import datetime
import logging

import dateparser
import numpy as np
from dateparser_data.settings import default_parsers
from dateutil.relativedelta import relativedelta

from utils.base_attributes_generation import get_fan_attribute_values
from .enrichment import Enrichment

component_logger = logging.getLogger().getChild("enrichment.enrich_age")

# Optimize and remove some un-necessary dateparsers. See https://dateparser.readthedocs.io/en/v1.0.0/settings.html
date_parsers = [x for x in default_parsers if x not in ["relative-time", "no-spaces-time", "custom-formats"]]


class EnrichAge(Enrichment):
    """
    Gets age from date of birth. If not date of birth but age is preset in source data, returns age.
    """

    source_attribute_ids = [
        9,  # 'userDob'
        10,  # 'userAge'
    ]

    result_attribute_ids = [97]  # 'enrAge'
    data_gathering_rule = "strict"

    def __init__(self, collection_id: int, schema: str, user_id: str, default_value: str = "unknown", **kwargs):
        super().__init__(collection_id, schema, user_id, default_value)

    def _run(self):
        """ Main enrichment method """
        source_df = self.available_data["source"]

        # Drop columns with all nans
        source_df = source_df.dropna(axis=1, how="all")

        if "9" in source_df.columns:
            if hasattr(source_df, "parallel_apply"):
                # Parallel apply to speed up this enrichment
                source_df["enrAge"] = source_df.parallel_apply(self._get_age_from_dob, axis=1, args=["9"])
            else:
                source_df["enrAge"] = source_df.apply(self._get_age_from_dob, axis=1, args=["9"])
        elif "10" in source_df.columns:
            source_df["enrAge"] = source_df["10"]
        """Moving row_id field to index as we require this data to be preserved for connecting with source"""
        source_df.set_index("row_id", inplace=True)

        source_df = source_df[["fan_id", "enrAge"]]

        self.result_df = source_df

    @staticmethod
    def _get_age_from_dob(row, col):
        """ Get date object out of string. We use dateparser to conveniently make date object out
        of almost any string representation of date - this is pretty fool-proof and can work with stuff like
        "20 November 2020" as well as "22/11/2016"
        """
        date_string = row[col]
        if date_string is None:
            # If we don't return None, we get "0" for missing dates (and in analytics falsely put to 0-17 age group)
            return date_string
        global date_parsers
        try:
            # Adding "en" language makes parsing of 10k dates ~60% faster
            dob_date_object = dateparser.parse(
                str(date_string), languages=["en"], settings={"PREFER_DATES_FROM": "past", "PARSERS": date_parsers}
            )
            now_date_object = datetime.datetime.now()
            age_in_years_now = relativedelta(now_date_object, dob_date_object).years
        except Exception as e:
            age_in_years_now = np.nan
        return age_in_years_now

    """ In age enrich we need to join with fan_id and row_id because the output is row based """

    def _generate_fan_attributes(self):
        """ Getting a list of attributes that are present in this enrichment"""
        condition = self.system_fields["a_id"].isin(self.result_attribute_ids)
        attributes_df = self.system_fields[condition][["a_system_name", "a_id"]]
        attributes_df.rename(columns={"a_system_name": "name", "a_id": "attribute_id"}, inplace=True)

        fan_attributes_df = get_fan_attribute_values(
            source_df=self.result_df, attributes_df=attributes_df, collection_id=self.enrichment_collection_id
        )
        self.fan_attribute = fan_attributes_df