After observing recent exit polls, I was eager to understand how the surveys transformed into valuable insights. Here are the results of my recent project on Data Cleaning and Transformation using Advanced Excel and Python:
Tools: Python, Advance Excel
Approach:
🧹 𝗖𝗼𝗹𝘂𝗺𝗻 𝗡𝗮𝗺𝗲 𝗙𝗼𝗿𝗺𝗮𝘁𝘁𝗶𝗻𝗴: I reformatted the column names in accordance with the client's requirements using Excel.
🐍 𝗨𝗻𝗽𝗶𝘃𝗼𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗣𝘆𝘁𝗵𝗼𝗻 𝗠𝗲𝗹𝘁: I used the Python melt function to unpivot the table and eliminate unwanted column entries.
🗑️ 𝗘𝗹𝗶𝗺𝗶𝗻𝗮𝘁𝗶𝗻𝗴 𝗨𝗻𝘄𝗮𝗻𝘁𝗲𝗱 𝗗𝘂𝗽𝗹𝗶𝗰𝗮𝘁𝗲𝘀: I removed duplicates to streamline the data.
➕ 𝗔𝗱𝗱𝗶𝗻𝗴 𝗡𝗲𝘄 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀: I introduced new features, such as calculating Total Respondents and Total Matching Answers, using the pandas merge function.
