def read_all(reread=False):
global words, sent
for i in dt.get_all_books():
if dt.no_description(i) or reread:
words = {}
sent = {}
read(i)
out = sorted(words.items(), key=lambda t: -t[1])
dt.save_words_as(out, i)
out = sorted(sent.items(), key=lambda t: t[0])
dt.save_words_as(out, i, 'sentenses')
def read_all(reread=False):
global words, sent, gramm, letters, unknown, combinations
global denials, names, multi_text
for i in dt.get_all_books():
if dt.no_description(i) or reread:
words = {}
sent = {}
gramm = {}
particals = {}
unknown = {}
combinations = {}
names = {'Name': 0, 'Surn': 0, 'Patr': 0, 'Fake': 0, 'Geox': 0}
denials = 0
letters = dict([(chr(j), 0) for j in range(1072, 1104)])
letters['ё'] = 0
multi_text = []
read(i)
gramm['denials'] = denials
save_read(i)
print(i + ' read.')
def sum_norm(x, A, B, C, D, E, F):
return A*np.e**(B*(x+C)**2)+D*np.e**(E*(x+F)**2)
def alternative(x, A, B, C, D , E, F, G, H):
return (A*x**5+B*x**4+C*x**3+D*x**2+E*x+F)*np.e**(x*H+G)
def norm(x, A, B, C):
return A*np.e**(-B*(x+C)**2)
NUMBER = 700
styles=['-','--','-.',':','']
books = dt.get_all_books()
#books = dt.get_books_by("Толстой Лев Николаевич", prop='author')
#books = ["Толстой Лев Николаевич#Война и мир#1",# "Толстой Лев Николаевич#Война и мир#2",
#"Толстой Лев Николаевич#Война и мир#3", "Толстой Лев Николаевич#Война и мир#4",
#"Толстой Лев Николаевич#Анна Каренина", "Тургенев Иван Сергеевич#Отцы и дети",
# "Достоевский Федор Михайлович#Преступление и наказание", "Неизвестный автор#Война и мир"]
all_y = {}
for i in books:
toConsider = dt.get_words(i,'sentenses')
all_y = dt.sum_dicts(all_y, dict(toConsider))
#[:NUMBER]
#C = sum(list(map(lambda t: t[1], dt.get_words(i))))
# print(C)
#y = np.array(list(map(lambda t: t[1], toConsider)))
# x = np.array(list(map(lambda t: t[0], toConsider)))
import sentence_length_comparator
import matplotlib.pyplot as plt
import math_worker as mt
import math
SQUARE_FUNCTION = lambda l1, l2: (l2 - l1)**2
SQUARE_FUNCTION.__name__ = 'SQUARE_FUNCTION'
##ABS_FUNCTION = lambda l1, l2: abs(l2 - l1)
##ABS_FUNCTION.__name__ = 'ABS_FUNCTION'
##POW_FUNCTION = lambda l1, l2: 2**(l2 - l1) - 1
##POW_FUNCTION.__name__ = 'POW_FUNCTION'
##LOG_FUNCTION = lambda l1, l2: abs(math.log(l1+1)-math.log(l2+1))
##LOG_FUNCTION.__name__ = 'LOG_FUNCTION'
##
all_data = dt.get_all_books()
prop_stack = ['letters', 'grammatics', 'combinations', 'sentences', 'unknown']
f_aviable = [SQUARE_FUNCTION]
##for p in range(1,10):
## for i in range(1,10):
## f = lambda l1, l2: (abs(l1-l2)**p)
## f.__name__ = str(p) + '#' + str(i)
## f_aviable.append(f)
methods = {}
rating = {}
while prop_stack:
prop_name = prop_stack[-1]
import data_worker as dt
for i in dt.get_all_books():
f = open(dt.get_file(i), 'r')
text = f.read()
f.close()
while True:
i1 = text.find('[')
i2 = text.find(']', i1)
if i1 == -1 or i2 == -1:
break
text = text[:i1] + text[i2 + 1:]
f = open(dt.get_file(i), 'w')
f.write(text)
f.close()