abhijeet-talaulikar

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

abhijeet-talaulikar

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

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

abhijeet-talaulikar

# 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]

abhijeet-talaulikar

# 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(

abhijeet-talaulikar

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

abhijeet-talaulikar

op_custom = st.container()

def updateChatBox():
  if st.session_state['response_default']:
    frm_ask = op_custom.form('frm_ask')
    question = frm_ask.text_area('If you have any specific question, ask here.', 'What are the three takeaways from this quarter?')
    frm_ask_submitted = frm_ask.form_submit_button('Ask')
    if frm_ask_submitted:
      if not openai_api_key.startswith('sk-'):
        op_custom.warning('Please enter your OpenAI API key!', icon='⚠')

abhijeet-talaulikar

# Response function - for questions identified in text
def generate_default_response(documents, prompt=prompt_default):
  qa = get_guery_function(documents)
  try:
      llm_response = qa(prompt)
      response = llm_response["result"]
  except Exception as err:
      response = str(err)
  return response

abhijeet-talaulikar

### Query function for the app ###
def get_guery_function(documents): 
  # Text splitter
  text_splitter = RecursiveCharacterTextSplitter(chunk_size=512, chunk_overlap=10)
  texts = text_splitter.split_documents(documents)

  # Embeddings
  embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
  vectordb = Chroma.from_documents(documents=texts, 
                                  embedding=embeddings,

abhijeet-talaulikar

prompt_default = '''
This document is the transcript of an earnings conference call of a company. Assume you are an analyst who 
attended this call. Identify which company this document is talking about. Identify 10 best questions and their 
answers that would help summarize the company's performance. 
Create a report in a markdown format that answers each of those 10 questions. Here is an example of the format.

Example

## Insert company name here

abhijeet-talaulikar

### Read text from PDF file ###
def read_pdf(file):
  loader = OnlinePDFLoader(file)
  documents = loader.load()
  return documents