gumdropsteve

gumdropsteve

"VendorID","tpep_pickup_datetime","tpep_dropoff_datetime","passenger_count","trip_distance","pickup_longitude","pickup_latitude","RateCodeID","store_and_fwd_flag","dropoff_longitude","dropoff_latitude","payment_type","fare_amount","extra","mta_tax","tip_amount","tolls_amount","improvement_surcharge","total_amount"
2,"2015-01-15 19:05:39","2015-01-15 19:23:42",1,1.59,-73.99389648,40.75011063,1,"N",-73.97478485,40.75061798,1,12.0,1.0,0.5,3.25,0.0,0.3,17.05
1,"2015-01-10 20:33:38","2015-01-10 20:53:28",1,3.3,-74.00164795,40.72424316,1,"N",-73.99441528,40.7591095,1,14.5,0.5,0.5,2.0,0.0,0.3,17.8
1,"2015-01-10 20:33:38","2015-01-10 20:43:41",1,1.8,-73.96334076,40.80278778,1,"N",-73.95182037,40.8244133,2,9.5,0.5,0.5,0.0,0.0,0.3,10.8
1,"2015-01-10 20:33:39","2015-01-10 20:35:31",1,0.5,-74.00908661,40.7138176,1,"N",-74.00432587,40.71998596,2,3.5,0.5,0.5,0.0,0.0,0.3,4.8
1,"2015-01-10 20:33:39","2015-01-10 20:52:58",1,3.0,-73.97117615,40.76242828,1,"N",-74.00418091,40.74265289,2,15.0,0.5,0.5,0.0,0.0,0.3,16.3
1,"2015-01-

gumdropsteve

gumdropsteve

gumdropsteve

import os 
import urllib
from blazingsql import BlazingContext

# set number of times to run each query
n_runs = 3
# let user know
print(f'nruns = {n_runs}')

'''CHECK FOR DATA

gumdropsteve

# This query determines the data load time and total time for all queries, showing the latest ones first. 
# load time and total time being the maximum load time and total time for any node.
log_query = """
            SELECT
            	MAX(end_time) as end_time, query_id, 
              	MAX(load_time) AS load_time, MAX(total_time) AS total_time 
            FROM (
            	SELECT
              	    query_id, node_id,
                    SUM(CASE WHEN info = 'evaluate_split_query load_data' THEN duration ELSE 0 END) AS load_time,

gumdropsteve

gumdropsteve

from blazingsql import BlazingContext
import cudf

# cuDF DataFrame from CSV stored external via URL
turkey_poll = cudf.read_csv('https://query.data.world/s/ss47hkdmqe5d6353neouv4ourm2ous')

# make columns easier to work with 
new_cols = []
for col in turkey_poll.columns:
    # replace spaces w/ underscore and drop question & quotation marks

gumdropsteve

Keybase proof

I hereby claim:

• I am gumdropsteve on github.
• I am winston_ (https://keybase.io/winston_) on keybase.
• I have a public key ASC6sL40hnMAmWH9Wum_6F-H8L-QvW_0BLvCJfSyQr4r7Ao

To claim this, I am signing this object:

gumdropsteve

from time import sleep
from selenium import webdriver

story = 'https://medium.com/dropout-analytics/selenium-and-geckodriver-on-mac-b411dbfe61bc'
story = story + '?source=friends_link&sk=18e2c2f07fbe1f8ae53fef5ad57dbb12'   # 'https://bit.ly/2WaKraO' <- short link

def gecko_test(site_000=story):
    """
    simple overview:
        1) set up webdriver