# Creating some simulated data for our example
import pandas as pd
import numpy as np
num_users = 10000
num_months = 12
signup_months = np.random.choice(np.arange(1, num_months), num_users) * np.random.randint(0,2, size=num_users) # signup_months == 0 means customer did not sign up
df = pd.DataFrame({
'user_id': np.repeat(np.arange(num_users), num_months),
'signup_month': np.repeat(signup_months, num_months), # signup month == 0 means customer did not sign up
'month': np.tile(np.arange(1, num_months+1), num_users), # months are from 1 to 12
'spend': np.random.poisson(500, num_users*num_months) #np.random.beta(a=2, b=5, size=num_users * num_months)*1000 # centered at 500
})
# A customer is in the treatment group if and only if they signed up
df["treatment"] = df["signup_month"]>0
# Simulating an effect of month (monotonically decreasing--customers buy less later in the year)
df["spend"] = df["spend"] - df["month"]*10
# Simulating a simple treatment effect of 100
after_signup = (df["signup_month"] < df["month"]) & (df["treatment"])
df.loc[after_signup,"spend"] = df[after_signup]["spend"] + 100
df.to_csv("data.csv", index=False)
