how to push a csv data to mongodb using python

Question

Trying to push csv data in to mongodb using python.i'm a beginner to python & mongodb..i used the following code

import csv
import json
import pandas as pd
import sys, getopt, pprint
from pymongo import MongoClient
#CSV to JSON Conversion
csvfile = open('C://test//final-current.csv', 'r')
jsonfile = open('C://test//6.json', 'a')
reader = csv.DictReader( csvfile )
header= [ "S.No", "Instrument Name", "Buy Price", "Buy Quantity", "Sell Price", "Sell Quantity", "Last Traded Price", "Total Traded Quantity", "Average Traded Price", "Open Price", "High Price", "Low Price", "Close Price", "V" ,"Time"]
#fieldnames=header
output=[]
for each in reader:
    row={}
    for field in header:
        row[field]=each[field]
    output.append(row)

json.dump(output, jsonfile, indent=None, sort_keys=False , encoding="UTF-8")
mongo_client=MongoClient() 
db=mongo_client.october_mug_talk
db.segment.drop()
data=pd.read_csv('C://test//6.json', error_bad_lines=0)
df = pd.DataFrame(data)
records = csv.DictReader(df)
db.segment.insert(records)

but the output is given in this format

/* 0 */
{
  "_id" : ObjectId("54891c4ffb2a0303b0d43134"),
  "[{\"AverageTradedPrice\":\"0\"" : "BuyPrice:\"349.75\""
}

/* 1 */
{
  "_id" : ObjectId("54891c4ffb2a0303b0d43135"),
  "[{\"AverageTradedPrice\":\"0\"" : "BuyQuantity:\"3000\""
}

/* 2 */
{
  "_id" : ObjectId("54891c4ffb2a0303b0d43136"),
  "[{\"AverageTradedPrice\":\"0\"" : "ClosePrice:\"350\""
}

/* 3 */
{
  "_id" : ObjectId("54891c4ffb2a0303b0d43137"),
  "[{\"AverageTradedPrice\":\"0\"" : "HighPrice:\"0\""
}

Actually i want the output to like for single id all the other fields should be showed as subtypes eg:

 _id" : ObjectId("54891c4ffb2a0303b0d43137")
    AveragetradedPrice :0
    HighPrice:0
    ClosePrice:350
    buyprice:350.75

Please help me Out.Thanks in advance

but if i'm pushing directly to mongodb ,it produces InvalidDocument: key 'S.No' must not contain '.' — Viswanathan
– Viswanathan, Commented Dec 11, 2014 at 6:36
Make header as a dict to map s.no as s_no so it will be accetable as json key — anhlc
– anhlc, Commented Dec 11, 2014 at 6:43

Viswanathan · Accepted Answer · 2014-12-11 07:36:23Z

20

Thank you for the suggestion.This one is the corrected code:

import csv
import json
import pandas as pd
import sys, getopt, pprint
from pymongo import MongoClient
#CSV to JSON Conversion
csvfile = open('C://test//final-current.csv', 'r')
reader = csv.DictReader( csvfile )
mongo_client=MongoClient() 
db=mongo_client.october_mug_talk
db.segment.drop()
header= [ "S No", "Instrument Name", "Buy Price", "Buy Quantity", "Sell Price", "Sell Quantity", "Last Traded Price", "Total Traded Quantity", "Average Traded Price", "Open Price", "High Price", "Low Price", "Close Price", "V" ,"Time"]

for each in reader:
    row={}
    for field in header:
        row[field]=each[field]

    db.segment.insert(row)

answered Dec 11, 2014 at 7:36

Viswanathan

4811 gold badge3 silver badges12 bronze badges

Sign up to request clarification or add additional context in comments.

Comments

CpILL · Accepted Answer · 2019-09-03 06:01:06Z

7

Why do you insert data one by one? Take a look at this one.

import pandas as pd
from pymongo import MongoClient

client = MongoClient(<your_credentials>)
database = client['YOUR_DB_NAME']
collection = database['your_collection']

def csv_to_json(filename, header=None):
    data = pd.read_csv(filename, header=header)
    return data.to_dict('records')

collection.insert_many(csv_to_json('your_file_path'))

Please be aware of that it might crash your app when the file is too big.

edited Sep 3, 2019 at 6:01

CpILL

7,2097 gold badges45 silver badges44 bronze badges

answered May 21, 2019 at 15:35

Perfect

1,6461 gold badge21 silver badges27 bronze badges

Comments

Adil · Accepted Answer · 2018-11-22 12:40:32Z

6

The easiest way is by using pandas my code is

import json
import pymongo
import pandas as pd
myclient = pymongo.MongoClient()

df = pd.read_csv('yourcsv.csv',encoding = 'ISO-8859-1')   # loading csv file
df.to_json('yourjson.json')                               # saving to json file
jdf = open('yourjson.json').read()                        # loading the json file 
data = json.loads(jdf)                                    # reading json file

now you can insert this json in your mangodb database :-]

answered Nov 22, 2018 at 12:40

Adil

711 silver badge3 bronze badges

1 Comment

mLstudent33 Over a year ago

er, showing that part you leave at is what the question asks.

deenaik · Accepted Answer · 2017-12-21 11:28:31Z

0

There is a better way with less number of imports, assuming you have a header row in your CSV.

from pymongo import MongoClient
import csv

# DB connectivity
client = MongoClient('localhost', 27017)
db = client.db
collection = db.collection

# Function to parse csv to dictionary
def csv_to_dict():
    reader = csv.DictReader(open(FILEPATH))
    result = {}
    for row in reader:
        key = row.pop('First_value')
        result[key] = row
    return query

# Final insert statement
db.collection.insert_one(csv_to_dict())

Hope that helps

answered Dec 21, 2017 at 11:28

deenaik

7537 silver badges13 bronze badges

Comments

sps · Accepted Answer · 2020-10-19 06:31:29Z

    from pymongo import MongoClient
    import csv
    import json
    # DB connectivity
    client = MongoClient('localhost', 27017)
    db = client["database name"]
    col = db["collection"]
    # Function to parse csv to dictionary
    def csv_to_dict():
        reader = csv.DictReader(open('File with path','r'))
        result = {}
        for row in reader:
            key = row.pop('id')
            result[key]= row
        return result
    
    # Final insert statement
    x=col.insert_one(csv_to_dict())
            print(x.inserted_id)

# to insert one row

#and to insert many rows following code is to be executed
from pymongo import MongoClient
import csv
# read csv file as a list of lists
client = MongoClient('localhost', 27017)
db = client["data base name"]
col = db["Collection Name"]
with open('File with path', 'r') as read_obj:
    # pass the file object to reader() to get the reader object
    csv_reader = csv.DictReader(read_obj)
    # Pass reader object to list() to get a list of lists
    mylist = list(csv_reader)
    #print(list_of_rows)
    x = col.insert_many(mylist)

    #print list of the _id values of the inserted documents:
    print(x.inserted_ids)

Collectives™ on Stack Overflow

how to push a csv data to mongodb using python

5 Answers 5

Comments

Comments

1 Comment

Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

5 Answers 5

Comments

Comments

1 Comment

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related