def test_read_xlsx(table, tmpdir):
filename = str(tmpdir.mkdir("data").join("table.xlsx"))
table.to_excel(filename, index=False)
df = read_tabular(filename)
assert (df["integer"] == table["integer"]).all()
assert isclose(df["numeric"], table["numeric"]).all()
assert (df["comments"].isnull() == table["comments"].isnull()).all()
assert (df.loc[df["comments"].notnull(), "comments"] ==
table.loc[table["comments"].notnull(), "comments"]).all()
def test_read_tsv(table, tmpdir):
filename = str(tmpdir.mkdir("data").join("table.tsv"))
table.to_csv(filename, sep="\t", index=False, encoding="utf-8")
df = read_tabular(filename)
assert (df["integer"] == table["integer"]).all()
assert isclose(df["numeric"], table["numeric"]).all()
assert (df["comments"].isnull() == table["comments"].isnull()).all()
assert (df.loc[df["comments"].notnull(), "comments"] ==
table.loc[table["comments"].notnull(), "comments"]).all()
def load(self, dtype_conversion=None):
"""
Load the data table and corresponding validation schema.
Parameters
----------
dtype_conversion : dict
Column names as keys and corresponding type for loading the data.
Please take a look at the `pandas documentation
<https://pandas.pydata.org/pandas-docs/stable/io.html#specifying-column-data-types>`__
for detailed explanations.
"""
self.data = read_tabular(self.filename, dtype_conversion)
with open_text(memote.experimental.schemata,
self.SCHEMA,
encoding="utf-8") as file_handle:
self.schema = json.load(file_handle)
def load(self):
"""Load the data table and corresponding validation schema."""
self.data = read_tabular(self.filename)
with open_text(memote.experimental.schemata, self.SCHEMA,
encoding="utf-8") as file_handle:
self.schema = json.load(file_handle)