jatinchauhann

.mystyle {
    font-size: 11pt;
    font-family: Arial;
    border-collapse: collapse;
    border: 1px solid silver;

}

.mystyle td, th {
    padding: 5px;

jatinchauhann

if __name__ == '__main__':
 
   file_name = args.jsonconfig
   css_file = args.cssfile
 
   try:
       spark = SparkSession.builder.enableHiveSupport().appName("HDFS Stats Generator").getOrCreate()
       print(spark.version)
       log=spark.sparkContext._jvm.org.apache.log4j.LogManager.getLogger(__name__)
 

jatinchauhann

def send_mail(franchise_name, send_from, send_to, subject, email_content, files,
             server_host, server_port):
   msg = MIMEMultipart()
   msg['From'] = send_from
   msg['To'] = send_to
   msg['Date'] = formatdate(localtime=True)
   msg['Subject'] = subject
   msg.preamble = """
   Please open these reports using Google Chrome!"""
 

jatinchauhann

def generate_mail(db_json, db_names_hdfs, df_all_stats, df_db_name_dict_seg_stats, admin):
   html_dump = ""
   for db in db_names_hdfs:
       # Function fingerprint: franchise_name, send_from, send_to, subject, email_content, files, server_host, server_port
       if admin == False:
           html_dump = get_html(df_all_stats, df_db_name_dict_seg_stats[db], db_json[db]["name"])
           send_mail(db_json[db]["name"], db_json["admin"]["email"], db_json[db]["email"], db_json["mail_format"]["subject"], db_json["mail_format"]["body"], html_dump, db_json["admin"]["server_host"], db_json["admin"]["server_port"])
       if admin == True:
           html_dump = html_dump + get_html(df_all_stats, df_db_name_dict_seg_stats[db], db_json[db]["name"])
   if admin == True:

jatinchauhann

def get_html_footer(dataframe_all_stats, dataframe, franchise):
   input_props = {
   "db_name" : str(franchise).upper(),
   "db_size" : str(get_total_size(dataframe)),
   "db_all_size" : str(get_total_size(dataframe_all_stats)),
   "top_10_tables" : get_top_table(dataframe, 10),
   "zerokb_tables" : get_zerokb_table(dataframe),
   "text_formatted_tables" : get_text_formatted_tables(dataframe)
   }
   html_buffer = '''

jatinchauhann

def get_html_header(dataframe_all_stats, dataframe, franchise):
   input_props = {
   "db_name" : str(franchise).upper(),
   "db_size" : str(get_total_size(dataframe)),
   "db_all_size" : str(get_total_size(dataframe_all_stats)),
   "hdfs_location_all" : get_common_location(dataframe_all_stats),
   "hdfs_location" : get_common_location(dataframe),
   "top_10_tables_style" : get_top_table(dataframe, 10),
   "zerokb_tables_style" : get_zerokb_table(dataframe),
   "style" : style

jatinchauhann

def get_html_header(dataframe_all_stats, dataframe, franchise):
   input_props = {
   "db_name" : str(franchise).upper(),
   "db_size" : str(get_total_size(dataframe)),
   "db_all_size" : str(get_total_size(dataframe_all_stats)),
   "hdfs_location_all" : get_common_location(dataframe_all_stats),
   "hdfs_location" : get_common_location(dataframe),
   "top_10_tables_style" : get_top_table(dataframe, 10),
   "zerokb_tables_style" : get_zerokb_table(dataframe),
   "style" : style

jatinchauhann

{
	"admin": {
		"email": "jatin.chauhan@abc.com",
		"all_stats_to_email": "jatin.chauhan@abc.com,kuldeepsingh.chauhan@abc.com",
		"server_host": "your_smtp_host_name",
		"server_port": "your_smtp_host_port_number"
	},
	"db_name_1": {
		"name": "DB Name 1",
		"email": "jatin.chauhan@abc.com"

jatinchauhann

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from scipy.spatial import distance

def euc(a,b):
    return distance.euclidean(a,b)

#Creating a sample classifier class
class ScrappyKNN():

jatinchauhann

//after installing mondodb
//cd to the 'bin' directory of the mongodb folder
//run the following commands in the cmd (run as administrator -for Windows)
mongod --directoryperdb --dbpath C:\mongodb\data\db --logpath C:\mongodb\log\mongo.log --logappend --rest --install

//to start the mongodb service
net start MongoDB

//to enter mongodb service (this is necessary to start the mongo service)
mongo