journal analysis

journal_analysis.py

# Export onenote section to pdf

# py -m venv venv-dir
# . ./venv-dir/scripts/activate

pdf_f="Gratitude Journal.pdf"

def process_pdf_to_text(pdf):
    # pip install --upgrade pymupdf
    import pymupdf

    doc = pymupdf.open(pdf)
    output_txt=f"{pdf}_output.txt"
    out = open(output_txt, "wb")

    for page in doc:
        text = page.get_text().encode("utf8")
        out.write(text)
        out.write(bytes((12,)))

    out.close()

    # read text into string object
    with open(output_txt, "r", errors="ignore") as file:
        content = file.read()
        # fix for unicode decode error
        cleaned_content = content.encode("ascii", errors="ignore").decode("ascii")
    
    return cleaned_content
#end

# pip install --upgrade wordcloud
from wordcloud import WordCloud
import matplotlib.pyplot as plt

def make_wordcloud(input_text="hello world"):
    # Generate word cloud
    wordcloud = WordCloud(width=1600,height=900,background_color="white").generate(input_text)

    # Display wordcloud
    plt.figure(figsize=(10,5))
    plt.imshow(wordcloud,interpolation="bilinear")
    plt.axis("off")
    plt.show()
# end

def get_word_freq():
# pip install nltk

    from collections import Counter
    # import regex
    import re
    content2 = process_pdf_to_text(pdf_f).lower()
    words = re.findall(r"\b\w+\b", content2)
    word_counts = Counter(words)

    # remove stop words (words you don't want to process)
    # add stop words? https://stackoverflow.com/questions/5511708/adding-words-to-nltk-stoplist
    from nltk.corpus import stopwords
    stop_words = set(stopwords.words("english"))
    extra_stop_words = [ "journal", "page", "â", "25", "like", "2025", "pm", "1"]
    for word in extra_stop_words:
        stop_words.add(word)
    #end
    filtered_words = [ word for word in words if word.lower() not in stop_words ]
    
    cleaned_text = " ".join(filtered_words)
    make_wordcloud(cleaned_text)
    
    word_counts = Counter(filtered_words)
    list_size = 200
    """
        print(word_counts)
    with open("journal_word_count.txt", "w") as file:
        for item,count in word_counts.items():
            file.write(f"{item}: {count}\n")
        #end
    #close
    """
    print(word_counts.most_common(list_size))

    make_chart = False
    # Make bar chart
    if make_chart:
        # Extract labels and values from the counter
        labels = list(word_counts.keys())
        values = list(word_counts.values())

        plt.figure(figsize=(8, 6))
        plt.bar(labels, values, color='skyblue')
        plt.xlabel('Item')
        plt.ylabel('Count')
        plt.title("Word Frequency in Journal")
        plt.show()
    #fi
# end

if __name__ == "__main__":
    get_word_freq()
    make_wordcloud_b = False
    if make_wordcloud_b:
        make_wordcloud()
    #fi
#fi