jamesrajendran

import pandas as pd
import seaborn as sns
data = pd.read_csv('C:\work\ML\Advertising.csv', index_col= 0)
print(data.head())

%matplotlib inline
#sns.pairplot  (data, x_vars=['TV','Radio','Newspaper'], y_vars='Sales')
#feature_cols =['TV','Radio','Newspaper']
#print(feature_cols)
X = data[['TV','Radio','Newspaper']]

jamesrajendran

from sklearn.cross_validation import train_test_split
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
from sklearn import metrics
from sklearn.neighbors import KNeighborsClassifier

iris = load_iris()
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4 )

jamesrajendran

from sklearn import metrics
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.datasets import load_iris

iris = load_iris()
X = iris.data
y = iris.target

logreg = LogisticRegression()

jamesrajendran

from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression

iris = load_iris()
X = iris.data
y = iris.target
logreg = LogisticRegression()
logreg.fit(X,y)
logreg.predict(X[0])

jamesrajendran

from sklearn.datasets import load_iris
from sklearn.neighbors import KNeighborsClassifier

#Load the data
iris = load_iris()

type(iris)
print(iris)
print( iris.feature_names)
print(iris.target)

jamesrajendran

select lo.*, 
       a.sql_text
from gv$sqlarea a, gv$session_longops lo
where lo.sql_id = a.sql_id
order by lo.start_time;


select s.sid, 
       s.username,
       s.machine,

jamesrajendran

# Spark ML example
# Here is the code URL (courtesy):   https://github.com/jayantshekhar/strata-2016/blob/master/src/main/scala/com/cloudera/spark/spamdetection/Spam.scala
------------------------

// scalastyle:off println
package com.cloudera.spark.spamdetection

import scala.beans.BeanInfo
import org.apache.spark.{SparkConf, SparkContext}

jamesrajendran

package kafkaHome;

import java.util.Properties;

//import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.*;
//import org.apache.kafka.clients.producer.ProducerRecord;
//import org.apache.kafka.clients.producer.RecordMetadata;
public class SimpleProducer {	

jamesrajendran

env # to get all env variables

#Find class files in a jar
all_hdp_classes () {
  find -L /usr/hdp/current -maxdepth 20 -name "*.jar" -print | while read line; do
    for i in `jar tf $line | grep .class`
    do
    echo $line : $i
    done 
  done

jamesrajendran

// SHELL COMMANDS FROM SPARK SHELL

:sh hdfs dfs -ls /user/cloudera
<result> foreach println  //use the result variable like 'res0' in the place of <result>