rikturr

rikturr

from sklearn.utils import all_estimators
import inspect

has_n_jobs = []
for est in all_estimators():
    s = inspect.signature(est[1])
    if 'n_jobs' in s.parameters:
        has_n_jobs.append(est)
print(has_n_jobs)

rikturr

rikturr

rikturr

organization,org_type,position,source,referral,end_stage,num_interviews,date_applied,date_interview1,date_interview2,date_interview3,date_rejected,date_declined,date_accepted,notes
Twitter,Public,Staff machine learning engineer,Referral,1,Reject-resume,0,4/8/2020,,,,4/29/2020,,,
Wikimedia foundation,Non-profit,Machine learning engineer,Search,0,Reject-ghosted,0,4/19/2020,,,,,,,
UNOPS,Government,Predictive Analytics Technical Specialist,Search,0,Reject-ghosted,0,4/19/2020,,,,,,,
Noom,Startup,Senior data scientist,Search,0,Reject-resume,0,4/20/2020,,,,4/23/2020,,,
Memorial Sloan Kettering Cancer Center,Private-L,Lead data scientist,Search,0,Reject-ghosted,0,4/20/2020,,,,,,,
Memorial Sloan Kettering Cancer Center,Private-L,Senior data engineer,Search,0,Reject-resume,0,4/20/2020,,,,5/13/2020,,,
Memorial Sloan Kettering Cancer Center,Private-L,Data engineer,Search,0,Decline-resume,0,4/20/2020,,,,,6/17/2020,,Took other job
Prominent Edge,Consulting,Lead data scientist,Search,0,Reject-ghosted,0,4/21/2020,,,,,,,
Open

rikturr

# notice "dask" in these imports
import dask_cudf
from cuml.dask.ensemble import RandomForestClassifier

taxi = dask_cudf.read_csv(
    's3://nyc-tlc/trip data/yellow_tripdata_2019-01.csv',
    parse_dates=['tpep_pickup_datetime', 'tpep_dropoff_datetime'],
    storage_options={'anon': True},
    assume_missing=True,
)

rikturr

from dask.distributed import Client
from dask_saturn import SaturnCluster

cluster = SaturnCluster(
  n_workers=3, 
  scheduler_size='medium', 
  worker_size='g4dnxlarge'
)
client = Client(cluster)

rikturr

from cuml.ensemble import RandomForestClassifier

# see notebook for prep_df function
taxi_train = prep_df(taxi)

rfc = RandomForestClassifier(n_estimators=100, max_depth=10, seed=42)
rfc.fit(taxi_train[features], taxi_train[y_col])

rikturr

import cudf
import s3fs
s3 = s3fs.S3FileSystem(anon=True)

taxi = cudf.read_csv(
    s3.open('s3://nyc-tlc/trip data/yellow_tripdata_2019-01.csv', mode='rb'),
    parse_dates=['tpep_pickup_datetime', 'tpep_dropoff_datetime']
)

rikturr