def perform_top_n_filtering(similarity_df, n):
"""Finds the n most similar user/item, and returns it in the form of a list of tuples
:param similarity_df: Pandas dataframe representing pairwise similarities between m users/items
:param n: The number of neighbors
:return: A dictionary that maps a user/item to at most n nearest users/items
"""
neighbor_dict = dict()
for row_idx, row in similarity_df.iterrows():
nearest = SortedList(n)
for col_idx, cell in row.iteritems():
if not (math.isnan(cell) or row_idx == col_idx):
nearest.insert(cell, col_idx)
neighbor_dict[row_idx] = nearest.get_all()
# print neighbor_list
return neighbor_dict
def perform_threshold_filtering(similarity_df, threshold):
"""Finds the user/item whose similarity >= threshold, and returns it in the form of a list of tuples
:param similarity_df: Pandas dataframe representing pairwise similarities between m users/items
:param threshold: The similarity threshold
:return: A list of tuples that maps a user/item to at most n nearest users/items
"""
neighbor_dict = dict()
cols = len(similarity_df.columns)
for row_idx, row in similarity_df.iterrows():
nearest = SortedList(cols)
for col_idx, cell in row.iteritems():
if not (math.isnan(cell) or row_idx == col_idx
or cell < threshold):
nearest.insert(cell, col_idx)
neighbor_dict[row_idx] = nearest.get_all()
# print neighbor_list
return neighbor_dict
