import pandas as pd

# Download a sample file from http://insideairbnb.com/ ! wget http://data.insideairbnb.com/united-states/fl/broward-county/2022-06-17/visualisations/listings.csv -O listings.csv airbnb = pd.read_csv("listings.csv") #display(airbnb) #displays the 'n' first rows of the table, default n = 5 airbnb.head(10) #displays the 'n' last rows of the table, default n = 5 airbnb.tail(10)

hosts = airbnb['host_name'] #to view multiple columns, pass the name of the column as a list, such that the function has double brackets hosts = airbnb[['host_id','host_name']] hosts.head()

airbnb.dtypes

airbnb['last_review'] = pd.to_datetime(airbnb['last_review']) airbnb.dtypes

airbnb['year'] = airbnb['last_review'].dt.year

airbnb['name'] = airbnb['name'].str.strip() airbnb['name'].head()

airbnb['name_upper'] = airbnb['name'].str.upper() airbnb['name_upper'].head()

airbnb['min_revenue'] = airbnb['minimum_nights']*airbnb['price'] airbnb.head()

airbnb['price'].std()

airbnb['price'].var()

airbnb[['room_type', 'price']].groupby('room_type', as_index = False).mean()

airbnb_under_1000 = airbnb[airbnb['price'] < 1000] airbnb_under_1000

airbnb_2020_under1000 = airbnb[(airbnb['price'] < 1000) & (airbnb['year'] == 2020)] airbnb_2020_under1000.head()

d = [[1,2], [3,4]] df = pd.DataFrame(d, index = ['r1', 'r2'], columns = ['a', 'b']) df

import numpy as np d = np.arange(24).reshape(6,4) df = pd.DataFrame(d, index = np.arange(1,7), columns = list("ABCD")) df

pd.DataFrame( { 'name': ['Ally','Jane','Belinda'], 'height':[160,155,163], }, # columns = ['name','height'], index = ['A1','A2','A3'] )

from pandas import DataFrame as DF my_df = DF(data = np.random.randn(16).round(2).reshape(4,4), index = ['r'+str(i) for i in range(1, 5)], columns = ['c'+str(i) for i in range(1, 5)]) my_df

my_df.T

my_df.loc[['r1', 'r4'], ['c3', 'c4']] my_df.iloc[[0, 3], [2, 3]] #both generate the same output

!head -5 listings.csv

import os [x for x in os.listdir(os.getcwd()) if 'csv' in x]

airbnb_grouped = airbnb.groupby('room_type') len(airbnb_grouped) airbnb_grouped.head()

airbnb_grouped.apply(lambda x: x[['host_name', 'price', 'room_type']].sort_values(by = 'price', ascending = False).iloc[:3,:])

airbnb.groupby(['room_type', 'neighbourhood'])['price'].mean()

airbnb.groupby(['room_type', 'neighbourhood'])['price'].mean().unstack()