Little comment and some git clean up

Author: dashjim

.gitignore

@@ -1,2 +1,9 @@
 *.pyc
 ch06/twitterauth.py
+.idea/
+ch03/data/dataset-379-20news-18828_EYKCY.zip
+ch03/data/379/raw/alt.atheism/100-53167
+ch03/data/379/raw/
+ch03/data/379/
+ch03/charts/
+playGround/user-basket/data/raw_user.csv

ch03/noise_analysis.py

@@ -40,6 +40,7 @@ def build_analyzer(self):
 forpostinpost_group]
 graphics=sorted([postforpostinallifpost[2] =='comp.graphics'])
 print(graphics[5])
+
 # (245, 'From: [email protected]\nSubject: test....(sorry)\nOrganization:
 # The University of Birmingham, United Kingdom\nLines: 1\nNNTP-Posting-Host: ibm3090.bham.ac.uk
 # \n\n==============================================================================\n',

ch03/plot_kmeans_example.py

@@ -1,3 +1,4 @@
+# coding=utf-8
 # This code is supporting material for the book
 # Building Machine Learning Systems with Python
 # by Willi Richert and Luis Pedro Coelho
@@ -26,6 +27,7 @@
 defplot_clustering(x, y, title, mx=None, ymax=None, xmin=None, km=None):
 pylab.figure(num=None, figsize=(8, 6))
 ifkm:
+# x,y 是数组，zip后变成一个元组的数列
 pylab.scatter(x, y, s=50, c=km.predict(list(zip(x, y))))
 else:
 pylab.scatter(x, y, s=50)
@@ -41,7 +43,8 @@ def plot_clustering(x, y, title, mx=None, ymax=None, xmin=None, km=None):
 
 returnpylab
 
-
+# http://www.wolframalpha.com/input/?i=exp(-x**2%2F2)%2Fsqrt(2*pi)
+# 正态分布的随机数，一共20个。loc是分布的中心点
 xw1=norm(loc=0.3, scale=.15).rvs(20)
 yw1=norm(loc=0.3, scale=.15).rvs(20)