def quality_pnn(i, jaccard_similarity_matrix, p):
'''Quality estimation by p nearest neighbors classification.
'''
k_most_similar_cols = jaccard_similarity_matrix[i, :].argsort()[-p:]
k_most_similar_targets = map(lambda c: graph_database[c][2], k_most_similar_cols)
true_target_i = graph_database[i][2]
estimated_target_i = statistics.predict_target_majority(k_most_similar_targets)
if type(true_target_i) is list:
return int(estimated_target_i in true_target_i) # zero-one loss
else:
return int(true_target_i == estimated_target_i) # zero-one loss
def quality_pnn(i, jaccard_similarity_matrix, p):
'''Quality estimation by p nearest neighbors classification.
'''
k_most_similar_cols = jaccard_similarity_matrix[i, :].argsort()[-p:]
k_most_similar_targets = map(lambda c: graph_database[c][2],
k_most_similar_cols)
true_target_i = graph_database[i][2]
estimated_target_i = statistics.predict_target_majority(
k_most_similar_targets)
if type(true_target_i) is list:
return int(estimated_target_i in true_target_i) # zero-one loss
else:
return int(true_target_i == estimated_target_i) # zero-one loss
def quality(i, jaccard_similarity_matrix, infl_point):
threshold = 1. - infl_point
similar_cols = np.where(jaccard_similarity_matrix[i, :] >= threshold)[0]
similar_targets = map(lambda c: graph_database[c][2], similar_cols)
true_target_i = graph_database[i][2]
estimated_target_i = statistics.predict_target_majority(similar_targets)
# print "Col:", i, ", Target:", true_target_i, ", Est. target: ", estimated_target_i
# print "Similar cols:", similar_cols
# print "Similar targets:", similar_targets
# print "--------------------------------------"
# fp = open(output_dir + "classification_threshold", "a")
# fp.write("Col: {0}, Target: {1}, Est. target: {2}\n".format(i, true_target_i, estimated_target_i))
# fp.write("Similar cols: {0}\n".format(similar_cols))
# fp.write("Similar targets: {0}\n".format(similar_targets))
# fp.write("--------------------------------------\n")
# fp.close()
if type(true_target_i) is list:
return int(estimated_target_i in true_target_i) # zero-one loss
else:
return int(true_target_i == estimated_target_i) # zero-one loss
def quality(i, jaccard_similarity_matrix, infl_point):
threshold = 1. - infl_point
similar_cols = np.where(
jaccard_similarity_matrix[i, :] >= threshold)[0]
similar_targets = map(lambda c: graph_database[c][2], similar_cols)
true_target_i = graph_database[i][2]
estimated_target_i = statistics.predict_target_majority(
similar_targets)
# print "Col:", i, ", Target:", true_target_i, ", Est. target: ", estimated_target_i
# print "Similar cols:", similar_cols
# print "Similar targets:", similar_targets
# print "--------------------------------------"
# fp = open(output_dir + "classification_threshold", "a")
# fp.write("Col: {0}, Target: {1}, Est. target: {2}\n".format(i, true_target_i, estimated_target_i))
# fp.write("Similar cols: {0}\n".format(similar_cols))
# fp.write("Similar targets: {0}\n".format(similar_targets))
# fp.write("--------------------------------------\n")
# fp.close()
if type(true_target_i) is list:
return int(estimated_target_i in true_target_i) # zero-one loss
else:
return int(true_target_i == estimated_target_i) # zero-one loss
def quality(i, sketch_matrix):
col_i = sketch_matrix.get_column(i)
similar_cols = list(sketch_matrix.get_similar_columns(col_i))
if i in similar_cols:
similar_cols.remove(i)
similar_targets = map(lambda c: graph_database[c][2], similar_cols)
true_target_i = graph_database[i][2]
estimated_target_i = statistics.predict_target_majority(similar_targets)
# print "Col:", i, ", Target:", true_target_i, ", Est. target: ", estimated_target_i
# print "Similar cols:", similar_cols
# print "Similar targets:", similar_targets
# print "--------------------------------------"
# fp = open(output_dir + "classification_sketch", "a")
# fp.write("Col: {0}, Target: {1}, Est. target: {2}\n".format(i, true_target_i, estimated_target_i))
# fp.write("Similar cols: {0}\n".format(similar_cols))
# fp.write("Similar targets: {0}\n".format(similar_targets))
# fp.write("--------------------------------------\n")
# fp.close()
if type(true_target_i) is list:
return int(estimated_target_i in true_target_i) # zero-one loss
else:
return int(true_target_i == estimated_target_i) # zero-one loss
def quality(i, sketch_matrix):
col_i = sketch_matrix.get_column(i)
similar_cols = list(sketch_matrix.get_similar_columns(col_i))
if i in similar_cols:
similar_cols.remove(i)
similar_targets = map(lambda c: graph_database[c][2], similar_cols)
true_target_i = graph_database[i][2]
estimated_target_i = statistics.predict_target_majority(
similar_targets)
# print "Col:", i, ", Target:", true_target_i, ", Est. target: ", estimated_target_i
# print "Similar cols:", similar_cols
# print "Similar targets:", similar_targets
# print "--------------------------------------"
# fp = open(output_dir + "classification_sketch", "a")
# fp.write("Col: {0}, Target: {1}, Est. target: {2}\n".format(i, true_target_i, estimated_target_i))
# fp.write("Similar cols: {0}\n".format(similar_cols))
# fp.write("Similar targets: {0}\n".format(similar_targets))
# fp.write("--------------------------------------\n")
# fp.close()
if type(true_target_i) is list:
return int(estimated_target_i in true_target_i) # zero-one loss
else:
return int(true_target_i == estimated_target_i) # zero-one loss
