core_templates2/docdiff.scala
author Christian Urban <christian.urban@kcl.ac.uk>
Mon, 25 Dec 2023 01:10:55 +0100
changeset 479 78cb5cdda3c3
parent 425 6e990ae2c6a3
permissions -rw-r--r--
updated jars
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
396
ea39bbc8d98d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 346
diff changeset
     1
// Core Part 2 about Code Similarity
ea39bbc8d98d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 346
diff changeset
     2
//===================================
283
3102d61edf45 updated
Christian Urban <urbanc@in.tum.de>
parents: 203
diff changeset
     3
3102d61edf45 updated
Christian Urban <urbanc@in.tum.de>
parents: 203
diff changeset
     4
396
ea39bbc8d98d updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 346
diff changeset
     5
object C2 { 
283
3102d61edf45 updated
Christian Urban <urbanc@in.tum.de>
parents: 203
diff changeset
     6
425
6e990ae2c6a3 updated solutions and templates
Christian Urban <christian.urban@kcl.ac.uk>
parents: 396
diff changeset
     7
// ADD YOUR CODE BELOW
6e990ae2c6a3 updated solutions and templates
Christian Urban <christian.urban@kcl.ac.uk>
parents: 396
diff changeset
     8
//======================
203
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
     9
425
6e990ae2c6a3 updated solutions and templates
Christian Urban <christian.urban@kcl.ac.uk>
parents: 396
diff changeset
    10
//(1)
479
78cb5cdda3c3 updated jars
Christian Urban <christian.urban@kcl.ac.uk>
parents: 425
diff changeset
    11
def clean(s: String) : List[String] = List("bla")
203
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    12
  
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    13
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    14
425
6e990ae2c6a3 updated solutions and templates
Christian Urban <christian.urban@kcl.ac.uk>
parents: 396
diff changeset
    15
//(2)
346
ed1b6b8c36e5 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 283
diff changeset
    16
def occurrences(xs: List[String]): Map[String, Int] = ???
203
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    17
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    18
425
6e990ae2c6a3 updated solutions and templates
Christian Urban <christian.urban@kcl.ac.uk>
parents: 396
diff changeset
    19
//(3)
346
ed1b6b8c36e5 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 283
diff changeset
    20
def prod(lst1: List[String], lst2: List[String]) : Int = ???
203
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    21
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    22
425
6e990ae2c6a3 updated solutions and templates
Christian Urban <christian.urban@kcl.ac.uk>
parents: 396
diff changeset
    23
//(4)
346
ed1b6b8c36e5 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 283
diff changeset
    24
def overlap(lst1: List[String], lst2: List[String]) : Double = ???
203
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    25
346
ed1b6b8c36e5 updated
Christian Urban <christian.urban@kcl.ac.uk>
parents: 283
diff changeset
    26
def similarity(s1: String, s2: String) : Double = ???
203
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    27
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    28
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    29
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    30
/* Test cases
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    31
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    32
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    33
val list1 = List("a", "b", "b", "c", "d") 
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    34
val list2 = List("d", "b", "d", "b", "d")
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    35
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    36
occurrences(List("a", "b", "b", "c", "d"))   // Map(a -> 1, b -> 2, c -> 1, d -> 1)
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    37
occurrences(List("d", "b", "d", "b", "d"))   // Map(d -> 3, b -> 2)
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    38
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    39
prod(list1,list2) // 7 
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    40
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    41
overlap(list1, list2)   // 0.5384615384615384
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    42
overlap(list2, list1)   // 0.5384615384615384
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    43
overlap(list1, list1)   // 1.0
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    44
overlap(list2, list2)   // 1.0
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    45
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    46
// Plagiarism examples from 
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    47
// https://desales.libguides.com/avoidingplagiarism/examples
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    48
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    49
val orig1 = """There is a strong market demand for eco-tourism in
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    50
Australia. Its rich and diverse natural heritage ensures Australia's
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    51
capacity to attract international ecotourists and gives Australia a
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    52
comparative advantage in the highly competitive tourism industry."""
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    53
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    54
val plag1 = """There is a high market demand for eco-tourism in
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    55
Australia. Australia has a comparative advantage in the highly
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    56
competitive tourism industry due to its rich and varied natural
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    57
heritage which ensures Australia's capacity to attract international
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    58
ecotourists."""
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    59
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    60
similarity(orig1, plag1) // 0.8679245283018868
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    61
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    62
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    63
// Plagiarism examples from 
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    64
// https://www.utc.edu/library/help/tutorials/plagiarism/examples-of-plagiarism.php
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    65
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    66
val orig2 = """No oil spill is entirely benign. Depending on timing and
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    67
location, even a relatively minor spill can cause significant harm to
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    68
individual organisms and entire populations. Oil spills can cause
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    69
impacts over a range of time scales, from days to years, or even
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    70
decades for certain spills. Impacts are typically divided into acute
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    71
(short-term) and chronic (long-term) effects. Both types are part of a
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    72
complicated and often controversial equation that is addressed after
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    73
an oil spill: ecosystem recovery."""
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    74
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    75
val plag2 = """There is no such thing as a "good" oil spill. If the
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    76
time and place are just right, even a small oil spill can cause damage
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    77
to sensitive ecosystems. Further, spills can cause harm days, months,
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    78
years, or even decades after they occur. Because of this, spills are
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    79
usually broken into short-term (acute) and long-term (chronic)
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    80
effects. Both of these types of harm must be addressed in ecosystem
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    81
recovery: a controversial tactic that is often implemented immediately
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    82
following an oil spill."""
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    83
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    84
overlap(clean(orig2), clean(plag2))  // 0.728
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    85
similarity(orig2, plag2)             // 0.728
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    86
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    87
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    88
 
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    89
// The punchline: everything above 0.6 looks suspicious and 
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    90
// should be investigated by staff.
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    91
e0420c7b8a19 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    92
*/
283
3102d61edf45 updated
Christian Urban <urbanc@in.tum.de>
parents: 203
diff changeset
    93
3102d61edf45 updated
Christian Urban <urbanc@in.tum.de>
parents: 203
diff changeset
    94
}