def count(self):
parser, opc = self.optionParser()
# Przekazanie argumentow
filel = opc.lines
filew = opc.words
# Wyjatek od liczby argumentow i przekazanie nazwy pliku
if (filew == "non" and opc.lines == "non") or (filew != "non" and opc.lines != "non"):
parser.error("niepoprawna liczba argumentow")
elif filew != "non" and filel == "non":
file = filew
print("wybrales liczenie SLOW\n")
elif filew == "non" and filel != "non":
file = filel
print("wybrales liczenie LINII\n")
# Nazwa pliku
print("plik do odczytu: %s\n" % file)
if filel != "non":
line_count.line_count(file)
if filew != "non":
word_count.word_count(file)
def search():
question_id = request.form['question-id']
max_num = int(request.form['max-num'])
record_txt_path = ''
result_dir_path = './word_count_results/'
# ------数据库写在下面，input: 问题ID---------------------------
# -----output: 1.待处理文本的txt文件路径-2.用问题ID和问题内容填充questions变量
questions = '<tr><td>1</td><td>你认为世界上最厉害的人是谁？</td><tr>'
if question_id == '1':
# 把响应id的问题答案写入下面这个路径的文件即可
record_txt_path = './answer-content.txt'
# -------------------------数据库写在上面-------------------------------------
word_count.word_count(input_file_path=record_txt_path,
output_dir_path=result_dir_path,
max_num=max_num)
def _txt_to_html(txt_path, title):
txt_in = open(txt_path)
def _read_file(file_in) -> 'html-str':
result = ''
for line in file_in:
result += '<tr><td>' + line.strip() + '</td></tr>\n'
return result
html = _read_file(txt_in)
html = '<table class="result-table" border="1"><tr><th>' + \
title+'</th></tr>\n'+html+'</table>'
txt_in.close()
return html
adjective_html = _txt_to_html(result_dir_path + 'adjective.txt', '形容词')
adverb_html = _txt_to_html(result_dir_path + 'adverb.txt', '副词')
noun_html = _txt_to_html(result_dir_path + 'noun.txt', '名词')
postposition_html = _txt_to_html(result_dir_path + 'postposition.txt',
'介词')
verb_html = _txt_to_html(result_dir_path + 'verb.txt', '动词')
results_html = '''
<div class="row">
<div class="col">%s</div>
<div class="col">%s</div>
<div class="col">%s</div>
<div class="col">%s</div>
<div class="col">%s</div>
</div>
''' % (adjective_html, adverb_html, noun_html, postposition_html,
verb_html)
return render_template('entry.html',
title='知乎问题答案分析',
results=results_html,
questions=questions)
def total_assets(arr):
text3=arr
total_assets = 0
for i in text3:
istring=i.split(' ')
cntstr=len(fnmatch.filter(istring,'20??'))
if(cntstr>1):break
for k in text3:
k=k.replace("|","")
k=k.replace("_","")
k=k.replace("=","")
k=k.replace("—-","")
k=k.replace("$","")
k=k.replace("W","")
if(k.split(" ")[0].isalpha()==False):
k=k.replace(k.split(" ")[0],"")
for l in range(0,len(assets['Assets'])):
if(word_count(k.lower())==word_count(assets['Assets'][l].lower())):
print("k identifier"+" "+k)
print("assets"+" "+assets['Assets'][l])
if(k.lower().find(assets['Assets'][l].lower())!=-1):
bal_str=k.lower().replace(assets['Assets'][l].lower(),"")
bal_str=bal_str.replace("|","")
bal_lst=bal_str.split(" ")
print(bal_lst)
bal_lst1=[]
for j in range(0,len(bal_lst)):
if(bal_lst[j] !=''):bal_lst1.append(bal_lst[j])
bal_lst=bal_lst1
if(len(bal_lst)>cntstr):
for m in range(0,((len(bal_lst))-cntstr)):
bal_lst.pop(0)
if(len(bal_lst)!=0):
str_ng=bal_lst[0].replace(",","")
str_ng=str_ng.replace(".","")
if((str_ng.isdigit()==True or str_ng.isdigit()==True) and (assets['Assets'][l].lower()=="total assets") and word_count(k.lower())==word_count("total assets")):
total_assets=float(bal_lst[0].replace(",",""))
print ("hh %s" %total_assets)
break
if(str_ng.isdigit()==True or str_ng.isdigit()==True):
total_assets=total_assets+ float(bal_lst[0].replace(",",""))
print ("gg %s" %total_assets)
elif(bal_lst[0]=="-"):
total_assets=total_assets+ float(bal_lst[0].replace("-","0"))
print ("kk %s" %total_assets)
if(k.lower().find("total assets")!=-1 and word_count(k.lower())==word_count("total assets")):
break
return total_assets
def main():
counter = word_count()
filereader = file_reader()
db_access = database_access()
# load folder linked to read the word documents
if (os.environ.get('MONITOREDFOLDER') == None):
monitoredfolder = './words/'
else:
monitoredfolder = os.environ.get('MONITOREDFOLDER')
while True:
# List all files in the folder
onlyfiles = [
f for f in listdir(monitoredfolder)
if isfile(join(monitoredfolder, f))
]
# create log folder
if not exists(monitoredfolder + 'logs/'):
makedirs(monitoredfolder + 'logs/')
# configure Log
logging.basicConfig(filename=monitoredfolder +
'logs/document_import.log',
level=logging.INFO)
logging.info(str(len(onlyfiles)) + " New Files")
# Process Single new File if there is one
if len(onlyfiles) != 0:
words = filereader.read(onlyfiles[0])
result = counter.count(words)
for key in result:
# update count for each word in the dictionary of the currenct file
db_access.add_value_to_word_count(key, result[key])
else:
time.sleep(60)
def test_tabs(self):
self.assertEqual(
{'rah': 2, 'ah': 3, 'roma': 2, 'ma': 1, 'ga': 2, 'oh': 1, 'la': 2,
'want': 1, 'your': 1, 'bad': 1, 'romance': 1},
word_count('rah rah ah ah ah\troma roma ma\tga ga oh la la\t'
'want your bad romance')
)
def words_of_diaries(dir='diaries'):
for file in os.listdir(os.path.join(os.getcwd(), dir)):
counter = word_count(os.path.join(os.getcwd(), dir, file))
results = sorted(counter, key=lambda k: counter[k], reverse=True)
maxes = list(
takewhile(lambda e: counter[e] == counter[results[0]], results))
print file, ':', maxes
def test_tabs(self):
self.assertEqual(
{'rah': 2, 'ah': 3, 'roma': 2, 'ma': 1, 'ga': 2, 'oh': 1, 'la': 2,
'want': 1, 'your': 1, 'bad': 1, 'romance': 1},
word_count('rah rah ah ah ah\troma roma ma\tga ga oh la la\t'
'want your bad romance')
)
def test_newlines(self):
self.assertEqual(
{'rah': 2, 'ah': 3, 'roma': 2, 'ma': 1, 'ga': 2, 'oh': 1, 'la': 2,
'want': 1, 'your': 1, 'bad': 1, 'romance': 1},
word_count('rah rah ah ah ah\nroma roma ma\n'
'ga ga oh la la\nwant your bad romance')
)
def test_newlines(self):
self.assertEqual(
{'rah': 2, 'ah': 3, 'roma': 2, 'ma': 1, 'ga': 2, 'oh': 1, 'la': 2,
'want': 1, 'your': 1, 'bad': 1, 'romance': 1},
word_count('rah rah ah ah ah\nroma roma ma\n'
'ga ga oh la la\nwant your bad romance')
)
def test_ignores_punctuation(self):
assert word_count('car : carpet as java : javascript!!&@$%^&') == {
'car': 1,
'carpet': 1,
'as': 1,
'java': 1,
'javascript': 1
}
def test_non_alphanumeric(self):
assert word_count('hey,my_spacebar_is_broken.') == {
'hey': 1,
'my': 1,
'spacebar': 1,
'is': 1,
'broken': 1
}
def test_count_multiple_occurences(self):
self.assertEqual({
'one': 1,
'fish': 4,
'two': 1,
'red': 1,
'blue': 1
}, word_count('one fish two fish red fish blue fish'))
def test_apostrophes(self):
assert word_count("First: don't laugh. Then: don't cry.") == {
'first': 1,
"don't": 2,
'laugh': 1,
'then': 1,
'cry': 1
}
def test_count(self):
count = word_count("toy.txt")
self.assertTrue("asdf" not in count)
self.assertEqual(count.get("coffers", 0), 1)
self.assertEqual(count.get("And", 0), 5)
self.assertEqual(count.get("honourable", 0), 5)
self.assertEqual(count.get("Caesar", 0), 4)
self.assertEqual(count.get("Caesar,", 0), 2)
def test_non_alphanumeric(self):
self.assertEqual(word_count('hey,my_spacebar_is_broken.'), {
'hey': 1,
'my': 1,
'spacebar': 1,
'is': 1,
'broken': 1
})
def test_count_multiple_occurrences_of_a_word(self):
self.assertEqual(word_count('one fish two fish red fish blue fish'), {
'one': 1,
'fish': 4,
'two': 1,
'red': 1,
'blue': 1
})
def test_apostrophes(self):
self.assertEqual(word_count("First: don't laugh. Then: don't cry."), {
'first': 1,
"don't": 2,
'laugh': 1,
'then': 1,
'cry': 1
})
def test_quotations(self):
assert word_count("Joe can't tell between 'large' and large.") == {
'joe': 1,
"can't": 1,
'tell': 1,
'between': 1,
'large': 2,
'and': 1
}
def word_count_article(dir):
result={}
for article in os.listdir(dir):
dic=wc.word_count(dir+article)
print(dic)
key,count=max(list(dic.items()),key=lambda d:d[1] )
result[str(article)]=key
return result
def test_ignores_punctuation(self):
self.assertEqual(
word_count('car : carpet as java : javascript!!&@$%^&'), {
'car': 1,
'carpet': 1,
'as': 1,
'java': 1,
'javascript': 1
})
def test_word_count(self):
# x = word_count("")
# self.assertTrue(x == {})
# x = word_count("Hello hello")
# self.assertTrue(x == {"hello": 2})
x = word_count('Hello, my cat. And my cat doesn\'t say "hello" back.')
self.assertTrue(x == {'hello': 2, 'my': 2, 'cat': 2, 'and': 1, "doesn't": 1, 'say': 1, 'back': 1})
x = word_count('This is a test of the Emergency Broadcast Network. This is only a test.')
self.assertTrue(x == {'this': 2, 'is': 2, 'a': 2, 'test': 2, 'of': 1, 'the': 1, 'emergency': 1, 'broadcast': 1, 'network': 1, 'only': 1})
x = word_count('":;,.-+=/\\|[]{}()*^&')
self.assertTrue(x == {})
x = word_count('a a\ra\na\ta \t\r\n')
self.assertTrue(x == {"a": 5})
def net_worth(arr):
text3=arr
net_worth = 0
for i in text3:
istring=i.split(' ')
cntstr=len(fnmatch.filter(istring,'20??'))
if(cntstr>1):break
for k in text3:
k=k.replace("|","")
k=k.replace("_","")
k=k.replace("=","")
if(k.split(" ")[0].isalpha()==False):
k=k.replace(k.split(" ")[0],"")
for l in range(0,len(netWorth['Networth'])):
if(word_count(k.lower())==word_count(netWorth['Networth'][l].lower())):
print("k identifier"+" "+k)
print("networt"+" "+netWorth['Networth'][l])
if(k.lower().find(netWorth['Networth'][l].lower())!=-1):
bal_str=k.lower().replace(netWorth['Networth'][l].lower(),"")
bal_str=bal_str.replace("|","")
bal_lst=bal_str.split(" ")
bal_lst1=[]
for j in range(0,len(bal_lst)):
if(bal_lst[j] !=''):bal_lst1.append(bal_lst[j])
bal_lst=bal_lst1
if(len(bal_lst)>cntstr):
for m in range(0,((len(bal_lst))-cntstr)):
bal_lst.pop(0)
if(len(bal_lst)!=0):
str_ng=bal_lst[0].replace(",","")
str_ng=str_ng.replace(".","")
if((str_ng.isdigit()==True or str_ng.isdigit()==True) and (netWorth['Networth'][l].lower()=="total equity") and word_count(k.lower())==word_count("total equity")):
net_worth=float(bal_lst[0].replace(",",""))
print ("hh %s" %net_worth)
break
if(str_ng.isdigit()==True or str_ng.isdigit()==True):
net_worth=net_worth+ float(bal_lst[0].replace(",",""))
print ("gg %s" %net_worth)
elif(bal_lst[0]=="-"):
net_worth=net_worth+ float(bal_lst[0].replace("-","0"))
print ("kk %s" %net_worth)
if(k.lower().find("total equity")!=-1 and word_count(k.lower())==word_count("total equity")):
break
return net_worth
def test_quotations(self):
self.assertDictEqual(
word_count("Joe can't tell between 'large' and large."), {
'joe': 1,
"can't": 1,
'tell': 1,
'between': 1,
'large': 2,
'and': 1
})
def test_apostrophes(self):
self.assertEqual(
word_count("First: don't laugh. Then: don't cry."),
{
"first": 1,
"don't": 2,
"laugh": 1,
"then": 1,
"cry": 1
},
)
def test_ignores_punctuation(self):
self.assertEqual(
word_count("car : carpet as java : javascript!!&@$%^&"),
{
"car": 1,
"carpet": 1,
"as": 1,
"java": 1,
"javascript": 1
},
)
def test_count_multiple_occurrences_of_a_word(self):
self.assertEqual(
word_count("one fish two fish red fish blue fish"),
{
"one": 1,
"fish": 4,
"two": 1,
"red": 1,
"blue": 1
},
)
def test_non_alphanumeric(self):
self.assertEqual(
word_count("hey,my_spacebar_is_broken."),
{
"hey": 1,
"my": 1,
"spacebar": 1,
"is": 1,
"broken": 1
},
)
def test_quotations(self):
self.assertEqual(
word_count("Joe can't tell between 'large' and large."),
{
"joe": 1,
"can't": 1,
"tell": 1,
"between": 1,
"large": 2,
"and": 1
},
)
def draw_histogram(file_name):
with open(file_name) as f:
words = f.read()
words = word_count(words)
sorted_words = sorted(words.items(), key=lambda x: (-x[1], x[0]))
longest_word = max(len(w) for w in words)
for x in sorted_words:
res = " " * (longest_word - len(x[0]) + 2)
for _ in range(x[1]):
res += "#"
print(f"{x[0].lower()}{res}")
def fquncy(s):
wordkey = word_count(s)
quincy = {}
for w in wordkey:
hertz = wordkey[w]
if hertz in quincy:
quincy[hertz].append(w)
else:
quincy[hertz] = [w]
hzs = list(quincy.keys())
hzs.sort(reverse=True)
for f in hzs:
for word in quincy[f]:
print(word, ' ' * (20 - len(word)), '#' * f)
def main():
# get data
try:
df_raw = pd.read_csv('df_raw.csv')
except IOError:
articles = ['articles1.csv', 'articles2.csv', 'articles3.csv']
df_raw = get_data(articles)
df_raw.to_csv('df_raw.csv')
# word count and df initialization
try:
stats_by_pub = pd.read_csv('stats_by_pub.csv')
print(stats_by_pub)
print('stats on disk')
except IOError:
stats_by_pub = word_count(df_raw)
stats_by_pub.to_csv('stats_by_pub.csv')
def test_tabs(self):
self.assertEqual(
word_count("rah rah ah ah ah\troma roma ma\tga ga oh la la\t"
"want your bad romance"),
{
"rah": 2,
"ah": 3,
"roma": 2,
"ma": 1,
"ga": 2,
"oh": 1,
"la": 2,
"want": 1,
"your": 1,
"bad": 1,
"romance": 1,
},
)
def test_word_count():
expected = {
'2000': 1,
'Green': 1,
'Hop': 1,
'Splash': 1,
'and': 2,
'cool': 1,
'in': 2,
'legs': 1,
'lily': 1,
'logs': 1,
'on': 4,
'pads': 1,
'speckled': 1,
'water': 2
}
filename = 'testfile.txt'
assert expected == word_count(filename)
def test_multiple_spaces_not_detected_as_a_word(self):
self.assertEqual(
word_count(' multiple whitespaces'),
{'multiple': 1, 'whitespaces': 1}
)
def test_cramped_list(self):
self.assertEqual(
word_count('one,two,three'),
{'one': 1, 'two': 1, 'three': 1}
)
import sys from word_count import word_count word_count(instances=int(sys.argv[1]))
def test_mixed_case(self):
self.assertEqual(
word_count('go Go GO Stop stop'),
{'go': 3, 'stop': 2}
)
def test_expanded_list(self):
self.assertEqual(
word_count('one,\ntwo,\nthree'),
{'one': 1, 'two': 1, 'three': 1}
)
def test_count_one_of_each(self):
self.assertEqual(
{'one': 1, 'of': 1, 'each': 1},
word_count('one of each')
)
def test_count_multiple_occurrences_of_a_word(self):
self.assertEqual(
word_count('one fish two fish red fish blue fish'),
{'one': 1, 'fish': 4, 'two': 1, 'red': 1, 'blue': 1}
)
def test_unicode(self):
self.assertEqual(
{decode_if_needed('аДаО'): 1, decode_if_needed('баВаИаДаАаНаИб'): 1},
word_count('аДаО№баВаИаДаАаНаИб!')
)
def test_count_multiple_occurences(self):
self.assertEqual(
{'one': 1, 'fish': 4, 'two': 1, 'red': 1, 'blue': 1},
word_count('one fish two fish red fish blue fish')
)
def test_apostrophes(self):
self.assertEqual(
word_count("First: don't laugh. Then: don't cry."),
{'first': 1, "don't": 2, 'laugh': 1, 'then': 1, 'cry': 1}
)
def test_multiple_spaces(self):
self.assertEqual(
{'wait': 1, 'for': 1, 'it': 1},
word_count('wait for it')
)
from word_count import word_count word_count(instances=1) word_count(instances=10) word_count(instances=20)
def test_include_numbers(self):
self.assertEqual(
{'testing': 2, '1': 1, '2': 1},
word_count('testing 1 2 testing')
)
def test_ignores_punctuation(self):
self.assertEqual(
{'car': 1, 'carpet': 1, 'as': 1, 'java': 1, 'javascript': 1},
word_count('car : carpet as java : javascript!!&@$%^&')
)
def test_non_alphanumeric(self):
self.assertEqual(
{'hey': 1, 'my': 1, 'spacebar': 1, 'is': 1, 'broken': 1},
word_count('hey,my_spacebar_is_broken.')
)
def test_count_one_word(self):
self.assertEqual(
{'word': 1},
word_count('word')
)
def test_mixed_case(self):
self.assertEqual(
[2, 3],
sorted(list(word_count('go Go GO Stop stop').values()))
)
def test_quotations(self):
self.assertEqual(
word_count("Joe can't tell between 'large' and large."),
{'joe': 1, "can't": 1, 'tell': 1, 'between': 1, 'large': 2,
'and': 1}
)
