from datetime import datetime
import logging
import pandas as pd
component_logger = logging.getLogger().getChild("tasks.base_attributes_gen")


def get_fan_attribute_values(source_df: pd.DataFrame,
                             attributes_df: pd.DataFrame,
                             collection_id: int) -> pd.DataFrame:
    """Returns fan_attribute table """
    """ We create a row_id """
    source_df['row_id'] = source_df.index

    """ We transpose attributes """
    fan_attribute_base = pd.DataFrame(source_df.set_index(['fan_id', 'row_id']).stack(), columns=['value'])
    fan_attribute_base.index.names = ['fan_id', 'row_id', 'name']
    fan_attribute_base = fan_attribute_base.reset_index(level=[0, 1])

    """ Left join and map attributes by name to get ids for attributes """
    fan_attribute_result = pd.merge(fan_attribute_base,
                                    attributes_df,
                                    left_on='name',
                                    right_on='name',
                                    how='left')

    # Limit the columns we want in fan_attribute table
    fan_attribute_result = fan_attribute_result[['fan_id', 'attribute_id', 'value', 'row_id']]

    # Add the field that holds collection_id
    fan_attribute_result['collection_id'] = collection_id
    """ Adding timestamp field to successfully stage the file during upload to RDS"""
    fan_attribute_result['timestamp'] = str(datetime.utcnow())
    return fan_attribute_result