import pandas as pd
from sklearn.preprocessing import MultiLabelBinarizer
mlb = MultiLabelBinarizer()

# load sample data
df = pd.DataFrame( {'user_id':['1','1','2','2','2','3'], 'fruits':['banana','orange','orange','apple','banana','mango']})

# collect fruits for each user
transformed_df= df.groupby('user_id').agg({'fruits':lambda x: list(x)}).reset_index()

print(transformed_df)
  user_id                   fruits
0       1         [banana, orange]
1       2  [orange, apple, banana]
2       3                  [mango]

# perform MultiLabelBinarizer
final_df = transformed_df.join(pd.DataFrame(mlb.fit_transform(transformed_df.pop('fruits')),columns=mlb.classes_,index=transformed_df.index))

print(final_df)
  user_id  apple  banana  mango  orange
0       1      0       1      0       1
1       2      1       1      0       1
2       3      0       0      1       0