from sklearn.metrics import pairwise_distances
import pandas as pd
import numpy as np
from sklearn.preprocessing import LabelEncoder
# Link the X vector with index
index = data.index.values
def get_top_5_person_who_resolved(row, distance_metric='cosine'):
# Concatenate the input data into a single string
input_data = ' '.join([str(row['ticket_category']), str(row['ticket_type']), str(row['ticket_item']),str(row['ticket_summary']),
str(row['ticket_severity']),str(row['resolution_sla_violated']),str(row['reopen_count']),
str(row['role_id']),str(row['ticket_resolution_time'])])
# Calculate the pairwise distances between the input vector and X
input_vector_x = np.array(list(row[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary',
'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'role_id','ticket_resolution_time']]))
if distance_metric == 'cosine':
distances = pairwise_distances(input_vector_x.reshape(1, -1), data[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary',
'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'role_id','ticket_resolution_time']], metric='cosine')[0]
elif distance_metric == 'euclidean':
distances = pairwise_distances(input_vector_x.reshape(1, -1), data[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary',
'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'role_id','ticket_resolution_time']], metric='euclidean')[0]
elif distance_metric == 'manhattan':
distances = pairwise_distances(input_vector_x.reshape(1, -1), data[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary',
'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'role_id','ticket_resolution_time']], metric='manhattan')[0]
else:
raise ValueError('Invalid distance metric')
# Get the indices of the top 5 closest tickets
closest_indices = np.argsort(distances)[:5]
# Get the person_who_resolved values for the closest tickets
closest_person_who_resolved = data.iloc[closest_indices]['person_who_resolved']
return closest_person_who_resolved.tolist()
# Apply the function to each row to get the top 5 person_who_resolved based on other features
data['top_5_person_who_resolved'] = data.apply(get_top_5_person_who_resolved, axis=1)
# Getting unique values
unique_values = data['top_5_person_who_resolved'].apply(lambda x: list(set(x))) # Remove duplicate values in each list
data['unique_top_5_person_who_resolved'] = unique_values.apply(lambda x: x[:5]) # Take only the first 5 unique values
# Display the updated dataframe
print(data.head())