drogon/analysis/market_snapshot.py

from datetime import datetime,  timedelta
import pandas as pd

available_date_ranges = [{'start': datetime(2017, 10, 1), 'end': datetime(2018, 1, 1)},
                         {'start': datetime(2017, 11, 1), 'end': datetime(2018, 2, 1)},
                         {'start': datetime(2017, 12, 1), 'end': datetime(2018, 3, 1)},
                         {'start': datetime(2018, 1, 1), 'end': datetime(2018, 4, 1)},
                         {'start': datetime(2018, 2, 1), 'end': datetime(2018, 5, 1)},
                         {'start': datetime(2018, 3, 1), 'end': datetime(2018, 6, 1)},
                         {'start': datetime(2018, 4, 1), 'end': datetime(2018, 7, 1)},
                         {'start': datetime(2018, 5, 1), 'end': datetime(2018, 8, 1)},
                         {'start': datetime(2018, 6, 1), 'end': datetime(2018, 9, 1)},
                         {'start': datetime(2018, 7, 1), 'end': datetime(2018, 10, 1)},
                         {'start': datetime(2018, 8, 1), 'end': datetime(2018, 11, 1)},
                         {'start': datetime(2018, 9, 1), 'end': datetime(2018, 12, 1)}]


class Market:

    def __init__(self):
        self.start_date = None
        self.end_date = None
        self.market = None

    def load_market(self, market_query_results, date_range):
        self.market = pd.DataFrame(market_query_results)
        self.start_date = date_range['start']
        self.end_date = date_range['end']

    def clean_market(self, method):

        if method == 'index':
            self.market = self.market.dropna(subset=['tamano_categorico'])
            self.market = self.market[~self.market['tamano_categorico'].isin(['2 coches o más', 'moto'])]
            self.market = self.market.drop_duplicates(subset=['tamano_categorico', 'precio', 'latitud', 'longitud', 'telefono'], keep='last')
            self.market = self.market[self.market['tipo_anuncio'] == 1]
            self.delete_outliers()

        if method == 'valoracion':
            self.market = self.market.dropna(subset=['tamano_categorico'])
            self.market = self.market[~self.market['tamano_categorico'].isin(['2 coches o más', 'moto'])]
            self.market = self.market[self.market['precision'].isin(['ROOFTOP'])]
            self.market = self.market.drop_duplicates(subset=['tamano_categorico', 'precio', 'latitud', 'longitud', 'telefono'], keep='last')
            self.market = self.market[self.market['tipo_anuncio'] == 1]
            self.delete_outliers()

    def delete_outliers(self):

        outlier_combinations = [{'tipo_anuncio': 1, 'tamano_categorico': 'coche grande',
                                 'min_precio': 1000, 'max_precio': 150000},
                                {'tipo_anuncio': 1, 'tamano_categorico': 'coche pequeño',
                                 'min_precio': 1000, 'max_precio': 150000},
                                {'tipo_anuncio': 1, 'tamano_categorico': 'coche y moto',
                                 'min_precio': 1000, 'max_precio': 200000},
                                {'tipo_anuncio': 1, 'tamano_categorico': 'moto',
                                 'min_precio': 1000, 'max_precio': 40000},
                                {'tipo_anuncio': 2, 'tamano_categorico': 'coche grande',
                                 'min_precio': 10, 'max_precio': 300},
                                {'tipo_anuncio': 2, 'tamano_categorico': 'coche pequeño',
                                 'min_precio': 10, 'max_precio': 300},
                                {'tipo_anuncio': 2, 'tamano_categorico': 'coche y moto',
                                 'min_precio': 10, 'max_precio': 3000},
                                {'tipo_anuncio': 2, 'tamano_categorico': 'moto',
                                 'min_precio': 10, 'max_precio': 150}]

        for combination in outlier_combinations:
            self.market = self.market.loc[~(
                (self.market['tipo_anuncio'] == combination['tipo_anuncio']) &
                (self.market['tamano_categorico'] == combination['tamano_categorico']) &
                ((self.market['precio'] < combination['min_precio']) | (self.market['precio'] > combination['max_precio']))
            )]

    def get_market_data(self):
        return self.market