In [1]:

    

import pymongo


    

In [2]:

    

client = pymongo.MongoClient('localhost', 27017)
db = client['adults-db']


    

In [3]:

    

incomeCollection = db['income']


    

In [9]:

    

column_headings = 'age,workclass,fnlwgt,education,education-num,marital-status,occupation,relationship,race,sex,capital-gain,capital-loss,hours-per-week,native-country,label'.split(',')


    

In [10]:

    

with open('adult.data') as f_in:
    for line in f_in:
        row_list = [x.strip() for x in line.rstrip('\n').split(',')]
        try:
            row_dict = dict(zip(column_headings, row_list))
            row_dict['age'] = int(row_dict['age'])
            incomeCollection.insert_one(row_dict)
        except:
            pass


    

In [11]:

    

incomeCollection.estimated_document_count()


    

    
Out[11]:





32561

In [12]:

    

over_35 = incomeCollection.find({'age': {'$gt': 35}})


    

In [13]:

    

type(over_35)


    

    
Out[13]:





pymongo.cursor.Cursor

In [14]:

    

over_35.next()


    

    
Out[14]:





{'_id': ObjectId('5c4747c80adc7432f4092783'),
 'age': 39,
 'workclass': 'State-gov',
 'fnlwgt': '77516',
 'education': 'Bachelors',
 'education-num': '13',
 'marital-status': 'Never-married',
 'occupation': 'Adm-clerical',
 'relationship': 'Not-in-family',
 'race': 'White',
 'sex': 'Male',
 'capital-gain': '2174',
 'capital-loss': '0',
 'hours-per-week': '40',
 'native-country': 'United-States',
 'label': '<=50K'}

In [15]:

    

import time


    

In [16]:

    

start = time.time()
age_50 = incomeCollection.find({'age': {'$gt': 50}})
end = time.time()
print(end - start)


    

    




0.0

In [17]:

    

index_result = db.profiles.create_index([('age', pymongo.ASCENDING)], unique=False)


    

In [18]:

    

start = time.time()
age_45 = incomeCollection.find({'age': {'$gt': 25}})
end = time.time()
print(end - start)


    

    




0.0

In [19]:

    

client.close()


    

In [ ]: