word_pair_pipeline

# Defining the window for context
window = 2

# Creating a placeholder for the scanning of the word list
word_lists = []
all_text = []

for text in texts:

    # Cleaning the text
    text = text_preprocessing(text)

    # Appending to the all text list
    all_text += text 

    # Creating a context dictionary
    for i, word in enumerate(text):
        for w in range(window):
            # Getting the context that is ahead by *window* words
            if i + 1 + w < len(text): 
                word_lists.append([word] + [text[(i + 1 + w)]])
            # Getting the context that is behind by *window* words    
            if i - w - 1 >= 0:
                word_lists.append([word] + [text[(i - w - 1)]])