File size: 2,795 Bytes
f3a1940 f17e764 f3a1940 f17e764 f3a1940 f17e764 6cad12f f3a1940 6cad12f f3a1940 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
import pandas as pd
import numpy as np
from scipy.sparse import csr_matrix, lil_matrix
"""
def calc_matches(filtered_df, project_df, similarity_matrix, top_x):
# matching project2 can be nay project
# indecies (rows) = project1
# columns = project2
# -> find matches
# filter out all row considering the filter
filtered_df_indecies_list = filtered_df.index
project_df_indecies_list = project_df.index
np.fill_diagonal(similarity_matrix, 0)
match_matrix = similarity_matrix[filtered_df_indecies_list, :][:, project_df_indecies_list]
best_matches_list = np.argsort(match_matrix, axis=None)
if len(best_matches_list) < top_x:
top_x = len(best_matches_list)
# get row (project1) and column (project2) with highest similarity in filtered df
top_indices = np.unravel_index(best_matches_list[-top_x:], match_matrix.shape)
# get the corresponding similarity values
top_values = match_matrix[top_indices]
p1_df = filtered_df.iloc[top_indices[0]]
p1_df["similarity"] = top_values
p2_df = project_df.iloc[top_indices[1]]
p2_df["similarity"] = top_values
return p1_df, p2_df
"""
def calc_matches(filtered_df, project_df, similarity_matrix, top_x):
# Ensure the matrix is in a suitable format for manipulation
if not isinstance(similarity_matrix, csr_matrix):
similarity_matrix = csr_matrix(similarity_matrix)
# Get indices from dataframes
filtered_df_indices = filtered_df.index.to_list()
project_df_indices = project_df.index.to_list()
# Efficiently zero out diagonal elements if necessary
if np.array_equal(filtered_df_indices, project_df_indices):
similarity_matrix = lil_matrix(similarity_matrix)
similarity_matrix.setdiag(0)
similarity_matrix = csr_matrix(similarity_matrix)
# Select submatrix based on indices from both dataframes
match_matrix = similarity_matrix[filtered_df_indices, :][:, project_df_indices]
# Get the linear indices of the top 'top_x' values
# (flattened index to handle the sparse matrix more effectively)
linear_indices = np.argsort(match_matrix.data)[-top_x:]
if len(linear_indices) < top_x:
top_x = len(linear_indices)
# Convert flat indices to 2D indices using the shape of the submatrix
top_indices = np.unravel_index(linear_indices, match_matrix.shape)
# Get the corresponding similarity values
top_values = match_matrix.data[linear_indices]
# Create resulting dataframes with top matches and their similarity scores
p1_df = filtered_df.iloc[top_indices[0]].copy()
p1_df['similarity'] = top_values
p2_df = project_df.iloc[top_indices[1]].copy()
p2_df['similarity'] = top_values
print("finished calc matches")
return p1_df, p2_df
|