import pandas as pd

# Step 1: Read the dataset
url = "https://www.piworks.net/Upload/Document/Original/country_vaccination_stats.csv"
data = pd.read_csv(url)

# Display the first few rows of the dataframe
print(data.head())

# Step 2: Calculate the minimum daily vaccination number per country
min_vaccinations = data.groupby('country')['daily_vaccinations'].min()

# Step 3: Fill missing values with the minimum vaccination number per country
def fill_missing_vaccinations(row):
    if pd.isnull(row['daily_vaccinations']):
        min_vacc = min_vaccinations[row['country']]
        return 0 if pd.isnull(min_vacc) else min_vacc
    else:
        return row['daily_vaccinations']

data['daily_vaccinations'] = data.apply(fill_missing_vaccinations, axis=1)

# Display the first few rows after imputation
print(data.head())

# Save the imputed data to a new CSV file (optional)
data.to_csv('imputed_country_vaccination_stats.csv', index=False)


















## answers
 country        date  daily_vaccinations   vaccines
0  Argentina  12/29/2020                 NaN  Sputnik V
1  Argentina  12/30/2020             15656.0  Sputnik V
2  Argentina  12/31/2020             15656.0  Sputnik V
3  Argentina    1/1/2021             11070.0  Sputnik V
4  Argentina    1/2/2021              8776.0  Sputnik V
     country        date  daily_vaccinations   vaccines
0  Argentina  12/29/2020              6483.0  Sputnik V
1  Argentina  12/30/2020             15656.0  Sputnik V
2  Argentina  12/31/2020             15656.0  Sputnik V
3  Argentina    1/1/2021             11070.0  Sputnik V
4  Argentina    1/2/2021              8776.0  Sputnik V