Add files via upload

DataGen.py

@@ -0,0 +1,43 @@
+import random
+
+
+from Read import Read
+
+
+# generate some random strings consisting of 1's and 0's
+class DataGenerator(object):
+    def __init__(self, size):
+        self.size = size
+        self.H1 = []
+        self.H2 = []
+        self.reads = []
+        for i in range(0, size / 20):
+            before = random.getrandbits(20)    # get 25 random integers
+            for j in range(0, 20):
+                after = (before & (1 << j)) >> j    # change integer values to 0's and 1's
+                self.H1.append(after)
+                self.H2.append(~after & 1)  # H2 is complimentary to H1
+
+    def create_string(self, min_size, max_size, min_distance, max_distance, error, overlap_chance):
+        index = 0
+        while index < self.size:
+            read_size = random.randint(min_size, max_size)
+            if random.random() < 0.5:
+                data = self.H1[index:index + read_size]
+            else:
+                data = self.H2[index:index + read_size]
+            if len(data) > 0:
+                read = Read(index, data, error)     # error will be 0 for now
+                self.reads.append(read)
+            if random.random() > overlap_chance:
+                index += min(random.randint(min_distance, max_distance), read_size - 1)
+
+    # make it so we can read what the original haplotype looked like not just 0x00... computer stuff
+    def __repr__(self):
+        result = ""
+        for H in self.H1:
+            result += str(H)
+        result += "\n"
+        for H in self.H2:
+            result += str(H)
+        return result

EasyAssembly.py

@@ -0,0 +1,20 @@
+class EasyAssembly:
+
+    @classmethod
+    def assemble(cls, reads, size):
+        hap = [0] * size
+        hap_index = 0
+        read_index = 0
+        while hap_index < size:
+            while read_index < len(reads) - 1 and reads[read_index + 1].start < hap_index:
+                read_index += 1
+            read = reads[read_index]
+
+            if hap_index > 0 and read.data[0] != hap[read.start]:
+                hap[hap_index:read.start + read.size] = list(read.flipped[hap_index - read.start:])
+            else:
+                hap[hap_index:read.start + read.size] = list(read.data[hap_index - read.start:])
+
+            hap_index += read.size - (hap_index - read.start)
+
+        return hap

Read.py

@@ -0,0 +1,19 @@
+import random
+
+
+# create readable string
+class Read(object):
+    def __init__(self, start, data, error):
+        self.start = start
+        self.data = [H if error == 0 or random.random() > error else random.choice([0, 1]) for H in data]
+        self.size = len(self.data)
+        self.flipped = [~H & 1 for H in data]
+
+    # repr will return a string containing a printable representation of an object
+    def __repr__(self):
+        result = ""
+        for _ in range(0, self.start):
+            result += " "
+        for H in self.data:
+            result += str(H)
+        return result

__init__.py

@@ -0,0 +1 @@
+# necessary for importing files to main #

main.py

@@ -0,0 +1,54 @@
+import timeit
+
+from DataGen import DataGenerator
+from EasyAssembly import EasyAssembly
+
+begin = timeit.default_timer()
+
+
+def main():
+    haplotypes = True
+    size = 100
+    info = DataGenerator(size)
+
+    if haplotypes:
+        print "\nOriginal Haplotypes:"
+        print info
+    min_size = 10
+    max_size = 20
+    min_distance = 0
+    max_distance = 5
+    error = 0  # currently working on easy algorithm
+    overlap_chance = 0.5  # 50/50 chance
+    info.create_string(min_size=min_size, max_size=max_size, min_distance=min_distance, max_distance=max_distance,
+                       error=error, overlap_chance=overlap_chance)
+
+    def print_hap(haplotype, flipped):
+        result = ""
+        if not flipped:
+            for H in haplotype:
+                result += str(H)
+        else:
+            for H in haplotype:
+                if H == 0:
+                    result += "1"
+                else:
+                    result += "0"
+        print result
+
+    print "\n- Easy Algorithm -\n"
+    assembled = EasyAssembly.assemble(info.reads, size)
+    if haplotypes:
+        print "Assembled haplotypes:"
+        print_hap(assembled, flipped=False)
+        print_hap(assembled, flipped=True)
+    print "\n- Accuracy: 100% -"
+
+
+if __name__ == "__main__":
+    main()
+
+end = timeit.default_timer()
+
+time = end - begin
+print "- Runtime:", time, "-"