exercise6.py

def gaussianKernel(x1, x2, sigma):
    return np.exp(-np.sum(np.square(x1 - x2)) / (2 * (sigma ** 2)))

def dataset3Params(X, y, Xval, yval):
    C_candidates = np.array([0.01, 0.03, 0.1, 0.3, 1, 3, 10, 30])
    sigma_candidates = np.array([0.01, 0.03, 0.1, 0.3, 1, 3, 10, 30])
    distance = np.zeros([C_candidates.size, sigma_candidates.size])
    
    for i in range(C_candidates.size):
        for j in range(sigma_candidates.size):
            model = utils.svmTrain(X, y, C_candidates[i], gaussianKernel, args=(sigma_candidates[j],))
            predictions = utils.svmPredict(model, Xval)
            distance[i, j] = np.mean(predictions != yval)

    # https://numpy.org/doc/stable/reference/generated/numpy.argmin.html    
    ind = np.unravel_index(np.argmin(distance, axis = None), distance.shape)
    
    C = C_candidates[ind[0]]
    sigma = sigma_candidates[ind[1]]
    
    return C, sigma


def processEmail(email_contents, verbose=True):
    """
    Preprocesses the body of an email and returns a list of indices 
    of the words contained in the email.    
    
    Parameters
    ----------
    email_contents : str
        A string containing one email. 
    
    verbose : bool
        If True, print the resulting email after processing.
    
    Returns
    -------
    word_indices : list
        A list of integers containing the index of each word in the 
        email which is also present in the vocabulary.
    
    Instructions
    ------------
    Fill in this function to add the index of word to word_indices 
    if it is in the vocabulary. At this point of the code, you have 
    a stemmed word from the email in the variable word.
    You should look up word in the vocabulary list (vocabList). 
    If a match exists, you should add the index of the word to the word_indices
    list. Concretely, if word = 'action', then you should
    look up the vocabulary list to find where in vocabList
    'action' appears. For example, if vocabList[18] =
    'action', then, you should add 18 to the word_indices 
    vector (e.g., word_indices.append(18)).
    
    Notes
    -----
    - vocabList[idx] returns a the word with index idx in the vocabulary list.
    
    - vocabList.index(word) return index of word `word` in the vocabulary list.
      (A ValueError exception is raised if the word does not exist.)
    """
    # Load Vocabulary
    vocabList = utils.getVocabList()

    # Init return value
    word_indices = []

    # ========================== Preprocess Email ===========================
    # Find the Headers ( \n\n and remove )
    # Uncomment the following lines if you are working with raw emails with the
    # full headers
    # hdrstart = email_contents.find(chr(10) + chr(10))
    # email_contents = email_contents[hdrstart:]

    # Lower case
    email_contents = email_contents.lower()
    
    # Strip all HTML
    # Looks for any expression that starts with < and ends with > and replace
    # and does not have any < or > in the tag it with a space
    email_contents =re.compile('<[^<>]+>').sub(' ', email_contents)

    # Handle Numbers
    # Look for one or more characters between 0-9
    email_contents = re.compile('[0-9]+').sub(' number ', email_contents)

    # Handle URLS
    # Look for strings starting with http:// or https://
    email_contents = re.compile('(http|https)://[^\s]*').sub(' httpaddr ', email_contents)

    # Handle Email Addresses
    # Look for strings with @ in the middle
    email_contents = re.compile('[^\s]+@[^\s]+').sub(' emailaddr ', email_contents)
    
    # Handle $ sign
    email_contents = re.compile('[$]+').sub(' dollar ', email_contents)
    
    # get rid of any punctuation
    email_contents = re.split('[ @$/#.-:&*+=\[\]?!(){},''">_<;%\n\r]', email_contents)

    # remove any empty word string
    email_contents = [word for word in email_contents if len(word) > 0]
    
    # Stem the email contents word by word
    stemmer = utils.PorterStemmer()
    processed_email = []
    for word in email_contents:
        # Remove any remaining non alphanumeric characters in word
        word = re.compile('[^a-zA-Z0-9]').sub('', word).strip()
        word = stemmer.stem(word)
        processed_email.append(word)

        if len(word) < 1:
            continue


        if word in vocabList:
            word_indices.append(vocabList.index(word))

    if verbose:
        print('----------------')
        print('Processed email:')
        print('----------------')
        print(' '.join(processed_email))
    return word_indices

def emailFeatures(word_indices):
    n = 1899

    x = np.zeros(n)

    x[word_indices] = 1    
    
    return x