Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add hamming exercise #45

Merged
merged 1 commit into from
Aug 28, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions config.json
Original file line number Diff line number Diff line change
Expand Up @@ -251,6 +251,14 @@
"practices": [],
"prerequisites": [],
"difficulty": 1
},
{
"slug": "hamming",
"name": "Hamming",
"uuid": "3ea9f608-75a0-49c9-bb62-28a8df533c26",
"practices": [],
"prerequisites": [],
"difficulty": 1
}
]
},
Expand Down
27 changes: 27 additions & 0 deletions exercises/practice/hamming/.docs/instructions.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# Instructions

Calculate the Hamming distance between two DNA strands.

Your body is made up of cells that contain DNA.
Those cells regularly wear out and need replacing, which they achieve by dividing into daughter cells.
In fact, the average human body experiences about 10 quadrillion cell divisions in a lifetime!

When cells divide, their DNA replicates too.
Sometimes during this process mistakes happen and single pieces of DNA get encoded with the incorrect information.
If we compare two strands of DNA and count the differences between them we can see how many mistakes occurred.
This is known as the "Hamming distance".

We read DNA using the letters C, A, G and T.
Two strands might look like this:

GAGCCTACTAACGGGAT
CATCGTAATGACGGCCT
^ ^ ^ ^ ^ ^^

They have 7 differences, and therefore the Hamming distance is 7.

The Hamming distance is useful for lots of things in science, not just biology, so it's a nice phrase to be familiar with :)

## Implementation notes

The Hamming distance is only defined for sequences of equal length, so an attempt to calculate it between sequences of different lengths should not work.
13 changes: 13 additions & 0 deletions exercises/practice/hamming/.meta/Example.roc
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
module [distance]

distance : Str, Str -> Result (Num *) [StrandsMustBeOfEqualLength]
distance = \strand1, strand2 ->
nucleotides1 = strand1 |> Str.toUtf8
nucleotides2 = strand2 |> Str.toUtf8
if List.len nucleotides1 == List.len nucleotides2 then
List.map2 nucleotides1 nucleotides2 \n1, n2 ->
if n1 == n2 then 0 else 1
|> List.sum
|> Ok
else
Err StrandsMustBeOfEqualLength
19 changes: 19 additions & 0 deletions exercises/practice/hamming/.meta/config.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
{
"authors": [
"ageron"
],
"files": {
"solution": [
"Hamming.roc"
],
"test": [
"hamming-test.roc"
],
"example": [
".meta/Example.roc"
]
},
"blurb": "Calculate the Hamming difference between two DNA strands.",
"source": "The Calculating Point Mutations problem at Rosalind",
"source_url": "https://rosalind.info/problems/hamm/"
}
17 changes: 17 additions & 0 deletions exercises/practice/hamming/.meta/template.j2
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
{%- import "generator_macros.j2" as macros with context -%}
{{ macros.canonical_ref() }}
{{ macros.header() }}

import {{ exercise | to_pascal }} exposing [{{ cases[0]["property"] | to_camel }}]

{% for case in cases -%}
# {{ case["description"] }}
expect
result = {{ case["property"] | to_camel }} {{ case["input"]["strand1"] | to_roc }} {{ case["input"]["strand2"] | to_roc }}
{%- if case["expected"]["error"] %}
result == Err {{ case["expected"]["error"] | to_pascal }}
{%- else %}
result == Ok {{ case["expected"] }}
{%- endif %}

{% endfor %}
67 changes: 67 additions & 0 deletions exercises/practice/hamming/.meta/tests.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,67 @@
# This is an auto-generated file.
#
# Regenerating this file via `configlet sync` will:
# - Recreate every `description` key/value pair
# - Recreate every `reimplements` key/value pair, where they exist in problem-specifications
# - Remove any `include = true` key/value pair (an omitted `include` key implies inclusion)
# - Preserve any other key/value pair
#
# As user-added comments (using the # character) will be removed when this file
# is regenerated, comments can be added via a `comment` key.

[f6dcb64f-03b0-4b60-81b1-3c9dbf47e887]
description = "empty strands"

[54681314-eee2-439a-9db0-b0636c656156]
description = "single letter identical strands"

[294479a3-a4c8-478f-8d63-6209815a827b]
description = "single letter different strands"

[9aed5f34-5693-4344-9b31-40c692fb5592]
description = "long identical strands"

[cd2273a5-c576-46c8-a52b-dee251c3e6e5]
description = "long different strands"

[919f8ef0-b767-4d1b-8516-6379d07fcb28]
description = "disallow first strand longer"
include = false

[b9228bb1-465f-4141-b40f-1f99812de5a8]
description = "disallow first strand longer"
reimplements = "919f8ef0-b767-4d1b-8516-6379d07fcb28"

[8a2d4ed0-ead5-4fdd-924d-27c4cf56e60e]
description = "disallow second strand longer"
include = false

[dab38838-26bb-4fff-acbe-3b0a9bfeba2d]
description = "disallow second strand longer"
reimplements = "8a2d4ed0-ead5-4fdd-924d-27c4cf56e60e"

[5dce058b-28d4-4ca7-aa64-adfe4e17784c]
description = "disallow left empty strand"
include = false

[db92e77e-7c72-499d-8fe6-9354d2bfd504]
description = "disallow left empty strand"
include = false
reimplements = "5dce058b-28d4-4ca7-aa64-adfe4e17784c"

[b764d47c-83ff-4de2-ab10-6cfe4b15c0f3]
description = "disallow empty first strand"
reimplements = "db92e77e-7c72-499d-8fe6-9354d2bfd504"

[38826d4b-16fb-4639-ac3e-ba027dec8b5f]
description = "disallow right empty strand"
include = false

[920cd6e3-18f4-4143-b6b8-74270bb8f8a3]
description = "disallow right empty strand"
include = false
reimplements = "38826d4b-16fb-4639-ac3e-ba027dec8b5f"

[9ab9262f-3521-4191-81f5-0ed184a5aa89]
description = "disallow empty second strand"
reimplements = "920cd6e3-18f4-4143-b6b8-74270bb8f8a3"
4 changes: 4 additions & 0 deletions exercises/practice/hamming/Hamming.roc
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
module [distance]

distance = \strand1, strand2 ->
crash "Please implement the 'distance' function"
59 changes: 59 additions & 0 deletions exercises/practice/hamming/hamming-test.roc
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
# These tests are auto-generated with test data from:
# https://github.com/exercism/problem-specifications/tree/main/exercises/hamming/canonical-data.json
# File last updated on 2024-08-28
app [main] {
pf: platform "https://github.com/roc-lang/basic-cli/releases/download/0.14.0/dC5ceT962N_4jmoyoffVdphJ_4GlW3YMhAPyGPr-nU0.tar.br",
}

import pf.Task exposing [Task]

main =
Task.ok {}

import Hamming exposing [distance]

# empty strands
expect
result = distance "" ""
result == Ok 0

# single letter identical strands
expect
result = distance "A" "A"
result == Ok 0

# single letter different strands
expect
result = distance "G" "T"
result == Ok 1

# long identical strands
expect
result = distance "GGACTGAAATCTG" "GGACTGAAATCTG"
result == Ok 0

# long different strands
expect
result = distance "GGACGGATTCTG" "AGGACGGATTCT"
result == Ok 9

# disallow first strand longer
expect
result = distance "AATG" "AAA"
result == Err StrandsMustBeOfEqualLength

# disallow second strand longer
expect
result = distance "ATA" "AGTG"
result == Err StrandsMustBeOfEqualLength

# disallow empty first strand
expect
result = distance "" "G"
result == Err StrandsMustBeOfEqualLength

# disallow empty second strand
expect
result = distance "G" ""
result == Err StrandsMustBeOfEqualLength