braaannigan

# The following must be executed in a jupyter notebook rather than a shell environment.
# Use numpy to work with arrays
import numpy as np
# Use scipy.stats to do plot some statistical data
import scipy.stats as stats

import holoviews as hv
# Holoviews builds on top of either the Matplotlib or Bokeh plotting library. Choose to use Bokeh 
# in these plots as interactive plots work very well with Bokeh
hv.notebook_extension('bokeh')

braaannigan

import pandas as pd
import polars as pl
import dask.dataframe as dd

# You can get the data from here:
# s3://coiled-datasets/h2o/G1_1e8_1e2_0_0/csv/G1_1e8_1e2_0_0.csv
fl = "data/G1_1e8_1e2_0_0.csv"
# Pandas and Dask examples based on this blog post
# https://coiled.io/blog/speed-up-pandas-query-10x-with-dask/

braaannigan

from datetime import timedelta, datetime

import polars as pl

# Make a dataframe with a one hour time series at 10-min intervals for group "a"
df = (
  pl.DataFrame(
  {'date':pl.date_range(start,stop,timedelta(minutes=10))
  })
  .with_column(