maplib-masterclass/parse_data.py at main · DataTreehouse/maplib-masterclass · 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
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
import polars as pl
pl.Config.set_fmt_str_lengths(150)

# Namespaces
ns = "http://data.treehouse.example/"
ns_tpl = "http://data.treehouse.example/tpl/"
ns_sh = "http://data.treehouse.example/sh/"

# PLANETS AND SATELLITES: https://github.com/devstronomy/nasa-data-scraper/tree/master
# STARS: https://www.kaggle.com/datasets/waqi786/stars-dataset/data

def planets():

    # Read planet CSV
    df_planets = pl.read_csv("data/planets.csv")

    # Create subject URI for planets
    df_planets = df_planets.with_columns(
        (ns + pl.col("planet")).alias("planet_uri")
        )

    # Chose columns to play with
    df_planets = df_planets.select(
        ["planet",
        "planet_uri", # the new column we just made :-)
        "mean_temperature",
        "length_of_day",
        "orbital_period"
        ])

    return df_planets


def satellites():

    df_satellites = pl.read_csv("data/satellites.csv")
    df_satellites = df_satellites.with_columns(
        (ns + pl.col("planet")).alias("planet_uri")
    )
    df_satellites = df_satellites.with_columns(
        (ns + pl.col("name")
        .str.replace_all("/", "-"))
        .str.replace_all(" ", "-")
        .alias("satellite_uri")
    )
    df_satellites = df_satellites.select(
        ["name", "planet_uri", "satellite_uri", "albedo", "radius"]
    )

    df_satellites = (
    df_satellites
    .with_columns(
        pl.col("albedo")
        .cast(pl.Float64, strict=False)
        .alias("albedo")
        )
    .with_columns(
        pl.col("radius")
        .cast(pl.Float64, strict=False)
        .alias("radius")
        )
    )

    return df_satellites

def stars():
    df_stars = pl.read_csv("data/stars.csv")
    return df_stars