langchain-ai/datafusion
1
0
Fork 0
mirror of https://github.com/langchain-ai/datafusion.git synced 2026-07-18 21:24:40 -04:00
Code Issues 3 Packages Projects Releases Wiki Activity

Define the unittests using pytest (#493)

Browse Source 
* Use pytest

* Formatting

* Update GHA conf

* Remove TODO note

* Format

* Test requirements file

* Update workflow file

* Merge requirements file

* Update workflow file
This commit is contained in:
Krisztián Szűcs
2021-06-09 20:23:23 +02:00
committed by GitHub
parent 8495f95d7b
commit 42f908e2b5
8 changed files with 324 additions and 408 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/tests/generic.py
+34 -17
View File
@@ -16,24 +16,30 @@
# under the License.
import datetime
import numpy
import pyarrow
import numpy as np
import pyarrow as pa
import pyarrow.parquet as pq
# used to write parquet files
import pyarrow.parquet
def data():
data = numpy.concatenate(
[numpy.random.normal(0, 0.01, size=50), numpy.random.normal(50, 0.01, size=50)]
np.random.seed(1)
data = np.concatenate(
[
np.random.normal(0, 0.01, size=50),
np.random.normal(50, 0.01, size=50),
]
)
return pyarrow.array(data)
return pa.array(data)
def data_with_nans():
data = numpy.random.normal(0, 0.01, size=50)
mask = numpy.random.randint(0, 2, size=50)
data[mask == 0] = numpy.NaN
np.random.seed(0)
data = np.random.normal(0, 0.01, size=50)
mask = np.random.randint(0, 2, size=50)
data[mask == 0] = np.NaN
return data
@@ -43,8 +49,19 @@ def data_datetime(f):
datetime.datetime.now() - datetime.timedelta(days=1),
datetime.datetime.now() + datetime.timedelta(days=1),
]
return pyarrow.array(
data, type=pyarrow.timestamp(f), mask=numpy.array([False, True, False])
return pa.array(
data, type=pa.timestamp(f), mask=np.array([False, True, False])
)
def data_date32():
data = [
datetime.date(2000, 1, 1),
datetime.date(1980, 1, 1),
datetime.date(2030, 1, 1),
]
return pa.array(
data, type=pa.date32(), mask=np.array([False, True, False])
)
@@ -54,16 +71,16 @@ def data_timedelta(f):
datetime.timedelta(days=1),
datetime.timedelta(seconds=1),
]
return pyarrow.array(
data, type=pyarrow.duration(f), mask=numpy.array([False, True, False])
return pa.array(
data, type=pa.duration(f), mask=np.array([False, True, False])
)
def data_binary_other():
return numpy.array([1, 0, 0], dtype="u4")
return np.array([1, 0, 0], dtype="u4")
def write_parquet(path, data):
table = pyarrow.Table.from_arrays([data], names=["a"])
pyarrow.parquet.write_table(table, path)
return path
table = pa.Table.from_arrays([data], names=["a"])
pq.write_table(table, path)
return str(path)