def testVeryShort():
WORD_OCCURRENCES = {
'airport': 348996,
'request': 2816909,
'wandered': 451106
}
LETTER_FREQ = [
0.03104758705050717, 0.0, 0.0, 0.03500991824543893, 0.2536276129665047,
0.0, 0.0, 0.0, 0.013542627927787708, 0.0, 0.0, 0.0, 0.0,
0.017504959122719464, 0.013542627927787708, 0.013542627927787708,
0.10930884736053291, 0.15389906233882777, 0.10930884736053291,
0.12285147528832062, 0.10930884736053291, 0.0, 0.017504959122719464,
0.0, 0.0, 0.0
]
print('Testing with very_short.csv...')
words = wordData.readWordFile('very_short.csv')
# test totalOccurrences
for word in words:
print('Total occurrences of', word + ':',
'OK' if wordData.totalOccurrences(word, words) == WORD_OCCURRENCES[word] \
else 'GOT: ' + str(wordData.totalOccurrences(word, words)) +
', EXPECTED: ' + str(WORD_OCCURRENCES[word]))
freqList = letterFreq.letterFreq(words)
for ch, got, expected in zip(string.ascii_lowercase, freqList,
LETTER_FREQ):
print(
'Frequency of', ch + ':', 'OK' if got == expected else 'GOT: ' +
str(got) + ', EXPECTED: ' + str(expected))
def main():
file = input("Enter the name of a file to read: ")
words = wordData.readWordFile(file)
print(words)
word = input("Enter word you want to count the occurences of: ")
print(totalOccurrences(word, words))
def testA():
WORD_OCCURRENCES = {
'airplane': 2487028,
'alien': 5400198,
'accept': 26299474
}
LETTER_FREQ_STRING = 'andetsrliocupgmybhvfwkxqjz'
print('Testing with a.txt...\n')
words = wordData.readWordFile('a.txt')
# test totalOccurrences
for word in WORD_OCCURRENCES:
print('Total occurrences of', word + ':',
'OK' if wordData.totalOccurrences(word, words) == WORD_OCCURRENCES[word] \
else 'GOT: ' + str(wordData.totalOccurrences(word, words)) +
', EXPECTED: ' + str(WORD_OCCURRENCES[word]))
freqString = letterFreq.letterFreq(words)
if freqString == LETTER_FREQ_STRING:
print('\nFrequency ordering of letters OK')
else:
print('Frequency ordering of letters incorrect.')
print('GOT: ' + freqString)
print('EXPECTED: ' + LETTER_FREQ_STRING)
def main():
file = input("Enter the name of a file to read: ")
words = wordData.readWordFile(file)
start = input("Enter starting year: ")
end = input("Enter ending year: ")
trends = (trending(words, float(start), float(end)))
print("")
print("The top 10 trending words from", start, "to", end, ":")
for x in trends[:10]:
print(x.word)
print("")
print("The bottom 10 trending words from", start, "to", end, ":")
mylist = []
for x in trends[-10:]:
mylist.append(x.word)
mylist.reverse()
for i in mylist:
print(i)
def testA():
"""
Test function for 'a.txt'.
:return: None
:rtype: NoneType
"""
# expected results
# each tuple contains startYr/endYr/index/word
# index 0 is the highest trending word, -1 is lowest
TRENDS = ((1927, 1931, 0, 'av'), (1927, 1931, -1, 'acetate'),
(1950, 1952, 0, 'antibiotics'), (1950, 1952, -1, 'atque'),
(1966, 1975, 0, 'algorithms'), (1966, 1975, -3, 'aeroplanes'),
(1981, 2008, 1, 'authentication'), (1981, 2008, -2, 'antisera'))
print('Testing with a.txt...\n')
words = wordData.readWordFile('a.txt')
for idx in range(len(TRENDS)):
print("testing: ", TRENDS[idx][0], "to", TRENDS[idx][1])
trendList = trending.trending(words, TRENDS[idx][0], TRENDS[idx][1])
if (trendList[TRENDS[idx][2]].word == TRENDS[idx][3]):
print("OK!")
else:
print("got:", trendList[TRENDS[idx][2]].word)
print("expected: ", TRENDS[idx][3])
def testVeryShort():
"""
Test function for 'very_short.csv'.
:return: None
:rtype: NoneType
"""
# expected results
AIRPORT_2007 = 175702
REQUEST_2004 = 0
AVG_WORD_LENGTH_2007 = 7.110627395031065
AVG_WORD_LENGTH_2004 = 0
AVG_WORD_LENGTHS_2005_2008 = [
7.1147602294958, # 2005
7.114548770228398, # 2006
7.110627395031065, # 2007
7.150069236398865 # 2008
]
print('Testing with very_short.csv...')
words = wordData.readWordFile('very_short.csv')
# test occurrencesInAYear
occurrences = wordLength.occurrencesInYear('airport', 2007, words)
print('Occurrences of "airport" in 2007:',
'OK' if occurrences == AIRPORT_2007
else 'GOT: ' + str(occurrences) +
', EXPECTED: ' + str(AIRPORT_2007))
occurrences = wordLength.occurrencesInYear('request', 2004, words)
print('Occurrences of "request" in 2004:',
'OK' if occurrences == REQUEST_2004
else 'GOT: ' + str(occurrences) +
', EXPECTED: ' + str(REQUEST_2004))
# test averageWordLength
length = wordLength.averageWordLength(2007, words)
print('Average word length in 2007:',
'OK' if length == AVG_WORD_LENGTH_2007
else 'GOT: ' + str(length) +
', EXPECTED: ' + str(AVG_WORD_LENGTH_2007))
length = wordLength.averageWordLength(2004, words)
print('Average word length in 2004:',
'OK' if length == AVG_WORD_LENGTH_2004
else 'GOT: ' + str(length) +
', EXPECTED: ' + str(AVG_WORD_LENGTH_2004))
# averageWordLengthYears
lengthsList = wordLength.averageWordLengthYears(2005, 2008, words)
yearList = list(range(2005, 2009))
for year, got, expected in zip(yearList, lengthsList,
AVG_WORD_LENGTHS_2005_2008):
print('Average word length for', str(year) + ':',
'OK' if got == expected else
'GOT:' + str(got) +
', EXPECTED: ' + str(expected))
def testVeryShort():
"""
Test function for 'very_short.csv'.
:return: None
:rtype: NoneType
"""
# expected results
AIRPORT_2007 = 175702
REQUEST_2004 = 0
AVG_WORD_LENGTH_2007 = 7.110627395031065
AVG_WORD_LENGTH_2004 = 0
AVG_WORD_LENGTHS_2005_2008 = [
7.1147602294958, # 2005
7.114548770228398, # 2006
7.110627395031065, # 2007
7.150069236398865 # 2008
]
print('Testing with very_short.csv...')
words = wordData.readWordFile('very_short.csv')
# test occurrencesInAYear
occurrences = wordLength.occurrencesInYear('airport', 2007, words)
print(
'Occurrences of "airport" in 2007:',
'OK' if occurrences == AIRPORT_2007 else 'GOT: ' + str(occurrences) +
', EXPECTED: ' + str(AIRPORT_2007))
occurrences = wordLength.occurrencesInYear('request', 2004, words)
print(
'Occurrences of "request" in 2004:',
'OK' if occurrences == REQUEST_2004 else 'GOT: ' + str(occurrences) +
', EXPECTED: ' + str(REQUEST_2004))
# test averageWordLength
length = wordLength.averageWordLength(2007, words)
print(
'Average word length in 2007:',
'OK' if length == AVG_WORD_LENGTH_2007 else 'GOT: ' + str(length) +
', EXPECTED: ' + str(AVG_WORD_LENGTH_2007))
length = wordLength.averageWordLength(2004, words)
print(
'Average word length in 2004:',
'OK' if length == AVG_WORD_LENGTH_2004 else 'GOT: ' + str(length) +
', EXPECTED: ' + str(AVG_WORD_LENGTH_2004))
# averageWordLengthYears
lengthsList = wordLength.averageWordLengthYears(2005, 2008, words)
yearList = list(range(2005, 2009))
for year, got, expected in zip(yearList, lengthsList,
AVG_WORD_LENGTHS_2005_2008):
print(
'Average word length for',
str(year) + ':', 'OK' if got == expected else 'GOT:' + str(got) +
', EXPECTED: ' + str(expected))
def main():
fileName=input("Enter word file: ")
words=wordData.readWordFile(fileName)
word=input("Enter word: ")
occ=wordData.totalOccurrences(word,words)
print("Total occurrences of ",word,":",occ)
print("Letter frequencies: ",letterFreq(words))
print("# plot is displayed")
freqList=letterFreq(words)
letterHist.letterFreqPlot(freqList)
input("Enter to exit")
def main():
"""
The main fucntion.
:return None
:rtype: NoneType
"""
fileName = input("Enter word file: ")
words = wordData.readWordFile(fileName)
freqList = wordFrequencies(words)
rank = int(input("Enter rank" + str((1,len(freqList))) + ":"))
print("Rank",rank,":", freqList[rank - 1])
simplePlot.wordFreqPlot(freqList)
def main():
fileName=input("Enter word file: ")
words=wordData.readWordFile(fileName)
word=input("Enter a word: ")
year=int(input("Enter a year: "))
occ=occurrencesInYear(word,year,words)
print("The word ",'"',word+'"',"occurred ",occ,"times in the year ",year)
year2=int(input("Enter a year: "))
avg=averageWordLength(year2,words)
print("The average word length for the year ",year2,"is ",avg," letters")
startYear=int(input("Enter a star year: "))
endYear=int(input("Enter an end year: "))
print("# plot is displayed")
lengthsList=averageWordLengthYears(startYear,endYear,words)
simplePlot.averageWordLengthPlot(startYear, endYear, lengthsList)
def main():
"""
The main function.
:return None
:rtype: NoneType
"""
fileName = input("Enter word file: ")
word = input("Enter word: ")
words = wordData.readWordFile(fileName)
print("Total occurrences of", word, ":",
wordData.totalOccurrences(word, words))
freqList = letterFreq(words)
print("Letter frequencies:", freqList)
letterHist.letterFreqPlot(freqList)
input("Hit Enter to EXIT")
def testVeryShort():
WORD_OCCURRENCES = {'airport' : 348996,
'request' : 2816909,
'wandered' : 451106}
LETTER_FREQ = [0.03104758705050717,
0.0,
0.0,
0.03500991824543893,
0.2536276129665047,
0.0,
0.0,
0.0,
0.013542627927787708,
0.0,
0.0,
0.0,
0.0,
0.017504959122719464,
0.013542627927787708,
0.013542627927787708,
0.10930884736053291,
0.15389906233882777,
0.10930884736053291,
0.12285147528832062,
0.10930884736053291,
0.0,
0.017504959122719464,
0.0,
0.0,
0.0]
print('Testing with very_short.csv...')
words = wordData.readWordFile('very_short.csv')
# test totalOccurrences
for word in words:
print('Total occurrences of', word + ':',
'OK' if wordData.totalOccurrences(word, words) == WORD_OCCURRENCES[word] \
else 'GOT: ' + str(wordData.totalOccurrences(word, words)) +
', EXPECTED: ' + str(WORD_OCCURRENCES[word]))
freqList = letterFreq.letterFreq(words)
for ch, got, expected in zip(string.ascii_lowercase, freqList, LETTER_FREQ):
print('Frequency of', ch + ':',
'OK' if got == expected else 'GOT: ' + str(got) +
', EXPECTED: ' + str(expected))
def main():
file = input("Enter word file: ")
words = wordData.readWordFile(file)
year = input("Enter year: ")
solution = summaryFromWords(words, int(year))
small = solution[0]
q1 = solution[1]
med = solution[2]
q3 = solution[3]
large = solution[4]
print("minimum: ", small)
print("1st quartile: ", q1)
print("median: ", med)
print("3rd quartile ", q3)
print("maximum: ", large)
boxAndWhisker.boxAndWhisker(small, q1, med, q3, large)
def main():
"""
The main function.
:return None
:rtype: NoneType
"""
fileName = input("Enter word file: ")
word = input("Enter a word: ")
year = int(input("Enter a year: "))
words = wordData.readWordFile(fileName)
totalOccur = occurrencesInYear(word, year, words)
print("The word",'"',word,'"', "occurred", totalOccur, \
"times in the year", year)
year = int(input("Enter a year: "))
avgWordLength = averageWordLength(year, words)
print("The average word length for the year", year,\
"is", avgWordLength, "letters")
startYear = int(input("Enter a start year: "))
endYear = int(input("Enter an end year: "))
lengthsList = averageWordLengthYears(startYear, endYear, words)
simplePlot.averageWordLengthPlot(startYear, endYear, lengthsList)
def testVeryShort():
"""
Test function for 'very_short.csv'.
:return: None
:rtype: NoneType
"""
# Expected results from the q words
MOST_FREQ_WORD = wordData.WordCount('request', 2816909)
SECOND_MOST_FREQ_WORD = wordData.WordCount('wandered', 451106)
LEAST_FREQ_WORD = wordData.WordCount('airport', 348996)
# read in the words
print('Testing with very_short.csv...')
words = wordData.readWordFile('very_short.csv')
# get the frequency of WordCount objects
freqList = wordFreq.wordFrequencies(words)
# test most frequent, second most frequent, and least frequent word
print('Most frequent word: ',
'OK' if freqList[0].word == MOST_FREQ_WORD.word and
freqList[0].count == MOST_FREQ_WORD.count
else 'GOT: '+ str(freqList[0]) +
', EXPECTED: ' + str(MOST_FREQ_WORD))
print('Second most frequent word: ',
'OK' if freqList[1].word == SECOND_MOST_FREQ_WORD.word and
freqList[1].count == SECOND_MOST_FREQ_WORD.count
else 'GOT: '+ str(freqList[1]) +
', EXPECTED: ' + str(SECOND_MOST_FREQ_WORD))
print('Least frequent word: ',
'OK' if freqList[2].word == LEAST_FREQ_WORD.word and
freqList[2].count == LEAST_FREQ_WORD.count
else 'GOT: '+ str(freqList[2]) +
', EXPECTED: ' + str(LEAST_FREQ_WORD))
def testVeryShort():
"""
Test function for 'very_short.csv'.
:return: None
:rtype: NoneType
"""
# Expected results from the q words
MOST_FREQ_WORD = wordData.WordCount('request', 2816909)
SECOND_MOST_FREQ_WORD = wordData.WordCount('wandered', 451106)
LEAST_FREQ_WORD = wordData.WordCount('airport', 348996)
# read in the words
print('Testing with very_short.csv...')
words = wordData.readWordFile('very_short.csv')
# get the frequency of WordCount objects
freqList = wordFreq.wordFrequencies(words)
# test most frequent, second most frequent, and least frequent word
print(
'Most frequent word: ', 'OK' if freqList[0].word == MOST_FREQ_WORD.word
and freqList[0].count == MOST_FREQ_WORD.count else 'GOT: ' +
str(freqList[0]) + ', EXPECTED: ' + str(MOST_FREQ_WORD))
print(
'Second most frequent word: ',
'OK' if freqList[1].word == SECOND_MOST_FREQ_WORD.word
and freqList[1].count == SECOND_MOST_FREQ_WORD.count else 'GOT: ' +
str(freqList[1]) + ', EXPECTED: ' + str(SECOND_MOST_FREQ_WORD))
print(
'Least frequent word: ',
'OK' if freqList[2].word == LEAST_FREQ_WORD.word
and freqList[2].count == LEAST_FREQ_WORD.count else 'GOT: ' +
str(freqList[2]) + ', EXPECTED: ' + str(LEAST_FREQ_WORD))
def testZ():
"""
Test function for 'z.txt'.
:return: None
:rtype: NoneType
"""
# Expected results from z.txt
WORDS = ((1900, 136049), (1931, 155940), (1964, 581610), (2008, 2450556))
# read in the words
print('Testing with z.txt...')
words = wordData.readWordFile('z.txt')
# get the list of words for each year
wordsByYearList = printedWords.printedWords(words)
for idx in range(len(WORDS)):
print("Testing year", WORDS[idx][0])
got = printedWords.wordsForYear(WORDS[idx][0], wordsByYearList)
if (got == WORDS[idx][1]):
print("OK")
else:
print("GOT:", got, "EXPECTED:", WORDS[idx][1])
def testFileName(filename, year, expected):
"""
testFileName: String NatNum (NatNum or Float)^5 -> Boolean
"""
return test(summaryFromWords(readWordFile(filename), year), expected)
def main():
file = input("Enter the name of a file to read: ")
words = wordData.readWordFile(file)
print(letterFreq(words))
