---
date: 2022-12-26 16:48
modification date: Monday 26th December 2022 16:48:45
title: "progress"
aliases: [progress]
---

# progress

## Progress Graph

```run-python pre
import os
import re
from datetime import datetime
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
results = pd.DataFrame(columns=['date', 'count'])

# Recursively walk through the directory and search for strings
def search_directory(directory):
    date_counts = {}
    # Find all markdown files in the directory and its subdirectories
    files = [os.path.join(root, file) for root, dirs, files in os.walk(directory) for file in files if file.endswith('.md') if not "IW-Queue" in root]

    # Initialize counter for total number of strings found
    total_count = 0

    # Iterate over all markdown files
    for file in files:
        with open(file, 'r') as f:
            contents = f.read()
            matches = re.findall(r"\u2705\s(\d{4}-\d{2}-\d{2})", contents)
            for match in matches:
                date = datetime.strptime(match, '%Y-%m-%d')
                if date not in date_counts:
                    # Initialize count for this date
                    date_counts[date] = 1
                else:
                    # Increment count for this date
                    date_counts[date] += 1
    return date_counts


directory = "/home/zack/SparkleShare/github.com/Notes/Obsidian"
# Run the search on the desired directory
counts = search_directory(directory)

df = pd.DataFrame(list(counts.items()), columns=['date', 'count']).sort_values(by='date')
df['cumulative_total'] = df['count'].cumsum()

sns.set_theme(style="darkgrid")
# Create the plot
sns.lineplot(x='date', y='cumulative_total', data=df)

# Set the x-axis label
plt.xlabel('Date')

# Set the y-axis label
plt.ylabel('Review items (total)')

# Set the title
plt.title('Cumulative Review Items')

# Rotate to make dates readable
plt.xticks(rotation=45, fontsize=6)

# Show the plot
plt.show()

df["Increment"] = df["count"].diff(periods=2).fillna(0)

# Create the plot
sns.lineplot(x='date', y='count', data=df)

# Set the x-axis label
plt.xlabel('Date')

# Set the y-axis label
plt.ylabel('Number of tasks')

# Set the title
plt.title('Tasks completed each day')

# Rotate to make dates readable
plt.xticks(rotation=45, fontsize=6)

# Show the plot
plt.show()

print(df.to_string())
```