Added files and solutions for Regular Expressions exercises

regex/chap08_1_classification.py

+""" Regular expressions: Challenge 1 - Experiments
+
+Author: Josiah Wang
+"""
+
+import re
+import sys
+
+def load_report(filename):
+    """ Read in scikit-learn report from a text file.
+        
+    Args:
+        filename (str) : Path to file containing the scikit-learn report
+    
+    Returns:
+        str : Content of the file 
+    """ 
+    with open(filename) as report_file:
+        content = report_file.read()
+        return content
+        
+    
+def extract_accuracy(content):
+    """ Extract accuracy from a scikit-learn report.
+        
+    Args:
+        content (str) : Content of the report.
+        
+    Returns:
+        float : The accuracy
+    """
+    pattern = "accuracy\s*(\d.\d+)\s*(?:\d+)"
+    match = re.search(pattern, content)
+    if match is not None:
+        return float(match.group(1))
+    else:
+        return 0.
+
+def extract_f1(content):
+    """ Prints the f1-score from a scikit-learn report.
+        
+    Args:
+        content (str) : Content of the report.
+    """    
+    pattern = "(\d+)\s*(?:\d.\d+)\s*(?:\d.\d+)\s*(\d.\d+)\s*(?:\d+)"
+    iterator = re.finditer(pattern, content)
+    for match in iterator:
+        print(f"f1-score for class {match.group(1)} = {match.group(2)}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) > 1:
+        filename = sys.argv[1]
+    else:
+        filename = "classification1.txt"
+    
+    content = load_report(filename)
+    
+    accuracy = extract_accuracy(content)
+    print(accuracy)
+    
+    extract_f1(content)
\ No newline at end of file

regex/chap08_2_grocery.py

+""" Regular expressions: Challenge 2 - Grocery shopping
+
+Author: Josiah Wang
+"""
+
+import re
+import sys
+
+def load_receipt(filename):
+    """ Read in receipt from a text file.
+        
+    Args:
+        filename (str) : Path to file containing the receipt
+    
+    Returns:
+        str : Content of the file 
+    """ 
+    with open(filename) as report_file:
+        content = report_file.read()
+        return content
+        
+        
+def extract_groceries(receipt):
+    """ Extract grocery items from a receipt
+        
+    Args:
+        receipt (str) : Content of the receipt.
+        
+    Returns:
+        list[tuple] : List of (item name, price)
+    """
+    pattern = "([\w ]+?)\s*\d+\s*£(\d+.\d+)[DV]"
+    iterator = re.finditer(pattern, receipt)
+    groceries = [(match.group(1), float(match.group(2))) for match in iterator]
+    return groceries
+    
+
+def extract_total(receipt):
+    """ Extract total from a receipt
+        
+    Args:
+        receipt (str) : Content of the receipt.
+        
+    Returns:
+        float : total as listed on the receipt
+    """
+    pattern = "TOTAL\s*£(\d+.\d+)"
+    match = re.search(pattern, receipt)
+    if match is not None:
+        return float(match.group(1))
+    else:
+        return 0.
+   
+   
+if __name__ == "__main__":
+    if len(sys.argv) > 1:
+        filename = sys.argv[1]
+    else:
+        filename = "receipt.txt"
+    
+    receipt = load_receipt(filename)
+    
+    groceries = extract_groceries(receipt)
+    print(groceries)
+
+    listed_total = extract_total(receipt)
+    print(listed_total)
+    
+    calculated_total = sum([price for (name, price) in groceries])
+    print(calculated_total)
+    
+    assert abs(listed_total - calculated_total) < 0.000000001 
\ No newline at end of file

regex/chap08_3_email.py

+""" Regular expressions: Challenge 3 - Harvesting emails
+
+Author: Josiah Wang
+"""
+
+import re
+import sys
+
+def load_email(filename):
+    """ Read in email from a text file.
+        
+    Args:
+        filename (str) : Path to file containing the email
+    
+    Returns:
+        str : Content of the email 
+    """ 
+    with open(filename) as report_file:
+        content = report_file.read()
+        return content
+
+
+def extract_recipients(email):
+    """ Find the To: field and extract the recipients list
+        
+    Args:
+        email (str) : Content of the email.
+        
+    Returns:
+        str : the recipients list
+    """
+    pattern = "To: (.*)\n"
+    match = re.search(pattern, email)
+    if match is not None:
+        return match.group(1)
+    else:
+        return ""
+    
+
+def print_student_emails(email):
+    """ Print list of students and their emails
+        
+    Args:
+        email (str) : Content of the email.
+        
+    Returns:
+        float : total as listed on the receipt
+    """
+    # Find the recipients list from the TO: field first
+    recipients = extract_recipients(email)
+        
+    # Then extract each recipient from the list
+    pattern = '"([A-Za-z ]+)" <(.*?)>'
+    iterator = re.finditer(pattern, recipients)
+    for match in iterator:
+        print(f"{match.group(1)}, {match.group(2)}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) > 1:
+        filename = sys.argv[1]
+    else:
+        filename = "email.txt"
+    
+    email = load_email(filename)
+    print_student_emails(email)
+    
\ No newline at end of file

regex/chap08_4_staff.py

+""" Regular expressions: Challenge 4 - Screen scraper
+
+Author: Josiah Wang
+"""
+
+import re
+import sys
+
+def load_html(filename):
+    """ Read in HTML source from a text file.
+        
+    Args:
+        filename (str) : Path to file containing the HTML source
+    
+    Returns:
+        str : Content of the HTML source
+    """ 
+    with open(filename) as report_file:
+        # Need to make sure that whitespace is removed from start and end of 
+        # line for easier regex matching
+        content = "\n".join([line.strip() for line in report_file])
+        return content
+        
+def print_staff_info(html):
+    """ Extract and print staff info from HTML source
+        
+    Args:
+        html (str) : Content of the HTML source.
+    """
+    
+    # Regex is sensitive to space!
+    pattern = re.compile('''
+<div class="name-wrapper">
+<h4>Personal details</h4>
+(?:<a class="name-link" target="_blank" href="(.*?)">)?<span class="person-name">(.*?)</span>(?:</a>)?
+<span class="job-title">(?:.*?)</span>
+<p class="contact"><a class="email" href="mailto:(.*?)">Send email</a>(?:<span class="tel">(?:.*?)</span>)?</p>
+</div>''')
+
+    matches = pattern.finditer(html)
+    for match in matches:
+        print(f"{match.group(2)}, {match.group(3)}, {match.group(1)}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) > 1:
+        filename = sys.argv[1]
+    else:
+        filename = "staff.txt"
+    
+    html = load_html(filename)
+    print_staff_info(html)
+    
\ No newline at end of file

regex/classification1.txt

+              precision    recall  f1-score   support
+
+           0       0.90      0.95      0.92        19
+           1       0.91      0.77      0.83        13
+           2       0.86      0.92      0.89        13
+
+    accuracy                           0.89        45
+   macro avg       0.89      0.88      0.88        45
+weighted avg       0.89      0.89      0.89        45

regex/classification2.txt

+              precision    recall  f1-score   support
+
+           0       0.97      0.80      0.88        75
+           1       0.80      0.85      0.82        52
+           2       0.83      0.93      0.87        41
+           3       0.82      0.81      0.82        52
+           4       0.79      0.88      0.83        51
+
+    accuracy                           0.85       271
+   macro avg       0.84      0.85      0.84       271
+weighted avg       0.85      0.85      0.85       271

regex/email.txt

+MIME-Version: 1.0
+Date: Wed, 21 Oct 2020 11:02:52 +0100
+Message-ID: <AdJIE+ww21321@xx.yy.com>
+Subject: Hello Pythonistas
+From: The Boss <the.boss@abc.ac.uk>
+To: "Don Garrett" <don.garrett@food.bz>, "Daryl Sears" <daryl.sears@defg.com>, "Szymon Walmsley" <szymon.walmsley@ijk.ac.uk>, "Frances Hurst" <frances.hurst@silly.org>, "Teegan Moses" <teegan.moses@silly.org>, "Klay Prentice" <klay.prentice@abc.ac.uk>, "Campbell Bowden" <campbell.bowden@pretty.edu>, "Karan Cuevas" <karan.cuevas@pretty.edu>, "Heidi Gardner" <heidi.gardner@somewhere.co.uk>, "Phoenix Mcclain" <phoenix.mcclain@abc.ac.uk>, "Bertha Connor" <bertha.connor@something.info>, "Kimberly Poole" <kimberly.poole@email.net>, "Jamil Munro" <jamil.munro@silly.org>, "Anton Britton" <anton.britton@silly.org>, "Tasha Harvey" <tasha.harvey@bba.com>, "Alexie Cantu" <alexie.cantu@ijk.ac.uk>, "Philip Chung" <philip.chung@pretty.edu>, "Kaisha Pearson" <kaisha.pearson@food.bz>, "Malika Huber" <malika.huber@bba.com>, "Jayce Aguilar" <jayce.aguilar@abc.ac.uk>
+Content-Type: text/plain; charset="UTF-8"
+
+Hi Pythonistas,
+
+Welcome to our class! I hope you enjoy this task!
+
+Best wishes,
+The Boss
+
+-- 
+The Boss does not need a signature. 

regex/receipt.txt

+ASDA SUPERMARKETS LTD.
+WWW.ADSA.COM
+TELEPHONE   0123 456 7890
+
+W MILK 4 PT    000002033217        £1.09D
+CANNED FRUIT   002400000143        £1.00D
+FRESH CREAM    505043902070        £1.85D
+BLUEBERRIES    505085498023        £1.56D
+GARLIC         000000001783        £0.78D
+SALAD          505478123059        £0.60D
+ICE LOLLIES    506002991123        £2.00V
+FROZEN VEG     505085427534        £1.10D
+BM MADELEINES  502978543211        £2.00D
+                       TOTAL      £11.98
+                        CARD      £11.98
+                   TOTAL EPS      £11.98
+
+            24/10/20   17:12:53
+                CHANGE DUE         £0.00
+PLEASE KEEP THIS COPY FOR YOUR RECORDS
+          No. ITEMS SOLD 9
+