Code Files Added

Author: packtpavanr

Chapter02/Listings.txt

@@ -0,0 +1,30 @@
+1.  loop1.py
+2.  loop2.py
+3.  codecomments.py
+4.  codecomments2.py
+5.  codecomments3.py
+6.  codecomments4.py
+7.  codecomments5.py
+8.  codecomments6.py
+9.  codecomments7.py
+10. a1.py
+11. b1.py
+12. a2.py
+13. a_text.py
+14. b_text.py
+15. a_text2.py
+16. b_text2.py
+17. textrank.py
+18. urlrank.py
+19. rankbase.py
+20. textrank2.py
+21. urlrank2.py
+22. power.py
+23. factorial.py
+24. metrictest1.py
+25. metrictest2.py
+26. metrictest_fix1.py
+27. metrictest_fix2.py
+28. metrictest.py
+
+

Chapter02/Listings.txt~

@@ -0,0 +1,32 @@
+Listing #       Filename
+                
+1           -   loop1.py
+2           -   loop2.py
+3           -   codecomments.py
+4           -   codecomments2.py
+5           -   codecomments3.py
+6           -   codecomments4.py
+7           -   codecomments5.py
+8           -   codecomments6.py
+9           -   codecomments7.py
+10          -   a1.py
+11          -   b1.py
+12          -   a2.py
+13          -   a_text.py
+14          -   b_text.py
+15          -   a_text2.py
+16          -   b_text2.py
+17          -   textrank.py
+18          -   urlrank.py
+19          -   rankbase.py
+20          -   textrank2.py
+21          -   urlrank2.py
+22          -   power.py
+23          -   factorial.py
+24          -   metrictest1.py
+25          -   metrictest2.py
+26          -   metrictest_fix1.py
+27          -   metrictest_fix2.py
+28          -   metrictest.py
+
+

Chapter02/a1.py

@@ -0,0 +1,33 @@
+# Code listing #10
+
+""" Module A (a.py) - Implement functions that operate on series of numbers """
+
+# Note this is version 1 of a.py so called a1.py
+
+def squares(narray):
+    """ Return array of squares of numbers """
+    return pow_n(array, 2)
+
+def cubes(narray):
+    """ Return array of cubes of numbers """
+    return pow_n(narray, 3)
+
+def pow_n(narray, n):
+    """ Return array of numbers raised to arbitrary power n each """
+    return [pow(x, n) for x in narray]
+    
+def frequency(string, word):
+    """ Find the frequency of occurrences of word in string
+    as percentage """
+
+    word_l = word.lower()
+    string_l = string.lower()
+
+    # Words in string
+    words = string_l.split()
+    count = w.count(word_l)
+
+    # Return frequency as percentage
+    return 100.0*count/len(words)
+
+

Chapter02/a2.py

@@ -0,0 +1,17 @@
+# Code listing #12
+
+""" Module A (a.py) - Implement functions that operate on series of numbers """
+
+# Note - this is rewritten version of a1, so called a2.py
+
+def squares(narray):
+    """ Return array of squares of numbers """
+    return pow_n(array, 2)
+
+def cubes(narray):
+    """ Return array of cubes of numbers """
+    return pow_n(narray, 3)
+
+def pow_n(narray, n):
+    """ Return array of numbers raised to arbitrary power n each """
+    return [pow(x, n) for x in narray]

Chapter02/a_text.py

@@ -0,0 +1,28 @@
+# Code listing #13
+
+""" Module A (a.py) - Provides string processing functions """
+
+# Note - this is the text processing version of a, so called a_text.py
+
+import b_text as b
+
+def ntimes(string, char):
+    """ Return number of times character 'char' 
+    occurs in string """
+    
+    return string.count(char)
+
+def common_words(text1, text2):
+    """ Return common words across text1 and text2 """
+    
+    # A text is a collection of strings split using newlines
+    strings1 = text1.split(“\n”)
+    strings2 = text2.split(“\n”)
+    
+    common = []
+    for string1 in strings1:
+        for string2 in strings2:
+            common += b.common(string1, string2)
+        
+    # Drop duplicates
+    return list(set(common))

Chapter02/a_text2.py

@@ -0,0 +1,32 @@
+# Code listing #15
+
+""" Module A (a.py) - Provides string processing functions """
+
+# Note - This is the rewritten version of a_text.py so called a_text2.py
+
+def ntimes(string, char):
+    """ Return number of times character 'char' 
+    occurs in string """
+
+    return string.count(char)
+
+def common(string1, string2):
+    """ Return common words across strings1 1 & 2 """
+    
+    s1 = set(string1.lower().split())
+    s2 = set(string2.lower().split())
+    return s1.intersection(s2)  
+
+def common_words(text1, text2):
+    """ Return common words across text1 and text2 """
+    
+    # A text is a collection of strings split using newlines
+    strings1 = text1.split("\n")
+    strings2 = text2.split("\n")
+    
+    common_w = []
+    for string1 in strings1:
+        for string2 in strings2:
+            common_w += common(string1, string2)
+
+    return list(set(common_w))

Chapter02/b1.py

@@ -0,0 +1,32 @@
+# Code listing #11
+
+""" Module B (b.py) - Implement functions provide some statistical methods """
+
+# Note - this is version 1 of b, so called b1.py
+
+import a1 as a
+
+def rms(narray):
+    """ Return root mean square of array of numbers"""
+
+    return pow(sum(a.squares(narray)), 0.5)
+
+def mean(array):
+    """ Return mean of an array of numbers """
+
+    return 1.0*sum(array)/len(array)
+
+def variance(array):
+    """ Return variance of an array of numbers """
+    
+    # Square of variation from mean
+    avg = mean(array)
+    array_d = [(x - avg) for x in array]
+    variance = sum(a.squares(array_d))
+    return variance
+
+def standard_deviation(array):
+    """ Return standard deviation of an array of numbers """
+    
+    # S.D is square root of variance
+    return pow(variance(array), 0.5)

Chapter02/b_text.py

@@ -0,0 +1,22 @@
+# Code listing #14
+
+""" Module B (b.py) - Provides text processing functions to user """
+
+# Note: This is the text processing version of b so called b_text.py
+
+import a_text as a
+
+def common(string1, string2):
+    """ Return common words across strings1 1 & 2 """
+
+    s1 = set(string1.lower().split())
+    s2 = set(string2.lower().split())
+    return s1.intersection(s2)  
+
+def common_words(filename1, filename2):
+    """ Return common words across two input files """
+
+    lines1 = open(filename1).read()
+    lines2 = open(filename2).read()
+
+    return a.common_words(lines1, lines2)

Chapter02/b_text2.py

@@ -0,0 +1,15 @@
+# Code listing #16
+
+""" Module B (b.py) - Provides text processing functions to user """
+
+# Note: This is the rewritten version of b_text.py so called b_text2.py
+
+import a_text2 as a
+
+def common_words(filename1, filename2):
+    """ Return common words across two input files """
+    
+    lines1 = open(filename1).read()
+    lines2 = open(filename2).read()
+    
+    return a.common_words(lines1, lines2)

Chapter02/codecomments.py

@@ -0,0 +1,26 @@
+# Code listing #3
+
+# This loop performs a network fetch of the URL, retrying upto 3
+# times in case of errors. In case the URL cant be fetched, 
+# an error is returned.
+
+# Initialize all state
+count, ntries, result, error = 0, 3, None, None
+while count < ntries:
+        try:
+            # NOTE: We are using an explicit timeout of 30s here
+            result = requests.get(url, timeout=30)
+        except Exception as error:
+            print('Caught exception', error, 'trying again after a while')
+            # increment count
+            count += 1
+            # sleep 1 second every time
+            time.sleep(1)
+    
+    if result == None:
+        print("Error, could not fetch URL",url)
+        # Return a tuple of (<return code>, <lasterror>)
+        return (2, error)
+
+      # Return data of URL
+      return result.content

Chapter02/codecomments2.py

@@ -0,0 +1,28 @@
+# Code listing #4
+
+def fetch_url(url, ntries=3, timeout=30):
+         " Fetch a given url and return its contents "
+
+        # This loop performs a network fetch of the URL, retrying upto      
+        # 3 times in case of errors. In case the URL cant be fetched,       
+        # an error is returned.
+
+        # Initialize all state
+        count, result, error = 0, None, None
+        while count < ntries:
+            try:
+                result = requests.get(url, timeout=timeout)
+            except Exception as error:
+                print('Caught exception', error, 'trying again after a while')
+                # increment count
+                count += 1
+                # sleep 1 second every time
+                time.sleep(1)
+    
+        if result == None:
+            print("Error, could not fetch URL",url)
+            # Return a tuple of (<return code>, <lasterror>)
+            return (2, error)
+    
+        # Return data of URL
+        return result.content

Chapter02/codecomments3.py

@@ -0,0 +1,38 @@
+# Code listing #5
+
+def fetch_url(url, ntries=3, timeout=30):
+        """ Fetch a given url and return its contents. 
+        
+        @params
+            url - The URL to be fetched.
+            ntries - The maximum number of retries.
+            timeout - Timout per call in seconds.
+    
+        @returns
+            On success - Contents of URL.
+            On failure - (error_code, last_error)
+        """
+
+        # This loop performs a network fetch of the URL, retrying upto      
+        # 'ntries' times in case of errors. In case the URL cant be 
+        # fetched, an error is returned.
+
+        # Initialize all state
+        count, result, error = 0, None, None
+        while count < ntries:
+            try:
+                result = requests.get(url, timeout=timeout)
+            except Exception as error:
+                print('Caught exception', error, 'trying again after a while')
+                # increment count
+                count += 1
+                # sleep 1 second every time
+                time.sleep(1)
+    
+        if result == None:
+            print("Error, could not fetch URL",url)
+            # Return a tuple of (<return code>, <lasterror>)
+            return (2, error)
+    
+        # Return data of the URL
+        return result.content

Chapter02/codecomments4.py

@@ -0,0 +1,54 @@
+# Code listing #6
+
+class UrlFetcher(object):
+         """ Implements the steps of fetching a URL.
+
+        Main methods:
+            fetch - Fetches the URL.
+            get - Return the URLs data.
+        """
+
+        def __init__(self, url, timeout=30, ntries=3, headers={}):
+            """ Initializer. 
+            @params
+                url - URL to fetch.
+                timeout - Timeout per connection (seconds).
+                ntries - Max number of retries.
+                headers - Optional request headers.
+            """
+            self.url = url
+            self.timeout = timeout
+            self.ntries = retries
+            self.headers = headers
+            # Enapsulated result object
+            self.result = result 
+
+        def fetch(self):
+            """ Fetch the URL and save the result """
+    
+            # This loop performs a network fetch of the URL, retrying 
+            # upto 'ntries' times in case of errors. 
+
+            count, result, error = 0, None, None
+            while count < self.ntries:
+                try:
+                    result = requests.get(self.url,
+                                          timeout=self.timeout,
+                                          headers = self.headers)
+                except Exception as error:
+                    print('Caught exception', error, 'trying again after a while')
+                    # increment count
+                    count += 1
+                    # sleep 1 second every time
+                    time.sleep(1)
+
+            if result != None:
+                # Save result
+                self.result = result
+    
+        def get(self):
+            """ Return the data for the URL """
+
+            if self.result != None:
+                return self.result.content
+