Add sme levels to questions

sme_questions.py

import pandas as pd
import numpy as np
import csv
import re

smeLevelDict = {
    'Data Ingestion': ['Experience Platform', 'Data Ingestion and Management', 'Data Ingestion'],
    'General': ['Experience Platform', 'Overview', 'General'],
    'CJA': ['Experience Cloud', 'Data Insights And Audiences', 'CJA'],
    'Schema': ['Experience Platform', 'Data Modeling', 'Schemas'],
    'Query Service': ['Experience Platform', 'Data Science and Queries', 'Query Service'],
    'Dataset': ['Experience Platform', 'Data Ingestion and Management', 'Dataset'],
    'AJO': ['Experience Cloud', 'Customer Journey', 'Journey Optimizer'],
    'Profile': ['Experience Platform', 'Customer Data', 'Real-time Customer Profile'],
    'Identity': ['Experience Platform', 'Customer Data', 'Identity Service'],
    'Source Connector': ['Experience Platform', 'Data Ingestion and Management', 'Sources'],
    'Destination Connectors': ['Experience Platform', 'Activation', 'Destinations'],
    'Segment': ['Experience Platform', 'Customer Data', 'Segmentation Service'],
    'License': ['Experience Platform', 'Administration', 'License Usage'],
    'Field': ['Experience Platform', 'Data Modeling', 'Schemas'],
    'Data Prep': ['Experience Platform', 'Data Ingestion and Management', 'Data Prep'],
    'B2B': ['Experience Platform', 'Customer Data', 'Real-time Customer Data Platform'],
    'JO': ['Experience Cloud', 'Customer Journey', 'Journey Orchestration'],
    'AJO': ['Experience Cloud', 'Customer Journey', 'Journey Optimizer'],
    'DULE': ['Experience Platform', 'Governance, Privacy, and Security', 'Data Governance'],
    'Event': ['Experience Platform', 'Data Collection', 'Event Forwarding'],
    'Hashed Email': ['Experience Platform', 'Customer Data', 'Identity Service'],
    'Destinations': ['Experience Platform', 'Activation', 'Destinations'],
    'UPSERT': ['Experience Platform', 'Data Ingestion and Management', 'Data Ingestion'],
    'Data Distiller': ['Experience Platform', 'Data Science and Queries', 'Query Service'],
    'Flow Service': ['Experience Platform', 'Data Ingestion and Management', 'Dataflows'],
    'Eloqua': ['Experience Platform', 'Data Ingestion and Management', 'Sources'],
    'TTL': ['Experience Platform', 'Customer Data', 'Real-time Customer Profile'],
    'data load': ['Experience Platform', 'Administration', 'License Usage'],
    'RTCDP': ['Experience Platform', 'Customer Data', 'Real-time Customer Data Platform'],
    'Guard Rails': ['Experience Platform', 'Data Ingestion and Management', 'Data Ingestion'],
    'Data security': ['Experience Platform', 'Governance, Privacy, and Security', 'Data Governance'],
    'Edge Network': ['Experience Platform', 'Data Collection', 'Edge Network Server API'],
    'AEP Architecture': ['Experience Platform', 'Overview', 'General'],
    'API': ['Experience Platform', 'Overview', 'General'],
    'WebSDK': ['Experience Platform', 'Data Collection', 'WebSDK'],
    'MobileSDK': ['Experience Platform', 'Data Collection', 'MobileSDK'],
}

smeLevelColumns=['sme_level1', 'sme_level2', 'sme_level3']

df = pd.read_csv('sme_concepts_qs_in.csv')

# deleting rows with empty 'question' column 
df = df.dropna(axis=0, subset=['question'])

# filling 'System' where sme_name is empty
df['sme_name'] = df['sme_name'].fillna('System')

df['sme_levels'] = df['sme_domain'].map(lambda x: [v for k, v in smeLevelDict.items() if bool(re.search(k.lower(), x.lower()))][0])

df_out = pd.DataFrame(df["sme_levels"].to_list(), columns=smeLevelColumns)

df_out = df_out.join(df)

df_out = df_out.drop(columns=['sme_domain', 'sme_levels'])

# reordering columns
df_out = df_out[['sme_name', 'question', 'sme_level1', 'sme_level2', 'sme_level3']]

df_out.to_csv('sme_concepts_qs_out.csv', index=False)

Thanks for the review @ken-russell! I have updated the above script and regenerated the csv.

Looks good, thanks!