Product Engineering Review: Mortgage_Calculator_Python

[chetan-hirapara]

Reviewer 1 comments:

• Use of pandas read_sql()
• Use of langchain framework
• We should look into using teradataml gen AI

Reviewer 1 suggestions:

• Create teradataml Dataframe using either from_table() or from_query()

Reviewer 2 comments:

• Use of pandas to read sql.
• use of execute_sql() to create table.

Reviewer 2 suggestions:

• Avoid db_drop_table in the beginning
• Instead of executing query to create table, Either use pandas dataframe or csv to load the data to vantage. copy_to_sql()
  function helps handling table creation.
• In secition 3.1, Avoid using pandas API call instead use DataFrame.from_query() method to examine the interest rate instead. Otherwise, use teradataml dataframe supported methods such as join and condition

---

@DallasBowden : PR

• Updates the description on Mortgage Calculator #600

[chetan-hirapara]

Reviewer 1 comments:

• Use of pandas read_sql() --- Thanks for suggestion, done
• Use of langchain framework --- This is the core framework to work with gen AI
• We should look into using teradataml gen AI --- Within teradataml, there are no such function like SQLAgent, memory, etc

Reviewer 1 suggestions:

• Create teradataml Dataframe using either from_table() or from_query() --- Thanks for suggestion, done

Reviewer 2 comments:

• Use of pandas to read sql. --- Thanks for suggestion, done
• use of execute_sql() to create table. --- Thanks for suggestion, done

Reviewer 2 suggestions:

• Avoid db_drop_table in the beginning --- Thanks for suggestion, done
• Instead of executing query to create table, Either use pandas dataframe or csv to load the data to vantage. copy_to_sql()
  function helps handling table creation. --- Thanks for suggestion, done
• In secition 3.1, Avoid using pandas API call instead use DataFrame.from_query() method to examine the interest rate instead. Otherwise, use teradataml dataframe supported methods such as join and condition --- Thanks for suggestion, done