In [1]:
# install kaggle to use kaggle sample data sets
!pip install kaggle
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/ Requirement already satisfied: kaggle in /usr/local/lib/python3.8/dist-packages (1.5.12) Requirement already satisfied: certifi in /usr/local/lib/python3.8/dist-packages (from kaggle) (2022.12.7) Requirement already satisfied: six>=1.10 in /usr/local/lib/python3.8/dist-packages (from kaggle) (1.15.0) Requirement already satisfied: python-slugify in /usr/local/lib/python3.8/dist-packages (from kaggle) (8.0.1) Requirement already satisfied: tqdm in /usr/local/lib/python3.8/dist-packages (from kaggle) (4.64.1) Requirement already satisfied: requests in /usr/local/lib/python3.8/dist-packages (from kaggle) (2.25.1) Requirement already satisfied: urllib3 in /usr/local/lib/python3.8/dist-packages (from kaggle) (1.26.14) Requirement already satisfied: python-dateutil in /usr/local/lib/python3.8/dist-packages (from kaggle) (2.8.2) Requirement already satisfied: text-unidecode>=1.3 in /usr/local/lib/python3.8/dist-packages (from python-slugify->kaggle) (1.3) Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.8/dist-packages (from requests->kaggle) (2.10) Requirement already satisfied: chardet<5,>=3.0.2 in /usr/local/lib/python3.8/dist-packages (from requests->kaggle) (4.0.0)
In [2]:
!mkdir ~/.kaggle
In [3]:
# install the main libraries
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
In [4]:
# download lexicon to work with pretrained text data
import nltk
nltk.download('vader_lexicon')
[nltk_data] Downloading package vader_lexicon to /root/nltk_data...
Out[4]:
True
In [5]:
# import e.g. sentiment analyzer to categorise reviews
from nltk.sentiment.vader import SentimentIntensityAnalyzer
sentiments = SentimentIntensityAnalyzer()
In [6]:
# use e.g. the available Hotel_Reviews.csv file, download from kaggle or from https://github.com/spribylova/Python_Hotels
# data = pd.read_csv("Hotel_Reviews.csv")
In [7]:
import pandas as pd
url = "https://raw.githubusercontent.com/spribylova/Python_Text_Sentiment/main/Hotel_Reviews.csv"
data = pd.read_csv(url)
data
Out[7]:
| address | categories | city | country | latitude | longitude | name | postalCode | province | reviews.date | reviews.dateAdded | reviews.doRecommend | reviews.id | reviews.rating | reviews.text | reviews.title | reviews.userCity | reviews.username | reviews.userProvince | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | Riviera San Nicol 11/a | Hotels | Mableton | US | 45.421611 | 12.376187 | Hotel Russo Palace | 30126 | GA | 2013-09-22T00:00:00Z | 2016-10-24T00:00:25Z | NaN | NaN | 4.0 | Pleasant 10 min walk along the sea front to th... | Good location away from the crouds | NaN | Russ (kent) | NaN |
| 1 | Riviera San Nicol 11/a | Hotels | Mableton | US | 45.421611 | 12.376187 | Hotel Russo Palace | 30126 | GA | 2015-04-03T00:00:00Z | 2016-10-24T00:00:25Z | NaN | NaN | 5.0 | Really lovely hotel. Stayed on the very top fl... | Great hotel with Jacuzzi bath! | NaN | A Traveler | NaN |
| 2 | Riviera San Nicol 11/a | Hotels | Mableton | US | 45.421611 | 12.376187 | Hotel Russo Palace | 30126 | GA | 2014-05-13T00:00:00Z | 2016-10-24T00:00:25Z | NaN | NaN | 5.0 | Ett mycket bra hotell. Det som drog ner betyge... | Lugnt l��ge | NaN | Maud | NaN |
| 3 | Riviera San Nicol 11/a | Hotels | Mableton | US | 45.421611 | 12.376187 | Hotel Russo Palace | 30126 | GA | 2013-10-27T00:00:00Z | 2016-10-24T00:00:25Z | NaN | NaN | 5.0 | We stayed here for four nights in October. The... | Good location on the Lido. | NaN | Julie | NaN |
| 4 | Riviera San Nicol 11/a | Hotels | Mableton | US | 45.421611 | 12.376187 | Hotel Russo Palace | 30126 | GA | 2015-03-05T00:00:00Z | 2016-10-24T00:00:25Z | NaN | NaN | 5.0 | We stayed here for four nights in October. The... | ������ ��������������� | NaN | sungchul | NaN |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 35907 | 1088 Powdermill Rd | Cabins,Resorts & Vacation Cottages,Wedding Cha... | Gatlinburg | US | 35.754868 | -83.457295 | Elk Springs Resort | 37738 | TN | 2012-03-20T00:00:00Z | 2016-06-23T16:50:58Z | NaN | NaN | 5.0 | Best of the Best!!!! My family and I stayed in... | Amazing time (both times!!) | Charlotte | Chelsa K. | NC |
| 35908 | 1088 Powdermill Rd | Cabins,Resorts & Vacation Cottages,Wedding Cha... | Gatlinburg | US | 35.754868 | -83.457295 | Elk Springs Resort | 37738 | TN | 2012-03-12T00:00:00Z | 2016-06-23T16:50:58Z | NaN | NaN | 5.0 | Amazing Vacation in Beautiful Cabin We stayed ... | Amazing time (both times!!) | Charlotte | Heather D. | NC |
| 35909 | 1088 Powdermill Rd | Cabins,Resorts & Vacation Cottages,Wedding Cha... | Gatlinburg | US | 35.754868 | -83.457295 | Elk Springs Resort | 37738 | TN | 2015-11-03T00:00:00Z | 2016-06-23T16:50:58Z | NaN | NaN | 5.0 | My husband and I stayed at Tree Tops which is ... | Amazing time (both times!!) | Charlotte | Carol W. | NC |
| 35910 | 3747 29th St S E | Hotels-Apartment,Corporate Lodging,Hotels,Lodging | Grand Rapids | US | 42.909480 | -85.573590 | Extended Stay America Grand Rapids - Kentwood | 49512 | MI | NaN | 2015-12-01T19:40:54Z | NaN | NaN | 0.0 | to share your opinion of this businesswith YP ... | NaN | NaN | write a review | NaN |
| 35911 | 3747 29th St S E | Hotels-Apartment,Corporate Lodging,Hotels,Lodging | Grand Rapids | US | 42.909480 | -85.573590 | Extended Stay America Grand Rapids - Kentwood | 49512 | MI | NaN | 2015-12-01T19:40:54Z | NaN | NaN | 0.0 | xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx | NaN | NaN | xxxxxxxxxxxxxx | NaN |
35912 rows × 19 columns
In [8]:
# the sample csv file only contains US country
data["country"].unique()
Out[8]:
array(['US'], dtype=object)
In [9]:
# there is many US unique hotel names in the file
data["name"].unique()
Out[9]:
array(['Hotel Russo Palace', 'Americas Best Value Inn', 'Intermezzo',
'Studio 6', 'Little Paradise Hotel', 'Comfort Suites',
'Thunderbird Executive Inn and Conference Center',
'Little Belt Inn Neihart',
'Hawthorn Suites By Wyndham Livermore Wine Country',
'Fairfield Inn By Marriott Binghamton', 'Howard Johnson',
'La Quinta', 'Days Inn El Reno Ok', 'Gresham Area Hotels',
'Berney Fly Bed and Breakfast', 'Polynesian Plaza',
'Hotel Vier Jahreszeiten KÜhlungsborn', 'The Point',
'The Houstonian Hotel', 'Best Western Plus Waterville Grand Hotel',
'The Amble Inn', 'Howard Johnson Inn Columbia',
'Osage Village Inn', 'Super 8 Columbia Dwntwn Sc',
'The Kingsport Inn',
'Azul Beach Hotel By Karisma Gourmet Inclusive', 'Red Roof Inn',
'Ocean Breeze Motel Apts', 'Days Inn Branson / Near The Strip',
'Country Lodge Motel', 'The Inn @ St. Botolph', 'Quality Inn',
'Comfort Suites Southport', 'Ramada', 'Ambassadors Inn and Suites',
'Tryp Dusseldorf Krefeld Hotel', 'Rodeway Inn',
'Centennial Bed and Breakfast',
'Americinn Lodge Suites Oscoda - Ausable River',
'Bridgetown Mill House Restaurant Inn', 'Gran Melia Victoria',
'Kaier Mansion', 'The National Conference Center',
'Holiday Inn Express & Suites Lenoir City (knoxville Area)',
'Manor Vail Lodge', 'Economy Inn',
'The Golden Hotel, An Ascend Hotel Collection Member',
'Hyatt Regency Reston', 'Glendale Gaslight Inn', 'Super 8',
'Motel 6', 'Country Inn Walker', 'Mt Gardner Inn',
'Hotel De La Ville', 'Econo Lodge St Robert',
'La Quinta Inn-houston', 'Best Western Plus',
'La Quinta Inn & Suites Auburn',
'The Citizen Hotel, Autograph Collection', 'Super 8 Ithaca',
'Big Mountain Lodge',
'Holiday Inn Express Atlanta Ne - I-85 Clairmont',
'Springhill Suites Columbia', 'Sportsmen Motel',
'North Country Inn B & B', 'Microtel of Ste Genevieve',
'Days Inn Barstow', 'Unionport Lodge No 333 F A M',
'Doubletree By Hilton Hotel Bay City - Riverfront',
'Hilton Garden Inn Burlington Downtown',
'Doubletree By Hilton West Palm Beach Airport',
'Courtyard Hattiesburg', 'Janmere Motel', 'Skidway Lake Motel',
'El Cortez', 'Enchanted Castle Hotel',
'Extended Stay America - Chicago - Westmont - Oak Brook',
'Extended Stay America', 'Econo Lodge', 'Hometown Inn',
'Days Inn Brookings', 'Pheasant Manor', 'Spirit Tree Inn B & B',
'Durango Travelodge', 'Americinn Lodge and Suites',
'Residence Inn Billings',
'Best Western Plus Arlington North Hotel and Suites',
'Knights Inn', 'La Quinta Inn and Suites Tucson - Reid Park',
'Staybridge Suites Tyler University Area',
'Country Inn and Suites By Carlson Corbin',
'Best Western Owasso Inn & Suites', 'Truckee Tahoe Htl Larkspur',
'Wyndham Resort At Fairfield Mountains', 'Quality Inn Spearfish',
'The White House Inn', 'Inn At Queen Anne', 'Comfort Inn',
'Budget Inn South',
'Residence Inn By Marriott Irvine John Wayne Airport',
'Blue Top Inn', 'Days Inn Warren', 'Budget Host Inn',
'Howard Johnson Gallup', 'Desert Sands Motel',
'Davison St Guest House', 'Travelodge', 'Parkway Inn Jellico',
'Days Inn & Suites Vicksburg', 'Chippewa Hotel',
'Martin Mason Hotel', "Comfort Inn and Suites O'fallon",
'La Quinta Inn & Suites Dublin',
'Sheraton Mission Valley San Diego Hotel', 'The Bluffs Inn Suites',
'Astro Motel', 'Best Western Luxury Inn',
'Extended Stay America San Diego - Carlsbad Village By The Sea',
'Seaside Oceanfront Inn & Restaurant', 'Lakeview Lodge',
'Extended Stay America - Los Angeles - Ontario Airport',
'Days Inn Marion', 'Protection Motel', 'Town Country Motel',
'Ramada Inn', 'Holiday Inn Canyon De Chelly', 'Lake Motel',
'Arcola Inn', 'Landmark Inn Lakes-mountain Region', 'Haltom Inn',
'Noyo Harbor Inn', 'Candlewood Suites West Springfield',
"Alyssa's Motel", 'Holiday Inn Express & Suites Portland',
'Royal Inn', 'Columbia Gorge Riverside Lodge', 'Cypress Suites',
'Best Western Burlington Inn', 'Eldorado Suites Hotel',
'Bent Elbow', 'Penzion Accom', 'La Quinta Inn and Suites Sunrise',
'Americana Resort Properties', 'Knights Inn Aiken',
'Inroads Ireland Tours', 'Mansfield Plantation Inc',
'Holiday Inn Express Pinetop',
'Holiday Inn Express Howe (sturgis, Mi)',
'Deluxe Inn Merrillville', 'Super 8 Pittsburgh/monroeville',
'La Quinta Inn', 'Townplace Suites By Marriott', 'Cadillac Motel',
'Hyatt Regency Kathmandu', 'Mainsail Motel & Cottages',
'Fairfield Inn & Suites Peoria East',
'Holiday Inn Express and Suites Canyonville', 'Solstice',
'Country Inns Suites', 'Dead Broke Inn',
'Hampton Inn & Suites Crescent City', 'The Grove Seaside Hotel',
'Savaii Roberts Motels', 'The Alexandrian, Autograph Collection',
'Hotel Monaco Chicago, A Kimpton Hotel', 'Rips Country Inn',
'Holiday Inn Express Gatesville',
'Hilton Garden Inn Kauai Wailua Bay',
'Holiday Inn Express Hotel and Suites Memphis Southwind',
'Clarion', 'Mountain Lodge At Telluride - A Noble House Resort',
'Hampton Inn New Orleans - Downtown',
'Baymont Inn and Suites Enid', 'Quality Inn & Suites',
'Super 8 Carlisle-south', 'Americinn Coralville',
'Travelodge Shakopee', 'Hampton Inn Fayetteville Fort Bragg',
'Four Points-kansas', "Cliff's Motor Inn",
'Days Inn & Suites Castle Rock', 'Candlewood Suites Olathe',
'Holiday Inn Express', 'Super 8 Alamosa',
"The Miner's Inn Motel Restaurant",
'Extended Stay America - Orlando Theme Parks - Vineland Rd.',
'White Cliff Manor Bed and Breakfast',
'Fiesta Inn Centro Historico', 'Pine Needles Golf Course',
'Days Inn Bloomington', 'Fairfield Inn/suites-marriott',
'Holiday Inn Express Hotel & Suites Hillview',
'Marquesa Hotel & Cafe Marquesa', 'Best Western',
'Mandarin Oriental Jakarta', 'Barber Joyce',
'Sunset Inn-yosemite Cabins', 'Ramada Vandalia',
'Holiday Inn Express & Suites Weslaco', 'Super 8 Elko Nv',
'Hotel Borgo Verde', 'Vista Hotel On Lake Tarpon',
'Miramar Boutique Hotel',
'Best Western Plus French Quarter Landmark Hotel',
'Red Carpet Inn', 'Adria Motor Inn', 'Quality Inn and Suites',
'Village Lodge', 'Super 8 Manhattan Ks', 'Olde Bridge Inn',
'Raintree Inn', 'Garden Bed and Breakfast', 'Alpine Motel',
'Wine Valley Lodge', 'Hilton Garden Inn Austin Nw - Arboretum',
'The Governor Hotel', 'Pullman Rail Journeys',
'Motor Inns of America', 'Profile Deluxe Motel',
'American Star Inn and Suites Atlantic City',
'Meadow Farm Bed and Breakfast', 'Days Inn Kuttawa',
'Hotel Relais De Margaux Golf and Spa',
'Hyatt Place San Antonio Airport - Quarry Market', 'Discovery Inn',
'Holiday Inn Lumberton North - I-95',
'Old Saco Inn Bed & Breakfast', 'Hotel Millersburg',
'Springhill Suites', 'Stratford Inn', 'Comfort Inn Livermore',
'Body Tuneup', 'Adobe Nido Bed & Breakfast',
'Tulip Inn Turin West', 'Hotel Portaventura', 'Relax Inn',
'Hotel Olcott', 'Radisson Hotel Hauppauge-long Island',
'Quality Inn & Suites Hanes Mall', 'Robins Roost Cabins',
'Hampton Inn', 'Candlewood Suites Huntersville',
'Super 8 Longmont / Del Camino', 'Holiday Inn Express Dahlonega',
'Briarcliff', 'Lake Hill Cabins', 'Warwick Denver',
'Econo Lodge Inn & Suites', 'Falls Motel',
'Holiday Inn Express Hotel and Stes Port Clinton-catawba Island',
'Berkshire By The Sea A Vri Resort', 'Days Inn Bangor Airport',
'Fireline Hotel', 'Brooks Donald L Jr', 'Days Inn Geneva',
'Fh Hotel Villa Fiesole', 'Clarion Inn', 'Porto Vista Hotel',
'The Litchfield Inn', "Sam's Town Hotel & Gmblng Hall",
'Hotel Deca - A Noble House Hotel',
'Boiling Springs Resort Canoe Rental', 'Advance Motel',
'Edgewater Inn & Cottages', 'Hilton Princess San Pedro Sula',
'Pelican Shores Inn', 'Hyatt Place Utica', 'Hotel Roc Lago Rojo',
'Amisos Hotel', 'Red Banks Motel', 'Hotel Guadalmedina',
'Intercontinental Hotels Resorts', 'Greektown Casino',
'The Kinney - Venice Beach', 'Scenic View Motel',
'Holiday Inn Rutland-killington Area',
'Plaza Hotel and Casino - Las Vegas', 'Monarch of Rancho Mirag',
'Seiling Motel', 'Quality Inn Johnson City', 'Fort Conde Inn',
'Regency Inn Motel', 'Super 8 Dallas South',
'Baymont Inn & Suites Griffin',
'Holiday Inn Express - Harrisburg East',
'Kilauea Lodge Restaurant', 'Dallas/fort Worth Marriott Solana',
'Old Wheeler Hotel', 'The Chestnut Boutique Hotel',
'Red Fox Motel', 'The Inn On Negley',
'Wyndham Vacation Resorts Towers On The Grove',
"America's Best Value Inn", 'Super 8 Kingston',
'Leakey Springs Cabins', 'Hotel Mc Call',
'Super 8 Worthington Minnesota', 'Quality Inn Near Six Flags',
'Americinn Lodge Suites Austin',
'Holiday Inn Spearfish-convention Center', 'Mar Mar Resort Tackle',
'Cambria Hotel & Suites', 'Best Western Hotel Goldenmile Milan',
"Rideout's Lakeside Lodge Cottages",
'Days Inn Ruther Glen Kings Dominion Area',
'Pueblo Bonito Sunset Beach Resort & Spa - All Inclusive',
'Turf Motel', 'Homewood Suites By Hilton',
'Rangeland Court Motel & Rv', 'Red Roof Inn St Louis - Troy',
'Best Western Plus-seaport Inn', 'Hampton Inn Abilene',
'Aspen Alps', 'Holiday Inn Express Henderson',
'Country Inn and Suites By Carlson', 'Main Street Bed & Breakfast',
'Tidewater Inn', 'Uptown Motel', 'Villa Carlotta',
'Extended Stay America - Fort Lauderdale - Davie',
'Spruce Meadow Cabins', 'Silver Run Cabins',
'Jacksonville Plaza Hotel and Suites',
'Hawthorn Suites Dayton North',
'Suburban Extended Stay of Memphis Bartlett',
'Knights Inn Durango Co', 'Homewood Suites - Mall of America',
'Days Inn', 'Twelve Hotels & Residences',
'Embassy Suites By Hilton Houston Downtown', 'Super 8 Cloquet',
'Extended Stay America - Rockford - I-90', 'Bailey Hotel',
'Red Rest Inn', 'Colonial Inns of Ontario',
'Hotel Silken Siete Coronas', 'Corey Motel', 'Cherry Orchard Inn',
'Hotel Vorbach', 'Eden Park Guest House', 'Lakeway Resort & Spa',
'Knights Inn Amarillo Airport',
'La Quinta Inn and Suites Nashville Franklin', 'Close For You',
'Blue Jay Motel', 'Chelsea Inn', 'Whiteface Chalet',
'Homewood Suites', 'Super 8 Motel Fairmont', 'Great Basin Inn',
'Comfort Inn - Springfield', 'Stirling City Hotel',
'Sombrero Resort and Marina', 'Key West Inn - Clanton',
'Days Inn West Memphis', 'Worldwide Hospitality Supply Company',
'Plantation Inn', 'Comfort Suites South',
'Marriott Hotels Resorts Suites', 'Sybaris Pool Suites',
"Miss Kitty's Boarding House", 'Sheraton Offenbach Hotel',
'Extended Stay America - Raleigh - Cary - Regency Parkway S',
'Suburban Extended Stay Warner Robins', 'Jvd Hotels',
'Holiday Inn-bayside', 'Pavilion Lodge', 'Ritz Hotel',
'Arrowhead Motel and Rv Park', 'Parkside Inn At Incline',
'Saddleback Motor Inn', 'Sherwood Hills Resort',
'Holiday Inn Express Hotel and Suites Raleigh-wakefield', 'Arion',
'Una Hotel Forte Dei Marmi', 'Days Inn Newton',
"A Swallow's Nest Motel", 'Canyon Gate Motel', 'Cascabel',
'Hampton Inn & Suites Fort Worth-west-i-30',
'Fireside Inn Santa Cruz', 'Mandarin Oriental Hotel Group',
'Bellaire Motel Lodge', 'Palomar Washington Dc, A Kimpton Hotel',
'Bay Shores Yachttennisclub 514 2 Br Condo By Redawning',
'Hilton Santo Domingo', 'Atlantic House', 'Frontier Cabins Motel',
'Samui Cliff View Resort & Spa', 'Country Inn & Suites By Carlson',
'Hampton Inn-st Robert', 'Best Western Holiday Hills',
'Tiffany House Bed & Breakfast', 'Progress Management Co',
'Norwood Inn and Suites', 'Howard Johnson Inn - Newburgh',
'Holiday Inn Express Colton-riverside North', 'Sutton Bay Resort',
'La Quinta Inn Calhoun', 'Colonial Motel', 'Fairfield Inn Saginaw',
'Extended Stay America Philadelphia - Exton',
'Saco River Recreational Council', 'Ihg', 'Red Roof Inn Somerset',
'Wallowa Lake Vacation Rentals', 'Hotel Casena Dei Colli',
'Chalet Leon At Hector Falls',
'Fairfield Inn Suites Chattanooga South/east Ridge',
'Midvalley Motel', 'Ubaa Old Crawford Inn',
'Holiday Inn Express Hotel Suites Sedalia',
'Hampton Inn & Suites Syracuse/carrier Circle',
'Quality Inn and Suites Eugene-springfield',
'Four Points By Sheraton Memphis Southwind',
'Americinn Lodge Suites Princeton', 'Juniper Lane Guest House',
'Bosselmans Pump Pantry Motel',
"Harrah's Laughlin Hotel and Casino",
'Americas Best Value Inn and Suites', 'Masters Inn',
'The Westin Europa and Regina', 'Super 8 Opelousas',
'Melia Paris Champs-elys��es', 'Sci�� On Martin',
'Springhill Suites By Marriott South Bend/mishawaka',
'Inn At The River',
'Country Inn and Suites By Carlson Charlotte University Place',
'Holiday Inn Express Eagle',
'Sir Walter Raleigh Inns of Greenbelt', 'Gardena Terrace Inn',
'Quality Suites Intercontinental Airport West', '1785 Inn',
'Best Western Knoxville Suites', 'The Jayakarta Bali',
'Holiday Inn Express Grove City (outlet Center)', 'Hotel Aura Sfo',
'Hampton Inn Bloomington West',
'Quality Inn & Suites Historic St. Charles',
'Best Western Plus San Marcos Inn', 'Budget Inn-santa Maria',
'Equestrian Estates Horse Farm Bed and Breakfast',
'Comfort Inn Deland - Near University', 'Boardroom Motel',
'Carleton Hotel', 'Wisconsin-aire Motel', 'High Desert Motel',
'Best Western of Long Beach', 'Days Inn Berea Ky',
'East Side Motel Cabins', 'Abbeville Inn',
'Comfort Suites Mount Vernon',
'Holiday Inn Express & Suites Phoenix Downtown - Ballpark',
'Holiday Inn Express Hotel Suites Cookeville', 'Fairbridge Inn',
'Four Seasons Country Inn', 'Gooding Hotel Bed Breakfast',
'Grand Hotel Cadenabbia', 'Pillar Hotels Resorts',
'Hotel An Der Philharmonie', 'Microtel Inn',
'Crestview Condominiums',
'Comfort Hotel Nation Pere Lachaise Paris 11', 'Cedar Crest Inn',
'Spring Fountain Motel', 'Innisbrook', 'Cougar Crest Lodge',
'Springhill Suites By Marriott Sarasota Bradenton',
'Fairfield Inn and Suites By Marriott Plainville',
'Holiday Inn Express Hotel & Suites Chicago-deerfield/lincolnshire',
'Camelback Resort Aquatopia Indoor Waterpark',
"Marriott's Mountainside At Park City",
'Fairfield Inn & Suites Atlanta Perimeter Center',
'Hampton Inn Jackson Hole', 'Shoshone Lodge', 'Magton Inc',
'Quality Inn & Suites - Riverfront',
'Super 8 Schenect/albany Area', 'Intown Suites El Paso',
'Extended Stay America - Columbia - Northwest Harbison',
'Hilton San Diego Airport/harbor Island',
'Candlewood Suites Oklahoma City-moore',
'Holiday Inn Express & Suites Bay City', 'Rodeway Inn-tacoma',
'Western Inn-glacier Park', 'Americinn Lodge & Suites Appleton',
'Hampton Inn Sarasota - I-75 Bee Ridge', 'Amerihost Inn',
'Country Inn and Suites By Carlson Galena', 'Days Inn Suites',
'Hampton Inn Roanoke/salem', 'School House Motel', '1900 House',
'Excellence Riviera Cancun - Adults Only - All Inclusive',
'Hyatt Centric Arlington', 'Days Inn Bowling Green',
'Hotel Metropole', 'Inn & Suites', 'Anglers Inn',
'Super 8 Crete Ne', 'H��tel Marinca and Spa',
'Hyatt Place Pittsburgh Cranberry', 'Four Seasons Hotel St. Louis',
'El Dorado Seaside Suites By Karisma - All Inclusive',
'Courtyard San Marcos', 'Fairfield Inn Suites Spearfish',
'Best Western Hospitality Hotel and Suites',
'Hotel Adler Cavalieri', 'Royal Inn Motel', 'Ambiance',
'Rodeway Inn Bushnell', 'Microtel Inn By Wyndham Knoxville',
'Candlewood', 'Menehune Reservations',
'Staybridge Suites Chicago - Glenview', 'Riverside Lodge',
'Patalya Thermal Resort', 'H��tel Les Bruy��res',
'Comfort Inn Birmingham - Irondale', 'Super 8 Madison',
'Comfort Inn & Suites', 'Concord Apartments By Boq Lodging',
'Holiday Inn Express & Suites West Monroe',
'Double Eagle Hotel and Casino', 'Rainbow Motel',
'Country Inn & Suites By Carlson, Rocky Mount, Nc',
'Ip Casino Resort Spa', 'La Quinta Inn & Suites Bryant',
'Travelodge Anaheim Convention Center',
'Hampton Inn Tucson-airport', 'Beacon Motel', 'Super 8 Sallisaw',
'Wilshire Inn Motel', 'Palm Suites',
'Hampton Inn & Suites-downtown-tutwiler', 'Narcis',
'Econo Lodge Big Spring',
'La Quinta Inn and Suites Miami Cutler Bay',
'Candlewood Suites Fort Smith', 'Courtyard Burlington Harbor',
'Terrace Inns Suites', 'Rapid City Days Inn', 'Foxburg Inn',
'Aspen Haus Bed and Breakfast', "Fort's Cedar View",
'Best Western Eufaula Inn', 'Terry Peak Ski Area',
'Super 8 - Effingham', 'Best Western Plus Kelly Inn',
'Days Inn Fort Wayne', 'Courtyard Columbus Worthington',
'Super 8 Bradenton Sarasota Area', 'Chalfant House',
'Hotel Corpus Christi', 'Sleep Inn', 'Bay Haven Inn Bed Breakfast',
'Hampton Inn & Suites Millington',
'Holiday Inn Express Suites Woodland Hills',
'Best Western Plus Humboldt House Inn',
'Red Lion Anaheim Maingate Hotel', "Albert's Motel", 'Octagon Inn',
'Budget Inn', 'Towneplace Suites', 'Hitching Horse Inn',
'Homewood Suites By Hilton Indpls Airport / Plainfield In',
'Kit Carson Lodge Restaurant', 'Watermark Bed Breakfast',
'Super 8 - Upland', 'Bailey House Bed & Breakfast',
'Microtel Inn Suites By Wyndham San Antonio By Seaworld',
'Comfort Hotel Bernau', 'Miami Executive Hotel',
'Extended Stay America Princeton - West Windsor',
'Mercure Curitiba Golden Hotel', 'Sheraton Baltimore North Hotels',
'Sids Resort', 'Hampton Inn & Suites Douglas',
'Comfort Inn Humboldt Bay', 'Super 8 Big Cabin Vinita Ok',
'Radisson Blu Conference and Airport Hotel',
'Days Inn North Columbia Ft. Jackson', 'Campanile Lyon Ecully',
'La Brea Hotel', 'Microtel Inn By Wyndham Southern Pines',
'Homewood Suites Dallas-market Center', 'Websters Manor',
'Holiday Inn Express & Suites Lawrence', 'Bethesda Gardens',
'Homestead Studio Suites', 'Bayside Resort Hotel',
'Super 8 Batesville Ar', 'Gateway Studios', 'Sunset Inn',
'Simpson House Inn', 'Longville Inn',
'A Bed & Breakfast In Cambridge', 'Clatskanie River Inn',
'Jellico Days Inn North Tennessee',
'Mountaintop Lodge Bed Breakfast', 'Inn At Mendenhall',
'Hampton Inn Waco', 'Roy-el Motel', 'Comfort Inn and Suites Bend',
'Eaglecrest Ski Area', 'Magnuson Hotel Summerton',
'La Quinta Inn and Suites Hopkinsville', 'Lindy Motel',
'Lighthouse Motel', 'Cal Neva Resort', 'Park Terrace Suites',
'Fairfield Inn & Suites Des Moines Airport',
'Super 8 Blackwell Ok', 'Sand Dunes Motel', 'Nantahala Cabins Inc',
'Holiday Inn', 'Holiday Inn & Suites Green Bay Stadium',
'Cliffrose Lodge Gardens',
'The Ritz-carlton Orlando, Grande Lakes', 'Super 8 Belle Fourche',
'Merritt House Inn', 'Comfort Suites Shreveport', 'Budget Host',
'Holiday Inn Express Hotel & Suites Bloomington-normal',
'Knights Inn - Wilmington', 'Pizza Hut', 'Comfort Inn Montgomery',
'Spinners Tailspin Inn', 'Triangle Motel',
'Residence Inn By Marriott Hartford Downtown',
'Great American Inn Suites', 'Hunting Lodge', 'Keyser Inn Inc',
'Patriots Inn', 'Super 8 Indianapolis',
'Holiday Inn Express Lubbock South', 'Stay Inn', 'Southside Motel',
'Residence Inn By Marriott Springdale', 'La Playa',
'Wingate By Wyndham Lagrange', 'Bear Cove Inn',
'Hyatt House Colorado Springs', 'Antlers Inn',
'Marylander Hotel Condo', 'Drury Inn & Suites Sikeston',
'Garden of The Gods Club & Resort',
'Sands Central Inn Hot Springs', 'Hamton Inn New Orleans Westbank',
'Holiday Inn Manhattan 6th Ave - Chelsea', 'Vacation Side Travel',
'Holiday Inn Express - Hillsboro', 'Sky Vue Motel',
'Blue Boar Inn', 'Hampton Inn Ft Chiswell',
"Fitzgerald's Restaurant", 'Super 8 Fort Collins',
'Inter-hotel Orl��ans Nord', 'Best Western Rama Inn & Suites',
'Clarion Inn Strasburg - Lancaster', 'Red Roof Inn Erie',
'Holiday Inn Express & Suites South Portland',
'The Parkview Memphis', 'Club Quarters, Rockefeller Center',
'Hampton Inn Dublin', 'Agate Beach Motel', 'Newark Budget Inn',
'Knights Inn Eau Claire', 'Laurel Manor Motel',
'Hampton Inn and Suites Annapolis', 'Riverside Motel and Cabins',
'Mineola Motel', 'Towneplace Suites Albany University Area',
'Monterey Beach Dunes Inn',
'Drury Inn & Suites San Antonio Northwest Medical Center',
'H��tel Sezz Paris', 'Hudson Hotel - Book Direct',
'Super 8 Kansas City Airport', 'Best Western Hotel De Neuville',
'Mccamly Plaza Hotel', 'Wingate By Wyndham Pueblo',
'Days Inn Lincolnton', 'Hotel Roc Flamingo', 'Lexington Inn',
'Nippersink Country Club, Inc.', 'Sterling Motel',
'Campus Inn & Suites Eugene Downtown', 'Days Inn Branson Mo',
'Mt. Washington Bed and Breakfast', 'Super 8 Metropolis',
'Melody Lodge Cabins', "Sand's Motel", 'Travelodge Ruther Glen',
'Texan Inn', 'Hotel Garibaldi',
'Lake Raystown Resort Lodge & Conference Center', 'Central House',
'The Concorde Inn', 'Economy Motel',
'Hampton Inn Virginia Beach Oceanfront North', 'Irish House Hotel',
'Clubhouse At River Country Est', 'Sleep Inn At Harbour View',
'Hotel Lavonia', 'Courtyard By Marriott Rockaway Mount Arlington',
'Fiesta Inn and Suites', 'Hilton Garden Inn Oconomowoc',
'P K Motel', 'Candlewood Suites Indianapolis Northwest',
'Holiday Inn Fond Du Lac', 'Arizona Inn of Prescott Valley',
'Koehne Dexter Terrie',
'Microtel Inn and Suites By Wyndham Burlington',
'The Inn At Bella Vista', 'Brasstown Valley Golf Club',
'Quality Inn Long Beach Airport', 'Calloway Inn',
'Grandison Bed Breakfast', 'Days Inn Tallulah',
'Twin Gables of Woodstock', 'Happy Tails Hotel & Playland',
'Baymont Inn and Suites Boone',
'Springhill Suites Marriott Colorado Springs South',
'Brightwood Inn Country Inn', 'Motel 6 Fort Bragg',
'Westernaire Motel', 'Super 8 Columbia East',
'Holiday Inn Express Hotel and Suites Va Beach Oceanfront',
'Hotel Valencia Santana Row', 'New York Marriott Marquis',
'Holiday Inn Express & Suites Willows',
'Hampton Inn Grand Junction Downtown/historic Main Street',
'Holiday Inn Express Suites Floresville', 'Villager Inn Motel',
'Lamothe House', 'Dor-shada Resort By The Sea',
'Hi-way Inn of Kiowa', 'Sleep Inn Slidell',
'Knights Inn New Castle/wilmington',
'La Posada Lodge & Casitas, An Ascend Hotel Collection Member',
'Comfort Inn Huntingdon', 'Mericana Motel',
'Hilton Americas-houston', 'Casino Queen Rv Park',
'Quality Inn and Suites Irvine Spectrum',
'Marriott Springhill Marina', 'Hampton Inn Suites Columbus',
'Milliken Creek Inn', 'Intown Suites Nashville North',
'The Desmond House Bed & Breakfast', 'The Booker-lewis',
'Shamrock Hill Inn', 'Econo Lodge Bellmawr',
'Crossland Economy Studios - Lake Charles - Sulphur',
'Hotel Columbia', 'Raton Pass Inn', 'Sumner Motor Inn',
'Days Inn-amarillo-medical Ctr', 'Best Western Silicon Valley Inn',
'Days Inn Lanham Washington Dc', 'Cliffs 7305 By Redawning',
'La Quinta Inn Auburn Worcester', 'Dockers Inn', 'Spring Bay Inn',
'Candlewood Suites Eugene Springfield', 'Anaheim Marriott Suites',
'Monarch Inn', 'Yakima Inn', 'Homeplace Inn and Suites',
'Innpoints Worldwide',
'Wingate By Wyndham Chantilly / Dulles Airport',
'Days Inn and Suites Albany', 'Holiday Inn Express San Clemente',
'The Westin Buckhead',
'Hyatt Place Atlanta/alpharetta/north Point Mall', 'Eldorado Inn',
'Americas Best Value Inn - Medical Center/airport', 'Outside Inn',
'Point Randall Resort', 'Courtyard By Marriott Downtown Boise',
'The Abbey Resort', 'Crossroads Hotel', 'Helios Resort',
'Best Western Plus Circle Inn',
'Fairfield Inn and Suites By Marriott Idaho Falls',
'Greenstay Hotel and Suites', 'Pine Shadows Motel',
"Beach Cove 411 Tower A Sierra's 1 Bedroom Condo By Prista Management",
'Residence Inn By Marriott Fort Lauderdale Weston',
'Petretti Apartments',
'Extended Stay America - Bloomington - Normal',
'40 Berkeley Hostel', 'La Quinta Inn & Suites Chicago Tinley Park',
'Welcome Inn Apartments', 'Candlewood Suites Lexington',
'Quinta Real Acapulco', 'Forest Hill Inn',
'Clarion Suites Philadelphia', "Sportsmen's Lodge",
'Port-o-call Motel',
'Drury Inn and Suites Columbus Convention Center',
'Avalon Hotel Group', 'Elba Sara Beach & Golf Resort',
'Good Nite Inn Rohnert Park', 'The Merritt Center and Lodge',
'Rustic Inn', 'Liberty Lodge', 'Comfort Suites Fort Pierce',
'Twin Pines Motel', 'Best Western Hartford Hotel & Suites',
'Courtyard By Marriott', 'La Quinta Inn and Suites Meridian',
'Residence Inn By Marriott Tucson Williams Centre',
'Hampton Inn Rockford', 'Red Roof Inn Cedar Rapids',
'Lewis River Inn', 'Tmc Resort Rentals',
'Homewood Suites By Hilton Albuquerque - Journal Center',
'Desert Motel Restaurant', 'Hyatt Dulles', 'West Side Motel',
'Casa Del Mar Inn Bandb',
'Holiday Inn Express and Suites Gahanna/columbus Airport E',
'Rodeway Inn Near Venice Beach', 'Citrus Hills Lodge Hernando',
'Econo Lodge Miles City', 'Atlanta Marriott Northwest At Galleria',
'Ibis Wuerzburg City', 'Hotel Eug��ne En Ville',
"Super 8 Chicago O'hare Airport", 'Comfort Inn and Suites',
'Pine Motel', 'Nesco Manor Hotel', 'Busy B Ranch',
'Best Western University Inn & Suites', 'Rodeway Inn Airport',
'Starwood Resorts Hotel', 'City Express Irapuato',
'Days Inn Statesville', 'The Lake Point Conference Center',
'Super 8 Gretna', 'Royal Dutch Inn', 'Sea View Motel',
'Castle Kona Reef', 'Brookside Motel', 'Acorn Motor Inn',
'Torian Plum By Wyndham Vacation Rentals', 'The Savoy Hotel',
'Holiday Inn Express & Suites Crossville',
'Holiday Inn Express Hotel and Suites Hesperia',
'Best Western Saint-etienne Aeroport',
'Mission Sands Vacation Rentals', 'River Oaks Golf Villas',
'Holiday Inn Victorville', 'Quality Inn and Suites Big Rapids',
'Residence Inn Burlington Colchester', 'Wakonda Hotel & Bar',
'Inturotel Esmeralda Park', 'Knights Inn Carmel Hill',
'Five Seasuns Bed & Breakfast Inn', 'Summit At Big Sky',
'Holiday Inn Express Hotel and Suites Cambridge', 'Breakers Hotel',
'Holiday Inn Express Hotel & Suites Emporia', 'The Dec',
'Lazy T Motel', 'Cherokee Lodge Bed and Breakfast',
'Beach Haven Vacation Rental House', 'Sonoma Coast Villa Spa',
'Ambassador Inn Albuquerque', 'Quality Inn Gulfport',
'Super 8 Van Horn', 'Residence Inn By Marriott Deptford',
'Rock A Bye Inn',
'Holiday Inn Express Hotel and Suites Meadowlands Area',
'Sky-lit Motel', "Simoni's Fremont Inn", 'Elk Springs Resort',
'Extended Stay America Grand Rapids - Kentwood'], dtype=object)
In [29]:
# see the unique values in rating column
data["reviews.rating"].unique()
Out[29]:
array([4. , 5. , 3. , 1. , 2. , 0. , 4.1 , 4.9 , 4.8 , 3.4 , 2.4 ,
3.1 , 3.2 , 3.3 , 4.15, 4.4 , 4.6 , 3.75, 3.95, 3.55, 3.8 , 2.9 ,
3.35, 3.15, 4.2 , 4.5 , 3.9 , 1.3 , 4.3 , 4.7 , 2.8 , 1.5 , 3.7 ,
2.7 , 2.5 , 3.5 , 4.75])
In [11]:
# fill the null reviews of the Hotels with 0
data['reviews.rating']=data['reviews.rating'].fillna(0)
In [12]:
# create a range of 5 maximum review numbers, all values above 5 are equal to 5
for i in range(0,len(data)):
if(data['reviews.rating'].loc[i] > 5):
temp = data['reviews.rating'].loc[i]
newtemp = (temp/10)*5
data.at[i,'reviews.rating'] = newtemp
In [13]:
# see the number of reviews for each rating number
ratings = data["reviews.rating"].value_counts()
numbers = ratings.index
quantity = ratings.values
ratings
Out[13]:
5.00 12772 4.00 9755 3.00 5709 1.00 3068 2.00 2979 0.00 1199 4.80 78 4.60 56 4.40 30 4.30 26 4.15 25 3.75 24 3.95 24 4.20 22 3.40 17 4.10 14 3.15 14 4.50 13 3.55 13 3.35 12 2.70 9 3.10 7 2.90 7 4.70 6 3.30 6 4.90 6 2.40 4 3.80 3 2.50 3 3.20 2 3.90 2 3.70 2 1.30 1 2.80 1 1.50 1 3.50 1 4.75 1 Name: reviews.rating, dtype: int64
In [14]:
# round decimal places in rating and sort output by rating level
ratings=data['reviews.rating'].round(0).value_counts()[[5,4,3,2,1]]
ratings
Out[14]:
5 12919 4 9954 3 5784 2 2987 1 3069 Name: reviews.rating, dtype: int64
In [15]:
# create indexes from rating value and counts
numbers = ratings.index
quantity = ratings.values
In [16]:
# assign color to each rating and revise the pie chart to see the share of rating values
# the majority of people is giving review 5, only small share of people was not satisfied
custom_colors = ["tan", "beige", 'silver', "grey", "black"]
plt.figure(figsize=(5, 5))
plt.pie(quantity, labels=numbers, colors=custom_colors)
central_circle = plt.Circle((0, 0), 0.5, color='white')
fig = plt.gcf()
fig.gca().add_artist(central_circle)
plt.rc('font', size=12)
plt.title("Hotel Reviews Ratings", fontsize=20)
plt.show()
In [17]:
# you can use various libraries to work with reviews: SentimentIntensityAnalyzer, transformers and textblob
In [18]:
pip install -q transformers
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.3/6.3 MB 58.8 MB/s eta 0:00:00 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.6/7.6 MB 28.5 MB/s eta 0:00:00 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 190.3/190.3 KB 19.3 MB/s eta 0:00:00
In [19]:
# create data frame reviews text, rt. Each review is in a single row.
rt = data[["reviews.text"]]
#rt = str(rt).encode('utf-8')
#rt["reviews.text"] = pd.to_numeric(rt["reviews.text"])
# convert column "reviews.text" to string type
rt = rt.astype({"reviews.text": str})
rt
Out[19]:
| reviews.text | |
|---|---|
| 0 | Pleasant 10 min walk along the sea front to th... |
| 1 | Really lovely hotel. Stayed on the very top fl... |
| 2 | Ett mycket bra hotell. Det som drog ner betyge... |
| 3 | We stayed here for four nights in October. The... |
| 4 | We stayed here for four nights in October. The... |
| ... | ... |
| 35907 | Best of the Best!!!! My family and I stayed in... |
| 35908 | Amazing Vacation in Beautiful Cabin We stayed ... |
| 35909 | My husband and I stayed at Tree Tops which is ... |
| 35910 | to share your opinion of this businesswith YP ... |
| 35911 | xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx |
35912 rows × 1 columns
In [20]:
# transforers library is using various pretrained models to classify and calculate score
# well known model names are e.g. XLNet, BERT, XLM, RoBERTa, ...
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
classifier("Really lovely hotel. The best one. Tip top.")
Downloading (…)lve/main/config.json: 0%| | 0.00/953 [00:00<?, ?B/s]
Downloading (…)"pytorch_model.bin";: 0%| | 0.00/669M [00:00<?, ?B/s]
Downloading (…)okenizer_config.json: 0%| | 0.00/39.0 [00:00<?, ?B/s]
Downloading (…)solve/main/vocab.txt: 0%| | 0.00/872k [00:00<?, ?B/s]
Downloading (…)cial_tokens_map.json: 0%| | 0.00/112 [00:00<?, ?B/s]
Out[20]:
[{'label': '5 stars', 'score': 0.9531726241111755}]
In [21]:
# use analyzer and download e.g. vader pretrained lexicon (Valence Aware Dictionary for sEntiment Reasoning)
import nltk
from nltk.sentiment.vader import SentimentIntensityAnalyzer
nltk.download("vader_lexicon")
import pandas as pd
[nltk_data] Downloading package vader_lexicon to /root/nltk_data... [nltk_data] Package vader_lexicon is already up-to-date!
In [22]:
# revise data types in rt data frame
rt.dtypes
Out[22]:
reviews.text object dtype: object
In [23]:
sentiments = SentimentIntensityAnalyzer()
# based on polarity score classify each line of text to positive, negative, neutral and compound
rt["Positive"] = [sentiments.polarity_scores(i)["pos"] for i in rt["reviews.text"]]
rt["Negative"] = [sentiments.polarity_scores(i)["neg"] for i in rt["reviews.text"]]
rt["Neutral"] = [sentiments.polarity_scores(i)["neu"] for i in rt["reviews.text"]]
rt['Compound'] = [sentiments.polarity_scores(i)["compound"] for i in rt["reviews.text"]]
rt.head()
Out[23]:
| reviews.text | Positive | Negative | Neutral | Compound | |
|---|---|---|---|---|---|
| 0 | Pleasant 10 min walk along the sea front to th... | 0.252 | 0.052 | 0.695 | 0.8299 |
| 1 | Really lovely hotel. Stayed on the very top fl... | 0.481 | 0.019 | 0.500 | 0.9828 |
| 2 | Ett mycket bra hotell. Det som drog ner betyge... | 0.000 | 0.000 | 1.000 | 0.0000 |
| 3 | We stayed here for four nights in October. The... | 0.289 | 0.000 | 0.711 | 0.9643 |
| 4 | We stayed here for four nights in October. The... | 0.289 | 0.000 | 0.711 | 0.9643 |
In [24]:
# classify column Compound
score = rt["Compound"].values
sentiment = []
for i in score:
if i >= 0.05 :
sentiment.append('Positive')
elif i <= -0.05 :
sentiment.append('Negative')
else:
sentiment.append('Neutral')
rt["Sentiment"] = sentiment
rt.head()
Out[24]:
| reviews.text | Positive | Negative | Neutral | Compound | Sentiment | |
|---|---|---|---|---|---|---|
| 0 | Pleasant 10 min walk along the sea front to th... | 0.252 | 0.052 | 0.695 | 0.8299 | Positive |
| 1 | Really lovely hotel. Stayed on the very top fl... | 0.481 | 0.019 | 0.500 | 0.9828 | Positive |
| 2 | Ett mycket bra hotell. Det som drog ner betyge... | 0.000 | 0.000 | 1.000 | 0.0000 | Neutral |
| 3 | We stayed here for four nights in October. The... | 0.289 | 0.000 | 0.711 | 0.9643 | Positive |
| 4 | We stayed here for four nights in October. The... | 0.289 | 0.000 | 0.711 | 0.9643 | Positive |
In [27]:
print(rt["Sentiment"].value_counts())
Positive 26819 Negative 6201 Neutral 2892 Name: Sentiment, dtype: int64
In [28]:
rt
Out[28]:
| reviews.text | Positive | Negative | Neutral | Compound | Sentiment | |
|---|---|---|---|---|---|---|
| 0 | Pleasant 10 min walk along the sea front to th... | 0.252 | 0.052 | 0.695 | 0.8299 | Positive |
| 1 | Really lovely hotel. Stayed on the very top fl... | 0.481 | 0.019 | 0.500 | 0.9828 | Positive |
| 2 | Ett mycket bra hotell. Det som drog ner betyge... | 0.000 | 0.000 | 1.000 | 0.0000 | Neutral |
| 3 | We stayed here for four nights in October. The... | 0.289 | 0.000 | 0.711 | 0.9643 | Positive |
| 4 | We stayed here for four nights in October. The... | 0.289 | 0.000 | 0.711 | 0.9643 | Positive |
| ... | ... | ... | ... | ... | ... | ... |
| 35907 | Best of the Best!!!! My family and I stayed in... | 0.293 | 0.011 | 0.695 | 0.9854 | Positive |
| 35908 | Amazing Vacation in Beautiful Cabin We stayed ... | 0.288 | 0.000 | 0.712 | 0.9759 | Positive |
| 35909 | My husband and I stayed at Tree Tops which is ... | 0.217 | 0.016 | 0.766 | 0.9965 | Positive |
| 35910 | to share your opinion of this businesswith YP ... | 0.263 | 0.000 | 0.737 | 0.6124 | Positive |
| 35911 | xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx | 0.000 | 0.000 | 1.000 | 0.0000 | Neutral |
35912 rows × 6 columns
In [49]:
# install libraries for pieplot and define colors
import matplotlib.pyplot as plt
import seaborn as sns
cmap = ("beige", "silver","grey")
# print the shares
plt.pie(x=rt["Sentiment"].value_counts(), labels=rt["Sentiment"].unique(), colors=cmap , autopct='%1.0f%%')
plt.show()
In [26]:
# save data frame to csv
rt.to_csv("sentiment.csv")