def test_dask_parquet(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
fs.mkdir("test")
STORAGE_OPTIONS = {
"account_name": "devstoreaccount1",
"connection_string": CONN_STR,
}
df = pd.DataFrame({
"col1": [1, 2, 3, 4],
"col2": [2, 4, 6, 8],
"index_key": [1, 1, 2, 2],
"partition_key": [1, 1, 2, 2],
})
dask_dataframe = dd.from_pandas(df, npartitions=1)
for protocol in ["abfs", "az"]:
dask_dataframe.to_parquet(
"{}://test/test_group.parquet".format(protocol),
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
)
fs = AzureBlobFileSystem(**STORAGE_OPTIONS)
assert fs.ls("test/test_group.parquet") == [
"test/test_group.parquet/_common_metadata",
"test/test_group.parquet/_metadata",
"test/test_group.parquet/part.0.parquet",
]
fs.rm("test/test_group.parquet")
df_test = dd.read_parquet(
"abfs://test/test_group.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
assert_frame_equal(df, df_test)
A = np.random.randint(0, 100, size=(10000, 4))
df2 = pd.DataFrame(data=A, columns=list("ABCD"))
ddf2 = dd.from_pandas(df2, npartitions=4)
dd.to_parquet(
ddf2,
"abfs://test/test_group2.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
)
assert fs.ls("test/test_group2.parquet") == [
"test/test_group2.parquet/_common_metadata",
"test/test_group2.parquet/_metadata",
"test/test_group2.parquet/part.0.parquet",
"test/test_group2.parquet/part.1.parquet",
"test/test_group2.parquet/part.2.parquet",
"test/test_group2.parquet/part.3.parquet",
]
df2_test = dd.read_parquet(
"abfs://test/test_group2.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
assert_frame_equal(df2, df2_test)
a = np.full(shape=(10000, 1), fill_value=1)
b = np.full(shape=(10000, 1), fill_value=2)
c = np.full(shape=(10000, 1), fill_value=3)
d = np.full(shape=(10000, 1), fill_value=4)
B = np.concatenate((a, b, c, d), axis=1)
df3 = pd.DataFrame(data=B, columns=list("ABCD"))
ddf3 = dd.from_pandas(df3, npartitions=4)
dd.to_parquet(
ddf3,
"abfs://test/test_group3.parquet",
partition_on=["A", "B"],
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
)
assert fs.glob("test/test_group3.parquet/*") == [
"test/test_group3.parquet/A=1",
"test/test_group3.parquet/_common_metadata",
"test/test_group3.parquet/_metadata",
]
df3_test = dd.read_parquet(
"abfs://test/test_group3.parquet",
filters=[("A", "=", 1)],
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
df3_test = df3_test[["A", "B", "C", "D"]]
df3_test = df3_test[["A", "B", "C", "D"]].astype(int)
assert_frame_equal(df3, df3_test)
A = np.random.randint(0, 100, size=(10000, 4))
df4 = pd.DataFrame(data=A, columns=list("ABCD"))
ddf4 = dd.from_pandas(df4, npartitions=4)
dd.to_parquet(
ddf4,
"abfs://test/test_group4.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
flavor="spark",
write_statistics=False,
)
fs.rmdir("test/test_group4.parquet/_common_metadata", recursive=True)
fs.rmdir("test/test_group4.parquet/_metadata", recursive=True)
fs.rm("test/test_group4.parquet/_common_metadata")
fs.rm("test/test_group4.parquet/_metadata")
assert fs.ls("test/test_group4.parquet") == [
"test/test_group4.parquet/part.0.parquet",
"test/test_group4.parquet/part.1.parquet",
"test/test_group4.parquet/part.2.parquet",
"test/test_group4.parquet/part.3.parquet",
]
df4_test = dd.read_parquet(
"abfs://test/test_group4.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
assert_frame_equal(df4, df4_test)
A = np.random.randint(0, 100, size=(10000, 4))
df5 = pd.DataFrame(data=A, columns=list("ABCD"))
ddf5 = dd.from_pandas(df5, npartitions=4)
dd.to_parquet(
ddf5,
"abfs://test/test group5.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
)
assert fs.ls("test/test group5.parquet") == [
"test/test group5.parquet/_common_metadata",
"test/test group5.parquet/_metadata",
"test/test group5.parquet/part.0.parquet",
"test/test group5.parquet/part.1.parquet",
"test/test group5.parquet/part.2.parquet",
"test/test group5.parquet/part.3.parquet",
]
df5_test = dd.read_parquet(
"abfs://test/test group5.parquet",
storage_options=STORAGE_OPTIONS,
engine="pyarrow",
).compute()
assert_frame_equal(df5, df5_test)
def test_glob(storage):
fs = AzureBlobFileSystem(account_name=storage.account_name,
connection_string=CONN_STR)
## just the directory name
assert fs.glob("data/root") == ["data/root"]
# top-level contents of a directory
assert fs.glob("data/root/") == [
"data/root/a",
"data/root/b",
"data/root/c",
"data/root/rfile.txt",
]
assert fs.glob("data/root/*") == [
"data/root/a",
"data/root/b",
"data/root/c",
"data/root/rfile.txt",
]
assert fs.glob("data/root/b/*") == ["data/root/b/file.txt"] # NOQA
assert fs.glob("data/root/b/**") == ["data/root/b/file.txt"] # NOQA
## across directories
assert fs.glob("data/root/*/file.txt") == [
"data/root/a/file.txt",
"data/root/b/file.txt",
]
## regex match
assert fs.glob("data/root/*/file[0-9].txt") == [
"data/root/c/file1.txt",
"data/root/c/file2.txt",
]
## text files
assert fs.glob("data/root/*/file*.txt") == [
"data/root/a/file.txt",
"data/root/b/file.txt",
"data/root/c/file1.txt",
"data/root/c/file2.txt",
]
## all text files
assert fs.glob("data/**/*.txt") == [
"data/root/a/file.txt",
"data/root/b/file.txt",
"data/root/c/file1.txt",
"data/root/c/file2.txt",
"data/root/rfile.txt",
]
## all files
assert fs.glob("data/root/**") == [
"data/root/a",
"data/root/a/file.txt",
"data/root/b",
"data/root/b/file.txt",
"data/root/c",
"data/root/c/file1.txt",
"data/root/c/file2.txt",
"data/root/rfile.txt",
]
assert fs.glob("data/roo**") == [
"data/root",
"data/root/a",
"data/root/a/file.txt",
"data/root/b",
"data/root/b/file.txt",
"data/root/c",
"data/root/c/file1.txt",
"data/root/c/file2.txt",
"data/root/rfile.txt",
]
## missing
assert fs.glob("data/missing/*") == []
