R Python : Data Read

Read a Text (.txt) file :

Language	Code
R	file1 = read.table("mydata.txt")
Python	file1 = open("MyFile.txt","a")

Read a Comma separated value (.csv) file :

Language	Code
R	file1 = read.csv("mydata.csv",header = TRUE)
Python	import CSV With open(‘some.csv’, ‘rb’) as f: reader = csv.reader(f) for row in reader: print row
Python	import pandas as pd file1 = pd.read_csv("input.csv")

Read a Excel (.xlsx) file :

Language	Code
R	import("gdata") file1 = read.xls("myfile.xlsx"), sheet = 1, header = TRUE)
Python	from openpyxl import load_workbook ws = wb.active wb = load_workbook(filename = 'file.xlsx')

Read a XML (.xml) file :

Language	Code
R	library("XML") library("methods") file1 <- xmlParse(file = "input.xml")
Python	from xml.dom import minidom file1 = minidom.parse('myfile.xml')

Read a HTML (.html) file :

Language	Code
R	doc.html = htmlTreeParse('http://apiolaza.net/babel.html', useInternal = TRUE) doc.text = unlist(xpathApply(doc.html, '//p', xmlValue))
Python	import pandas file1 = pandas.read_html("input.html")

Read a JSON (.json) file :

Language	Code
R	library("rjson") file1 <- fromJSON(file = "input.json")
Python	import urllib sock = urllib.urlopen("http://diveintopython.org/") htmlSource = sock.read()

Read data from MySQL table :

Language	Code
R	library(RMySQL) mydb = dbConnect(MySQL(), user='user', password='password', dbname='database_name', host='host') file1 = dbSendQuery(mydb, "select * from user_table")
Python	import MySQLdb import sys connection = MySQLdb.connect (host = "192.168.1.2", user = "user", passwd = "password, db = "scripting_mysql") cursor = connection.cursor () cursor.execute ("select * from table")
	import mysql.connector

Read data from Microsoft SQL table :

Language	Code
R	library(RODBC) channel <- odbcConnect("DATABASE", uid="USERNAME", pwd="PASSWORD") file1 <- sqlQuery(channel, "SELECT * FROM SCHEMA.DATATABLE")
Python	import cx_Oracle connection = raw_input("Enter Oracle DB connection (uid/pwd@database) : ") orcl = cx_Oracle.connect(connection) curs = orcl.cursor() sql = "select * from tab" curs.execute(sql)

Read data from Mongo DB table :

Language	Code
R	library(rmongodb) m <- mongo.create(host = "localhost", db = "example") rawData <- mongo.find.all(m, "example.request", query = list(this = "AUTO"), fields = list(hello = 1L, is = 1L, an = 1L, data.facebook = 1L, the_point = 1L))
Python	from pymongo import MongoClient import datetime client = MongoClient("127.0.0.1:8080",username="admin",password="abc") db=client.admin db = client['tutorial'] coll = db['articles'] results = coll.find({"start_date": {'$lt': datetime(2015, 9, 1)}}) for doc in results: print(doc)