count the number of lines in your jupyter notebooks

recursive_line_count.py

from glob import glob
from json import load

def loc(nb):
    cells = load(open(nb))["cells"]
    return sum(len(c["source"]) for c in cells)

root_folder = "~"
summation = 0
for File in glob(root_folder+"/**/*.ipynb", recursive=True):
    summation += loc(File)

print(summation)

Thanks very much for this useful way to count the number of code line in Jupyter notebooks. The version below uses the glob method of pathlib Path objects to list files. It prints the number of lines for each files in the directory and the total number as well.

from json import load
from pathlib import Path

def count_lines(notebook):
    """Count the number of source code lines in a Jupyter notebook."""
    cells = load(open(notebook))["cells"]
    return sum(len(c["source"]) for c in cells)

def count_lines_in_dir(directory):
    """Count the number of source code lines in all Jupyter notebook in the directory."""    
    print("Base directory", directory)
    n_lines_total = 0
    for file in directory.rglob("*.ipynb"):
        print(count_lines(file), "lines in", file)
        n_lines_total += count_lines(file)
    return n_lines_total

count_lines_in_dir(Path.cwd())

Nice! This is a pretty neat way to do this as well :)