How to import data from mongodb to pandas?
You can load your mongodb data to pandas DataFrame using this code. It works for me. Hopefully for you too.
import pymongo
import pandas as pd
from pymongo import MongoClient
client = MongoClient()
db = client.database_name
collection = db.collection_name
data = pd.DataFrame(list(collection.find()))
pymongo
might give you a hand, followings are some codes I'm using:
import pandas as pd
from pymongo import MongoClient
def _connect_mongo(host, port, username, password, db):
""" A util for making a connection to mongo """
if username and password:
mongo_uri = 'mongodb://%s:%s@%s:%s/%s' % (username, password, host, port, db)
conn = MongoClient(mongo_uri)
else:
conn = MongoClient(host, port)
return conn[db]
def read_mongo(db, collection, query={}, host='localhost', port=27017, username=None, password=None, no_id=True):
""" Read from Mongo and Store into DataFrame """
# Connect to MongoDB
db = _connect_mongo(host=host, port=port, username=username, password=password, db=db)
# Make a query to the specific DB and Collection
cursor = db[collection].find(query)
# Expand the cursor and construct the DataFrame
df = pd.DataFrame(list(cursor))
# Delete the _id
if no_id:
del df['_id']
return df
Monary
does exactly that, and it's super fast. (another link)
See this cool post which includes a quick tutorial and some timings.