def test_converts_nan_to_empty_strings(self):
data = {"A": ["A", "B ", " C", np.nan]}
df = pd.DataFrame(data)
data2 = {"A": ["A", "B", "C", ""]}
expected = pd.DataFrame(data2)
remove_whitespace(df)
assert_frame_equal(df, expected)
def test_handles_empty_strings(self):
data = {"A": ["A", "B ", " C", " "]}
df = pd.DataFrame(data)
data2 = {"A": ["A", "B", "C", ""]}
expected = pd.DataFrame(data2)
remove_whitespace(df)
assert_frame_equal(df, expected)
def test_remove_leading_and_trailing_spaces_from_dataframe(self):
data = {
"A": ["A", "B ", " C", "D ", " Ed ", " 1 "],
"B": ["Aa", "Bb ", " Cc", "Dd ", " Ed Ed ", " 11 "],
}
df = pd.DataFrame(data)
data2 = {
"A": ["A", "B", "C", "D", "Ed", "1"],
"B": ["Aa", "Bb", "Cc", "Dd", "Ed Ed", "11"],
}
expected = pd.DataFrame(data2)
remove_whitespace(df)
assert_frame_equal(df, expected)
def test_ignores_numeric_columns(self):
data = {
"A": ["A", "B ", " C"],
"B": [1, 2, 3],
"C": [1.1, 2.2, 3.3],
}
df = pd.DataFrame(data)
data2 = {
"A": ["A", "B", "C"],
"B": [1, 2, 3],
"C": [1.1, 2.2, 3.3],
}
expected = pd.DataFrame(data2)
remove_whitespace(df)
assert_frame_equal(df, expected)
def create_taxa_list_df(df):
fields = taxa_rank_fields + taxa_fields + pdbd_fields
print("fields:", fields)
filtered_taxa = pd.DataFrame(df, columns=fields)
remove_whitespace(filtered_taxa)
print("initial df: ", filtered_taxa.shape)
add_normalized_name_column(filtered_taxa)
filtered_taxa = filtered_taxa.drop(
filtered_taxa[filtered_taxa["normalized_name"] == ""].index)
print("remove nontaxa df: ", filtered_taxa.shape)
filtered_taxa.drop_duplicates(keep="first",
inplace=True,
subset=["normalized_name", "taxon_group"])
print("drop duplicates df: ", filtered_taxa.shape)
return filtered_taxa