djsegal

import pandas as pd

from sklearn.model_selection import train_test_split

def custom_train_test_split(cur_data, random_state=42, cur_target="price", cur_boolean="is_brooklyn"):
    if cur_boolean in cur_data.columns:
        cur_train_1, cur_test_1 = _custom_train_test_split(
            cur_data[cur_data[cur_boolean]], random_state, cur_target
        )

djsegal

djsegal

import numpy as np
import pandas as pd

from sklearn.base import BaseEstimator, TransformerMixin 

class ReciprocalFeatures(BaseEstimator, TransformerMixin):
    def __init__(self):
        self.input_features = None
        self.rename_lambda = \
            lambda input_feature: f"_inv_{input_feature}"

djsegal

import numpy as np
from sklearn.compose import TransformedTargetRegressor

class LogTransformedTargetRegressor(TransformedTargetRegressor):
    def __init__(self, regressor):
        inverse_func = lambda cur_log_val: 10 ** cur_log_val
        
        TransformedTargetRegressor.__init__(
            self, regressor=regressor,
            func=np.log10, inverse_func=inverse_func

djsegal

import numpy as np

from sklearn.base import BaseEstimator
from sklearn.feature_selection.base import SelectorMixin

class CleanFeatures(BaseEstimator, SelectorMixin):
    def __init__(self):
        self.sieve = []
    
    def _get_support_mask(self):

djsegal

from sklearn.base import BaseEstimator, TransformerMixin 

class PassThroughTransformer(BaseEstimator, TransformerMixin):
    def __init__(self):
        self.input_features = None

    def fit(self, X, y=None):
        assert self.input_features is None
        
        if type(X) == np.ndarray : 

djsegal

cur_data = price_data.copy()
cur_data = cur_data.merge(rental_data, on="id")
cur_data = cur_data.merge(location_data, on="id")

X_train, X_test, y_train, y_test = \
    custom_train_test_split(cur_data)

pass_cols = ["is_brooklyn", "density"]
drop_cols = ["year", "geometry", "zipcode"]
one_hot_cols = ["month"]

djsegal

djsegal

djsegal

import numpy as np
import pandas as pd

import geopandas
import pickle

from sklearn.cluster import KMeans
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler