| 202 |      1 | // Part 1 about Code Similarity
 | 
|  |      2 | //==============================
 | 
|  |      3 | 
 | 
|  |      4 | 
 | 
|  |      5 | object CW7a { // for purposes of generating a jar
 | 
|  |      6 | 
 | 
|  |      7 | //(1) Complete the clean function below. It should find
 | 
|  |      8 | //    all words in a string using the regular expression
 | 
|  |      9 | //    \w+  and the library function 
 | 
|  |     10 | //
 | 
|  |     11 | //         some_regex.findAllIn(some_string)
 | 
|  |     12 | //
 | 
| 203 |     13 | //    The words should be Returned as a list of strings.
 | 
| 202 |     14 | 
 | 
|  |     15 | def clean(s: String) : List[String] = 
 | 
|  |     16 |   ("""\w+""".r).findAllIn(s).toList
 | 
|  |     17 | 
 | 
|  |     18 | 
 | 
| 203 |     19 | //(2) The function occurrences calculates the number of times  
 | 
|  |     20 | //    strings occur in a list of strings. These occurrences should 
 | 
| 202 |     21 | //    be calculated as a Map from strings to integers.
 | 
|  |     22 | 
 | 
| 203 |     23 | def occurrences(xs: List[String]): Map[String, Int] =
 | 
| 202 |     24 |   (for (x <- xs.distinct) yield (x, xs.count(_ == x))).toMap
 | 
|  |     25 | 
 | 
|  |     26 | //(3) This functions calculates the dot-product of two documents
 | 
| 203 |     27 | //    (list of strings). For this it calculates the occurrence
 | 
|  |     28 | //    maps from (2) and then multiplies the corresponding occurrences. 
 | 
| 202 |     29 | //    If a string does not occur in a document, the product is zero.
 | 
|  |     30 | //    The function finally sums up all products. 
 | 
|  |     31 | 
 | 
|  |     32 | def prod(lst1: List[String], lst2: List[String]) : Int = {
 | 
|  |     33 |     val words = (lst1 ::: lst2).distinct
 | 
| 203 |     34 |     val occs1 = occurrences(lst1)
 | 
|  |     35 |     val occs2 = occurrences(lst2)
 | 
| 202 |     36 |     words.map{ w => occs1.getOrElse(w, 0) * occs2.getOrElse(w, 0) }.sum
 | 
|  |     37 | }
 | 
|  |     38 | 
 | 
|  |     39 | //(4) Complete the functions overlap and similarity. The overlap of
 | 
|  |     40 | //    two documents is calculated by the formula given in the assignment
 | 
|  |     41 | //    description. The similarity of two strings is given by the overlap
 | 
|  |     42 | //    of the cleaned (see (1)) strings.  
 | 
|  |     43 | 
 | 
|  |     44 | def overlap(lst1: List[String], lst2: List[String]) : Double = {
 | 
|  |     45 |     val m1 = prod(lst1, lst1)
 | 
|  |     46 |     val m2 = prod(lst2, lst2) 
 | 
|  |     47 |     prod(lst1, lst2).toDouble / (List(m1, m2).max)
 | 
|  |     48 | }
 | 
|  |     49 | 
 | 
|  |     50 | def similarity(s1: String, s2: String) : Double =
 | 
|  |     51 |   overlap(clean(s1), clean(s2))
 | 
|  |     52 | 
 | 
|  |     53 | 
 | 
|  |     54 | /*
 | 
|  |     55 | 
 | 
|  |     56 | 
 | 
|  |     57 | val list1 = List("a", "b", "b", "c", "d") 
 | 
|  |     58 | val list2 = List("d", "b", "d", "b", "d")
 | 
|  |     59 | 
 | 
| 203 |     60 | occurrences(List("a", "b", "b", "c", "d"))   // Map(a -> 1, b -> 2, c -> 1, d -> 1)
 | 
|  |     61 | occurrences(List("d", "b", "d", "b", "d"))   // Map(d -> 3, b -> 2)
 | 
| 202 |     62 | 
 | 
|  |     63 | prod(list1,list2) // 7 
 | 
|  |     64 | 
 | 
|  |     65 | overlap(list1, list2)   // 0.5384615384615384
 | 
|  |     66 | overlap(list2, list1)   // 0.5384615384615384
 | 
|  |     67 | overlap(list1, list1)   // 1.0
 | 
|  |     68 | overlap(list2, list2)   // 1.0
 | 
|  |     69 | 
 | 
|  |     70 | // Plagiarism examples from 
 | 
|  |     71 | // https://desales.libguides.com/avoidingplagiarism/examples
 | 
|  |     72 | 
 | 
|  |     73 | val orig1 = """There is a strong market demand for eco-tourism in
 | 
|  |     74 | Australia. Its rich and diverse natural heritage ensures Australia's
 | 
|  |     75 | capacity to attract international ecotourists and gives Australia a
 | 
|  |     76 | comparative advantage in the highly competitive tourism industry."""
 | 
|  |     77 | 
 | 
|  |     78 | val plag1 = """There is a high market demand for eco-tourism in
 | 
|  |     79 | Australia. Australia has a comparative advantage in the highly
 | 
|  |     80 | competitive tourism industry due to its rich and varied natural
 | 
|  |     81 | heritage which ensures Australia's capacity to attract international
 | 
|  |     82 | ecotourists."""
 | 
|  |     83 | 
 | 
|  |     84 | similarity(orig1, plag1)
 | 
|  |     85 | 
 | 
|  |     86 | 
 | 
|  |     87 | // Plagiarism examples from 
 | 
|  |     88 | // https://www.utc.edu/library/help/tutorials/plagiarism/examples-of-plagiarism.php
 | 
|  |     89 | 
 | 
|  |     90 | val orig2 = """No oil spill is entirely benign. Depending on timing and
 | 
|  |     91 | location, even a relatively minor spill can cause significant harm to
 | 
|  |     92 | individual organisms and entire populations. Oil spills can cause
 | 
|  |     93 | impacts over a range of time scales, from days to years, or even
 | 
|  |     94 | decades for certain spills. Impacts are typically divided into acute
 | 
|  |     95 | (short-term) and chronic (long-term) effects. Both types are part of a
 | 
|  |     96 | complicated and often controversial equation that is addressed after
 | 
|  |     97 | an oil spill: ecosystem recovery."""
 | 
|  |     98 | 
 | 
|  |     99 | val plag2 = """There is no such thing as a "good" oil spill. If the
 | 
|  |    100 | time and place are just right, even a small oil spill can cause damage
 | 
|  |    101 | to sensitive ecosystems. Further, spills can cause harm days, months,
 | 
|  |    102 | years, or even decades after they occur. Because of this, spills are
 | 
|  |    103 | usually broken into short-term (acute) and long-term (chronic)
 | 
|  |    104 | effects. Both of these types of harm must be addressed in ecosystem
 | 
|  |    105 | recovery: a controversial tactic that is often implemented immediately
 | 
|  |    106 | following an oil spill."""
 | 
|  |    107 | 
 | 
|  |    108 | overlap(clean(orig2), clean(plag2))
 | 
|  |    109 | similarity(orig2, plag2)
 | 
|  |    110 | 
 | 
|  |    111 | // The punchline: everything above 0.6 looks suspicious and 
 | 
|  |    112 | // should be looked at by staff.
 | 
|  |    113 | 
 | 
|  |    114 | */
 | 
|  |    115 | 
 | 
|  |    116 | 
 | 
|  |    117 | }
 |