import pandas as pd pd.__version__

! 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)

airbnb.head()

airbnb.tail()

airbnb['name']

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['year'].head()

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

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

airbnb['name_lower'] = airbnb['name'].str.lower() airbnb['name_lower'].tail()

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

airbnb['price'].mean()

airbnb['price'].median()

airbnb['price'].std()

airbnb['price'].var()

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

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

airbnb_under_1000 = airbnb[airbnb['price'] < 1000] airbnb_under_1000.head()

airbnb_2019_under_1000 = airbnb[(airbnb['price'] < 1000) & (airbnb['year'] == 2020)] airbnb_2019_under_1000.head()

ax = airbnb_under_1000['price'].plot.hist(bins=40)

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

import numpy as np d = np.arange(24).reshape(6,4) d

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

from pandas import DataFrame my_df = DataFrame(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]]

# allows you to see some of the stuff before importing file !head -5 listings.csv

%ls

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

!mkdir data

%ls

airbnb.to_csv('./data/listings.csv')

os.listdir(os.getcwd() + '/data')

airbnb_grouped = airbnb.groupby("room_type") len(airbnb_grouped)

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

airbnb.groupby('room_type').apply(lambda x: x['price'].describe())

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

pd.pivot_table(data = airbnb, index = 'room_type', values = 'price', aggfunc = 'mean')

%timeit airbnb.groupby('room_type')['price'].mean()