def testTurnTriangle(self):
dh = DataHolder("test")
data = pd.DataFrame(data={'col1': ["", "", 0], 'col2': [0, 0, 2], '1991': [0, 0, 0], '1992': [1, 0, 0]})
prof = pd.DataFrame(data={'col1': [1, 1, 6], 'col2': [6, 6, 6], '1991': [6, 6, 6], '1992': [2, 6, 6]})
dh.add_sheet("test", data, prof)
data = pd.DataFrame(data={'col1': ["", "", 0], 'col2': [1, 1, 0], '1991': [0, 0, 0], '1992': [1, 0, 0]})
prof = pd.DataFrame(data={'col1': [1, 1, 6], 'col2': [6, 6, 6], '1991': [6, 6, 6], '1992': [2, 6, 6]})
dh.add_sheet("test", data, prof)
data = pd.DataFrame(data={'col1': ["", "", 0], 'col2': [3, 1, 0], '1991': [0, 0, 0], '1992-': [1, 0, 0]})
prof = pd.DataFrame(data={'col1': [1, 1, 6], 'col2': [6, 6, 6], '1991': [6, 6, 6], '1992-': [2, 6, 6]})
dh.add_sheet("test", data, prof)
tr_cols_dict = {tuple(dh.data_struct_list[0].df_data.columns) + dh.data_struct_list[0].df_data.shape:
pd.Series([False, True, True, True], index=dh.data_struct_list[0].df_data.columns),
tuple(dh.data_struct_list[2].df_data.columns) + dh.data_struct_list[0].df_data.shape:
pd.Series([False, True, True, True], index=dh.data_struct_list[2].df_data.columns)
}
dh_copy = dh.copy_without_memory()
TriangleStripper.turn_triangle(dh, tr_cols_dict, alt_min_score=0.6)
for ds in dh_copy.data_struct_list:
tr_cols = tr_cols_dict[tuple(ds.df_data.columns) + ds.df_data.shape]
tri_part = ds.df_data[tr_cols.index[tr_cols]].values
ds.df_data[tr_cols.index[tr_cols]] = np.transpose(tri_part)
for ds, ds_copy in zip(dh.data_struct_list, dh_copy.data_struct_list):
self.assertTrue(ds.df_data.equals(ds_copy.df_data))
self.assertTrue(ds.df_profiles.equals(ds_copy.df_profiles))
def find_triangles(dh, **kwargs):
return_meta = False
if 'return_meta' in kwargs:
return_meta = kwargs['return_meta']
triangle_dh = DataHolder(dh.name)
rest_dh = DataHolder(dh.name + '_non-triangular')
#bool_array = np.zeros(triangle_dh.n, dtype=bool)
for dh_ind, ds in enumerate(dh.data_struct_list):
df_data, df_profiles = ds.df_data, ds.df_profiles
# now select triangles in som smart way
bool = TriangleFinder.is_triangle(ds, **kwargs)
if bool:
TriangleFinder.add_triangle_to_dh(ds, triangle_dh)
else:
rest_dh.add_sheet(ds.name,
df_data,
df_profiles,
orig_sheet_name=ds.orig_sheet_name)
# Now get the triangle similiar data structs
triangle_similar = TriangleFinder.find_triangles_by_similarity(
triangle_dh, rest_dh)
if len(triangle_similar) > 0:
rest_copy = rest_dh.copy_without_memory()
rest_dh = DataHolder(rest_copy.name)
for ds in rest_copy:
if ds.id in triangle_similar:
TriangleFinder.add_triangle_to_dh(ds, triangle_dh)
else:
rest_dh.add_sheet(ds.name,
ds.df_data,
ds.df_profiles,
orig_sheet_name=ds.orig_sheet_name)
if return_meta:
return triangle_dh, rest_dh
else:
return triangle_dh