import pandas as pd books=pd.read_csv("/work/bestsellers with categories.csv") books.head()

#A: Altering Row Names books.set_index("Author")

#a. altering rows or columns #modifying the code to only select author and year as columns with name as index books_transpose = books.set_index('Name')[['Year', 'Author']] books_transpose.head()

#a continued: switching rows and columns using tranpose books_transpose = books.set_index('Name')[['Year', 'Author']].transpose() # Print the new code print(books_transpose)

#b: using pivot table or groupby # Use pivot table to get all user ratings by year and author books_pivot_table = books.pivot_table (index='Year', columns='Author', aggfunc='mean') books_pivot_table.head()

#B Ex 2 GroupBy #display the count of the number of books for each author books.groupby('Author').Price.count()

#c Applying functions to entire dataset or columns #print the most expensive book and the author based on the author books[['Author', 'Price']][books.Price==books['Price'].max()]

#C Ex 2: Applying mean function to data to get average price by author as index and genre as columns books_pivot_table=books.pivot_table(index='Author', columns='Genre', aggfunc='mean') print(books_pivot_table)

#d: creating new column 'rate_number' based off existing one books_rating=books.melt(id_vars=['Name', 'Author'], value_vars=['User Rating', 'Reviews'], var_name='feature', value_name='rate_number') books_rating.head()

#D Ex2 books['yearlyrate']=books['Year']/ books['User Rating'] books[['yearlyrate', 'Year', 'User Rating']].head()

#e: descriptive stats books.describe()

#e books.describe(include='object')