def test_1_1_permutations(self, tmp_path, engine):
df_1_1 = pd.DataFrame(data, columns=reg_columns, index=reg_index)
dset_1_1 = mp.Dataset(df_1_1)
dset_1_1.to_excel(tmp_path / "dset_1_0.xlsx", engine=engine, header=True, index=False)
dset_1_1.to_excel(tmp_path / "dset_0_1.xlsx", engine=engine, header=False, index=True)
dset_1_1.to_excel(tmp_path / "dset_1_1.xlsx", engine=engine, header=True, index=True)
dset_1_1.to_excel(tmp_path / "dset_0_0.xlsx", engine=engine, header=False, index=False)
# 1_1: test 1 header 1 index
dset_1_1_parsed = mp.read_excel(tmp_path / "dset_1_1.xlsx")
assert_frame_equal(dset_1_1, dset_1_1_parsed)
# 1_0: test 1 header 0 index
dset_1_1_parsed = mp.read_excel(tmp_path / "dset_1_0.xlsx")
dset_1_1_parsed.index = reg_index
assert_frame_equal(dset_1_1, dset_1_1_parsed)
# 0_1: test 0 header 1 index
dset_1_1_parsed = mp.read_excel(tmp_path / "dset_0_1.xlsx")
dset_1_1_parsed.index.name = None # if no header, pandas inserts a default index name of 0
dset_1_1_parsed.columns = reg_columns
assert_frame_equal(dset_1_1, dset_1_1_parsed)
# 0_0: test 0 header 0 index
dset_1_1_parsed = mp.read_excel(tmp_path / "dset_0_0.xlsx")
dset_1_1_parsed.index = reg_index
dset_1_1_parsed.columns = reg_columns
assert_frame_equal(dset_1_1, dset_1_1_parsed)
def test_dups(cli_link_small_with_dups):
mal = mp.read_excel(cli_link_small_with_dups, as_collection=True)
dups = mal.get_duplicates()
assert len(dups["instr2_all"]) == 12
assert len(dups["instr3_all"]) == 17
def test_2_1(self, tmp_path, engine):
df_2_1 = pd.DataFrame(data, columns=mi_columns, index=reg_index)
dset_2_1 = mp.Dataset(df_2_1)
dset_2_1.to_excel(tmp_path / "dset_2_1.xlsx", engine=engine, header=True, index=True)
# 2_1: test 2 header 1 index
dset_2_1_parsed = mp.read_excel(tmp_path / "dset_2_1.xlsx")
assert_frame_equal(dset_2_1, dset_2_1_parsed)
def test_1_2(self, tmp_path, engine):
df_1_2 = pd.DataFrame(data, columns=reg_columns, index=mi_index)
dset_1_2 = mp.Dataset(df_1_2)
dset_1_2.to_excel(tmp_path / "dset_1_2.xlsx", engine=engine, header=True, index=True)
# 1_2: test 1 header 2 index
dset_1_2_parsed = mp.read_excel(tmp_path / "dset_1_2.xlsx")
assert_frame_equal(dset_1_2, dset_1_2_parsed)
def test_read_file(cli_link_small_with_merge):
mal = mp.read_excel(cli_link_small_with_merge, as_collection=True)
assert type(mal) is MergeableAnchoredList
mal_dict = mal.to_excel_dict()
assert mal_dict["primary"]["name"] == "small"
assert mal_dict["primary"]["id_col_name"] == "InstrID"
def test_basiclist(tmp_path):
dset1 = mp.Dataset({"A": [1, 2, 3], "B": [4, 5, 6], "C": [7, 8, 9]})
dset1.to_excel(tmp_path / "dset1.xlsx")
with mp.MACPieExcelFile(tmp_path / "dset1.xlsx") as reader:
dset1_from_file = mp.read_excel(reader, sheet_name="NO_NAME")
# dset1_from_file = mp.read_excel(tmp_path / "dset1.xlsx", sheet_name="NO_NAME")
assert dset1.equals(dset1_from_file)
dset2 = mp.Dataset(
{
"A": [1, 2, 3],
"albert": [4, 5, 6],
"C": [7, 8, 9]
},
id_col_name="albert",
name="renee",
tags=["a", "b"],
)
basic_list = mp.BasicList([dset1, dset2])
with mp.MACPieExcelWriter(tmp_path / "basic_list.xlsx") as writer:
basic_list.to_excel(writer)
with mp.MACPieExcelFile(tmp_path / "basic_list.xlsx") as reader:
basic_list_from_file = mp.read_excel(reader, as_collection=True)
# basic_list_from_file = mp.read_excel(tmp_path / "basic_list.xlsx", as_collection=True)
assert len(basic_list_from_file) == 2
assert basic_list_from_file[0].equals(dset1)
assert basic_list_from_file[1].equals(dset2)
def test_basic_collection(self, tmp_path, engine):
basic_list = mp.BasicList([reg_dset, mi_dset])
with mp.MACPieExcelWriter(tmp_path / "basic_list.xlsx", engine=engine) as writer:
basic_list.to_excel(writer)
basic_list_from_file = mp.read_excel(tmp_path / "basic_list.xlsx")
basic_list_from_file.index = reg_index
assert_frame_equal(basic_list_from_file, reg_dset)
basic_list_from_file = mp.read_excel(tmp_path / "basic_list.xlsx", sheet_name=0)
basic_list_from_file.index = reg_index
assert_frame_equal(basic_list_from_file, reg_dset)
basic_list_from_file = mp.read_excel(
tmp_path / "basic_list.xlsx", sheet_name="mi_test_name"
)
basic_list_from_file.index = mi_index
assert_frame_equal(basic_list_from_file, mi_dset)
basic_list_from_file = mp.read_excel(tmp_path / "basic_list.xlsx", sheet_name=[0, 1])
reg_dset_parsed = basic_list_from_file[0]
reg_dset_parsed.index = reg_index
assert_frame_equal(reg_dset_parsed, reg_dset)
mi_dset_parsed = basic_list_from_file[1]
mi_dset_parsed.index = mi_index
assert_frame_equal(mi_dset_parsed, mi_dset)
basic_list_from_file = mp.read_excel(
tmp_path / "basic_list.xlsx", sheet_name=[0, "mi_test_name"]
)
reg_dset_parsed = basic_list_from_file[0]
reg_dset_parsed.index = reg_index
assert_frame_equal(reg_dset_parsed, reg_dset)
mi_dset_parsed = basic_list_from_file["mi_test_name"]
mi_dset_parsed.index = mi_index
assert_frame_equal(mi_dset_parsed, mi_dset)
basic_list_from_file = mp.read_excel(tmp_path / "basic_list.xlsx", sheet_name=None)
reg_dset_parsed = basic_list_from_file["NO_NAME"]
reg_dset_parsed.index = reg_index
assert_frame_equal(reg_dset_parsed, reg_dset)
mi_dset_parsed = basic_list_from_file["mi_test_name"]
mi_dset_parsed.index = mi_index
assert_frame_equal(mi_dset_parsed, mi_dset)
def test_2_2_permutations(self, tmp_path, engine):
df_2_2 = pd.DataFrame(data, columns=mi_columns, index=mi_index)
dset_2_2 = mp.Dataset(df_2_2)
dset_2_2.to_excel(tmp_path / "dset_2_2.xlsx", engine=engine, header=True, index=True)
dset_2_2.to_excel(tmp_path / "dset_2_0.xlsx", engine=engine, header=True, index=False)
dset_2_2.to_excel(tmp_path / "dset_0_2.xlsx", engine=engine, header=False, index=True)
dset_2_2.to_excel(tmp_path / "dset_0_0.xlsx", engine=engine, header=False, index=False)
# 2_2: test 2 header 2 index
dset_2_2_parsed = mp.read_excel(tmp_path / "dset_2_2.xlsx")
assert_frame_equal(dset_2_2, dset_2_2_parsed)
# 2_0: test 2 header 0 index
dset_2_2_parsed = mp.read_excel(tmp_path / "dset_2_0.xlsx")
dset_2_2_parsed.index = mi_index
assert_frame_equal(dset_2_2, dset_2_2_parsed)
# 0_2: test 0 header 2 index
dset_2_2_parsed = mp.read_excel(tmp_path / "dset_0_2.xlsx")
dset_2_2_parsed.index.names = mi_index.names
dset_2_2_parsed.columns = mi_columns
assert_frame_equal(dset_2_2, dset_2_2_parsed)
# 0_0: test 0 header 0 index
dset_2_2_parsed = mp.read_excel(tmp_path / "dset_0_0.xlsx")
dset_2_2_parsed.index = mi_index
dset_2_2_parsed.columns = mi_columns
assert_frame_equal(dset_2_2, dset_2_2_parsed)
# test legacy format of merge_cells=False
dset_2_2.to_excel(
tmp_path / "dset_2_2_no_merge.xlsx",
engine=engine,
merge_cells=False,
header=True,
index=True,
)
dset_2_2.to_excel(
tmp_path / "dset_2_0_no_merge.xlsx",
engine=engine,
merge_cells=False,
header=True,
index=False,
)
dset_2_2.to_excel(
tmp_path / "dset_0_2_no_merge.xlsx",
engine=engine,
merge_cells=False,
header=False,
index=True,
)
dset_2_2.to_excel(
tmp_path / "dset_0_0_no_merge.xlsx",
engine=engine,
merge_cells=False,
header=False,
index=False,
)
# 2_2: test 2 header 2 index
dset_2_2_parsed = mp.read_excel(tmp_path / "dset_2_2_no_merge.xlsx")
dset_2_2_parsed.columns = mi_columns
assert_frame_equal(dset_2_2, dset_2_2_parsed)
# 2_0: test 2 header 0 index
dset_2_2_parsed = mp.read_excel(tmp_path / "dset_2_0_no_merge.xlsx")
dset_2_2_parsed.index = mi_index
dset_2_2_parsed.columns = mi_columns
assert_frame_equal(dset_2_2, dset_2_2_parsed)
# 0_2: test 0 header 2 index
dset_2_2_parsed = mp.read_excel(tmp_path / "dset_0_2_no_merge.xlsx")
dset_2_2_parsed.index.names = mi_index.names
dset_2_2_parsed.columns = mi_columns
assert_frame_equal(dset_2_2, dset_2_2_parsed)
# 0_0: test 0 header 0 index
dset_2_2_parsed = mp.read_excel(tmp_path / "dset_0_0_no_merge.xlsx")
dset_2_2_parsed.index = mi_index
dset_2_2_parsed.columns = mi_columns
assert_frame_equal(dset_2_2, dset_2_2_parsed)
def execute(self):
self.results = read_excel(self.primary, as_collection=True)