{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# This R environment comes with all of CRAN preinstalled, as well as many other helpful packages\n# The environment is defined by the kaggle/rstats docker image: https://github.com/kaggle/docker-rstats\n# For example, here's several helpful packages to load in \n\nlibrary(ggplot2) # Data visualization\nlibrary(readr) # CSV file I/O, e.g. the read_csv function\n\n# Input data files are available in the \"../input/\" directory.\n\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\n#system(\"ls ../input\")\n\nfbdata_full <- read.csv(\"../input/train.csv\")\n#check the rows and colms of fbdata_full\ndim(fbdata_full)\n\n# Since the data is large , I have taken 5% sample of the tran.csv data for below Analysis.\n#fbdata <- sample(fbdata_full, nrow(fbdata_full) * 0.05)\nfbdata <- fbdata_full[sample(nrow(fbdata_full)*0.01),]\n\nrm(fbdata_full) # to free memory\n\n#check the rows and colms of fbdata\ndim(fbdata)\n\n#Let's check first 6 rows of the 5% sample to get better understanding of data in file \nhead(fbdata)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":""}],"metadata":{"kernelspec":{"display_name":"R","language":"R","name":"ir"}},"nbformat":4,"nbformat_minor":0}