def test_asof_without_nan(dates, subset):
data = {"a": [10, 20, 30, 40, 50], "b": [70, 600, 30, -200, 500]}
index = pd.DatetimeIndex([
"2018-02-27 09:01:00",
"2018-02-27 09:02:00",
"2018-02-27 09:03:00",
"2018-02-27 09:04:00",
"2018-02-27 09:05:00",
])
modin_where = pd.DatetimeIndex(dates)
pandas_where = pandas.DatetimeIndex(dates)
compare_asof(data, index, modin_where, pandas_where, subset)
def test_asof():
df = pd.DataFrame(
{
"a": [10, 20, 30, 40, 50],
"b": [None, None, None, None, 500]
},
index=pd.DatetimeIndex([
"2018-02-27 09:01:00",
"2018-02-27 09:02:00",
"2018-02-27 09:03:00",
"2018-02-27 09:04:00",
"2018-02-27 09:05:00",
]),
)
with pytest.warns(UserWarning):
df.asof(
pd.DatetimeIndex(["2018-02-27 09:03:30", "2018-02-27 09:04:30"]))
def test_reindex_like():
df1 = pd.DataFrame(
[
[24.3, 75.7, "high"],
[31, 87.8, "high"],
[22, 71.6, "medium"],
[35, 95, "medium"],
],
columns=["temp_celsius", "temp_fahrenheit", "windspeed"],
index=pd.date_range(start="2014-02-12", end="2014-02-15", freq="D"),
)
df2 = pd.DataFrame(
[[28, "low"], [30, "low"], [35.1, "medium"]],
columns=["temp_celsius", "windspeed"],
index=pd.DatetimeIndex(["2014-02-12", "2014-02-13", "2014-02-15"]),
)
with pytest.warns(UserWarning):
df2.reindex_like(df1)
import numpy as np
#import pandas as pd
import ray
ray.init(huge_pages=False,
plasma_directory="/localdisk/gashiman/plasma",
memory=1024 * 1024 * 1024 * 200,
object_store_memory=1024 * 1024 * 1024 * 200)
import modin.pandas as pd
df = pd.DataFrame([[2, np.datetime64('2013-08-01 08:14:37'), 1.1],
[5, np.datetime64('2014-08-01 09:13:00'), 2.2],
[8, np.datetime64('2015-08-01 09:48:00'), 3.3]],
index=[1, 2, 3],
columns=['health', 'timestamp', 'shield'])
print(df)
transformed = df[['health', 'timestamp', 'shield']].transform({
'health':
lambda x: x,
'timestamp':
lambda x: pd.DatetimeIndex(x).year,
'shield':
lambda x: x
}).groupby(['health', 'timestamp', 'shield'])
print(transformed)
df1 = transformed.size().reset_index().sort_values(by=['timestamp', 0],
ascending=[True, False])
print(df1)
