arpitmailgun

import pandas as pd
import numpy as np
from statsmodels.stats.proportion import proportions_ztest

# Sample data for combined_data (with model_type and converted columns)
data = {
    'lead_score': [85, 70, 60, 45, 90, 75, 80, 55, 65, 78, 85, 68, 72, 90, 82, 75, 70, 88],
    'converted': [1, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1],
    'model_type': ['rule_based'] * 9 + ['ml_based'] * 9
}

arpitmailgun

import pandas as pd
import numpy as np
from statsmodels.stats.proportion import proportions_ztest

# Separate data for rule_based and ml_based model types
rule_data = combined_data[combined_data['model_type'] == 'rule_based'].sample(n=sample_size_rule, random_state=1)
ml_data = combined_data[combined_data['model_type'] == 'ml_based'].sample(n=sample_size_ml, random_state=1)

# Calculate number of conversions and total leads for each model type
rule_converted = rule_data['converted'].sum()

arpitmailgun

from statsmodels.stats.power import TTestIndPower

# Define conversion rates and desired effect size
baseline_conversion_rate = 0.1
desired_effect_size = 0.1
alpha = 0.05
power = 0.8

# Calculate required sample size per group
number_of_leads_per_group = TTestIndPower().solve_power(