# Homework 2-4, CSCI 0931 2013 # Much of the code for this activity is provided for you. Skeleton code is # provided for the parts you must complete. Specifically, I've defined some # function signatures and descriptions. The function signature is the line that # begin with "def" and specifies the names of the function and its arguments. # The function description comes right after the signature --- it's the string # in triple quotes that says what the function does. # # Complete all the parts marked "TODO". Fill in functions so that their # behavior matches their description, and run some test cases to make sure. # The next line is needed to provide built-in tools for cleaning up text and # splitting it into words. We'll discuss these tools, called "regular # expressions" later in the semester. import re # Examples with dictionaries (pay attentions to the use of [] and {}): inventory = {} # This creates an empty dictionary. inventory = {'orange':5, 'apple':3, 'banana':5, 'mango':4} inventory['peach'] = 10 # Add a new key and its value to a dictionary. inventory['banana'] = 9 # Update the value of a key already in the dictionary. numOfBananas = inventory['banana'] # Get the value associated with a key. for k in inventory.keys(): # Iterate through dictionary keys. print(k) print(inventory[k]) # Your name here: TODO # Here is dictionary of movies with their box office grosses. # The keys are movie titles (strings) and the values are domestic revenues, # adjusted for inflation (integers). # This dictionary is made so that you have some data to test your functions. # Again, your functions should perform correctly on ANY input. domesticGrosses = {'Snow White and the Seven Dwarfs':868730000, 'Avatar':775124500, 'Return of the Jedi':749653500, 'Jurassic Park':687060600, 'Gone with the Wind':1610295700, 'The Graduate':682004000, 'The Empire Strikes Back':782499700, 'Star Wars':1419613200, 'The Sound of Music':1135050500, 'Pirates of the Caribbean: Dead Mans Chest':515088100, 'The Lion King':615537400, 'The Godfather':629012900, 'Forrest Gump':626008500, 'The Lord of the Rings: The Return of the King':490459000, 'My Fair Lady':478200000, 'Harry Potter and the Sorcerers Stone':445626500, 'Spider-Man':553793400, 'The Dark Knight':592028200, 'Titanic':1022916700, 'E.T.':1130579000} def printMovieNames(movie_dict): '''Given a dictionary of movies and revenues, print out the movie names.''' keys = movie_dict.keys() for k in keys: print(k) return # TODO: Write a function that prints out the revenues instead. def printMovieRevenues(dict): ''' Given a dictionary of movies and revenues, print out the revenues.''' # TODO: Fill in the function body so it matches the description. return def startsWithTHE(dict): '''Given a dictionary of movies and revenues, return a dictionary of all the movies whose titles start with the word 'The', and their revenues.''' result = {} for k in dict.keys(): if k[0:3] == 'The': result[k] = dict[k] return result def hugeMovies(dict): '''Given a dictionary of movies and revenues, return a dictionary of all the movies that grossed over one billion dollars.''' # TODO: Fill in the function body so that the function behaves according to # its description. return dict # This is not the correct answer. Change it to what you compute! # TODO: Write a function that takes a movie-revenue dictionary as input, and # returns the title of the movie that had the highest revenue. It's a pretty # complicated function, so here are some steps to guide you (or you can ignore # them if you prefer): # 1. Create two variables called biggestMovieSoFar and biggestRevenueSoFar. # (What should their initial values be?) # 2. Iterate through all movies in your input, and for each one, do the # following # a. Compare its revenue to biggestRevenueSoFar # b. If its revenue is bigger, update biggestRevenueSoFar to be this bigger # revenue, and update biggestMovieSoFar to be its title. # c. Otherwise do nothing # 3. At the end, your biggestMovieSoFar should hold the name of the highest # grossing movie. Convince yourself why. def biggestMovie(dict): '''Given a dictionary of movies and revenues, return the title of the highest-grossing movie.''' # TODO: Fill in the function body so that the function behaves according to # its description. return 'Gigli' # This is not correct. Compute and return the right answer. def buildConcordance(text): '''Given a string, returns a dictionary that maps unique words in the string to lists of integers. The integers in each list are positions of the occurrences of that word in the string.''' concordance = {} # Start with an empty dictionary. text = text.lower() # The next few lines are basically the same as cleaning up the text, # splitting it into a list of words, and iterating over that list. However, # we've used regular expressions to do this more efficiently, while also # easily keeping track of the position in the string where each word is # found. Don't worry too much about how this works; we'll cover it more in # class. iter = re.finditer(r"\w+", text) for match in iter: # Iterate through all matches to the pattern. word = match.group(0) # This is the matched string. position = match.start(0) # This is the position where it was found. print(word + ": " + str(position)) # TODO: Fill in the rest of this loop so that the function does what # its description says it should do. return concordance def testBuildConcordance(): # TODO: Fill in three test cases here. Return False if any one of them # fails; return True if they all pass. def printConcordance(word, concord, text): ''' Given a word, a concordance (dictionary) and the original text, Prints all occurrences of the word with a little bit of context surrounding each occurence.''' # TODO: Implement this function. return # The following string is for testing purposes. test_text = '''Call me Ishmael. Some years ago--never mind how long precisely--having little or no money in my purse, and nothing particular to interest me on shore, I thought I would sail about a little and see the watery part of the world. ''' def testPrintConcordance(): # TODO: Fill in five test cases here. Since printConcordance() just prints # out values and doesn't return anything, there's no way to programmatically # test whether each call does the right thing or not. Instead, just write # five calls to printConcordance, following each one by a series of print() # calls that print the expected output. You can use the variable test_text, # defined above, in this function. # Read something interesting from a file into s when you are ready to test on # big texts. For example, you could use something like the following line. # s = open('C:\\WinData\\Desktop\\MobyDick.txt').read() conc = build_concordance(test_text) print_concordance('i', conc, test_text)