MortenHegewald

def datetime_converter(value: datetime) -> str:
    if isinstance(value, datetime):
        return value.__str__()

def get_batch_size(record: dict) -> int:
    batch = json.dumps({'items': record}, default=datetime_converter)
    return floor(4000 / (sys.getsizeof(batch) / 1024))

def import_data(clientid: str, clientsecret: str,
                data_extension: str, data: list[dict) -> None:

MortenHegewald

def generate_access_token(clientid: str, clientsecret: str) -> str:
    subdomain = 'YOUR_SUBDOMAIN'
    auth_base_url = f'https://{subdomain}.auth.marketingcloudapis.com/v2/token'
    headers = {'content-type': 'application/json'}
    payload = {
      'grant_type': 'client_credentials',
      'client_id': clientid,
      'client_secret': clientsecret
    }
    authentication_response = requests.post(

MortenHegewald

import bs4
import pandas as pd
import requests


def numeric_value(movie, tag, class_=None, order=None):
    if order:
        if len(movie.findAll(tag, class_)) > 1:
            to_extract = movie.findAll(tag, class_)[order]['data-value']
        else:

MortenHegewald

def markov_chain_allocations(removal_effects, total_conversions):
    re_sum = np.sum(list(removal_effects.values()))

    return {k: (v / re_sum) * total_conversions for k, v in removal_effects.items()}


attributions = markov_chain_allocations(removal_effects_dict, total_conversions)

MortenHegewald

def removal_effects(df, conversion_rate):
    removal_effects_dict = {}
    channels = [channel for channel in df.columns if channel not in ['Start',
                                                                     'Null',
                                                                     'Conversion']]
    for channel in channels:
        removal_df = df.drop(channel, axis=1).drop(channel, axis=0)
        for column in removal_df.columns:
            row_sum = np.sum(list(removal_df.loc[column]))
            null_pct = float(1) - row_sum

MortenHegewald

def transition_matrix(list_of_paths, transition_probabilities):
    trans_matrix = pd.DataFrame()
    list_of_unique_channels = set(x for element in list_of_paths for x in element)

    for channel in list_of_unique_channels:
        trans_matrix[channel] = 0.00
        trans_matrix.loc[channel] = 0.00
        trans_matrix.loc[channel][channel] = 1.0 if channel in ['Conversion', 'Null'] else 0.0

    for key, value in transition_probabilities.items():

MortenHegewald

def transition_prob(trans_dict):
    list_of_unique_channels = set(x for element in list_of_paths for x in element)
    trans_prob = defaultdict(dict)
    for state in list_of_unique_channels:
        if state not in ['Conversion', 'Null']:
            counter = 0
            index = [i for i, s in enumerate(trans_dict) if state + '>' in s]
            for col in index:
                if trans_dict[list(trans_dict)[col]] > 0:
                    counter += trans_dict[list(trans_dict)[col]]

MortenHegewald

def transition_states(list_of_paths):
    list_of_unique_channels = set(x for element in list_of_paths for x in element)
    transition_states = {x + '>' + y: 0 for x in list_of_unique_channels for y in list_of_unique_channels}

    for possible_state in list_of_unique_channels:
        if possible_state not in ['Conversion', 'Null']:
            for user_path in list_of_paths:
                if possible_state in user_path:
                    indices = [i for i, s in enumerate(user_path) if possible_state in s]
                    for col in indices:

MortenHegewald

list_of_paths = df_paths['path']
total_conversions = sum(path.count('Conversion') for path in df_paths['path'].tolist())
base_conversion_rate = total_conversions / len(list_of_paths)

MortenHegewald

df_paths = df.groupby('cookie')['channel'].aggregate(
    lambda x: x.unique().tolist()).reset_index()
    
df_last_interaction = df.drop_duplicates('cookie', keep='last')[['cookie', 'conversion']]
df_paths = pd.merge(df_paths, df_last_interaction, how='left', on='cookie')

df_paths['path'] = np.where(
    df_paths['conversion'] == 0,
    ['Start'] + df_paths['channel'] + ['Null'],
    ['Start'] + df_paths['channel'] + ['Conversion'])