Update

Author: gdancik

assignments.md

@@ -14,6 +14,7 @@ Note: all Assignments are due at the beginning of class unless noted otherwise
     * [logs.zip]({{ site.baseurl }}/data/hw/logs.zip)
 * [Lab #3: Python]({{ site.baseurl }}/data/hw/lab3-python.py) (Due: Monday, 2/11/19)
 * [Lab #4: MapReduce]({{ site.baseurl }}/data/hw/MapReduce-hw.pdf) (Due: Wednesday, 2/20/19)
+    * [lab4_help.py]({{ site.baseurl }}/data/hw/lab4_help.py)
     * [customers.zip]({{ site.baseurl }}/data/hw/customers.zip)
 * [Lab #5: MySQL]({{ site.baseurl }}/data/hw/MySQL.pdf) (Due: Wednesday, 3/06/19)
 * [Lab #6: Sqoop, Impala, and Hive]({{ site.baseurl }}/data/hw/sqoop.pdf) (Due: Wednesday, 3/20/19)

data/hw/lab4_help.py

@@ -0,0 +1,39 @@
+# Sample Code for Lab 4
+
+# Sample Code to Remove Punctuation
+
+import string
+  
+# the string module includes punctuation characters
+print("punctuation characters:", string.punctuation)
+
+# create a translation table, which says to delete all characters specified in
+# the third argument (i.e., to delete all punctuation)
+t = str.maketrans('', '', string.punctuation)
+
+# example string
+s = "Look! Hey!?"
+
+# call the translate function which translates string based on the translation table
+# in this case, all punctuation is removed
+new_s = s.translate(t)
+
+print(s)
+print(new_s)
+
+
+# Sample code to work with a set (a collection of unique values)
+
+# If you have a list, you can remove duplicate values by converting to a set
+l = ['a','b','c','a'] # create a list containing 'a','b','c', and 'a'
+s = set(l) # convert from a list to a set, which will contain only 'a','b',and 'c'
+print(s)
+print(','.join(s)) # print a comma-separated string of values
+
+# You can keep a set of unique values as you go, by starting with an empty set 
+s = set() # start with an empty set
+s.add('a') # add an 'a'
+s.add('b') # add a 'b'
+s.add('a') # 'a' is not added, since it already exists in the set
+print(s)  # the set contains only 'a','b'
+