uam

Python

import pandas as pd
from ChannelAttributionPro import uam

token = "yourtoken"

df_aggr = pd.read_csv("https://app.channelattribution.io/data/data_mmm_2.csv", sep=",")

D_variables = pd.DataFrame({
    "variable": [
        "direct_searches",
        "facebook_impressions",
        "facebook_clicks",
        "google_impressions",
        "google_clicks",
    ],
    "channel": [
        "direct",
        "facebook_ads",
        "facebook_ads",
        "google_ads",
        "google_ads",
    ],
    "measure": [
        "direct_searches",
        "impressions",
        "clicks",
        "impressions",
        "clicks",
    ],
})

target = "conversions"

Aggregated-data attribution without customer journey paths:

res = uam(
    df_aggr=df_aggr,
    D_variables=D_variables,
    target=target,
    df_paths=None,
    baseline_model="reward",  # "reward", "copula", or "linear"
    max_p=12,
    nsim=1000,
    seed=1234567,
    verbose=1,
    password=token,
)

attribution = res["attribution"]
print(attribution.head())

With already aggregated customer journey paths:

df_paths = pd.read_csv("https://app.channelattribution.io/data/data_uam_paths_t.csv", sep=";")

res = uam(
    df_aggr=df_aggr,
    D_variables=D_variables,
    target=target,
    df_paths=df_paths,
    baseline_model="reward",  # "reward", "copula", or "linear"
    var_path="path",
    var_conv="total_conversions",
    var_null="total_null",
    order=1,
    sep=">",
    verbose=1,
    password=token,
)

attribution = res["attribution"]
print(attribution.head())

With event-level customer journey paths:

df_paths = pd.read_csv("https://app.channelattribution.io/data/data_uam_paths.csv", sep=";")

res = uam(
    df_aggr=df_aggr,
    D_variables=D_variables,
    target=target,
    df_paths=df_paths,
    baseline_model="reward",
    channel_conv="((CONV))",
    order=1,
    sep=">",
    verbose=1,
    password=token,
)

attribution = res["attribution"]
print(attribution.head())

With diagnostics:

diag = uam(
    df_aggr=df_aggr,
    D_variables=D_variables,
    target=target,
    df_paths=df_paths,
    baseline_model="reward",
    return_diagnostics=True,
    password=token,
)

print(diag["baseline_model"])
print(diag["parameters_mta_markov_blend_summary"])