import re

## do not remove the extra print statements
print('Question 1')
#################################################################
# QUESTION 1                                                    #
# 
# Converting a BED file to a GFF file. You are provide a path to 
# a file that the autograder has access to below. Please read in 
# the file, then convert it to a GFF file. Here are some example 
# lines: 
#
# 2R	22136967	22172834	a	.	+
# 2R	24378629	24390294	mAChR-A	.	-
# 2R	6013909	6015689	Act42A	.	-
#
# As with most BED files, this is a tab-delimited file.
# Use the name in the name column of the BED file to be an ID in 
# the GFF, but put it in quotes so that it is something like:
# gene_symbol "a"
#
# when the name in the name column of the BED File is a. Convert the 
# positions from the GFF one-based inclusive positions to the 
# BED Files 0-based non-inclusive ends (like python substrings).
# For the source, use "FlyBase" (just the name without quotes)
# For the frame, you can just use a dot ".".
# for the seqtype/feature type please use "gene" (without the quotes)
# You can use the score from the bed as-is, even if it is a dot "."
# and print the same thing for the GFF.
# please print this as a tab-delimited file to an output GFF file
# named: flybase_assignment8.gff
#
#################################################################

##add code for question 1 here
bed_file = '/autograder/source/flybase_example.bed'


## do not remove the extra print statements
print('Question 2')
#################################################################
# QUESTION 2                                                    #
#
# Converting a GFF file to a BED file You are provide a path to
# a file that the autograder has access to below. Please read in
# the file, then convert it to a BED file. Here are some example
# lines from the GFF:
#
# 2R	FlyBase	gene	22136968	22172834	.	+		gene_id "FBgn0000008"; gene_symbol "a"; 
# 2R	FlyBase	gene	24378630	24390294	.	-		gene_id "FBgn0000037"; gene_symbol "mAChR-A"; 
# 2R	FlyBase	gene	6013910	6015689	.	-		gene_id "FBgn0000043"; gene_symbol "Act42A"; 
#
# Use the term in the attribute column of the GFF file to be a name
# in the name column of the BED file. The GFF has these attribute:
# columns: 
#
# gene_id "FBgn0000008"; gene_symbol "a";
# 
# so you need to extract the gene_symbol and remove the quotes 
# and use this for the name in the BED File.
# Convert the positions from the  BED Files 0-based non-inclusive 
# ends (like python substrings) to the GFF one-based inclusive
# positions. 
# if the score is a dot "." you can keep it a dot ".".
# 
# please print this as a tab-delimited file to an output BED file 
# named: flybase_assignment8.bed
#
#################################################################


gff_file = '/autograder/source/flybase_example.gff'
##add code for question 2 here

## do not remove the extra print statements
print('Question 3')
#################################################################
# QUESTION 3                                                    #
#                                                               #
# Read in the FASTA file in the path given below. Store the     #
# contents to a dictionary, with the defline as the key, and the#
# sequence as the value. Then print a tab-delimited file with 
# two colummns and the name "seq_lengths.txt". 
# the first column should be defline, and the second column to 
# be the length of the sequence. In addition! The sequence lengths
# should be sorted in descending order, with the longest
# chromosome lengths printed first. 
#                                                               #
#################################################################


##add code for question 3 here
genome_fasta = '/autograder/source/example.fasta'


## do not remove the extra print statements
print('Question 4')
#################################################################
# QUESTION 4                                                    #
#                                                               #
# For the following variables, use an f-string to print them 
# out to 3 decimal places. Write the output so that each variable
# is printed to include the variable name, followed immediately
# by an equal sign, and then the value (to three digits after the 
# decimal: pi=3.141
#
#  and then print tabs between each variables name/value pair. 
# The result should just be one line of text, with the three 
# variables, and their values separated by tabs. Print out 
# directly and not to a file
#################################################################

pi = 3.14159265358979
e = 2.718281828459045
phi = 1.618033988749895
##add code for question 4 here



## do not remove the extra print statements
print('Question 5')
#####################################################################
# QUESTION 5                                                        #
#                                                                   #
# Do the same thing as in Question 4, but using interpolated 
# strings. Meaing, print out the same numbers and their values
# separated by tabs. Let's do this one to four decimila places.
#
# For the following variables, use interpolated strings to print them
# out to 4 decimal places. Write the output so that each variable
# is printed to include the variable name, followed immediately
# by an equal sign, and then the value (to four digits after the
# decimal: pi=3.1416
#
# and then print tabs between each variable's name/value pair.
# The result should just be one line of text, with the three
# variables, and their values separated by tabs. Print out directly
# and not to a file.
#####################################################################

pi = 3.14159265358979
e = 2.718281828459045
phi = 1.618033988749895
##add code for question 5 here