def test_keep_existing_small_cols(self):
''' test that columns that already exist in df_small are retained'''
df_large, df_small = load_dfs('reference.shp', 'keep.shp')
large_cols = ['large_str']
small_cols = ['col_str']
df = distribute_label(df_large, large_cols, df_small, small_cols)
check_df(df, ['col_str', 'keep_col'])
def test_reset_small_cols(self):
''' test that prior duplicate columns in df_small will be deleted'''
df_large, df_small = load_dfs('reference.shp', 'reset.shp')
large_cols = ['large_str', 'large_int', 'large_flt']
# Apply and test
df = distribute_label(df_large, large_cols, df_small)
check_df(df, large_cols, True)
def test_default_small_cols(self):
''' test that the default columns work. This will just use all of the
large_cols'''
df_large, df_small = load_dfs('reference.shp', 'within.shp')
large_cols = ['large_str', 'large_int', 'large_flt']
# Apply and test
df = distribute_label(df_large, large_cols, df_small)
check_df(df, large_cols, True)
def test_centroid(self):
''' Check label distribution when bounding box does not intersect with
any larger geometry'''
df_large, df_small = load_dfs('reference.shp', 'centroid.shp')
large_cols = ['large_str']
small_cols = ['col_str']
# Apply and test
df = distribute_label(df_large, large_cols, df_small, small_cols)
check_df(df, small_cols)
def test_shared(self):
''' Check label distribution when bounding box interesects with
multiple larger geometries'''
df_large, df_small = load_dfs('reference.shp', 'shared.shp')
large_cols = ['large_str']
small_cols = ['col_str']
# Apply and test
df = distribute_label(df_large, large_cols, df_small, small_cols)
check_df(df, small_cols)
def test_within(self):
''' Check label distribution when bounding box intersection is with
only one large geometry'''
df_large, df_small = load_dfs('reference.shp', 'within.shp')
large_cols = ['large_str']
small_cols = ['col_str']
# Apply and test
df = distribute_label(df_large, large_cols, df_small, small_cols)
check_df(df, small_cols)
def test_attribute_subset(self):
''' Check that False is returned when the an element of large_cols is
not in the dataframe itself'''
# load dataframe
df_large, df_small = load_dfs('reference.shp', 'within.shp')
# Get same length column sizes
large_cols = df_large.columns
large_cols = [x + 'foo' for x in large_cols]
df = distribute_label(df_large, large_cols, df_small)
assert df == False
def test_attribute_list_size_comparison(self):
''' Check that False is returned when the size of attribute lists
are not of the same length'''
# load
df_large, df_small = load_dfs('reference.shp', 'within.shp')
# Get different length column sizes
large_cols = df_large.columns
small_cols = ['a']
df = distribute_label(df_large, large_cols, df_small, small_cols)
assert df == False