from typing import List, Dict, Any
from collections import Counter

import pandas as pd

from model_data.utils import correct_spelling
from model_data.epc_attributes.FloorAttributes import FloorAttributes
from model_data.epc_attributes.HotWaterAttributes import HotWaterAttributes
from model_data.epc_attributes.MainFuelAttributes import MainFuelAttributes
from model_data.epc_attributes.MainheatAttributes import MainHeatAttributes
from model_data.epc_attributes.MainheatControlAttributes import MainheatControlAttributes
from model_data.epc_attributes.RoofAttributes import RoofAttributes
from model_data.epc_attributes.WallAttributes import WallAttributes
from model_data.epc_attributes.WindowAttributes import WindowAttributes
from model_data.epc_attributes.LightingAttributes import LightingAttributes


class EpcClean:
    """
    Container for methods which we utilise for epc_attributes EPC data
    """

    CLEANING_FIELDS: List[str] = [
        "floor-description",
        "hotwater-description",
        "main-fuel",
        "mainheat-description",
        "mainheatcont-description",
        "roof-description",
        "walls-description",
        "windows-description",
        "lighting-description"
    ]

    def __init__(self, data: List[Dict[str, Any]]) -> None:
        """
        EpcClean constructor.

        :param data: List of dictionaries containing EPC data.
        """
        self.data: List[Dict[str, Any]] = data
        self.unique_vals: Dict[str, Any] = {}
        self.cleaned: Dict[str, List[Any]] = {}

        self.lighting_averages = self._calculate_lighting_averages()

    def _calculate_lighting_averages(self):

        """
        This is a simple utility function that for few textual lighting descritpions, will calculate the average
        low energy lighting proportion. This is only valid for a very tiny number of cases and so a very simple
        methodology is applied
        :return: Dataframe of avergages for the corresponding descriptions
        """

        df = pd.DataFrame(self.data)
        aggs = df[
            df["lighting-description"].isin(
                [
                    'Below average lighting efficiency',
                    'Good lighting efficiency',
                    'Excelent lighting efficiency'
                ]
            )
        ].copy()
        aggs["low-energy-lighting"] = aggs["low-energy-lighting"].astype(float)

        averages = aggs.groupby("lighting-description")["low-energy-lighting"].mean().reset_index()
        averages["lighting-description"] = averages["lighting-description"].str.lower()

        # Correct spelling mistakes in averages
        averages["lighting-description"] = averages["lighting-description"].apply(correct_spelling)

        return averages

    def clean(self) -> None:
        """
        Cleans the EPC data, mapping text fields to property epc_attributes.
        """
        self._init_empty_cleaned_obj()

        for field in self.CLEANING_FIELDS:
            self.unique_vals[field] = Counter([v[field] for v in self.data])

        self.clean_wrapper(field="floor-description", cleaning_cls=FloorAttributes)
        self.clean_wrapper(field="hotwater-description", cleaning_cls=HotWaterAttributes)
        self.clean_wrapper(field="main-fuel", cleaning_cls=MainFuelAttributes)
        self.clean_wrapper(field="mainheat-description", cleaning_cls=MainHeatAttributes)
        self.clean_wrapper(field="mainheatcont-description", cleaning_cls=MainheatControlAttributes)
        self.clean_wrapper(field="roof-description", cleaning_cls=RoofAttributes)
        self.clean_wrapper(field="walls-description", cleaning_cls=WallAttributes)
        self.clean_wrapper(field="windows-description", cleaning_cls=WindowAttributes)

        self.clean_wrapper(
            field="lighting-description", cleaning_cls=LightingAttributes, averages=self.lighting_averages
        )

    def _init_empty_cleaned_obj(self) -> None:
        """
        Initializes an empty object for cleaned data.
        """
        self.cleaned = {field: [] for field in self.CLEANING_FIELDS}

    def clean_wrapper(self, field, cleaning_cls, **kwargs):
        for description in self.unique_vals[field].keys():
            self.cleaned[field].append(
                {
                    "original_description": description,
                    **cleaning_cls(description, **kwargs).process()
                }
            )