Untitled
unknown
plain_text
2 years ago
9.9 kB
4
Indexable
from sklearn.metrics import pairwise_distances import pandas as pd import numpy as np from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import train_test_split from feature_engineering import * import pdb def get_top_5_person_who_resolved(df, row, data ,distance_metric='cosine'): ##Fetching the ticket data details from API #pdb.set_trace() ticket_data= data print("Ticket Details are :",ticket_data) # 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['owner_user_id']),str(row['role_name_encoded']),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', 'owner_user_id','role_name_encoded','ticket_resolution_time']])) if distance_metric == 'cosine': distances = pairwise_distances(input_vector_x.reshape(1, -1), df[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary', 'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'owner_user_id','role_name_encoded','ticket_resolution_time']], metric='cosine')[0] elif distance_metric == 'euclidean': distances = pairwise_distances(input_vector_x.reshape(1, -1), df[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary', 'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'owner_user_id','role_name_encoded','ticket_resolution_time']], metric='euclidean')[0] elif distance_metric == 'manhattan': distances = pairwise_distances(input_vector_x.reshape(1, -1), df[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary', 'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'owner_user_id','role_name_encoded','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, owner_user_id, and role_name values for the closest tickets closest_person_who_resolved = df.iloc[closest_indices]['person_who_resolved'] closest_owner_user_id = df.iloc[closest_indices]['owner_user_id'] closest_role_name_encoded = df.iloc[closest_indices]['role_name_encoded'] closest_role_name_decoded = df.iloc[closest_indices]['role_name_decoded'] # Get the actual person_who_resolved, owner_user_id, and role_name value for the input ticket actual_person_who_resolved = row['person_who_resolved'] actual_owner_user_id = row['owner_user_id'] actual_role_name_encoded = row['role_name_encoded'] actual_role_name_decoded = row['role_name_decoded'] # Apply the function to the input data to get the recommendations ticket_data['recommendations'], ticket_data['actual_person_who_resolved'] = zip(*ticket_data.apply(lambda row: get_top_5_person_who_resolved(df, row), axis=1)) # Remove duplicate values from recommendations ticket_data['recommendations'] = ticket_data['recommendations'].apply(lambda x: list(set(x))) # Return the recommendations as a list recommendations = ticket_data['recommendations'].tolist() return {"recommendations": recommendations} I am making a changes in the code like below- from sklearn.metrics import pairwise_distances import pandas as pd import numpy as np from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import train_test_split from feature_engineering import * import pdb def get_top_5_person_who_resolved(df, row, data ,distance_metric='cosine'): ##Fetching the ticket data details from API #pdb.set_trace() ticket_data= data print("Ticket Details are :",ticket_data) X=df.drop(columns=['person_who_resolved']) # 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['owner_user_id']),str(row['role_name_encoded']),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', 'owner_user_id','role_name_encoded','ticket_resolution_time']])) if distance_metric == 'cosine': distances = pairwise_distances(input_vector_x.reshape(1, -1), df[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary', 'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'owner_user_id','role_name_encoded','ticket_resolution_time']], metric='cosine')[0] elif distance_metric == 'euclidean': distances = pairwise_distances(input_vector_x.reshape(1, -1), df[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary', 'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'owner_user_id','role_name_encoded','ticket_resolution_time']], metric='euclidean')[0] elif distance_metric == 'manhattan': distances = pairwise_distances(input_vector_x.reshape(1, -1), df[['ticket_category', 'ticket_type', 'ticket_item','ticket_summary', 'ticket_severity', 'resolution_sla_violated', 'reopen_count', 'owner_user_id','role_name_encoded','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, owner_user_id, and role_name values for the closest tickets closest_person_who_resolved = df.iloc[closest_indices]['person_who_resolved'] closest_owner_user_id = df.iloc[closest_indices]['owner_user_id'] closest_role_name_encoded = df.iloc[closest_indices]['role_name_encoded'] closest_role_name_decoded = df.iloc[closest_indices]['role_name_decoded'] # Get the actual person_who_resolved, owner_user_id, and role_name value for the input ticket actual_person_who_resolved = row['person_who_resolved'] actual_owner_user_id = row['owner_user_id'] actual_role_name_encoded = row['role_name_encoded'] actual_role_name_decoded = row['role_name_decoded'] # Apply the function to the input data to get the recommendations ticket_data['recommendations'], ticket_data['actual_person_who_resolved'] = zip(*ticket_data.apply(lambda row: get_top_5_person_who_resolved(X, row), axis=1)) # Remove duplicate values from recommendations ticket_data['recommendations'] = ticket_data['recommendations'].apply(lambda x: list(set(x))) # Return the recommendations as a list recommendations = ticket_data['recommendations'].tolist() return {"recommendations": recommendations} Will this code work still? Because we are passing through FAST API the below code- from fastapi import FastAPI, Request from feature_engineering import feature_engineering from model_training_building import get_top_5_person_who_resolved from sklearn.preprocessing import LabelEncoder import pandas as pd import pdb app = FastAPI() @app.post("/run_recommendation/") async def run_recommendation(request: Request): pdb.set_trace() if request.method ==['POST']: param_vals = await request.json() # Retrieve the JSON data from the request body ticket_data = param_vals['ticket_data'] data = pd.DataFrame(ticket_data) print("Data", data) ## Making a function call for data pre-processing processed_data= feature_engineering(data) print("Processed Data : ",processed_data) df=processed_data label_enc = LabelEncoder() df['role_name_encoded'] = label_enc.fit_transform(df['role_name']) df['role_name_decoded'] = label_enc.inverse_transform(df['role_name_encoded']) # Link the X vector with index index = df.index.values recommendations=get_top_5_person_who_resolved(df, row, data ,distance_metric='cosine') print("Recommended users for the sample ticket:") for i, rec in enumerate(recommendations[0]): print(f"Recommendation {i+1}: User {rec[0]}, Owner User ID {rec[1]}, Role Name {rec[2]}") return recommendations if __name__ == "__main__": app.run(host='100.87.2.56', port=8895, threaded=True) ANd this is the URL we are passing through for API testing where we are passing all parameters in a dictionary named ticket_data- http://100.87.12.56:8895/run_recommendation/?ticket_data={'ticket_category':'Process','ticket_type':'HRO - Payroll','ticket_item':'Benefits and Payments','ticket_summary':'Incorrect Result','ticket_severity':'4 -Default','resolution_sla_violated':False,'reopen_count':0,'owner_user_id':104,'role_name':'L2 Support','created_date':'2020-08-06 10:35:33','ticket_resolution_date':'2020-08-06 17:07:04','person_who_resolved'=' '} Can you show the changes in original code as we dont want to include person_who_resolved as it is the target column and we need to predict/recommend .
Editor is loading...