Untitled

Code-

from flask import jsonify, request, Flask, render_template, json
from feature_engineering import feature_engineering
from model_training import get_top_persons_who_resolved
from sklearn.preprocessing import LabelEncoder
import pandas as pd
import pdb
from urllib.parse import quote, unquote
import ast
import json
from pandas.io.json import json_normalize

app = Flask(__name__)
app.app_context().push()

@app.route('/run_recommendation', methods=['POST'])
def run_recommendation():
    #pdb.set_trace()
    
    if request.method =='POST':
        param_vals = request.args.get('ticket_data')  # Retrieve the JSON data from the request body
        #print("param_vals: ", param_vals)
        # URL-decode the ticket_data
        ticket_data_encoded = unquote(param_vals)
        # Convert the decoded string back to a dictionary
        ticket_data = ast.literal_eval(ticket_data_encoded)
        
        ticket_data= str(ticket_data)
        
        json_data = ast.literal_eval(ticket_data)
        
        
        recommendations=get_top_persons_who_resolved(pred_data)
        
        for i, rec in enumerate(recommendations.iterrows()):
            index, row = rec
            print(f"Recommendation {i+1}: User {row['person_who_resolved']}, Owner User ID {row['owner_user_id']}, Role Name {row['role_name']}")

        return jsonify(recommendations)
        
if __name__ == "__main__":
    app.run(host='100.187.21.56', port=8895, threaded=True)

Error on sending request-

File "/tmp/ipykernel_25888/1424686922.py", line 59, in run_recommendation
    recommendations=get_top_persons_who_resolved(pred_data)
  File "/Analytics/venv/Jup/CAPE_ServicePlus_UC/model_training.py", line 57, in get_top_persons_who_resolved
    predicted_output_data=output_df.iloc[similar_indices]
  File "/Analytics/venv/CAPEANALYTICS/lib/python3.8/site-packages/pandas/core/indexing.py", line 925, in __getitem__
    return self._getitem_tuple(key)
  File "/Analytics/venv/CAPEANALYTICS/lib/python3.8/site-packages/pandas/core/indexing.py", line 1506, in _getitem_tuple
    self._has_valid_tuple(tup)
  File "/Analytics/venv/CAPEANALYTICS/lib/python3.8/site-packages/pandas/core/indexing.py", line 754, in _has_valid_tuple
    self._validate_key(k, i)
  File "/Analytics/venv/CAPEANALYTICS/lib/python3.8/site-packages/pandas/core/indexing.py", line 1424, in _validate_key
    raise IndexError("positional indexers are out-of-bounds")
IndexError: positional indexers are out-of-bounds

SO it goes into get_top_persons_who_resolved function and faces this issue-

COde for get_top_persons_who_resolved is -

def get_top_persons_who_resolved(pred_data):
    distance_metric='cosine'
    print("pred_data: ", pred_data)
    row=feature_engineering(pred_data)
    print("row: ", row)
    label_enc = LabelEncoder()
    #row['role_name_encoded'] = label_enc.fit_transform(row['role_name'])
    #row['role_name_decoded'] = label_enc.inverse_transform(row['role_name_encoded'])
    
    # Link the X vector with index
    #index = row.index.values
    
    ##Fetching the ticket data details from API
    #pdb.set_trace()
    ticket_data= ticket_data = pd.concat(map(pd.read_csv, ['/Analytics/venv/Jup/CAPE_ServicePlus_UC/ServicePlusIncidentData_Post_01-01-2019_Till_07-07-2019.csv', '/Analytics/venv/Jup/CAPE_ServicePlus_UC/ServicePlusTicket_Data_Till-2019-01-01.csv']), ignore_index=True)
    df=feature_engineering(ticket_data)
    #print("Dataframe",df)
    
    # Sample training data with text features
    train_data = df.drop(columns=['person_who_resolved','owner_user_id','role_name'])
    #print("Train data",train_data)

    output_df =df[['person_who_resolved','owner_user_id','role_name']]
    print("Output Columns",output_df)

    # New data for similarity calculation
    new_data = row
    print("New Data",new_data)

    # Create TF-IDF vectorizer and fit on training data
    #vectorizer = TfidfVectorizer()
    X = vectorizer.fit_transform(train_data)
    
    # Transform new data using the same vectorizer
    X_new = vectorizer.transform(new_data)

    # Calculate cosine similarity between new data and training data
    similarity_matrix = cosine_similarity(X_new, X)
    print("Similarity Matrix:",similarity_matrix)

    # Find the most similar training data indices for each new data point
    similar_indices = np.where(similarity_matrix > 0.5)
    print('Similar Indices',similar_indices)

    # Get the corresponding output TF-IDF vectors for new data
    predicted_output_data=output_df.iloc[similar_indices]
    print("Predicted Output",predicted_output_data)

    print("Similarity Matrix:")
    print(similarity_matrix)
    print("\nSimilar Data Indices with Cosine Similarity > 0.5:", similar_indices)
    print("\nPredicted Output Data:")
    print(predicted_output_data)

so similar indices we are getting output-

Similar Indices (array([0, 1, 2, 3, 4, 5]), array([ 3,  4,  5,  6,  7, 16]))

but later on its not getting predicted_output_data.

If you want I can share the code for feature_engineering() function as well.