def update():
global mylist
i = j = 0
mylist[:]= []
key = input("enter student's tp")
myf = open("data.txt","r+")
ml = myf.readlines()
#print(ml[1])
for line in ml:
words = line.split()
mylist.append(words)
print(mylist)
l = len(mylist)
w = len(words)
print(w)
print(l)
for i in range(l):
for j in range(w):
print(mylist[i][j])
## if(key == mylist[i][j]):
## print("found at ",i,j)
## del mylist[i][j]
## mylist[i].insert((j+1), "xxx")
below is the error
print(mylist[i][j])
IndexError: list index out of range
I am trying to update contents in a file. I am saving the file in a list as lines and each line is then saved as another list of words. So "mylist" is a 2D list but it is giving me error with index
Your l variable is the length of the last line list. Others could be shorter.
A better idiom is to use a for loop to iterate over a list.
But there is an even better way.
It appears you want to replace a "tp" (whatever that is) with the string xxx everywhere. A quicker way to do that would be to use regular expressions.
import re
with open('data.txt') as myf:
myd = myf.read()
newd = re.sub(key, 'xxx', myd)
with open('newdata.txt', 'w') ad newf:
newf.write(newd)
Related
I have a code which iterates through the text, and tells me which is the maximum amount of times each dna STR is found. The only step missing to be able to match these values with the CSV file, is to store them into a list, BUT I AM NOT ABLE TO DO SO. When I run the code, the maximum values are printed independently for each STR sequence.
I have tried to "append" the values into a list, but I was not successful, thus, I cannot match it with the dna sequences of the CSV (large nor small).
Any help or advcise is greatly appreciated!
Here is my code, and the results I get with using "text 1" and "small csv":
`
import cs50
import sys
import csv
import os
if len(sys.argv) != 3:
print("Usage: python dna.py data.csv sequence.txt")
csv_db = sys.argv[1]
file_seq = sys.argv[2]
with open(csv_db, newline='') as csvfile: #with open(csv_db) as csv_file
csv_reader = csv.reader(csvfile, delimiter=',')
header = next(csv_reader)
i = 1
while i < len(header):
STR = header[i]
len_STR = len(STR)
with open(file_seq, 'r') as my_file:
file_reader = my_file.read()
counter = 0
a = 0
b = len_STR
list = []
for text in file_reader:
if file_reader[a:b] != STR:
a += 1
b += 1
else:
counter += 1
a += len_STR
b += len_STR
list.append(counter)
print(list)
i += 1
`
The problem is in place of variable "list" declaration. Every time you iterates through STRs in variable "header" you declares:
list = []
Thus, you create absolutely new variable, which stores only the length of current STR. To make a list with all STRs appended you need to declare variable "list" before the while loop and operator "print" after the while loop:
list = []
while i < len(header):
<your loop code>
print(list)
This should solve your problem.
P.S. Avoid to use "list" as a variable declaration. The "list" is a python built-in function and it is automatically declared. So, when you redeclare it, you will not be able to use list() function in your code.
Alien Dictionary
Link to the online judge -> LINK
Given a sorted dictionary of an alien language having N words and k starting alphabets of standard dictionary. Find the order of characters in the alien language.
Note: Many orders may be possible for a particular test case, thus you may return any valid order and output will be 1 if the order of string returned by the function is correct else 0 denoting incorrect string returned.
Example 1:
Input:
N = 5, K = 4
dict = {"baa","abcd","abca","cab","cad"}
Output:
1
Explanation:
Here order of characters is
'b', 'd', 'a', 'c' Note that words are sorted
and in the given language "baa" comes before
"abcd", therefore 'b' is before 'a' in output.
Similarly we can find other orders.
My working code:
from collections import defaultdict
class Solution:
def __init__(self):
self.vertList = defaultdict(list)
def addEdge(self,u,v):
self.vertList[u].append(v)
def topologicalSortDFS(self,givenV,visited,stack):
visited.add(givenV)
for nbr in self.vertList[givenV]:
if nbr not in visited:
self.topologicalSortDFS(nbr,visited,stack)
stack.append(givenV)
def findOrder(self,dict, N, K):
list1 = dict
for i in range(len(list1)-1):
word1 = list1[i]
word2 = list1[i+1]
rangej = min(len(word1),len(word2))
for j in range(rangej):
if word1[j] != word2[j]:
u = word1[j]
v = word2[j]
self.addEdge(u,v)
break
stack = []
visited = set()
vlist = [v for v in self.vertList]
for v in vlist:
if v not in visited:
self.topologicalSortDFS(v,visited,stack)
result = " ".join(stack[::-1])
return result
#{
# Driver Code Starts
#Initial Template for Python 3
class sort_by_order:
def __init__(self,s):
self.priority = {}
for i in range(len(s)):
self.priority[s[i]] = i
def transform(self,word):
new_word = ''
for c in word:
new_word += chr( ord('a') + self.priority[c] )
return new_word
def sort_this_list(self,lst):
lst.sort(key = self.transform)
if __name__ == '__main__':
t=int(input())
for _ in range(t):
line=input().strip().split()
n=int(line[0])
k=int(line[1])
alien_dict = [x for x in input().strip().split()]
duplicate_dict = alien_dict.copy()
ob=Solution()
order = ob.findOrder(alien_dict,n,k)
x = sort_by_order(order)
x.sort_this_list(duplicate_dict)
if duplicate_dict == alien_dict:
print(1)
else:
print(0)
My problem:
The code runs fine for the test cases that are given in the example but fails for ["baa", "abcd", "abca", "cab", "cad"]
It throws the following error for this input:
Runtime Error:
Runtime ErrorTraceback (most recent call last):
File "/home/e2beefe97937f518a410813879a35789.py", line 73, in <module>
x.sort_this_list(duplicate_dict)
File "/home/e2beefe97937f518a410813879a35789.py", line 58, in sort_this_list
lst.sort(key = self.transform)
File "/home/e2beefe97937f518a410813879a35789.py", line 54, in transform
new_word += chr( ord('a') + self.priority[c] )
KeyError: 'f'
Running in some other IDE:
If I explicitly give this input using some other IDE then the output I'm getting is b d a c
Interesting problem. Your idea is correct, it is a partially ordered set you can build a directed acyclcic graph and find an ordered list of vertices using topological sort.
The reason for your program to fail is because not all the letters that possibly some letters will not be added to your vertList.
Spoiler: adding the following line somewhere in your code solves the issue
vlist = [chr(ord('a') + v) for v in range(K)]
A simple failing example
Consider the input
2 4
baa abd
This will determine the following vertList
{"b": ["a"]}
The only constraint is that b must come before a in this alphabet. Your code returns the alphabet b a, since the letter d is not present you the driver code will produce an error when trying to check your solution. In my opinion it should simply output 0 in this situation.
I have written a program which is counting trigrams that occur 5 times or more in a text file. The trigrams should be printed out according to their frequency.
I cannot find the problem!
I get the following error message:
list index out of range
I have tried to make the range bigger but that did not work out
f = open("bsp_file.txt", encoding="utf-8")
text = f.read()
f.close()
words = []
for word in text.split():
word = word.strip(",.:;-?!-–—_ ")
if len(word) != 0:
words.append(word)
trigrams = {}
for i in range(len(words)):
word = words[i]
nextword = words[i + 1]
nextnextword = words[i + 2]
key = (word, nextword, nextnextword)
trigrams[key] = trigrams.get(key, 0) + 1
l = list(trigrams.items())
l.sort(key=lambda x: x[1])
l.reverse()
for key, count in l:
if count < 5:
break
word = key[0]
nextword = key[1]
nextnextword = key[2]
print(word, nextword, nextnextword, count)
The result should look like this:(simplified)
s = "this is a trigram which is an example............."
this is a
is a trigram
a trigram which
trigram which is
which is an
is an example
As the comments pointed out, you're iterating over your list words with i, and you try to access words[i+1], when i will reach the last cell of words, i+1 will be out of range.
I suggest you read this tutorial to generate n-grams with pure python: http://www.albertauyeung.com/post/generating-ngrams-python/
Answer
If you don't have much time to read it all here's the function I recommend adaptated from the link:
def get_ngrams_count(words, n):
# generates a list of Tuples representing all n-grams
ngrams_tuple = zip(*[words[i:] for i in range(n)])
# turn the list into a dictionary with the counts of all ngrams
ngrams_count = {}
for ngram in ngrams_tuple:
if ngram not in ngrams_count:
ngrams_count[ngram] = 0
ngrams_count[ngram] += 1
return ngrams_count
trigrams = get_ngrams_count(words, 3)
Please note that you can make this function a lot simpler by using a Counter (which subclasses dict, so it will be compatible with your code) :
from collections import Counter
def get_ngrams_count(words, n):
# turn the list into a dictionary with the counts of all ngrams
return Counter(zip(*[words[i:] for i in range(n)]))
trigrams = get_ngrams_count(words, 3)
Side Notes
You can use the bool argument reverse in .sort() to sort your list from most common to least common:
l = list(trigrams.items())
l.sort(key=lambda x: x[1], reverse=True)
this is a tad faster than sorting your list in ascending order and then reverse it with .reverse()
A more generic function for the printing of your sorted list (will work for any n-grams and not just tri-grams):
for ngram, count in l:
if count < 5:
break
# " ".join(ngram) will combine all elements of ngram in a string, separated with spaces
print(" ".join(ngram), count)
I have a list of file names, like this.
file_names = ['file1', 'file2']
Also, I have a list of key words I am trying to extract from some files. So, the list of key words (list_1, list_2) and the text string that come from file1 and file2 are below,
## list_1 keywords
list_1 = ['hi', 'hello']
## list_2 keywords
list_2 = ['I', 'am']
## Text strings from file_1 and file_2
big_list = ['hi I am so and so how are you', 'hello hope all goes well by the way I can help you']
My function to extract text,
def my_func(text_string, key_words):
sentences = re.findall(r"([^.]*\.)" ,text_string)
for sentence in sentences:
if all(word in sentence for word in key_words):
return sentence
Now, I am going through multiple lists with two different for loops (as shown below) and with the funciton. After end of each iteration of these multiple for loops, I want to save the file with the filenames from file_names list.
for a,b in zip(list_1,list_2):
for item in big_list:
sentence_1 = my_func(item, a.split(' '))
sentence_2 = my_func(item, b.split(' '))
## Here I would like to add the file name i.e (print(filename))
print(sentence_1)
print(sentence_2)
I need an output that looks like this,
file1 is:
None
file2 is:
None
You can ignore None in my output now, as my main focus is to iterate though filename list and add them to my output. I would appreciate any help to achieve this.
You can access the index in Python for loops and use this index to find the file to which the string corresponds. With this you can print out the current file.
Here is an example of how you can do it:
for a,b in zip(list_1,list_2):
# idx is the index here
for idx, item in enumerate(big_list):
sentence_1 = extract_text(item, a)
sentence_2 = extract_text(item, b)
prefix = file_names[idx] + " is: " # Use idx to get the file from the file list
if sentence_1 is not None:
print(prefix + sentence_1)
if sentence_2 is not None:
print(prefix + sentence_2)
Update:
If you want to print the results after the iteration you can save temporarily the results in a dictionary and then loop through it:
for a,b in zip(list_1,list_2):
# idx is the index here
resMap = {}
for idx, item in enumerate(big_list):
sentence_1 = extract_text(item, a)
sentence_2 = extract_text(item, b)
if sentence_1 is not None:
resMap[file_names[idx]] = sentence_1
if sentence_2 is not None:
resMap[file_names[idx]] = sentence_2
for k in resMap.keys():
prefix = k + " is: " # Use idx to get the file from the file list
print (prefix + resMap[k])
I'm working out how to remove a specific item from a list.
"peppers", "cheese", "mushrooms", "bananas", "peppers"
I can locate the item "peppers", and change it to "gone!", but I really want to deleting the item, using
del blist[idx]
But that causes an error and I don't know why.
myList = ["peppers", "cheese", "mushrooms", "bananas", "peppers"]
def findInList (needle, haystack):
needle = needle.lower()
findy = []
# loops over list elements
for i in range(0, len(haystack)):
temp = haystack[i].lower()
idx = temp.find(needle)
if (idx != -1): findy.append(i)
return findy
def deleteItemInList(alist, blist):
for i in range(0, len(alist)):
idx = alist[i]
blist[idx] = "Gone!"
# del blist[idx]
# find items in list
mySearch = findInList("Peppers", myList)
# remove item from list
deleteItemInList(mySearch, myList)
print myList
Traceback: as follows
Traceback (most recent call last):
File "delete_in_list.py", line 23, in <module>
deleteItemInList(mySearch, myList)
File "delete_in_list.py", line 16, in deleteItemInList
blist[idx] = "Gone!"
IndexError: list assignment index out of range
Could someone look over the code above and point out where I'm going wrong.
You can use a list comprehension for this.
def removeWord(needle, haystack):
return [word for word in haystack if word.lower() != needle.lower()]
To find an element use this function. Or alternatively just define it as usual:
>>> find = lambda _list, query: [item.lower() for item in _list].index(query.lower())
>>> l = ['red', 'pepper']
>>> q = 'Pepper'
>>> find(l, q)
1
To remove by index just use del:
>>> del l[find(l, q)]
>>> l
['red']
I finally figured it out! Whilst iterating over the list deleting items in the list I was effectively sawing off the branch I was sitting on.
You need to loop over the list in reverse:
def deleteItemInList(alist, blist):
for i in range(len(alist) -1, -1, -1):
idx = alist[i]
del blist[idx]