Meet Dr. Ignaz Semmelweis

import pandas as pd yearly = pd.read_csv('datasets/yearly_deaths_by_clinic.csv') print(yearly)

# Calculate proportion of deaths per no. births yearly['proportion_deaths']= yearly['deaths']/yearly['births'] # Extract Clinic 1 data into clinic_1 and Clinic 2 data into clinic_2 clinic_1 = yearly[yearly['clinic']=='clinic 1'] clinic_2 = yearly[yearly['clinic']=='clinic 2'] # Print out clinic_1 print(clinic_1)

# This makes plots appear in the notebook %matplotlib inline # Plot yearly proportion of deaths at the two clinics ax = clinic_1.plot(x="year", y="proportion_deaths", label="Clinic 1") clinic_2.plot(x="year", y="proportion_deaths", label="Clinic 2", ax=ax, ylabel="Proportion of Deaths",xlabel="Year")

# Read datasets/monthly_deaths.csv into monthly monthly = pd.read_csv('datasets/monthly_deaths.csv', parse_dates=["date"]) # Calculate proportion of deaths per no. births monthly["proportion_deaths"] = monthly['deaths'] / monthly['births'] # Print out the first rows in monthly monthly.loc[0]

# Plot monthly proportion of deaths ax = monthly.plot(x="date", y="proportion_deaths")

# Date when handwashing was made mandatory handwashing_start = pd.to_datetime('1847-06-01') # Split monthly into before and after handwashing_start before_washing = monthly[monthly['date'] < handwashing_start] after_washing = monthly[monthly['date'] >= handwashing_start] # Plot monthly proportion of deaths before and after handwashing ax = before_washing.plot(x="date", y="proportion_deaths", label="Before Washing") after_washing.plot(x="date", y="proportion_deaths", label="After Washing", ax=ax, ylabel="Proportion of Deaths",xlabel="Year")

# Difference in mean monthly proportion of deaths due to handwashing before_proportion = before_washing['proportion_deaths'] after_proportion = after_washing['proportion_deaths'] mean_diff = after_proportion.mean() - before_proportion.mean() mean_diff