import pandas as pd

!pip install xlrd !pip install openpyxl

percapitaGDP = pd.read_excel( "https://github.com/PacktPublishing/Python-Data-Cleaning-Cookbook/raw/master/Chapter01/data/GDPpercapita.xlsx", sheet_name="OECD.Stat export", skiprows=4, skipfooter=1, usecols="A,C:T" )

percapitaGDP.head()

percapitaGDP.info()

percapitaGDP.rename(columns={"Year":"metro"}, inplace=True)

percapitaGDP.metro = percapitaGDP.metro.str.strip()

percapitaGDP.dtypes

for col in percapitaGDP.columns[1:]: percapitaGDP[col] = pd.to_numeric(percapitaGDP[col], errors='coerce') percapitaGDP.rename(columns={col:'pcGDP'+col}, inplace=True)

percapitaGDP.dtypes

percapitaGDP.describe()

percapitaGDP.dropna(subset=percapitaGDP.columns[1:], how='all', inplace=True) percapitaGDP.describe()

percapitaGDP.head()

percapitaGDP.metro.count() == percapitaGDP.metro.nunique()

percapitaGDP.set_index('metro', inplace=True)

percapitaGDP.head()

percapitaGDP.loc['AUS01: Greater Sydney']