Merge pull request #90 from madefu/master

Code/Day 3_Multiple_Linear_Regression.py

@@ -31,4 +31,4 @@ y_pred = regressor.predict(X_test)
 
 # regression evaluation
 from sklearn.metrics import r2_score
-print(r2_score(Y_test,y_pred))
+print(r2_score(Y_test, y_pred))

Code/KafkaProducer.py

@@ -0,0 +1,13 @@
+#!/usr/bin/python
+
+from kafka import KafkaProducer
+
+kafkaHosts=["kafka01.paas.longfor.sit:9092"
+            ,"kafka02.paas.longfor.sit:9092"
+            ,"kafka03.paas.longfor.sit:9092"]
+
+producer = KafkaProducer(bootstrap_servers=kafkaHosts);
+
+for _ in range(20):
+    producer.send("testapplog_plm-prototype",b"Hello....")
+producer.flush();

Code/TestKafka.py

@@ -0,0 +1,24 @@
+#!/usr/bin/python
+
+from kafka import KafkaConsumer;
+
+
+kafkaHosts=["kafka01.paas.longfor.sit:9092"
+            ,"kafka02.paas.longfor.sit:9092"
+            ,"kafka03.paas.longfor.sit:9092"]
+
+'''
+earliest 
+当各分区下有已提交的offset时，从提交的offset开始消费；无提交的offset时，从头开始消费 
+latest 
+当各分区下有已提交的offset时，从提交的offset开始消费；无提交的offset时，消费新产生的该分区下的数据 
+none 
+topic各分区都存在已提交的offset时，从offset后开始消费；只要有一个分区不存在已提交的offset，则抛出异常
+'''
+consumer = KafkaConsumer(
+    bootstrap_servers=kafkaHosts,group_id='mdf_group',auto_offset_reset='latest');
+
+consumer.subscribe("testapplog_plm-prototype");
+
+for msg in consumer:
+    print(msg.value)

Code/my/Data_age_salary.csv

@@ -0,0 +1,11 @@
+Age,Salary
+44,72000
+27,48000
+30,54000
+38,61000
+40,78000
+35,58000
+35,52000
+48,79000
+50,83000
+37,67000

Code/my/LinerTest.py

@@ -0,0 +1,6 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+dataset = pd.read_csv('Data_age_salary.csv');
+dataset.iloc[:1]