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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
|
import pandas as pd
import pytest
from vega_datasets import data
from vega_datasets.utils import connection_ok
skip_if_no_internet = pytest.mark.skipif(
not connection_ok(), reason="No internet connection"
)
@skip_if_no_internet
def test_download_iris():
iris = data.iris(use_local=False)
assert type(iris) is pd.DataFrame
assert sorted(iris.columns) == [
"petalLength",
"petalWidth",
"sepalLength",
"sepalWidth",
"species",
]
iris = data.iris.raw(use_local=False)
assert type(iris) is bytes
def test_stock_date_parsing():
stocks = data.stocks()
assert all(stocks.dtypes == ["object", "datetime64[ns]", "float64"])
def test_stock_pivoted():
stocks = data.stocks(pivoted=True)
assert stocks.index.name == "date"
assert sorted(stocks.columns) == ["AAPL", "AMZN", "GOOG", "IBM", "MSFT"]
@skip_if_no_internet
def test_download_stock_parsing():
stocks = data.stocks(use_local=False)
assert all(stocks.dtypes == ["object", "datetime64[ns]", "float64"])
@skip_if_no_internet
def test_miserables_parsing():
miserables = data.miserables()
assert type(miserables) is tuple
assert all(type(df) is pd.DataFrame for df in miserables)
@skip_if_no_internet
def test_us_10m_parsing():
us_10m = data.us_10m()
assert type(us_10m) is dict
@skip_if_no_internet
def test_world_110m_parsing():
world_110m = data.world_110m()
assert type(world_110m) is dict
@skip_if_no_internet
def test_unemployment_tsv():
unemployment = data.unemployment()
assert len(unemployment.columns) == 2
@skip_if_no_internet
def test_zipcodes_parsing():
zipcodes = data.zipcodes()
assert all(
zipcodes.columns
== ["zip_code", "latitude", "longitude", "city", "state", "county"]
)
assert all(
zipcodes.dtypes
== ["object", "float64", "float64", "object", "object", "object"]
)
|
