DatatableTon: 100 Python Datatable Exercises | H2O.ai

DatatableTon: 100 Python Datatable Exercises | H2O.ai

python

import datatable as dt
import pandas as pd

dframe = pd.DataFrame({'v1': range(11),
'v2': ['N', 'E', 'V', 'E', 'R', 'G', 'I', 'V', 'E', 'U', 'P']})
data_pd = dt.Frame(dframe)
pd_data = data_pd.to_pandas()

python

import datatable as dt
from seaborn import load_dataset

data = dt.Frame(load_dataset('penguins'))
data.replace('NA', None)
data[:, dt.median(dt.f.body_mass_g), dt.by([dt.f.species, dt.f.sex])]

python

import datatable as dt

data = list(dt.iread('datatableton_sample.zip'))

orders_jan = data[1]
orders_feb = data[0]
orders_mar = data[2]
orders_all = dt.rbind(orders_jan, orders_feb, orders_mar)
returns = data[3]

orders_all.key = 'Order ID'
sales = returns[:, :, dt.join(orders_all)]

python

import datatable as dt
from datatable.models import Ftrl

data = dt.fread('kdd_ctr.csv', fill=True)[1:,:]
target = data['click']
del data['click']

model_ftrl = Ftrl()
model_ftrl.fit(data, target)

python

import datatable as dt
from datatable.models import Ftrl

train = dt.fread('tradeshift-text-classification/train.csv.gz')
test = dt.fread('tradeshift-text-classification/test.csv.gz')
train_labels = dt.fread('tradeshift-text-classification/trainLabels.csv.gz')

test_ids = test['id']

del train['id']
del test['id']

submission = dt.Frame()

for target in train_labels.names[1:]:
print(f'Model for target {target}')

model_ftrl = Ftrl(nepochs=5, nbins=10**8, lambda1=0.1)
model_ftrl.fit(train, train_labels[target])

preds_test = model_ftrl.predict(test)
submission_target = dt.Frame(id_label=test_ids[:, dt.as_type(dt.f.id, str) + f'_{target}'], pred=preds_test['True'])
submission.rbind(submission_target)

submission.to_csv('submission.csv')