Testing for Manifold

import sys; sys.version.split()[0]

0.2s

Python

'3.7.5'

pip install xgboostpip install --upgrade pandas

11.9s

Bash in Python

listings.csv

import pandas as pdlistings = pd.read_csv(listings.csv
)listings.head()

0.4s

Python

	id	name	host_id	host_name	neighbourhood	latitude	longitude	room_type	price	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365
0	2818	Quiet Garden View Room & Super Fast WiFi	3159	Daniel	Oostelijk Havengebied - Indische Buurt	52.36575	4.94142	Private room	59	3	277	2019-11-21	2.09	1	37
1	20168	Studio with private bathroom in the centre 1	59484	Alexander	Centrum-Oost	52.36509	4.89354	Private room	100	1	321	2020-02-07	2.65	2	134
2	25428	Lovely apt in City Centre (w.lift) near Jordaan	56142	Joan	Centrum-West	52.37297	4.88339	Entire home/apt	125	14	5	2020-02-09	0.2	2	129
3	27886	Romantic, stylish B&B houseboat in canal district	97647	Flip	Centrum-West	52.387609999999995	4.8918800000000005	Private room	155	2	213	2020-02-10	2.16	1	163
4	28871	Comfortable double room	124245	Edwin	Centrum-West	52.36719	4.8909199999999995	Private room	75	2	323	2020-02-10	2.8	3	114

5 items

y = listings['price']print(y[0:10])

0.4s

Python

X = listings.drop(columns=['id', 'host_id', 'name', 'host_name', 'last_review', 'price', 'neighbourhood_group', 'neighbourhood', 'availability_365'])#X['neighbourhood'] = X['neighbourhood'].astype('category')#X['room_type'] = X['room_type'].astype('category')X['room_type'] = X['room_type'].replace('Shared room', 0).replace('Hotel room', 1).replace('Private room', 2).replace('Entire home/apt', 3)X['room_type'] = X['room_type'].astype('int64')print(X.head())

0.4s

Python

print(X.isnull().sum())

0.4s

Python

X = X.fillna(0)

0.1s

Python

from sklearn.linear_model import BayesianRidge, LinearRegressionfrom sklearn.ensemble import RandomForestRegressor

0.2s

Python

from sklearn.model_selection import train_test_splitX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)

0.2s

Python

model = LinearRegression()model.fit(X_train, y_train)

0.1s

Python

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)

y_predict = model.predict(X_test)print(y_predict)

0.4s

Python

from sklearn.metrics import explained_variance_score, r2_scoreprint(explained_variance_score(y_test, y_predict))print(r2_score(y_test, y_predict))

0.5s

Python

Downloads

X_test

1.1s

Python

y_test

0.8s

Python

pd.DataFrame(y_predict)

1.0s

Python

Testing for Manifold

Downloads

Runtimes (1)