ium_478815/IUM2.ipynb

!pip install kaggle
!pip install pandas
!pip install seaborn
!pip install opendatasets --upgrade
import opendatasets as od
import pandas as pd

cd ~/.kaggle

!kaggle datasets download -d shree1992/housedata

!unzip -o housedata.zip

!wc -l data.csv
data = pd.read_csv('data.csv')

data

!head -n -1 data.csv | shuf > data.csv.shuf

!head -n 460 data.csv.shuf > data.csv.test
!head -n 920 data.csv.shuf | tail -n 460 > data.csv.dev
!tail -n +920 data.csv.shuf > data.csv.train

!rm data.csv.shuf
!wc -l data.csv*

data_test = pd.read_csv('data.csv.test')
data_dev = pd.read_csv('data.csv.dev')
data_train = pd.read_csv('data.csv.train')

data.describe(include='all')

data_train.describe(include='all')

data_dev.describe(include='all')

data_test.describe(include='all')

grep -P "^$" -n data.csv