# load the BHSL app and data
BHS = use ("etcbc/BHSA",hoist=globals())

# The following will push the Text-Fabric stylesheet to this notebook (to facilitate proper display with notebook viewer)
BHS.dh(BHS.getCss())

levQuery = '''
book
  chapter
     verse
       word lex=LBB/|LB/ 
'''

levResults = BHS.search(levQuery)

# Libraries for table formatting and data display
import pandas as pd
from IPython.display import display

# Initialize dictionary for storing results
resultDict = {}

# Process each item in the levResults
for item in levResults:
    book = F.book.v(item[0])
    lex = F.lex.v(item[3])
    
    if book in resultDict:
        # If it exists, add the count to the existing value
        resultDict[book][0] += 1
        if lex == 'LB/':
            resultDict[book][1] += 1
        else:
            resultDict[book][2] += 1
    else:
        # If it doesn't exist, initialize the count as the value
        if lex == 'LB/':
            resultDict[book] = [1, 1, 0]
        else:
            resultDict[book] = [1, 0, 1]

# Convert the dictionary into a DataFrame and sort by total frequency
tableData = pd.DataFrame(
    [[key, value[0], value[1], value[2]] for key, value in resultDict.items()],
    columns=["Book", "Total", "Lev", "Levav"]
)
tableData = tableData.sort_values(by="Total", ascending=False)

# Display the table
display(tableData)

import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd

# Sample data setup (replace with your actual data)
# Initialize dictionary for storing results
resultDict = {}

# Process each item in the levResults
for item in levResults:
    book = F.book.v(item[0])
    lex = F.lex.v(item[3])
    
    if book in resultDict:
        # If it exists, add the count to the existing value
        resultDict[book][0] += 1
        if lex == 'LB/':
            resultDict[book][1] += 1
        else:
            resultDict[book][2] += 1
    else:
        # If it doesn't exist, initialize the count as the value
        if lex == 'LB/':
            resultDict[book] = [1, 1, 0]
        else:
            resultDict[book] = [1, 0, 1]

# Convert the dictionary into a DataFrame and sort by total frequency
tableData = pd.DataFrame(
    [[key, value[0], value[1], value[2]] for key, value in resultDict.items()],
    columns=["Book", "Total", "LB", "LBB"]
)

# Set up the data for plotting with LB as positive and LBB as negative values
tableData['LB_Positive'] = tableData['LB']  # LB counts as positive values
tableData['LBB_Negative'] = -tableData['LBB']  # LBB counts as negative values

# Set up the plot
plt.figure(figsize=(14, 10))

# Plot LB (positive values)
lb_bars = plt.barh(tableData["Book"], tableData["LB_Positive"], color='blue', label='לֵב')

# Plot LBB (negative values)
lbb_bars = plt.barh(tableData["Book"], tableData["LBB_Negative"], color='orange', label='לֵבָב')

# Add the counts on each bar
for bar, count in zip(lb_bars, tableData['LB']):
    plt.text(bar.get_width() + 1, bar.get_y() + bar.get_height()/2, str(count), va='center', color='blue')

for bar, count in zip(lbb_bars, tableData['LBB']):
    plt.text(bar.get_width() - 1, bar.get_y() + bar.get_height()/2, str(count), va='center', ha='right', color='orange')

# Customize x-axis to show absolute values
x_ticks = plt.xticks()[0]  # Get current tick positions
plt.xticks(x_ticks, [str(int(abs(x))) for x in x_ticks])  # Set absolute values for labels

# Add labels, title, and legend
plt.xlabel("Count")
plt.ylabel("Book")
plt.title('Distribution of לֵב and לֵבָב Counts per Book in the Tenach')
plt.axvline(0, color="black", linewidth=0.5)  # Center line at x=0
plt.legend(title="Category")

# Show the plot
plt.show()