Script for apartment price benchmarking based on market data
Project description
Melon analytics pricing
This package provides one class: ImmoNeighbors. You should train one such instance per floor(number_of_rooms) from 1 to 6+. Example code:
''' no_of_rooms = 3
training_data = immo[np.floor(immo["rooms"]) == no_of_rooms] neighbors = ImmoNeighbors(training_data.copy())
apartments = apartments_to_benchmark[['lon','lat','area']].to_numpy() dists,inds,rents = neighbors.k_neighbors(apartments)
rent_percentiles = neighbors.weighted_percentiles(dists,rents,percentiles=[10,50,90]) '''
Usually, problematic inputs will be ignored and have a corresponding row of NaNs in the output. More details about that can be found in the documentation of the respective function.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for melon_analytics_pricing-0.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0507f9b44e1b1f62deb84b162401a16855aca6ebcf1e4709297c00f64a7cf9a8 |
|
MD5 | 7730182557763589f0ed890c6b8f9424 |
|
BLAKE2b-256 | 2799c2666b23cddd55eb89ada317d1bb346317e0cd2dff13ed57531b03deb560 |
Hashes for melon_analytics_pricing-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 361fcad7eeba6e517dac43763101b82d9e41ae118394eff91cae8e66c92b06c9 |
|
MD5 | fadebeb5d6a2c61c3792faeb21d8bbae |
|
BLAKE2b-256 | 59d4d0e95ff615a51bf5e4c0cc95f322dbd2ad1d80563a6d02047546a8c36e24 |