Converting docx to pdf using libreoffice and pandas binning

 Converting docx to pdf using libreoffice

 

import subprocess, docx, time   # first do: pip install python-docx
t0 = time.time()
subprocess.call(r'C:\Program Files\LibreOffice\program\soffice.exe --headless --convert-to pdf summary.docx --outdir . --nocrashreport --nodefault --nofirststartwizard --nolockcheck --nologo --norestore"')
print('PDF generated in %.1f sec' % (time.time()-t0)) 

Pandas binning

df.loc[df['score'].between(0, 50, 'both'), 'grade'] = 'C'
df.loc[df['score'].between(50, 80, 'right'), 'grade'] = 'B'
df.loc[df['score'].between(80, 100, 'right'), 'grade'] = 'A'

https://towardsdatascience.com/how-to-bin-numerical-data-with-pandas-fe5146c9dc55 

labels = ["low", "medium low", "medium", "medium high", "high"]
df["binned alcohol"] = pd.qcut(df['alcohol'], q=5, labels=labels)
df.groupby("binned alcohol")["alcohol"].count()

bins = [0, 1.5, 2, 2.5, 3, 16]
labels = ["{:.1f}g-{:.1f}g".format(x, y) for x, y in zip(bins, bins[1:])]
df["binned residual sugar"] = pd.cut(df['residual sugar'], bins=bins, labels=labels)
df.groupby("binned residual sugar")["residual sugar"].count()

https://brettromero.com/pandas-how-to-pivot-data/