Bible Translation Sentiment Analysis

import re

import pandas as pd

import matplotlib.pyplot as plt

import nltk

from nltk.sentiment.vader import SentimentIntensityAnalyzer

nltk.download('vader_lexicon')  

import matplotlib.pyplot as plt

import numpy as np

# List file names

filenamelist = ("wbt.txt", "web.txt", "ylt.txt", "akjv.txt", "asv.txt", "cpdv.txt", "dbt.txt", "drb.txt", "erv.txt", "jps.txt", "KJV.txt", "slt.txt")

# Define column names

columns = ["Translation","Positive", "Negative", "Neutral"]

totals_df = pd.DataFrame(columns=columns)

# Itterate through each file

for i in filenamelist:

    #Construct the full file path

    path = "C:/Users/jpapi/OneDrive/Documents/Jasons/Projects/BibleSentimentAnalysis/" + i

    # Get bible abreviation

    bible_name = i.split(".")[0]

    print(bible_name)

    # Read text

    with open(path) as f:

        lines = f.readlines()

    # Put text into Dataframe, separated by individual verses

    df = pd.DataFrame(lines)

    df["row_id"] = df.index + 1

    df.columns=["TextColumn", "RowID"]

    # Clean numbers, tabs, colons, tabs, and white spaces

    df["TextColumn"] = df["TextColumn"].str.strip()

    df["TextColumn"] = df["TextColumn"].str.replace('\d+', '', regex=True)

    df["TextColumn"] = df["TextColumn"].str.replace(':', '', regex=True)

    df["TextColumn"] = df["TextColumn"].str.replace('\t', '', regex=True)

    df["TextColumn"] = df["TextColumn"].str.split(n=1).str[1]

    # Function to analize sentiment of the text with scores

    def analyze_sentiment(text):

        sia = SentimentIntensityAnalyzer()

        sentiment = sia.polarity_scores(text)

        return sentiment['compound']

    # Apply function to each verse

    df['TextColumn'] = df['TextColumn'].astype(str)

    df['TextColumnOutput'] = df['TextColumn'].apply(analyze_sentiment)

    # Classify the scores of each verse into Positve, Negative, and Neutral

    def classify_sentiment(score):

        if score >= 0.05:

            return 'Positive'

        elif score <= -0.05:

            return 'Negative'

        else:

            return 'Neutral'

    # Put the classification into an adjacent column        

    df['SentimentClassify'] = df['TextColumnOutput'].apply(classify_sentiment)

    # Count number of verses in with each classification

    CountOfPositives = (df['SentimentClassify'] == "Positive").sum()

    CountOfNegatives = (df['SentimentClassify'] == "Negative").sum()

    CountOfNeutrals = (df['SentimentClassify'] == "Neutral").sum()

    # Put counts into single line dataframe

    single_bible_df = pd.DataFrame({

        'Translation': [bible_name],

        'Positive': [CountOfPositives],

        'Negative': [CountOfNegatives],

        'Neutral': [CountOfNeutrals]

    })

    # Add single line dataframe onto larger dataframe

    totals_df = pd.concat([totals_df, single_bible_df], ignore_index = True)

# View results

print(totals_df)

# Set width of bars

bar_width = 0.2

# Set positions of bars on X-axis

r1 = np.arange(len(totals_df['Translation']))

r2 = [x + bar_width for x in r1]

r3 = [x + bar_width for x in r2]

# Create a bar chart

plt.figure(figsize=(12, 6))

plt.bar(r1, totals_df['Positive'], color='yellow', width=bar_width, edgecolor='grey', label='Positive')

plt.bar(r2, totals_df['Negative'], color='red', width=bar_width, edgecolor='grey', label='Negative')

plt.bar(r3, totals_df['Neutral'], color='blue', width=bar_width, edgecolor='grey', label='Neutral')

# Add labels and title

plt.xlabel('Translation', fontweight='bold')

plt.xticks([r + bar_width for r in range(len(totals_df['Translation']))], totals_df['Translation'])

plt.ylabel('Count', fontweight='bold')

plt.title('Sentiment Analysis of Bible Translations', fontweight='bold')

plt.legend()

# Show the plot

plt.show()