lpillmann

import gcsfs
import pyarrow

def read_parquet(gs_directory_path, to_pandas=True):
    """
    Reads multiple (partitioned) parquet files from a GS directory
    e.g. 'gs://<bucket>/<directory>' (without ending /)
    """
    gs = gcsfs.GCSFileSystem()
    arrow_df = pyarrow.parquet.ParquetDataset(gs_directory_path, filesystem=gs)

lpillmann

# Use ipdb as default debugger (you need to install it with conda install ipdb)
export PYTHONBREAKPOINT=ipdb.set_trace

lpillmann

import matplotlib
import matplotlib.pyplot as plt

%matplotlib inline

# Heuristics to make labels always readable, for dpi = 100 (default)
fig_w, fig_h = 10, 6  # Figure dimensions (in inches)
font_size = fig_w + fig_h  # Font size (in pts.)

matplotlib.rcParams.update({

lpillmann

import altair as alt

# Custom theme for readability
def readable():   
    return {
        "config" : {
             "title": {'fontSize': 16},
             "axis": {
                  "labelFontSize": 14,
                  "titleFontSize": 14,

lpillmann

#!/usr/bin/env python
'''Crop an image to just the portions containing text.

Usage:

    ./crop_morphology.py path/to/image.jpg

This will place the cropped image in path/to/image.crop.png.

For details on the methodology, see