Develop Reference

While reading a text file sequentially how to go back to a particular line and start again from there

Newbie alert!
Path = "C:/Users/Kailash/Downloads/Results_For_Stride-Table.csv"
counter_start = 0
counter_end = 0
num_lines = len(open(Path).read().splitlines())
print("num_lines = ", num_lines)
with open(Path, "r") as f:
for lines in f:
print("lines = ", lines)
counter_end += 1
Stride_Length = lines.split(", ")
Previous_Sum = distances
Previous_Sum_GCT = Total_GCT
Previous_Heading = Sum_Heading
GCT = float(Stride_Length[2])
Total_GCT += GCT
print("Total_GCT = ", Total_GCT)
distances += float(Stride_Length[3])
print("distances = ", distances)
Sum_Heading += float(Stride_Length[7])
print("Sum_Heading = ", Sum_Heading)
print("counter_end = ", counter_end)
if(GCT == 0.00):
distances = 0
counter_end = 0
if distances > 762:
print("counter_end = ", counter_end)
counter_start = counter_end
lines_test = f.readlines()
print("counter start = ", counter_start)
print("move = ", lines_test[counter_start-counter_end-1])
print("Distance is above 762")
distances = 0
I want to know how to go back to a particular line in a file and start reading from there again in python. when I try to use f.readlines() in the last but 5th line in my code, the processing stops right there.

You can build a list of line start positions (file offsets), and then use file.seek(line_offsets[n]) to go back to the nth line (counting from zero). After that you can read the line (and those following it sequentially) once again.
Here's example code showing building such a list incrementally:
filepath = "somefile"
line_offsets = []
with open(filepath, "r") as file:
while True:
posn = file.tell()
line = file.readline()
if not line: # end-of-file?
break
line_offsets.append(posn) # Remember where line started.
""" Process line """

... code above ...
for line in data:
if counter_end<= <line to stop at>:
continue
counter_end += 1
...

a = linecache.getlines('D:/aaa.txt')[5]

import linecache
a = linecache.getlines('D:/aaa.txt')[5]

Sorting Columns within csv files(Python)

Having issues with code. was given a file called "racing.csv" that stored the variables found in the "Drive" class. Concept behind the problem is that the program should sort the racetimes (lowest to highest) and assign points to the top 3 racers then export this data to a new file. All code is working fine aside from when I'm calling the shortBubbleSort on Drive and isn't sorting the racetimes correctly. Help is appreciated.
import csv
class Drive(object):
driver = ""
team = ""
racetime = 0.0
points = 0
def __init__(self,driver,team,racetime,points):
self.driver = driver
self.team = team
self.racetime = racetime
self.points = points
f = open('racing.csv', 'r')
csv_f = list(csv.reader(f))
driverclasses = []
for i in range(len(csv_f)):
d = Drive(csv_f[i][0],csv_f[i][1],csv_f[i][2],csv_f[i][3])
driverclasses.append(d)
for row in csv_f:
print (row)
for x in range(0, 6):
csv_f[x][2]=(input("Enter Racetime"))
def shortBubbleSort(alist):
exchanges = True
passnum = len(alist)-1
while passnum > 0 and exchanges:
exchanges = False
for i in range(passnum):
if alist[i]>alist[i+1]:
exchanges = True
temp = alist[i]
alist[i] = alist[i+1]
alist[i+1] = temp
passnum = passnum-1
shortBubbleSort(Drive)
print(csv_f)
csv_f[0][3] = 25
csv_f[1][3] = 18
csv_f[2][3] = 15
f = open('RacingResults.csv', 'w')
for row in csv_f:
print (row)

Does this help?
**range function sintax*: range([start], stop[, step])
start: Starting number of the sequence.
stop: Generate numbers up to, but not including this number.
step: Difference between each number in the sequence.
def shortBubbleSort(alist):
for passnum in range(len(alist)-1,0,-1):
for i in range(passnum):
if alist[i]>alist[i+1]:
temp = alist[i]
alist[i] = alist[i+1]
alist[i+1] = temp

TypeError: 'int' object is not iterable Python read file

This is a magic square program that can find out if any size matrix is a magic square. When i run the code i get error TypeError: 'int' object is not subscriptable. I decided to change line = int(i) to line = i but that just gave me another error. Cant use numpy
EDIT: Now i get this error TypeError: 'int' object is not iterable
text file:
1 1
6 8
Here is code:
def main():
filNam = "matrix8.txt"
matrix = (readMatrix(filNam))
rowNum = 0
colNum = 0
print(rowSum(matrix, rowNum))
def readMatrix(filNam):
matrixList = []
numFile = open(filNam, "r")
lines = numFile.readlines()
for line in lines:
line = line.split()
row = []
for i in line:
row.append(int(i))
matrixList.append(row)
return matrixList
def eachNumPresent(matrix):
if len(matrix) % 2 != 0:
return False
else:
return True
def rowSum(matrix, rowNum):
for row in matrix[rowNum]:
row = sum(int(row))
rowNum = rowNum + 1
return i
def colSum(matrix):
length = len(matrix)
col_rows = 0
for i in range(length):
col_rows = col_rows + matrix[i][0]
return col_rows
main()

The problem is that the matrix gets "flatten" into one long row. In order to fix it you should read & construct the matrix row-by-row.
Change:
def readMatrix(filNam):
matrixList = []
numFile = open(filNam, "r")
lines = numFile.readlines()
for line in lines:
line = line.split()
for i in line:
line = int(i)
matrixList.append(line)
return matrixList
to:
def readMatrix(filNam):
matrixList = []
numFile = open(filNam, "r")
lines = numFile.readlines()
for line in lines:
line = line.split()
row = [] # 1st change
for i in line:
row.append(int(i)) # 2nd change
matrixList.append(row) #3rd change
return matrixList
changing the code and running it on the input provided in the question it prints 2 which is the sum of the first row in the matrix.

Python Key Error=0 - Can't find Dict error in code

basically I have been racking my brains for a good while now as to why my code is not working, I have tested parts separately and have look throughout the web to see if it can help, to no avail.
I am getting an error that the traceback is:
Traceback (most recent call last):
File "yes2.py", line 62, in <module>
g.add_edge(row_index,col_index, b)
File "yes2.py", line 27, in add_edge
self.adj[u].append(edge)
KeyError: 0
The two parts with errors are
def add_edge(self, u, v, w=0):
if u == v:
raise ValueError("u == v")
edge = Edge(u,v,w)
redge = Edge(v,u,0)
edge.redge = redge
redge.redge = edge
self.adj[u].append(edge) #### LINE 27 ####
self.adj[v].append(redge)
self.flow[edge] = 0
self.flow[redge] = 0
and
g = FlowNetwork()
map(g.add_vertex, ['0','1','2','3','4','5','6'])
with open('network.txt', "r") as file:
for row_index, row in enumerate(file):
for col_index, value in enumerate(row.split(",")):
b = int(value)
if b != 0:
g.add_edge(row_index,col_index, b) ### LINE 62 ####
And here is the completed code, as without this it may be difficult to see what is happening
class Edge(object):
def __init__(self, u, v, w):
self.source = u
self.sink = v
self.capacity = w
def __repr__(self):
return "%s->%s:%s" % (self.source, self.sink, self.capacity)
class FlowNetwork(object):
def __init__(self):
self.adj = {}
self.flow = {}
def add_vertex(self, vertex):
self.adj[vertex] = []
def get_edges(self, v):
return self.adj[v]
def add_edge(self, u, v, w=0):
if u == v:
raise ValueError("u == v")
edge = Edge(u,v,w)
redge = Edge(v,u,0)
edge.redge = redge
redge.redge = edge
self.adj[u].append(edge)
self.adj[v].append(redge)
self.flow[edge] = 0
self.flow[redge] = 0
def find_path(self, source, sink, path):
if source == sink:
return path
for edge in self.get_edges(source):
residual = edge.capacity - self.flow[edge]
if residual > 0 and not (edge,residual) in path:
result = self.find_path( edge.sink, sink, path + [(edge,residual)] )
if result != None:
return result
def max_flow(self, source, sink):
path = self.find_path(source, sink, [])
while path != None:
flow = min(res for edge,res in path)
for edge,res in path:
self.flow[edge] += flow
self.flow[edge.redge] -= flow
path = self.find_path(source, sink, [])
return sum(self.flow[edge] for edge in self.get_edges(source))
g = FlowNetwork()
map(g.add_vertex, ['0','1','2','3','4','5','6'])
with open('network.txt', "r") as file:
# enumerate allows you to iterate through the list with an index and an object
for row_index, row in enumerate(file):
# split allows you to break a string apart with a string key
for col_index, value in enumerate(row.split(",")):
#convert value from string to int
b = int(value)
if b != 0:
g.add_edge(row_index,col_index, b)
print g.max_flow('1','6')
Many thanks for your time, much appreciated.

The error you're getting is that self.adj doesn't already have a key 0. You're trying to append to a list that doesn't exist yet.
Consider using a defaultdict instead, replacing this line (in __init__):
self.adj = {}
with this:
self.adj = defaultdict(list)
You'll need to import at the top:
from collections import defaultdict
Now rather than raise a KeyError, self.adj[0].append(edge) will create a list automatically to append to.

The defaultdict solution is better.
But for completeness you could also check and create empty list before the append.
Add the + lines:
+ if not u in self.adj.keys():
+ self.adj[u] = []
self.adj[u].append(edge)
.
.

It only comes when your list or dictionary not available in the local function.

Try this:
class Flonetwork(Object):
def __init__(self,adj = {},flow={}):
self.adj = adj
self.flow = flow

Printing values following comparison of two csv files only if in a specific range using Python 3.3

I'm new at programming and I've got two CSV files that I'm trying to compare. The first file, snp.csv is shown below:
chrom position ref var gene var
1 21421 G T WASH7P snp.LOH
1 1251593 T C CPSF3L snp.somatic
6 107474777 - A PDSS2 indel.somatic
14 106586168 G T ADAM6 snp.LOH
The second file, quad.csv is shown below:
chrom Start End Sequence
1 21420 21437 GGGACGGGGAGGGTTGGG
1 23058 23078 GGGCTGGGGCGGGGGGAGGG
1 23515 23534 GGGAAGGGACAGGGCAGGG
1 45098 45118 GGGAAAGGGCAGGGCCCGGG
3 1148 1173 GGGCCGGGCAAGGCCGGGTGCAGGG
I want to compare these two files and if the two chrom values match, I want to print only those having position value (in snp.csv file) in the range of the start and end value (in the quad.csv file).
So, I am looking for a solution that will give me something like the following (basically the snp.csv file with start, end and sequence value of the quad.csv file)
chrom position ref var gene var Start End Sequence
1 21421 G T WASH7P snp.LOH 21420 21437 GGGACGGGGAGGGTTGGG
I've searched the posts and found some interesting answers that helped me a lot but I’m still experiencing some issues. I’m still learning Python…
Here is my script up to now, I know I have a problem with the range function...I'm stuck
import csv
snp_file = open("snp.csv", "r")
quad_file = open("quad.csv", "r")
out_file = open("results.csv", "wb")
snp = csv.reader(snp_file, delimiter='\t')
quad = csv.reader(quad_file, delimiter='\t')
out = csv.reader(out_file, delimiter='\t')
quadlist = [row for row in quad]
for snp_row in snp:
row = 1
found = False
for quad_row in quadlist:
results_row = snp_row
if snp_row[0] == quad_row[0]:
quad_pos = range(quad_row[1], quad_row[2])
if snp_row[1] in quad_pos:
results_row.append(quad_row)
found = True
break
row = row + 1
if not found:
pass
print (results_row)
snp.close()
quad.close()
out.close()

from bisect import bisect_right
from collections import defaultdict
import csv
TOO_HIGH = 2147483647 # higher than any actual gene position
SNP_FMT = "{0:<7} {1:<11} {2:3} {3:3} {4:11} {5:15}".format
QUAD_FMT = " {1:<7} {2:<7} {3}".format
def line_to_quad(line):
row = line.split()
return int(row[0]), int(row[1]), int(row[2]), row[3]
def line_to_snp(line):
row = line.split()
return int(row[0]), int(row[1]), row[2], row[3], row[4], row[5]
class Quads:
#classmethod
def from_file(cls, fname):
with open(fname, "rU") as inf:
next(inf, None) # skip header line
quads = (line_to_quad(line) for line in inf)
return cls(quads)
def __init__(self, rows):
self.chromosomes = defaultdict(list)
for row in rows:
self.chromosomes[row[0]].append(row[1:])
for segs in self.chromosomes.values():
segs.sort()
def find_match(self, chromosome, position):
segs = self.chromosomes[chromosome]
index = bisect_right(segs, (position, TOO_HIGH, "")) - 1
try:
seg = segs[index]
if seg[0] <= position <= seg[1]:
return (chromosome,) + seg
except IndexError:
pass
def main():
quads = Quads.from_file("quad.csv")
print( # header
SNP_FMT("chrom", "position", "ref", "var", "gene", "var") +
QUAD_FMT("chrom", "Start", "End", "Sequence")
)
with open("snp.csv") as inf:
next(inf, None) # skip header line
for line in inf:
snp = line_to_snp(line)
quad = quads.find_match(snp[0], snp[1])
if quad:
print(SNP_FMT(*snp) + QUAD_FMT(*quad))
if __name__=="__main__":
main()
which gives
chrom position ref var gene var Start End Sequence
1 21421 G T WASH7P snp.LOH 21420 21437 GGGACGGGGAGGGTTGGG