def merge_top_contributors(nestdf, groupbycol, nestcol, newcolname, mergedf,
key):
contributorsdf = uf.nest_for_json(nestdf, groupbycol, nestcol, newcolname)
newdf = pd.merge(mergedf, contributorsdf, on=key, how='inner')
return newdf
def construct_network_graph_dict(df, groupbycols, nestcol, nestedkeyname):
"""
df: Dataframe that holds the data
groupbycols: The single-value (non-array) values of a JSON Object
nestcol: The data that will be put into an array
nestedkeyname: New columns name
Returns an array of JSON objects.
Pythonically, it's a list of dictionaries (that contain lists in themselves)
"""
new_df = uf.nest_for_json(prune_dataframe(df, groupbycols + [nestcol]),
groupbycols, nestcol, nestedkeyname)
return new_df.to_dict('r')
def calculate_group_similarities(df, groupbycol, nestcol, newcolname):
newdf = uf.nest_for_json(df, groupbycol=groupbycol,
nestcol=nestcol,
newcolname=newcolname)
length = len(newdf)
similarity_matrix = np.zeros((length, length))
for i in range(length):
for j in range(length):
similarity_matrix[i,j] = uf.list_similarites(newdf[newcolname][i],newdf[newcolname][j])
similarity_df = pd.DataFrame(similarity_matrix)
similarity_df.columns = newdf[groupbycol]
similarity_df[groupbycol]= newdf[groupbycol]
return similarity_df
def add_groups_item_to_dict(init_json, df, nestcol, newcolname):
"""
init_json: Initial Json Array of Objects
df: Dataframe to add group items
nestcol: Name of columns that will be nested (thrown into a list)
newcolname: Name of new column
Matches on guid
Adds a specific column (nestcol) with name (newcolname) from
Pandas dataframe (df) to the array (init_json)
"""
new_dict = uf.nest_for_json(prune_dataframe(df, ['guid', nestcol]), 'guid',
nestcol, newcolname).to_dict('r')
for init_item in init_json:
for new_item in new_dict:
# Matches on guid between the two items
if init_item['guid'] == new_item['guid']:
init_item[newcolname] = new_item[newcolname]