def test_parse_categories():
data = convert_csv_pd("""
str1,str2
a1,a1
2,2
3,3
4,4
5,5
6,6
7,7
8,8
9,9
10,10
11,11
12,12
13,13
14,14
15,15
16,16
17,17
18,18
19,19
20,20
21,20
""")
parse_categories(data)
_check_categories_parsed(data, ["str2"])
def test_complex_df_report():
"""Test our dataframe importing with types of DFs user's upload"""
tz_df = convert_csv_pd("""
date,datetime,datetime_tz
2017-01-10,2017-01-21T23:10:24,2020-03-23T00:00:00.000Z
2017-01-11,2017-01-23T23:01:24,2020-04-23T00:00:00.000Z
""")
raw_data = {
"first_name": ["Jason", "Molly", "Tina", "Jake", "Amy"],
"last_name": ["Miller", "Jacobson", "Ali", "Milner", "Cooze"],
"age": [42, 52, 36, 24, 73],
"preTestScore": [4, 24, 31, 2, 3],
"postTestScore": [25, 94, 57, 62, 70],
}
index_df = pd.DataFrame(raw_data,
columns=[
"first_name", "last_name", "age",
"preTestScore", "postTestScore"
])
df_desc = index_df.describe()
df_desc_2 = df_desc.reset_index()
tz_t = dp.Table(tz_df)
index_t = dp.Table(index_df)
df_desc_t = dp.Table(df_desc)
df_desc_2_t = dp.Table(df_desc_2)
with deletable(dp.Report(tz_t, index_t, df_desc_t,
df_desc_2_t)) as dp_report:
dp_report.publish(name=gen_name())
def test_parse_timedelta_regular():
data = convert_csv_pd("""
timedelta_col,float_col,string_col
"1 day, 4:08:25.159814",0.23,bla1
"1 day, 18:34:16.196687",0.23,bla1
""")
parse_timedelta(data)
_check_timedelta_parsed(data, ["timedelta_col"])
def test_parse_dates_wrong_date():
data = convert_csv_pd("""
data_col1,data_col2,float_col,string_col
2017-01-10,2017-01-21T23:10:24,0.23,bla1
2017-01-1s,2017-01-23T23:01:24,0.23,bla1
""")
parse_dates(data)
_check_dates_parsed(data, ["data_col2"])
def test_to_str_timedelta():
data = convert_csv_pd("""
timedelta_col,float_col,string_col
"1 day, 4:08:25.159814",0.23,bla1
"1 day, 18:34:16.196687",0.23,bla1
""")
parse_timedelta(data)
to_str(data)
_check_is_object(data, ["timedelta_col"])
def test_parse_dates_nulls():
# NOTE - using just Z, not .000Z means pandas doesn't infer timezone, so naive datetime object
data = convert_csv_pd("""
timestamp,value
2019-02-19T03:00:02Z,1
,2
2019-01-10T12:10:10Z,3
""")
parse_dates(data)
_check_dates_parsed(data, ["timestamp"])
def test_parse_timedelta_with_assertion_error():
data = convert_csv_pd("""
timedelta_col1,timedelta_col2,float_col,string_col
4:08:25.159814,"1 day, 4:08:25.159814",0.23,bla1
18:34:16.196687,"1 day, 18:34:16.196687",0.23,bla1
""")
parse_timedelta(data)
# timedelta_col1's dtype is a datetime64[ns]
_check_dates_parsed(data, ["timedelta_col1"])
with pytest.raises(AssertionError):
_check_timedelta_parsed(data, ["timedelta_col1", "timedelta_col2"])