwords

zipfs_law_autostopwords_5.py

# List of data
l_data = []

# Highest frequency
max_freq = top_words[0][1]

# Alpha
alpha = 1

# Loop
for index, item in enumerate(iterable = top_words, start = 1):
    # New data
    j_data = {
        'rank': index,
        'word': item[0],
        'actual_freq': item[1],
        'relative_freq': '1/{}'.format(index),
        'zipf_freq': round(
            number = max_freq * (1 / (index ** alpha)),
            ndigits = 2
        )
    }
    
    # Append new data
    l_data.append(j_data)

# Convert list of dictionary into data frame
df = pd.DataFrame(
    data = l_data
)

# Show the data
df.head()