Sandy4321

from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.vectorstores import Chroma
from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings
from typing import Annotated, Dict, TypedDict
from langchain_core.messages import BaseMessage

import json
import operator
from typing import Annotated, Sequence, TypedDict

Sandy4321

## LAMNDA FUNCTION lambda_function.py

import boto3
import json

# grab environment variables
ENDPOINT_NAME = "jumpstart-dft-meta-textgeneration-llama-2-7b-rs"
runtime= boto3.client('runtime.sagemaker')

def lambda_handler(event, context):

Sandy4321

import numpy as np
import pandas as pd

campaign_data = pd.read_csv("cashback_activation_data.csv")

campaign_data = campaign_data.sort_values(['customer_id', 'timestamp'],
                    ascending=[False, True])

campaign_data['visit_order'] = campaign_data.groupby('customer_id').cumcount() + 1

Sandy4321

# Step 1: Convert all interactions to a list
journeys = campaign_data.groupby('customer_id')['channel'].aggregate(
    lambda x: x.tolist()).reset_index()

# Step 2: Add last interaction as 1 or 0 event representing activation
activation_results = campaign_data.drop_duplicates('customer_id', keep='last')[['customer_id', 'activation']]
journeys = pd.merge(journeys, activation_results, how='left', on='customer_id')

# Step 3: Add start and end states based on whether customer activated
journeys['path'] = np.where(

Sandy4321

# Function to create intermediate path strings
def transition_states(paths):
    unique_channels = set(x for element in paths for x in element)
    transition_states = {x + '>' + y: 0 for x in unique_channels for y in unique_channels}

    for possible_state in unique_channels:
        if possible_state not in ['Activation', 'Null']:
            for user_path in paths:
                if possible_state in user_path:
                    indices = [i for i, s in enumerate(user_path) if possible_state in s]

Sandy4321

import matplotlib.pyplot as plt
import seaborn as sns
from markovchain import MarkovChain

mc = MarkovChain(trans_matrix.values, trans_matrix.index)
mc.draw()

Sandy4321

def removal_effects(df, conversion_rate):
    removal_effects_dict = {}
    channels = [channel for channel in df.columns if channel not in ['Start',
                                                                     'Null',
                                                                     'Activation']]
    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

Sandy4321

df_multi = pd.DataFrame({
    'Channel': attributions.keys(),
    'Attribution style': 'Journey',
    'Activations': attributions.values()
})

df_first = pd.DataFrame({
    'Channel': attributions.keys(),
    'Attribution style': 'First touchpoint'
})

Sandy4321

df_scatter = df_multi.copy()

df_scatter['Coverage'] = df_scatter['Channel'].map(
    campaign_data.groupby('channel')['customer_id'].nunique().to_dict()
)

df_scatter['Total Clicks'] = df_scatter['Channel'].map(
    journeys['path'].apply(lambda x: x[-2]).value_counts().to_dict()
)

Sandy4321

plt.figure(figsize=(10,5))
sns.scatterplot(data=df_scatter, x='Click Activation Rate', y='Activation Rate', s=200, color='#2653de')

for line in range(0, df_scatter.shape[0]):
     plt.text(df_scatter['Click Activation Rate'][line]+0.001, df_scatter['Activation Rate'][line], 
     df_scatter['Channel'][line], horizontalalignment='left', 
     size='medium', color='black', weight='semibold')