histogram

histogram.py

import pandas as pd
import matplotlib.pyplot as plt
import json
from io import StringIO

# Read the JSON file
with open('your_file.json', 'r') as file:
    data = file.read()

# Convert the JSON data to a pandas DataFrame
df = pd.read_json(StringIO(data), lines=True)

# Convert the 'date' column to datetime
df['date'] = pd.to_datetime(df['date'])

# Group by month and sum the 'num_docs'
monthly_sum = df.groupby(df['date'].dt.to_period('M'))['num_docs'].sum().reset_index()

# Sort the data by date
monthly_sum = monthly_sum.sort_values('date')

# Create the histogram
plt.figure(figsize=(12, 6))
plt.bar(monthly_sum['date'].astype(str), monthly_sum['num_docs'])

# Customize the plot
plt.title('Monthly Document Count for 2023')
plt.xlabel('Month')
plt.ylabel('Number of Documents')
plt.xticks(rotation=45, ha='right')
plt.tight_layout()

# Show the plot
plt.show()