Exercise 4

import pandas as pd

df = pd.read_csv('/datasets/drink_preferences.csv')
df = df.dropna(subset=['nonalcoholic_drink'])
df_female = df[df['gender'] == 'Female']


# Сгруппируйте и отсортируйте данные
df_agg = (df_female
          .groupby('nonalcoholic_drink')
          .agg({'resp_id': 'nunique'})
          .sort_values(by='resp_id', ascending=False)
          .reset_index())
df_agg = pd.DataFrame({'nonalcoholic_drink': ['Coffee', 'Green Tea', 'Black Tea',
                                              'Apple Juice', 'Water', 'Gatorade',
                                              'Dr. Pepper', 'Coke', 'Pepsi', 'Red Bull'],
                      'resp_id': [25, 22, 21, 19, 19, 15, 12, 8, 7, 4]})
print(df_agg)