Pandas DataFrames
dict = {"country": ["Brazil", "Russia", "India", "China", "South Africa"],
"capital": ["Brasilia", "Moscow", "New Dehli", "Beijing", "Pretoria"],
"area": [8.516, 17.10, 3.286, 9.597, 1.221],
"population": [200.4, 143.5, 1252, 1357, 52.98] }
import pandas as pd
brics = pd.DataFrame(dict)
print(brics)
Adding index to DataFrame
# Set the index for brics brics.index = ["BR", "RU", "IN", "CH", "SA"] # Print out brics with new index values print(brics)
Reading CSV by Pandas DataFrame
# Import pandas as pd
import pandas as pd
# Import the cars.csv data: cars
cars = pd.read_csv('cars.csv')
# Print out cars
print(cars)
Reading CSV file by Pandas DataFrame with 1st column as index
# Import pandas and cars.csv
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)
# Print out country column as Pandas Series
print(cars['cars_per_cap'])
# Print out country column as Pandas DataFrame
print(cars[['cars_per_cap']])
# Print out DataFrame with country and drives_right columns
print(cars[['cars_per_cap', 'country']])
Print partial rows (observations) from a DataFrame
# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)
# Print out first 4 observations
print(cars[0:4])
# Print out fifth, sixth, and seventh observation
print(cars[4:6])