{"id":22784509,"url":"https://github.com/anushadatta/airbnb-in-seattle","last_synced_at":"2025-06-13T11:33:07.003Z","repository":{"id":130892400,"uuid":"259557392","full_name":"anushadatta/Airbnb-in-Seattle","owner":"anushadatta","description":"🏨 Understanding the Airbnb rental landscape in Seattle using data science. ","archived":false,"fork":false,"pushed_at":"2020-04-28T19:44:58.000Z","size":3055,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-05T16:49:04.222Z","etag":null,"topics":["airbnb","data-analysis","data-exploration","data-visualization","datascience","sentiment-analysis"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/anushadatta.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-04-28T06:59:08.000Z","updated_at":"2023-04-11T10:59:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"4fdad674-2923-4ec3-97ba-b6061e6ee037","html_url":"https://github.com/anushadatta/Airbnb-in-Seattle","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anushadatta%2FAirbnb-in-Seattle","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anushadatta%2FAirbnb-in-Seattle/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anushadatta%2FAirbnb-in-Seattle/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anushadatta%2FAirbnb-in-Seattle/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anushadatta","download_url":"https://codeload.github.com/anushadatta/Airbnb-in-Seattle/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246335578,"owners_count":20760871,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["airbnb","data-analysis","data-exploration","data-visualization","datascience","sentiment-analysis"],"created_at":"2024-12-11T22:24:16.105Z","updated_at":"2025-03-30T15:23:19.339Z","avatar_url":"https://github.com/anushadatta.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Airbnb in Seattle\n\nSince 2008, guests and hosts have used Airbnb to travel in a more unique, personalized way. As part of the Airbnb Inside initiative, this dataset describes the listing activity of homestays in Seattle, WA.\n\n## Dataset\nThe Seattle Airbnb Open data can be found at kaggle [here](https://www.kaggle.com/airbnb/seattle).\nThe following Airbnb activity is included in this Seattle dataset:\n\n* Listings, including full descriptions and average review score\n* Reviews, including unique id for each reviewer and detailed comments\n* Calendar, including listing id and the price and availability for that day\n\n## Data Analysis \n\n#### Data Pre-processing / Cleaning\nDrop unnecessary features (eg scraper id scrape date, listing url, picture urls, hosturl, host thumbnail, host pic etc).\nDrop NaN values for catgegorical features, replace Nan values with statistical means for numerical features.\nFormat data (eg. drop $ for price).\nOne hot encode amenities.\nDerive feature Revenue.\n#### Exploratory Analysis for Feature Selection\nExplore which of the features has the highest correlation with listing price.\nExplore categorical variables (value counts, count plots, swarm plots).\nExplore numeric variables (statistical analysis, boxplots, displots, violinplots, heatmap, joinplot). \n\n\u003cimg src=\"assets/1.PNG\" width=\"280\"\u003e \u003cimg src=\"assets/2.PNG\" width=\"280\"\u003e \u003cimg src=\"assets/3.PNG\" width=\"280\"\u003e\n\n\u003cp align = \"center\"\u003e \u003cimg src=\"assets/4.png\" width=\"300\"\u003e \u003cimg src=\"assets/catplot.PNG\" width=\"300\"\u003e \u003c/p\u003e \n\n\u003cp align = \"center\"\u003e \u003cimg src=\"assets/jointplot.PNG\" width=\"200\"\u003e \u003cimg src=\"assets/heatmap.png\" width=\"200\"\u003e \u003c/p\u003e\n\nVisualise the bookings clusters with map of Seattle using _GeoPandas_ library and _Folium_ map.\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"assets/geopandas.png\" width=\"150\"\u003e \u003cimg src=\"assets/folium.png\" width=\"230\"\u003e \u003c/p\u003e\n\n#### Sentiment Analysis\nClean textual data : Convert summary objects into strings. Ensure same capitalisation. Use regex to remove non alphanumeric characters and numbers. Remove stopwords (i, and, we etc) which are frequently occuring words that do not contribute to sentiment. Convert stemmed words to root words and lemmatize them. \n\nApply VADER sentiment intensity analyser to obtain compound VADER polarity scores, to identify words that strongest influence sentiment. \nGenerate heat maps for frequency of positive and negative words, with VADER polarity scores.\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"assets/vadar.png\" width=\"400\"\u003e \u003c/p\u003e\n\nVisualise the top aggregated positive words used in summary using Text Cloud.\n\n\u003cp align=\"center\"\u003e \u003cimg src=\"assets/textcloud1.png\" width=\"270\"\u003e \u003cimg src=\"assets/textcloud2.png\" width=\"90\"\u003e \u003c/p\u003e\n\n#### Machine Learning\nImplement feature scaling. Attempt multivariate regression to predict listing price. Training approaches adopted are RandomForestRegressor and XGBRegressor (Boosted Trees). Evaluate model accuracy for both Train and Test data using _Mean Squared Error (MSE)_ and _R\u003csup\u003e2\u003c/sup\u003e_.\n\n## Objectives\n\nThe primary goals of this comprehensive analysis are:\n* Determining best predictors of listing price, and modelling a multi-variate listing price predictor.\n* Sentiment analysis on listing summary and advise host on how to best advertise their listing.\n* Predicting important features for price determination.\n\n## Insights\n\n* Geographically, Airbnb listings are scattered around Seattle evenly, with two main clusters: Central District and Downtown Seattle. \n* Easier to visualise listing clusters using GeoPandas as opposed to Folium map.\n* Surprisingly, despite being able to identify cluster centres, expensive listings ($500 to $1000) are not notably clustered at any area. Hence, price is not a valuable factor in determining the location. \n* Most frequently used words might not contribute that highly to overall sentiment. \n* No strong correlation between listing description sentiment polarity score with estimated revenue or listing price.\n* Price and Revenue are not affected by overall rating. \n* Best predictors for listing price, with strongest correlations, are : neighbourhood_group_cleansed,  property_type,   room_type,  accommodates, bathrooms,  bedrooms, beds,  guests_included, Heating,  Internet, Kitchen,  Smoke Detector,  Washer, Wireless Internet. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanushadatta%2Fairbnb-in-seattle","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanushadatta%2Fairbnb-in-seattle","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanushadatta%2Fairbnb-in-seattle/lists"}