datasets/src/house_price.py at d465eb295107e69e6c75eb4bd4e741e739c1e004 · skrub-data/datasets · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33


import os
from collections import namedtuple
import re

import pandas as pd

DatasetInfo = namedtuple('DatasetInfo', ['name', 'urlinfos', 'main_file', 'source'])
UrlInfo = namedtuple('UrlInfo', ['url', 'filenames', 'uncompress'])

HOUSE_PRICE_CONFIG = DatasetInfo(
    name='house_price',
    urlinfos=(
        UrlInfo(
            url="https://www.kaggle.com/c/house-prices-advanced-regression-techniques/overview",
            filenames=(
                "profile.csv",
            ), uncompress=False
        ),
    ),
    main_file="train_test.csv",
    source="https://www.kaggle.com/c/house-prices-advanced-regression-techniques/overview"
)


def get_house_price_df(save=True):

    df = pd.read_csv('data/house-prices/train.csv')
    df.rename(columns={col: re.sub(' ', '_', col) for
              col in df.columns}, inplace=True)

    return df