init hashtable commit

app.y

@@ -0,0 +1,8 @@
+import os
+from dotenv import load_dotenv
+from subprocess import Popen
+load_dotenv()
+
+command = ["mercury", "run", f"0.0.0.0:{os.environ.get('PORT', 7860)}"] 
+worker = Popen(command) 
+worker.wait()

data_processing/distribution_parser.py

@@ -0,0 +1,108 @@
+from data_structures import hash_table as hashing
+
+
+def get_unique_kmers(kmer_distribution):
+    """
+    Creates a kmer distribution composed of only unique kmers
+    """
+    unique_kmers = []
+    for kmer in kmer_distribution:
+        # if the kmer only appears once, add it to the list
+        if kmer[1] == 1:
+            unique_kmers.append(kmer)
+
+    return unique_kmers
+
+
+def get_most_common_kmers(kmer_distribution, n):
+    """
+    Creates a list of the n most common kmers
+    """
+    most_common_kmers = []
+
+    for _ in range(n):
+        highest_count = 0
+        most_common_kmer = None
+        for kmer in kmer_distribution:
+            if kmer[1] > highest_count and kmer not in most_common_kmers:
+                highest_count = kmer[1]
+                most_common_kmer = kmer
+
+        if most_common_kmer:
+            most_common_kmers.append(most_common_kmer)
+
+    return most_common_kmers
+
+
+def parse_table(table: hashing.hash_table, kmer_list):
+    """
+    Parses the hash table and returns a list of tuples containing the kmer and the count
+    """
+
+    kmer_distribution = []
+
+    unique_kmers = set(kmer_list)
+
+    for kmer in unique_kmers:
+        if table.search(kmer) is not None:
+            kmer_distribution.append((kmer, table.search(kmer)))
+
+    return kmer_distribution
+
+
+def get_kmers_with_count(kmer_distribution, count):
+    """
+    Creates a list of kmers whose occurrences are equal to the count
+    """
+    kmers_with_count = []
+    for kmer in kmer_distribution:
+        if kmer[1] == count:
+            kmers_with_count.append(kmer)
+
+    return kmers_with_count
+
+
+def parse_math_expression(expression):
+    """
+    Parses a math expression and returns the result
+    """
+
+    num = 0
+
+    # if expression contains ^, then it is a power
+    if "^" in expression:
+        # split the expression into the base and the exponent
+        base = int(expression.split("^")[0])
+        power = int(expression.split("^")[1])
+        return base ** power
+
+    # if expression contains *, then it is a multiplication
+    if "*" in expression:
+        # split the expression into the two factors
+        factor1 = int(expression.split("*")[0])
+        factor2 = int(expression.split("*")[1])
+        return factor1 * factor2
+
+    num = int(expression)
+    return num
+
+
+def get_inputs():
+    """
+    Gets user input for kmer distribution generation
+    """
+
+    alphabet = input("Enter the dna alphabet: ")
+    dna_length = (input("Enter the length of the dna: "))
+    k_mer = input("Enter the length of the kmer: ")
+
+    dna_length = parse_math_expression(dna_length)
+    k_mer = parse_math_expression(k_mer)
+
+    # return an object containing the alphabet, dna length, and kmer length
+
+    return {
+        "alphabet": alphabet,
+        "dna_length": dna_length,
+        "kmer_length": k_mer
+    }

data_processing/generate_kmers.ipynb

@@ -0,0 +1,54 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# this function is a recursive function that imitates the factorial operation\n",
+    "def generate_kmers(dna_sequence, k):\n",
+    "\n",
+    "    kmers = []\n",
+    "    pivot = 0\n",
+    "    def generate(kmers, dna_sequence, k, pivot):\n",
+    "        if(len(dna_sequence) < k):\n",
+    "            return kmers\n",
+    "\n",
+    "        candidate = dna_sequence[pivot:pivot+k]\n",
+    "        kmers.append(candidate)\n",
+    "\n",
+    "        return generate(kmers, dna_sequence[1:], k, pivot)\n",
+    "\n",
+    "    return generate(kmers, dna_sequence, k, pivot)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.10.8 64-bit",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

data_processing/generate_kmers.py

@@ -0,0 +1,35 @@
+# %%
+import random
+
+
+def generate_kmers(dna_sequence, k):
+    """
+    A function that generates all the kmers of length k from a dna sequence
+    """
+
+    kmers = []
+    pivot = 0
+
+    def generate(kmers, dna_sequence, k, pivot):
+        while (pivot + k <= len(dna_sequence)):
+            candidate = dna_sequence[pivot:pivot+k]
+            kmers.append(candidate)
+            pivot += 1
+        return kmers
+
+    return generate(kmers, dna_sequence, k, pivot)
+
+
+# %%
+def create_dna_sequence(bases, length):
+    """
+    Generates a random dna sequence of the desired length using the bases provided
+    """
+    sequence = ""
+    for i in range(length):
+        # get a random base
+        sequence += bases[random.randint(0, len(bases) - 1)]
+
+    return sequence
+
+# %%

data_processing/graph_distribution.py

@@ -0,0 +1,108 @@
+import plotly.graph_objects as go
+from matplotlib import pyplot as plt
+from collections import Counter
+from prettytable import PrettyTable
+
+
+def print_hashing_statistics(tabulated_data, title):
+    """
+    Creates and prints the tabulated performance data for the hash table
+    """
+
+    table = PrettyTable(
+        ["Hash Function", "Insertion Time", "Parsing Time", "Collisions"])
+
+    table.title = title
+
+    table.add_row([tabulated_data["Hash Function"][0], tabulated_data["Insertion Time"]
+                  [0], tabulated_data["Parsing Time"][0], tabulated_data["Collisions"][0]])
+    table.add_row([tabulated_data["Hash Function"][1], tabulated_data["Insertion Time"]
+                  [1], tabulated_data["Parsing Time"][1], tabulated_data["Collisions"][1]])
+
+    print(table)
+
+
+def py_bar_graph(kmer_distribution):
+    """
+    Creates a bar graph using matplotlib
+    """
+
+    kmer_len = len(kmer_distribution[0][0])
+    kmer_count = len(kmer_distribution)
+
+    title = str(kmer_count) + " Kmer Distribution for " + \
+        str(kmer_len) + "-mers"
+
+    x_title = "Kmer"
+    y_title = "Count"
+
+    x = list()
+    y = list()
+
+    for kmer in kmer_distribution:
+        x.append(kmer[0])
+        y.append(kmer[1])
+
+    plt.bar(x, y)
+    plt.title(title)
+    plt.xlabel(x_title)
+    plt.ylabel(y_title)
+    plt.show()
+
+
+def bar_graph(kmer_distribution):
+    """
+    Creates a bar graph using plotly
+    """
+
+    kmer_len = len(kmer_distribution[0][0])
+    kmer_count = len(kmer_distribution)
+
+    title = str(kmer_count) + " Kmer Distribution for " + \
+        str(kmer_len) + "-mers"
+
+    x_title = "Kmer"
+    y_title = "Count"
+
+    x = list()
+    y = list()
+
+    for kmer in kmer_distribution:
+        x.append(kmer[0])
+        y.append(kmer[1])
+
+    fig = go.Figure(data=[go.Bar(x=x, y=y)])
+    fig = fig.update_layout(
+        title=title,
+        xaxis_title=x_title,
+        yaxis_title=y_title,
+    )
+    fig.show()
+
+
+def pie_chart(kmer_distribution):
+    """
+    Creates a pie chart using plotly
+    """
+
+    x = list()
+    y = list()
+
+    for kmer in kmer_distribution:
+        x.append(kmer[0])
+        y.append(kmer[1])
+
+    fig = go.Figure(data=[go.Pie(labels=x, values=y)])
+    fig.show()
+
+
+def histogram(kmer_distribution):
+    """
+    Prints the kmer distribution as a primitive vertical histogram
+    """
+
+    histogram = Counter([kmer[0] for kmer in kmer_distribution])
+    for key in sorted(histogram):
+        count = histogram[key]
+        padding = (max(histogram.values()) - count) * " "
+        print(f"{key:3} {'■' * count}{padding} ({count})")

data_structures/binary_search_tree.ipynb

@@ -0,0 +1,209 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class node:\n",
+    "    # constructor\n",
+    "    def __init__(self) -> None:\n",
+    "        self.left = None\n",
+    "        self.right = None\n",
+    "        self.value = None\n",
+    "        self.counter = 0\n",
+    "\n",
+    "    def _display_aux(self):\n",
+    "        \"\"\"Returns list of strings, width, height, and horizontal coordinate of the root.\"\"\"\n",
+    "        # No child.\n",
+    "        if self.right is None and self.left is None:\n",
+    "            line = '%s : %s' % (self.counter, self.value)\n",
+    "            width = len(line)\n",
+    "            height = 1\n",
+    "            middle = width // 2\n",
+    "            return [line], width, height, middle\n",
+    "\n",
+    "        # Only left child.\n",
+    "        if self.right is None:\n",
+    "            lines, n, p, x = self.left._display_aux()  # type: ignore\n",
+    "            s = '%s : %s' % (self.counter, self.value)\n",
+    "            u = len(s)\n",
+    "            first_line = (x + 1) * ' ' + (n - x - 1) * '_' + s\n",
+    "            second_line = x * ' ' + '/' + (n - x - 1 + u) * ' '\n",
+    "            shifted_lines = [line + u * ' ' for line in lines]\n",
+    "            return [first_line, second_line] + shifted_lines, n + u, p + 2, n + u // 2\n",
+    "\n",
+    "        # Only right child.\n",
+    "        if self.left is None:\n",
+    "            lines, n, p, x = self.right._display_aux()\n",
+    "            s = '%s : %s' % (self.counter, self.value)\n",
+    "            u = len(s)\n",
+    "            first_line = s + x * '_' + (n - x) * ' '\n",
+    "            second_line = (u + x) * ' ' + '\\\\' + (n - x - 1) * ' '\n",
+    "            shifted_lines = [u * ' ' + line for line in lines]\n",
+    "            return [first_line, second_line] + shifted_lines, n + u, p + 2, u // 2\n",
+    "\n",
+    "        # Two children.\n",
+    "        left, n, p, x = self.left._display_aux()\n",
+    "        right, m, q, y = self.right._display_aux()\n",
+    "        s = '%s : %s' % (self.counter, self.value)\n",
+    "        u = len(s)\n",
+    "        first_line = (x + 1) * ' ' + (n - x - 1) * \\\n",
+    "            '_' + s + y * '_' + (m - y) * ' '\n",
+    "        second_line = x * ' ' + '/' + \\\n",
+    "            (n - x - 1 + u + y) * ' ' + '\\\\' + (m - y - 1) * ' '\n",
+    "        if p < q:\n",
+    "            left += [n * ' '] * (q - p)\n",
+    "        elif q < p:\n",
+    "            right += [m * ' '] * (p - q)\n",
+    "        zipped_lines = zip(left, right)\n",
+    "        lines = [first_line, second_line] + \\\n",
+    "            [a + u * ' ' + b for a, b in zipped_lines]\n",
+    "        return lines, n + m + u, max(p, q) + 2, n + u // 2\n",
+    "\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def add_node(root, value):\n",
+    "\n",
+    "    # if root is null, this node must be the root\n",
+    "    if root is None:\n",
+    "        root = node()\n",
+    "        root.value = value\n",
+    "        root.counter += 1\n",
+    "        return root\n",
+    "    if root.value is None:\n",
+    "        root.value = value\n",
+    "        return\n",
+    "    # if value is less than root.value go to left nodes\n",
+    "    if value < root.value:\n",
+    "        # if the left node does not exist\n",
+    "        if(root.left is None):\n",
+    "            root.left = node()\n",
+    "            root.left.value = value\n",
+    "            root.left.counter += 1\n",
+    "        else:\n",
+    "            root.left = add_node(root.left, value)\n",
+    "        \n",
+    "    if value > root.value:\n",
+    "        if(root.right is None):\n",
+    "            root.right = node()\n",
+    "            root.right.value = value\n",
+    "            root.right.counter += 1\n",
+    "        else:\n",
+    "            root.right = add_node(root.right, value)\n",
+    "\n",
+    "    if value == root.value:\n",
+    "        root.counter += 1\n",
+    "\n",
+    "    return"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# returns the counter of a node\n",
+    "def search_value(root, value):\n",
+    "\n",
+    "    if root is None:\n",
+    "        return 0\n",
+    "    \n",
+    "    if root == value:\n",
+    "        return root.counter\n",
+    "\n",
+    "    if value < root.value:\n",
+    "        return search_value(root.left, value)\n",
+    "    \n",
+    "    if value > root.value:\n",
+    "        return search_value(root.right, value)\n",
+    "    \n",
+    "    # if we are at the bottom of the tree and the value has still not been found, the value must not be within the tree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def destroy_tree(root):\n",
+    "\n",
+    "    # if a left node exists\n",
+    "    if root.left is not None:\n",
+    "        # recursively destroy the left node\n",
+    "        destroy_tree(root.left)\n",
+    "\n",
+    "    # if a right node exists\n",
+    "    if root.right is not None:\n",
+    "        # recursively destroy the right node\n",
+    "        destroy_tree(root.right)\n",
+    "\n",
+    "    # delete the root node\n",
+    "    del root"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_tree():\n",
+    "    return add_node(None, None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def show_tree(root):\n",
+    "\n",
+    "    if(root is None):\n",
+    "        return\n",
+    "\n",
+    "    lines, *_ = root._display_aux()\n",
+    "    for line in lines:\n",
+    "        print(line)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.10.8 64-bit",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

data_structures/binary_search_tree.py

@@ -0,0 +1,157 @@
+# %%
+class node:
+    # constructor
+    def __init__(self) -> None:
+        self.left = None
+        self.right = None
+        self.value = None
+        self.counter = 0
+
+    def _display_aux(self):
+        """Returns list of strings, width, height, and horizontal coordinate of the root."""
+        # No child.
+        if self.right is None and self.left is None:
+            line = '%s : %s' % (self.counter, self.value)
+            width = len(line)
+            height = 1
+            middle = width // 2
+            return [line], width, height, middle
+
+        # Only left child.
+        if self.right is None:
+            lines, n, p, x = self.left._display_aux()  # type: ignore
+            s = '%s : %s' % (self.counter, self.value)
+            u = len(s)
+            first_line = (x + 1) * ' ' + (n - x - 1) * '_' + s
+            second_line = x * ' ' + '/' + (n - x - 1 + u) * ' '
+            shifted_lines = [line + u * ' ' for line in lines]
+            return [first_line, second_line] + shifted_lines, n + u, p + 2, n + u // 2
+
+        # Only right child.
+        if self.left is None:
+            lines, n, p, x = self.right._display_aux()
+            s = '%s : %s' % (self.counter, self.value)
+            u = len(s)
+            first_line = s + x * '_' + (n - x) * ' '
+            second_line = (u + x) * ' ' + '\\' + (n - x - 1) * ' '
+            shifted_lines = [u * ' ' + line for line in lines]
+            return [first_line, second_line] + shifted_lines, n + u, p + 2, u // 2
+
+        # Two children.
+        left, n, p, x = self.left._display_aux()
+        right, m, q, y = self.right._display_aux()
+        s = '%s : %s' % (self.counter, self.value)
+        u = len(s)
+        first_line = (x + 1) * ' ' + (n - x - 1) * \
+            '_' + s + y * '_' + (m - y) * ' '
+        second_line = x * ' ' + '/' + \
+            (n - x - 1 + u + y) * ' ' + '\\' + (m - y - 1) * ' '
+        if p < q:
+            left += [n * ' '] * (q - p)
+        elif q < p:
+            right += [m * ' '] * (p - q)
+        zipped_lines = zip(left, right)
+        lines = [first_line, second_line] + \
+            [a + u * ' ' + b for a, b in zipped_lines]
+        return lines, n + m + u, max(p, q) + 2, n + u // 2
+
+
+# %%
+def add_node(root, value):
+
+    # if root is null, this node must be the root
+    if root is None:
+        root = node()
+        if value is not None:
+            root.value = value
+            root.counter += 1
+        return root
+
+    if root.value is None and value is not None:
+        root.value = value
+        root.counter += 1
+        return root
+
+    # if value is less than root.value go to left nodes
+    if value < root.value:
+        root.left = add_node(root.left, value)
+        # if the left node does not exist
+        # if root.left is None:
+        #     root.left = node()
+        #     root.left.value = value
+        #     if value is not None:
+        #         root.left.counter += 1
+        # else:
+        #     root.left = add_node(root.left, value)
+
+    if value > root.value:
+        root.right = add_node(root.right, value)
+        # if root.right is None:
+        #     root.right = node()
+        #     root.right.value = value
+        #     if value is not None:
+        #         root.right.counter += 1
+        # else:
+        #     root.right = add_node(root.right, value)
+
+    if value == root.value and value is not None:
+        root.counter += 1
+
+    return root
+
+# %%
+
+
+def search_value(root, value):
+
+    if value == root.value:
+        return root.counter
+
+    if root is None:
+        return 0
+
+    if value < root.value:
+        return search_value(root.left, value)
+
+    if value > root.value:
+        return search_value(root.right, value)
+
+    # if we are at the bottom of the tree and the value has still not been found, the value must not be within the tree
+
+# %%
+
+
+def destroy_tree(root):
+
+    # if a left node exists
+    if root.left is not None:
+        # recursively destroy the left node
+        destroy_tree(root.left)
+
+    # if a right node exists
+    if root.right is not None:
+        # recursively destroy the right node
+        destroy_tree(root.right)
+
+    # delete the root node
+    del root
+
+# %%
+
+
+def create_tree():
+    return add_node(None, None)
+
+# %%
+
+
+def show_tree(root):
+
+    if (root is None):
+        return
+
+    lines, *_ = root._display_aux()
+    for line in lines:
+        print(line)
+
+# %%

data_structures/hash_table.ipynb

@@ -0,0 +1,125 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from xxhash import xxh128 as xxhash\n",
+    "from mmh3 import hash128 as mmh3\n",
+    "\n",
+    "class hash_table:\n",
+    "\n",
+    "    # this table is designed for counting kmers\n",
+    "    # key : kmer\n",
+    "    # value : count\n",
+    "\n",
+    "    def __init__(self, size, hashing_flag):\n",
+    "        # set python's default hashing function as the default\n",
+    "        DEFAULT_HASH = self.__hash__\n",
+    "        MMH3_FLAG = \"mmh\"\n",
+    "        XXH_FLAG = \"xxh\"\n",
+    "\n",
+    "        self.size = size\n",
+    "        # a list of keys\n",
+    "        self.keys = [None for i in range(size)]\n",
+    "        # a list of values\n",
+    "        self.values = [0 for i in range(size)]\n",
+    "        self.hash = DEFAULT_HASH\n",
+    "        self.collision_count = 0\n",
+    "\n",
+    "        if hashing_flag == XXH_FLAG or hashing_flag == 1:\n",
+    "            self.hash = self.xxhash\n",
+    "        if hashing_flag == MMH3_FLAG or hashing_flag == 2:\n",
+    "            self.hash = self.mmh3\n",
+    "\n",
+    "    def __len__(self):\n",
+    "        return self.size\n",
+    "\n",
+    "    def insert(self, key):\n",
+    "        hash_index = self.hash(key)\n",
+    "        if self.keys[hash_index] is not None:\n",
+    "            if self.keys[hash_index] == key:\n",
+    "                self.values[hash_index] += 1\n",
+    "            else:\n",
+    "                # different keys have the same hash index\n",
+    "                # this is a collision\n",
+    "                self.collision_count += 1\n",
+    "                self.handle_collision(hash_index, key)\n",
+    "        else:\n",
+    "            self.keys[hash_index] = key\n",
+    "            self.values[hash_index] += 1\n",
+    "    \n",
+    "    def search(self, key):\n",
+    "        hash_index = self.hash(key)\n",
+    "        # return the value if the key is found\n",
+    "        if self.keys[hash_index] == key:\n",
+    "            return self.values[hash_index]\n",
+    "\n",
+    "        return None\n",
+    "\n",
+    "    def delete(self, key):\n",
+    "        hash_index = self.hash(key)\n",
+    "        # delete the key value pair if the key is found\n",
+    "        if self.keys[hash_index] == key:\n",
+    "            self.values[hash_index] = 0\n",
+    "            self.keys[hash_index] = None\n",
+    "\n",
+    "    def handle_collision(self, hash_index, key):\n",
+    "        def linear_probing(key):\n",
+    "            return (key + 1) % self.size\n",
+    "\n",
+    "        while self.keys[hash_index] is not None:\n",
+    "            hash_index = linear_probing(hash_index)\n",
+    "            if hash_index > self.size:\n",
+    "                return \n",
+    "\n",
+    "        self.keys[hash_index] = key\n",
+    "        self.values[hash_index] += 1\n",
+    "        return\n",
+    "\n",
+    "    def __hash__(self, key):\n",
+    "        return hash(key) % self.size\n",
+    "\n",
+    "    def xxhash(self, key):\n",
+    "        return xxhash(key).intdigest() % self.size\n",
+    "    \n",
+    "    def mmh3(self, key):\n",
+    "        return mmh3(key, signed=False) % self.size\n",
+    "\n",
+    "    def print(self):\n",
+    "        for i in range(self.size):\n",
+    "            if self.keys[i] is not None:\n",
+    "                print(f\"{self.keys[i]} : {self.values[i]}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.10.8 64-bit",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

data_structures/hash_table.py

@@ -0,0 +1,87 @@
+# %%
+from xxhash import xxh128 as xxhash
+from mmh3 import hash128 as mmh3
+
+
+class hash_table:
+
+    # this table is designed for counting kmers
+    # key : kmer
+    # value : count
+
+    def __init__(self, size, hashing_flag):
+        # set python's default hashing function as the default
+        DEFAULT_HASH = self.hasher
+        MMH3_FLAG = "mmh"
+        XXH_FLAG = "xxh"
+
+        self.size = size
+        # a list of keys
+        self.keys = [None for i in range(size)]
+        # a list of values
+        self.values = [0 for i in range(size)]
+        self.hash = DEFAULT_HASH
+        self.collision_count = 0
+
+        if hashing_flag == XXH_FLAG or hashing_flag == 1:
+            self.hash = self.xxhash
+        if hashing_flag == MMH3_FLAG or hashing_flag == 2:
+            self.hash = self.mmh3
+
+    def __len__(self):
+        return self.size
+
+    def insert(self, key):
+        hash_index = self.hash(key)
+        if self.keys[hash_index] is not None:
+            if self.keys[hash_index] == key:
+                self.values[hash_index] += 1
+            else:
+                # different keys have the same hash index
+                # this is a collision
+                self.collision_count += 1
+                self.handle_collision(hash_index, key)
+        else:
+            self.keys[hash_index] = key
+            self.values[hash_index] += 1
+
+    def search(self, key):
+        hash_index = self.hash(key)
+        # return the value if the key is found
+        if self.keys[hash_index] == key:
+            return self.values[hash_index]
+
+        return None
+
+    def delete(self, key):
+        hash_index = self.hash(key)
+        # delete the key value pair if the key is found
+        if self.keys[hash_index] == key:
+            self.values[hash_index] = 0
+            self.keys[hash_index] = None
+
+    def handle_collision(self, hash_index, key):
+        def linear_probing(key):
+            return (key + 1) % self.size
+
+        while self.keys[hash_index] is not None:
+            hash_index = linear_probing(hash_index)
+            if hash_index > self.size:
+                return
+
+        self.keys[hash_index] = key
+        self.values[hash_index] += 1
+
+    def hasher(self, key):
+        return hash(key) % self.size
+
+    def xxhash(self, key):
+        return xxhash(key).intdigest() % self.size
+
+    def mmh3(self, key):
+        return mmh3(key, signed=False) % self.size
+
+    def print(self):
+        for i in range(self.size):
+            if self.keys[i] is not None:
+                print(f"{self.keys[i]} : {self.values[i]}")

hash_table_kmer_distribution.ipynb

@@ -0,0 +1,4186 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "title: K-mer distribution table Hash Table\n",
+    "description: Generate a k-mer distribution table using a binary search tree\n",
+    "show-code: False\n",
+    "format:\n",
+    "   theme: night\n",
+    "params:\n",
+    "   dna_string:\n",
+    "      input: text\n",
+    "      label: input dna_string\n",
+    "      value: ACGT\n",
+    "   dna_len:\n",
+    "      input: numeric\n",
+    "      label: input dna_length\n",
+    "      value: 100\n",
+    "      min: 5\n",
+    "      max: 10000000000\n",
+    "      step: 10\n",
+    "   kmer_size:\n",
+    "      input: numeric\n",
+    "      label: input kmer_length\n",
+    "      value: 7\n",
+    "      min: 1\n",
+    "      max: 1000\n",
+    "      step: 1\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Edit the cell below to input your desired values. You can also input values using the input scanner."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dna_string = \"ACGT\"\n",
+    "dna_len = 10**6\n",
+    "kmer_size = 5"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from data_processing import generate_kmers as generator\n",
+    "from data_processing import graph_distribution as graph\n",
+    "from data_structures import hash_table as hashing\n",
+    "from data_processing import distribution_parser as parse\n",
+    "\n",
+    "import time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_table(kmer_list, hashing_function):\n",
+    "    \"\"\"\n",
+    "    Generates a hash table from a list of kmers and the desired hashing function\n",
+    "    \"\"\"\n",
+    "    list_len = len(kmer_list)\n",
+    "    table = hashing.hash_table(list_len, hashing_function)\n",
+    "    for kmer in kmer_list:\n",
+    "        table.insert(kmer)\n",
+    "\n",
+    "    return table"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def test_hash_table(dna_string, dna_len, kmer_size):\n",
+    "    \"\"\"\n",
+    "    Utility function to test the hash table\n",
+    "    \"\"\"\n",
+    "    alphabet = dna_string\n",
+    "    if dna_string is None:\n",
+    "        alphabet = input(\"Enter the alphabet: \")\n",
+    "    \n",
+    "    dna_length = dna_len\n",
+    "    if dna_len is None:\n",
+    "        dna_length = (input(\"Enter the length of the DNA string: \"))\n",
+    "        dna_length = parse.parse_math_expression(dna_length) \n",
+    "\n",
+    "    k_mer = kmer_size\n",
+    "    if kmer_size is None:\n",
+    "        k_mer = input(\"Enter the length of the kmer: \")\n",
+    "        k_mer = parse.parse_math_expression(k_mer)\n",
+    "\n",
+    "    # generate the DNA sequence\n",
+    "    DNA_SEQUENCE = generator.create_dna_sequence(alphabet, dna_length)\n",
+    "\n",
+    "    # generate the list of k-mers\n",
+    "    kmer_list = generator.generate_kmers(DNA_SEQUENCE, k_mer)\n",
+    "\n",
+    "    # test the mmh3 hashing function\n",
+    "    start = time.time()\n",
+    "    mmh3_table = generate_table(kmer_list, \"mmh\")\n",
+    "    end = time.time()\n",
+    "\n",
+    "    mmh3_insertion_time = end - start\n",
+    "\n",
+    "    # test the xxh hashing function\n",
+    "    start = time.time()\n",
+    "    xxh_table = generate_table(kmer_list, \"xxh\")\n",
+    "    end = time.time()\n",
+    "\n",
+    "    xxh_insertion_time = end - start\n",
+    "    # generate the distributions\n",
+    "    start = time.time()\n",
+    "    mmh3_distribution = parse.parse_table(mmh3_table, kmer_list)\n",
+    "    end = time.time()\n",
+    "\n",
+    "    mmh_parsing_time = end - start\n",
+    "\n",
+    "    start = time.time()\n",
+    "    xxh_distribution = parse.parse_table(xxh_table, kmer_list)\n",
+    "    end = time.time()\n",
+    "\n",
+    "    xxh_parsing_time = end - start\n",
+    "\n",
+    "    tabulated_data = {\n",
+    "        \"Hash Function\": [\"mmh3\", \"xxh\"],\n",
+    "        \"Insertion Time\": [mmh3_insertion_time, xxh_insertion_time],\n",
+    "        \"Parsing Time\": [mmh_parsing_time, xxh_parsing_time],\n",
+    "        \"Collisions\": [mmh3_table.collision_count, xxh_table.collision_count]\n",
+    "    }\n",
+    "\n",
+    "    graph.print_hashing_statistics(tabulated_data, alphabet + str(dna_length) + \" \" + str(k_mer) + \"mers\")\n",
+    "    unique_kmers = parse.get_unique_kmers(xxh_distribution)\n",
+    "    graph.bar_graph(xxh_distribution)\n",
+    "\n",
+    "    if len(unique_kmers) == 0:\n",
+    "        print(\"No unique k-mers found\")\n",
+    "    else:\n",
+    "        print(f\"Unique k-mers: {len(unique_kmers)}\")\n",
+    "        graph.bar_graph(unique_kmers)\n",
+    "\n",
+    "    if (len(xxh_distribution) > 100):\n",
+    "        print(\"Most common 10% kmers: \")\n",
+    "        most_common_kmers = parse.get_most_common_kmers(xxh_distribution, int(len(xxh_distribution) * 0.10))\n",
+    "        graph.bar_graph(most_common_kmers)\n",
+    "\n",
+    "    # the distribution of one is the same as the other\n",
+    "    # graph.bar_graph(mmh3_distribution)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+------------------------------------------------------------------------+\n",
+      "|                           ACGT1000000 5mers                            |\n",
+      "+---------------+--------------------+----------------------+------------+\n",
+      "| Hash Function |   Insertion Time   |     Parsing Time     | Collisions |\n",
+      "+---------------+--------------------+----------------------+------------+\n",
+      "|      mmh3     | 1.2975947856903076 | 0.06290507316589355  |    1935    |\n",
+      "|      xxh      | 0.805696964263916  | 0.026388883590698242 |     0      |\n",
+      "+---------------+--------------------+----------------------+------------+\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.plotly.v1+json": {
+       "config": {
+        "plotlyServerURL": "https://plot.ly"
+       },
+       "data": [
+        {
+         "type": "bar",
+         "x": [
+          "GCCGC",
+          "TTTGT",
+          "GCCGG",
+          "TAGCA",
+          "GGTTG",
+          "TACGG",
+          "CCCCA",
+          "GATGT",
+          "CACTA",
+          "CGTTA",
+          "CACCA",
+          "ACGAG",
+          "TGCAA",
+          "AAATC",
+          "AGATA",
+          "CGCAT",
+          "GGGTA",
+          "GTCAG",
+          "AGGTG",
+          "TACCA",
+          "TGGAG",
+          "TTTAT",
+          "CACGG",
+          "TATTC",
+          "TAATT",
+          "AGCGA",
+          "AGTTA",
+          "TGTTT",
+          "GCGAT",
+          "TTTGG",
+          "ACCTC",
+          "TTCAT",
+          "TGCGA",
+          "ATCGA",
+          "GAATA",
+          "GTGAG",
+          "GCTTG",
+          "CAGGT",
+          "AACCC",
+          "GGCAC",
+          "AAACT",
+          "GGATT",
+          "CTGTC",
+          "TCTAT",
+          "TTACC",
+          "CCGAT",
+          "ACAGA",
+          "ACTAT",
+          "CGGTT",
+          "CTTGT",
+          "ACTTT",
+          "CTTTT",
+          "TTAAA",
+          "CTCAT",
+          "GTCTA",
+          "GCTGG",
+          "CCAAG",
+          "TTGGC",
+          "AGCAA",
+          "GTTGA",
+          "CAAAT",
+          "CACCC",
+          "GCAGG",
+          "GTGTC",
+          "ACCTA",
+          "TTCAC",
+          "GCTAT",
+          "CTAGT",
+          "TTGGG",
+          "TCAGG",
+          "CAATA",
+          "ACGGT",
+          "CATGC",
+          "GATAC",
+          "TGGCT",
+          "GCGTC",
+          "ATTTC",
+          "GGTAC",
+          "CGTCA",
+          "CTATA",
+          "GAACG",
+          "GCGGG",
+          "ATCGC",
+          "AGCTG",
+          "CAACG",
+          "ATAAG",
+          "AGTCC",
+          "GTTTC",
+          "AAAAC",
+          "GCACC",
+          "ACATT",
+          "CTGGA",
+          "CTGTT",
+          "GCTCA",
+          "ATTCC",
+          "CCCTG",
+          "GTGGA",
+          "TCCCA",
+          "AATGG",
+          "CTCAA",
+          "CTATG",
+          "TCAAG",
+          "AGCTA",
+          "CGTCG",
+          "GGAGC",
+          "CCTCA",
+          "GTCGT",
+          "CGTAC",
+          "GACAT",
+          "GGGGG",
+          "AGGTC",
+          "TAGGG",
+          "TCGCA",
+          "CCTCG",
+          "ATACA",
+          "TTTAA",
+          "AACGA",
+          "TGCCA",
+          "GTGTA",
+          "AATAT",
+          "ATCGT",
+          "CCATG",
+          "TGACC",
+          "ATGGG",
+          "AATAC",
+          "AAATT",
+          "GGCGA",
+          "CCTCC",
+          "TGGAA",
+          "CGAGA",
+          "TCCAA",
+          "CTAGA",
+          "TCTCG",
+          "TGAAG",
+          "CACTG",
+          "TTTTT",
+          "AGGAA",
+          "TTAAT",
+          "ACAAG",
+          "GGGGA",
+          "CATGA",
+          "GGTGG",
+          "TTATA",
+          "CCACG",
+          "AGCGC",
+          "TCGAG",
+          "TAATC",
+          "TCCGG",
+          "CCAAT",
+          "TTTGA",
+          "TGAAC",
+          "ACACG",
+          "ACGTA",
+          "ACACT",
+          "TCAGT",
+          "CAAGT",
+          "CGTAG",
+          "CCCTA",
+          "GGCGC",
+          "GCCAC",
+          "TCCCG",
+          "AATCC",
+          "ACAAT",
+          "CGACT",
+          "GGTCT",
+          "TCCCT",
+          "CCGCC",
+          "AATTC",
+          "TGGCC",
+          "CTGTG",
+          "CCCCT",
+          "TAGAG",
+          "AATTA",
+          "CCCAG",
+          "CTCGT",
+          "TATGG",
+          "TGTCG",
+          "GTACG",
+          "GTTTA",
+          "TCTTA",
+          "TCACG",
+          "CATAT",
+          "AATCT",
+          "TTACA",
+          "CTTGC",
+          "CGACA",
+          "AACTG",
+          "TAATA",
+          "CAGTG",
+          "CCTGG",
+          "ATTAC",
+          "AATAG",
+          "GAGCT",
+          "CGACC",
+          "GAGAT",
+          "CGATC",
+          "ACTAG",
+          "GGATG",
+          "CGGGT",
+          "GGCGG",
+          "CCACA",
+          "AAAAG",
+          "CCAAA",
+          "GTTCG",
+          "CCCAC",
+          "GAGAG",
+          "CCGGC",
+          "ACAGT",
+          "AGTGG",
+          "CGTAA",
+          "CAATG",
+          "ACATC",
+          "ATATT",
+          "ATCTC",
+          "CATAA",
+          "AATAA",
+          "GATCG",
+          "GTGTG",
+          "CATTC",
+          "GGGAT",
+          "TAGCG",
+          "GGAGA",
+          "ATATA",
+          "GACAG",
+          "CCTAC",
+          "CACAC",
+          "ATCTT",
+          "ACGAA",
+          "ACCAC",
+          "TGTGT",
+          "CATAC",
+          "CCGGT",
+          "GGTAA",
+          "TGGTA",
+          "TGCAC",
+          "GAACA",
+          "CTGGG",
+          "GAGCG",
+          "CCATT",
+          "AACCG",
+          "TCATA",
+          "TCGTC",
+          "CCGTC",
+          "CCAGT",
+          "GTAAG",
+          "AGCGT",
+          "CCGCT",
+          "CCGTG",
+          "TCATG",
+          "TTAAC",
+          "TTGTT",
+          "ATCAT",
+          "CGCTT",
+          "AAGCT",
+          "ATCCA",
+          "CGGTG",
+          "GATGG",
+          "ACGAT",
+          "TATTA",
+          "CCTTG",
+          "TTGAT",
+          "CACCT",
+          "CCTGA",
+          "ATGAC",
+          "TATAC",
+          "TGGGG",
+          "AACTA",
+          "TCCTG",
+          "ATTAG",
+          "GGTCG",
+          "GAGGA",
+          "CCGGG",
+          "ACGGG",
+          "GGCGT",
+          "GTCCA",
+          "CATGT",
+          "TTCGA",
+          "GACCG",
+          "GCCCA",
+          "TGAGC",
+          "GCCGA",
+          "AACAG",
+          "GGGGT",
+          "GAAAC",
+          "TGTTA",
+          "GACCT",
+          "TCCAC",
+          "ATCTA",
+          "CTTCG",
+          "TCAGC",
+          "ATTGT",
+          "CTTTG",
+          "TGTCA",
+          "ACGGC",
+          "TACTG",
+          "TTCAA",
+          "GACCC",
+          "TACTA",
+          "GAATC",
+          "TCTTT",
+          "TTGTA",
+          "TCTAA",
+          "CATTG",
+          "ATTAA",
+          "GACAC",
+          "GAAGT",
+          "CACAG",
+          "GTATA",
+          "CAGTA",
+          "TGAAT",
+          "CGAAA",
+          "CCCGT",
+          "CTTCA",
+          "GTGGG",
+          "GAAGG",
+          "CACAA",
+          "GCTAG",
+          "AGCTC",
+          "AGGCC",
+          "GGAGG",
+          "GCGGC",
+          "TTCCC",
+          "TTTTC",
+          "AGAAA",
+          "TTTGC",
+          "ACAGG",
+          "CAGCC",
+          "ACTCA",
+          "CAGCG",
+          "GTTAC",
+          "GAAGA",
+          "CGCCG",
+          "AACAC",
+          "ACCCT",
+          "GCCTC",
+          "ATAAT",
+          "TACAG",
+          "AATTT",
+          "CGGTC",
+          "AAAGA",
+          "GACTT",
+          "CGAAG",
+          "AACTC",
+          "GCGTT",
+          "ACCGA",
+          "AGCCT",
+          "TCCAG",
+          "AAACA",
+          "GATCT",
+          "CACCG",
+          "CGTGT",
+          "TAGTA",
+          "TTTAG",
+          "CGAGG",
+          "GCAGT",
+          "AACGC",
+          "GGGTG",
+          "CTACC",
+          "GGGGC",
+          "TGACT",
+          "AATGA",
+          "ATGGT",
+          "AAGGT",
+          "ACGCT",
+          "ATGTT",
+          "GATGC",
+          "AGATG",
+          "CATCC",
+          "GACGG",
+          "AAACC",
+          "ATAGC",
+          "GTTTT",
+          "AGTTG",
+          "AAGAA",
+          "TACTT",
+          "CTACA",
+          "TCGGC",
+          "GCCCG",
+          "ACCAA",
+          "AAGAT",
+          "GACGA",
+          "ACGTT",
+          "CAACC",
+          "CAATC",
+          "CTCGA",
+          "ACCGT",
+          "GGACT",
+          "AATGT",
+          "GCATT",
+          "CTAGC",
+          "CTTTC",
+          "AGACC",
+          "TTTTG",
+          "TTAGC",
+          "AGTAT",
+          "CTCCC",
+          "GATAT",
+          "CTAAT",
+          "AAATA",
+          "ATTGG",
+          "AAAAT",
+          "TTTCT",
+          "TCGTA",
+          "ACTGT",
+          "TCACC",
+          "ACTCT",
+          "GAGTA",
+          "GTAGT",
+          "ACTAC",
+          "TTCTA",
+          "ATGCT",
+          "AGATC",
+          "CAAGC",
+          "CAAAA",
+          "TAACC",
+          "GCTTC",
+          "CCTGC",
+          "ATAAC",
+          "GTCGG",
+          "AGGCG",
+          "CCGCG",
+          "GAGTC",
+          "GGCTG",
+          "GTGCG",
+          "AGGCA",
+          "TCGCG",
+          "CTTAC",
+          "TGATG",
+          "TTCGC",
+          "TGAAA",
+          "TACGA",
+          "CCGCA",
+          "GCAAG",
+          "ACTAA",
+          "GGACA",
+          "TACTC",
+          "GGTCC",
+          "TTCTC",
+          "AGATT",
+          "GTGCC",
+          "GGGTC",
+          "AGCGG",
+          "TTCCT",
+          "CGTTG",
+          "GGGAC",
+          "CTTTA",
+          "AAGAG",
+          "ACTCC",
+          "TCGGG",
+          "GCTTA",
+          "GGCTC",
+          "TGATA",
+          "CACGT",
+          "CGGAA",
+          "ACCCG",
+          "GGCCA",
+          "GTATG",
+          "AAGCC",
+          "CGGGA",
+          "TCTTC",
+          "AGCAT",
+          "CTGAC",
+          "ATAAA",
+          "TAGCC",
+          "AATTG",
+          "GGCTT",
+          "TCTGT",
+          "GTAGA",
+          "AGTGA",
+          "ATTTA",
+          "ATATC",
+          "GCGTA",
+          "GGGAG",
+          "GGCCT",
+          "GCGTG",
+          "ACTGA",
+          "TCCCC",
+          "CAGCT",
+          "CAGCA",
+          "TCTCC",
+          "ATGGC",
+          "TAGTT",
+          "GGAAG",
+          "CCCGG",
+          "GAGAC",
+          "CCCAT",
+          "CATCA",
+          "CTCAC",
+          "CGGGG",
+          "GTCAT",
+          "TAGGA",
+          "TATAA",
+          "CTCCG",
+          "TAAAG",
+          "ATCAG",
+          "TTTCG",
+          "TATGT",
+          "GCCAA",
+          "AAACG",
+          "TCCTT",
+          "TATGC",
+          "GAGGC",
+          "GGCCC",
+          "TAAAA",
+          "TCTAC",
+          "TTGCA",
+          "CTCTG",
+          "TCTCT",
+          "TCTAG",
+          "CAGGG",
+          "ACCAG",
+          "GCTCC",
+          "GCACT",
+          "GAGTT",
+          "GCCTA",
+          "GAGCC",
+          "CCGAG",
+          "TGCGT",
+          "AGTGT",
+          "TCAAT",
+          "TAGGC",
+          "GGGTT",
+          "TAACG",
+          "CGGAT",
+          "AGGAT",
+          "TCGGA",
+          "TTGAG",
+          "CCCAA",
+          "ATGCA",
+          "CGTGC",
+          "CTGAT",
+          "CCGAC",
+          "TATTT",
+          "GTACC",
+          "ATTGA",
+          "TCAAA",
+          "CCCTC",
+          "GTTGT",
+          "CCAGA",
+          "GTCTC",
+          "CTATT",
+          "ATCCC",
+          "AAAGT",
+          "TAGTC",
+          "TCGGT",
+          "TTCTG",
+          "CGGCA",
+          "GGCAG",
+          "GAATT",
+          "TTACT",
+          "TACGC",
+          "TAAGC",
+          "AGCAC",
+          "TGCGC",
+          "ACGCC",
+          "CAATT",
+          "CGTTC",
+          "TGTAC",
+          "TGTGG",
+          "GACAA",
+          "TGTTG",
+          "AATCA",
+          "ACATA",
+          "TAGCT",
+          "GCTGC",
+          "CATTT",
+          "TTAGG",
+          "AAGTA",
+          "GGAAT",
+          "AAGAC",
+          "GACGT",
+          "AAGCA",
+          "AGAGA",
+          "AGTCA",
+          "GGGCG",
+          "ATATG",
+          "GGAAC",
+          "AGCCA",
+          "TCTCA",
+          "GTTCC",
+          "ACCGC",
+          "TGCTT",
+          "AGACG",
+          "GCGGA",
+          "CTTCC",
+          "GTCCG",
+          "CACAT",
+          "GCTCT",
+          "TACAT",
+          "ACACC",
+          "CTGCC",
+          "AACAT",
+          "GATAA",
+          "CGCGA",
+          "CAAAG",
+          "TCGAT",
+          "AGTGC",
+          "ATGAT",
+          "ACGCA",
+          "CTAAC",
+          "GCACA",
+          "CGGCT",
+          "ATCAC",
+          "TAAAC",
+          "CACGA",
+          "CCGGA",
+          "CTGTA",
+          "GTTGG",
+          "CGAAT",
+          "CTAGG",
+          "AACAA",
+          "GCGCC",
+          "CCGTT",
+          "GCATA",
+          "TAGAT",
+          "GGTGT",
+          "GAACT",
+          "CGCTA",
+          "GTCTT",
+          "ACTTA",
+          "CTGCT",
+          "CATCG",
+          "CACTC",
+          "CCTAG",
+          "TGCCT",
+          "GTAGC",
+          "ACATG",
+          "GGTGA",
+          "GGACG",
+          "AAATG",
+          "ATTTT",
+          "TGAGA",
+          "ATCCT",
+          "TATAG",
+          "CTGCG",
+          "AGTAC",
+          "TCCTC",
+          "TGCGG",
+          "ATGTC",
+          "ACCCC",
+          "GTCCT",
+          "CGGCG",
+          "ACGTC",
+          "CTTGA",
+          "GTTTG",
+          "AGAAT",
+          "CATCT",
+          "TGTGC",
+          "AGGGC",
+          "CAGAT",
+          "GTTCT",
+          "GTATC",
+          "TCCGT",
+          "GCATC",
+          "ATACT",
+          "GTTGC",
+          "GATCC",
+          "CCAAC",
+          "TTTAC",
+          "ACCCA",
+          "GCGGT",
+          "CTTAA",
+          "ACTTC",
+          "GATTA",
+          "TTGAA",
+          "TAGAC",
+          "CCGAA",
+          "GGTCA",
+          "CTCGC",
+          "TAGGT",
+          "AAAGC",
+          "GACCA",
+          "GTGGC",
+          "TGCCG",
+          "ACCTG",
+          "TAAGG",
+          "GCTGT",
+          "AGACA",
+          "CGCTC",
+          "GCATG",
+          "CGCTG",
+          "CAGAC",
+          "ATGCG",
+          "TTCTT",
+          "AGTCT",
+          "TTCCA",
+          "CCATC",
+          "GCCCT",
+          "TACAA",
+          "ACTGG",
+          "GGACC",
+          "CGTTT",
+          "AGCTT",
+          "GCTTT",
+          "GTCAA",
+          "TGTCT",
+          "GTAAC",
+          "CGTCC",
+          "GCGAC",
+          "TTCAG",
+          "GTAAA",
+          "GGATA",
+          "GTACT",
+          "CGACG",
+          "ACTTG",
+          "TCGCC",
+          "TCGAC",
+          "CTGAA",
+          "GAAAT",
+          "TTACG",
+          "ACCGG",
+          "CACGC",
+          "TTAAG",
+          "ATGAA",
+          "CTCCT",
+          "CGATT",
+          "GGCAA",
+          "CTGAG",
+          "GCCAG",
+          "CCAGG",
+          "TCGCT",
+          "CGCCA",
+          "GTGAT",
+          "ATCGG",
+          "TTTCA",
+          "AACCA",
+          "ATGTG",
+          "CGCGT",
+          "TATGA",
+          "TGTTC",
+          "TACCG",
+          "AGCCG",
+          "CAAAC",
+          "GTTCA",
+          "GGGAA",
+          "GATGA",
+          "CTGCA",
+          "ACAAC",
+          "GGAGT",
+          "CCGTA",
+          "GCAGC",
+          "ATGTA",
+          "GTCAC",
+          "TGCTG",
+          "CTCTA",
+          "AACCT",
+          "GCGAG",
+          "AGAAG",
+          "TAGTG",
+          "GAGGT",
+          "AAAAA",
+          "GTGGT",
+          "GTCGA",
+          "CCTCT",
+          "GCAAT",
+          "GATTG",
+          "GGTAT",
+          "ATAGA",
+          "CCCCG",
+          "AAGTG",
+          "GGCAT",
+          "TGCAG",
+          "CTGGT",
+          "GCTGA",
+          "GCTCG",
+          "CGGGC",
+          "CGTGA",
+          "AAGGC",
+          "TAGAA",
+          "TGCCC",
+          "TGTAG",
+          "TAAGA",
+          "AAGTC",
+          "CGAAC",
+          "GGTTA",
+          "TCACA",
+          "TGGTC",
+          "TGTGA",
+          "GTGAC",
+          "GCTAC",
+          "AGGTA",
+          "ACACA",
+          "GCGCA",
+          "CAGGA",
+          "AGACT",
+          "GAGGG",
+          "ATTCG",
+          "CGGAC",
+          "CATTA",
+          "CTACG",
+          "AGGGA",
+          "TCAAC",
+          "CGGTA",
+          "TTTCC",
+          "GTTAT",
+          "TAAAT",
+          "TGAGT",
+          "TTAGT",
+          "CGAGT",
+          "CAAGA",
+          "TCGAA",
+          "ACGCG",
+          "ATCCG",
+          "CTTCT",
+          "CGATA",
+          "CTCAG",
+          "TAACT",
+          "AGGTT",
+          "CTCTT",
+          "GCCCC",
+          "ACGAC",
+          "AGTAA",
+          "TAATG",
+          "ATTCA",
+          "TGACA",
+          "AAGTT",
+          "CGCAC",
+          "CGCCC",
+          "ATGAG",
+          "AGCCC",
+          "TGGTG",
+          "ATGCC",
+          "TATTG",
+          "AGAGC",
+          "ATGGA",
+          "GAAAA",
+          "CTTAG",
+          "GATTC",
+          "ATACC",
+          "TGACG",
+          "GAAGC",
+          "GCGAA",
+          "CTCTC",
+          "TGGCG",
+          "CCTAT",
+          "TTGGA",
+          "TCCAT",
+          "TATCA",
+          "TCGTG",
+          "GTTAA",
+          "CTATC",
+          "ATTAT",
+          "GATAG",
+          "GATTT",
+          "TGGAT",
+          "CAACT",
+          "GTCCC",
+          "GCTAA",
+          "GTCTG",
+          "TGGAC",
+          "AGGGT",
+          "AGGAC",
+          "CAGTT",
+          "AGAGT",
+          "TCACT",
+          "CCCGA",
+          "AGCAG",
+          "TTATC",
+          "GCCTG",
+          "TTATT",
+          "CTTAT",
+          "AGTTC",
+          "AAGGG",
+          "TTGGT",
+          "TTGTG",
+          "CCACT",
+          "TCTGC",
+          "GAGTG",
+          "TATCT",
+          "CGATG",
+          "TTGCG",
+          "CATGG",
+          "ATAGT",
+          "CGCGG",
+          "GCCTT",
+          "TCCGC",
+          "ATTTG",
+          "CAACA",
+          "ACCAT",
+          "GCGCT",
+          "TGCTA",
+          "TATAT",
+          "GTTAG",
+          "CTAAG",
+          "GGGCA",
+          "TGGTT",
+          "CCTGT",
+          "GGGCC",
+          "TATCC",
+          "GGCTA",
+          "TCTTG",
+          "AGTTT",
+          "GGTTC",
+          "AGAGG",
+          "GAATG",
+          "GTAAT",
+          "AAGCG",
+          "CCTTC",
+          "TGTCC",
+          "ACAGC",
+          "TCATT",
+          "GACTC",
+          "TTCGT",
+          "GTGCA",
+          "CCCCC",
+          "ATACG",
+          "TTGCT",
+          "GTATT",
+          "TTAGA",
+          "ATAGG",
+          "AACGT",
+          "CAGTC",
+          "TTGTC",
+          "CCCTT",
+          "AGAAC",
+          "TCCTA",
+          "ATCTG",
+          "CAGAG",
+          "TGGCA",
+          "GTGTT",
+          "CCTAA",
+          "CAGGC",
+          "CTGGC",
+          "GACGC",
+          "GCGCG",
+          "AGGGG",
+          "TAACA",
+          "GGAAA",
+          "CCCGC",
+          "ACGGA",
+          "GTAGG",
+          "GTCGC",
+          "TCTGG",
+          "TACAC",
+          "TTCGG",
+          "CCATA",
+          "TGATC",
+          "CGTGG",
+          "ACCTT",
+          "TGTAT",
+          "GGTTT",
+          "CAAGG",
+          "AGTAG",
+          "GAAAG",
+          "TGATT",
+          "TCCGA",
+          "GACTG",
+          "CGTAT",
+          "ATTCT",
+          "AAAGG",
+          "ATCAA",
+          "TTTTA",
+          "TACCT",
+          "TGAGG",
+          "TAAGT",
+          "ACTGC",
+          "CGTCT",
+          "GTGCT",
+          "AGGAG",
+          "CGGAG",
+          "GAACC",
+          "TGTAA",
+          "GCAAC",
+          "CGCAA",
+          "TGGGA",
+          "TTATG",
+          "GCCAT",
+          "CCTTT",
+          "ACAAA",
+          "GGTAG",
+          "CATAG",
+          "CCAGC",
+          "CTTGG",
+          "TACGT",
+          "TTGCC",
+          "TCATC",
+          "GGGCT",
+          "GAGAA",
+          "ATTGC",
+          "CTACT",
+          "TTGAC",
+          "GTGAA",
+          "CAGAA",
+          "ACGTG",
+          "GGTGC",
+          "CTCCA",
+          "GATCA",
+          "CACTT",
+          "GCCGT",
+          "CTAAA",
+          "GCAAA",
+          "TATCG",
+          "TGGGC",
+          "AGGCT",
+          "AACTT",
+          "TACCC",
+          "CGCAG",
+          "GGCCG",
+          "GGATC",
+          "AATCG",
+          "CTCGG",
+          "TCTGA",
+          "TGCTC",
+          "CGAGC",
+          "TCGTT",
+          "AACGG",
+          "TCAGA",
+          "CGCCT",
+          "TGGGT",
+          "TGCAT",
+          "GCACG",
+          "ACTCG",
+          "GTACA",
+          "CCACC",
+          "CGCGC",
+          "GAGCA",
+          "AAGGA",
+          "AATGC",
+          "GCAGA",
+          "CCTTA",
+          "GACTA",
+          "CGGCC",
+          "TTCCG",
+          "AGTCG"
+         ],
+         "y": [
+          960,
+          1032,
+          976,
+          1001,
+          1005,
+          999,
+          986,
+          1005,
+          993,
+          937,
+          988,
+          984,
+          1002,
+          989,
+          999,
+          991,
+          981,
+          917,
+          968,
+          977,
+          956,
+          946,
+          950,
+          1008,
+          928,
+          993,
+          1021,
+          959,
+          983,
+          963,
+          982,
+          965,
+          993,
+          1008,
+          974,
+          975,
+          947,
+          1000,
+          952,
+          1002,
+          982,
+          984,
+          969,
+          1000,
+          956,
+          936,
+          972,
+          935,
+          975,
+          1007,
+          1009,
+          987,
+          945,
+          999,
+          978,
+          974,
+          951,
+          965,
+          988,
+          1000,
+          981,
+          997,
+          1026,
+          991,
+          975,
+          915,
+          972,
+          954,
+          993,
+          945,
+          964,
+          1014,
+          991,
+          967,
+          995,
+          902,
+          999,
+          978,
+          910,
+          900,
+          1004,
+          984,
+          923,
+          1025,
+          989,
+          959,
+          980,
+          1001,
+          929,
+          1024,
+          962,
+          970,
+          959,
+          940,
+          955,
+          940,
+          925,
+          962,
+          1062,
+          981,
+          975,
+          984,
+          965,
+          973,
+          1002,
+          932,
+          991,
+          976,
+          1003,
+          969,
+          972,
+          992,
+          993,
+          986,
+          927,
+          915,
+          962,
+          967,
+          1013,
+          937,
+          949,
+          979,
+          1022,
+          1033,
+          969,
+          968,
+          994,
+          991,
+          976,
+          1018,
+          964,
+          1040,
+          1043,
+          968,
+          946,
+          932,
+          981,
+          949,
+          937,
+          924,
+          994,
+          950,
+          928,
+          1009,
+          981,
+          987,
+          906,
+          981,
+          1058,
+          1042,
+          977,
+          942,
+          973,
+          991,
+          936,
+          918,
+          1002,
+          933,
+          955,
+          1005,
+          1006,
+          966,
+          994,
+          996,
+          965,
+          928,
+          976,
+          961,
+          986,
+          1024,
+          991,
+          983,
+          959,
+          964,
+          943,
+          981,
+          1011,
+          984,
+          910,
+          969,
+          970,
+          962,
+          1020,
+          933,
+          983,
+          944,
+          982,
+          959,
+          1003,
+          943,
+          928,
+          960,
+          991,
+          968,
+          1029,
+          935,
+          1013,
+          982,
+          999,
+          958,
+          976,
+          988,
+          958,
+          1004,
+          994,
+          1005,
+          990,
+          1000,
+          975,
+          960,
+          1007,
+          974,
+          989,
+          958,
+          1005,
+          970,
+          999,
+          973,
+          916,
+          924,
+          985,
+          981,
+          1004,
+          930,
+          945,
+          982,
+          946,
+          981,
+          984,
+          1011,
+          951,
+          963,
+          984,
+          970,
+          1001,
+          932,
+          994,
+          1049,
+          995,
+          934,
+          957,
+          944,
+          959,
+          960,
+          962,
+          953,
+          982,
+          932,
+          1027,
+          979,
+          927,
+          969,
+          944,
+          975,
+          969,
+          951,
+          1005,
+          918,
+          981,
+          1042,
+          985,
+          964,
+          1000,
+          1038,
+          918,
+          978,
+          974,
+          972,
+          979,
+          980,
+          1000,
+          975,
+          933,
+          965,
+          965,
+          1039,
+          987,
+          993,
+          931,
+          1027,
+          964,
+          979,
+          1071,
+          964,
+          967,
+          974,
+          933,
+          1045,
+          975,
+          999,
+          951,
+          990,
+          991,
+          978,
+          940,
+          964,
+          992,
+          928,
+          1000,
+          1005,
+          1008,
+          941,
+          965,
+          945,
+          1026,
+          978,
+          1018,
+          1007,
+          992,
+          1022,
+          967,
+          999,
+          979,
+          1013,
+          1003,
+          982,
+          990,
+          974,
+          1012,
+          1002,
+          1018,
+          1023,
+          954,
+          932,
+          944,
+          898,
+          915,
+          1006,
+          979,
+          974,
+          974,
+          973,
+          988,
+          973,
+          982,
+          936,
+          933,
+          989,
+          998,
+          962,
+          983,
+          974,
+          1013,
+          1013,
+          966,
+          954,
+          1001,
+          1016,
+          950,
+          968,
+          954,
+          949,
+          1016,
+          998,
+          1048,
+          1022,
+          1084,
+          986,
+          997,
+          1006,
+          1014,
+          978,
+          970,
+          961,
+          1007,
+          975,
+          992,
+          947,
+          1022,
+          946,
+          920,
+          925,
+          957,
+          943,
+          962,
+          994,
+          935,
+          950,
+          1038,
+          997,
+          942,
+          935,
+          1049,
+          992,
+          1025,
+          935,
+          957,
+          972,
+          906,
+          955,
+          958,
+          984,
+          1006,
+          979,
+          967,
+          1009,
+          1050,
+          929,
+          939,
+          959,
+          1027,
+          940,
+          982,
+          946,
+          932,
+          1024,
+          933,
+          916,
+          978,
+          994,
+          990,
+          1028,
+          928,
+          964,
+          974,
+          952,
+          972,
+          964,
+          987,
+          969,
+          993,
+          1006,
+          957,
+          980,
+          1004,
+          968,
+          976,
+          1012,
+          957,
+          985,
+          939,
+          930,
+          939,
+          969,
+          994,
+          997,
+          977,
+          964,
+          980,
+          987,
+          1046,
+          1001,
+          963,
+          1009,
+          940,
+          1029,
+          978,
+          927,
+          1017,
+          962,
+          1006,
+          1008,
+          994,
+          1002,
+          1002,
+          1048,
+          1046,
+          954,
+          978,
+          1019,
+          969,
+          990,
+          973,
+          942,
+          989,
+          978,
+          1001,
+          992,
+          968,
+          929,
+          978,
+          970,
+          1006,
+          1005,
+          1011,
+          974,
+          1033,
+          993,
+          960,
+          909,
+          1032,
+          957,
+          1022,
+          986,
+          956,
+          960,
+          953,
+          946,
+          1019,
+          972,
+          1012,
+          901,
+          956,
+          942,
+          957,
+          978,
+          929,
+          997,
+          923,
+          985,
+          999,
+          1066,
+          969,
+          1000,
+          1038,
+          1006,
+          1019,
+          993,
+          1025,
+          1004,
+          940,
+          992,
+          1006,
+          1019,
+          976,
+          997,
+          1029,
+          980,
+          996,
+          933,
+          994,
+          1018,
+          984,
+          1015,
+          986,
+          981,
+          981,
+          963,
+          979,
+          1026,
+          1002,
+          931,
+          955,
+          959,
+          975,
+          959,
+          955,
+          960,
+          980,
+          1010,
+          999,
+          948,
+          966,
+          922,
+          975,
+          917,
+          926,
+          967,
+          1010,
+          973,
+          964,
+          908,
+          1012,
+          975,
+          995,
+          992,
+          1005,
+          997,
+          1007,
+          976,
+          995,
+          913,
+          942,
+          976,
+          1027,
+          992,
+          992,
+          935,
+          940,
+          988,
+          967,
+          951,
+          979,
+          911,
+          913,
+          985,
+          982,
+          949,
+          969,
+          1008,
+          991,
+          960,
+          980,
+          952,
+          977,
+          986,
+          954,
+          984,
+          962,
+          956,
+          939,
+          947,
+          956,
+          963,
+          970,
+          991,
+          991,
+          1014,
+          985,
+          976,
+          977,
+          959,
+          981,
+          946,
+          993,
+          1005,
+          959,
+          1003,
+          1036,
+          1019,
+          969,
+          945,
+          923,
+          1016,
+          979,
+          1030,
+          975,
+          977,
+          1012,
+          927,
+          996,
+          932,
+          960,
+          940,
+          987,
+          1050,
+          988,
+          1030,
+          927,
+          1033,
+          989,
+          961,
+          1009,
+          1013,
+          969,
+          930,
+          972,
+          994,
+          977,
+          937,
+          950,
+          1018,
+          986,
+          977,
+          998,
+          981,
+          973,
+          953,
+          948,
+          994,
+          989,
+          933,
+          926,
+          921,
+          905,
+          1003,
+          1006,
+          995,
+          932,
+          1002,
+          948,
+          1008,
+          932,
+          911,
+          975,
+          1019,
+          964,
+          1016,
+          1038,
+          955,
+          995,
+          944,
+          979,
+          905,
+          989,
+          1020,
+          967,
+          990,
+          904,
+          991,
+          1030,
+          967,
+          1011,
+          1004,
+          1009,
+          1010,
+          961,
+          940,
+          1005,
+          983,
+          929,
+          936,
+          971,
+          992,
+          965,
+          998,
+          999,
+          937,
+          956,
+          1062,
+          959,
+          961,
+          983,
+          922,
+          993,
+          971,
+          990,
+          971,
+          969,
+          948,
+          990,
+          989,
+          956,
+          1000,
+          913,
+          945,
+          969,
+          999,
+          973,
+          1002,
+          964,
+          979,
+          958,
+          975,
+          989,
+          1028,
+          960,
+          998,
+          1039,
+          986,
+          987,
+          970,
+          1028,
+          1002,
+          987,
+          1006,
+          969,
+          986,
+          1011,
+          1014,
+          922,
+          1001,
+          974,
+          1041,
+          987,
+          1045,
+          1015,
+          955,
+          980,
+          971,
+          911,
+          996,
+          960,
+          982,
+          970,
+          963,
+          986,
+          984,
+          970,
+          970,
+          935,
+          1021,
+          977,
+          1085,
+          966,
+          913,
+          952,
+          942,
+          982,
+          967,
+          988,
+          983,
+          943,
+          969,
+          941,
+          967,
+          922,
+          982,
+          993,
+          948,
+          981,
+          1016,
+          1040,
+          898,
+          976,
+          920,
+          989,
+          941,
+          962,
+          963,
+          943,
+          989,
+          976,
+          1005,
+          975,
+          952,
+          987,
+          972,
+          969,
+          987,
+          1012,
+          971,
+          933,
+          964,
+          943,
+          921,
+          1014,
+          975,
+          995,
+          977,
+          953,
+          956,
+          983,
+          936,
+          1007,
+          979,
+          997,
+          927,
+          1001,
+          935,
+          1002,
+          955,
+          996,
+          995,
+          966,
+          980,
+          939,
+          981,
+          994,
+          1039,
+          964,
+          989,
+          982,
+          972,
+          926,
+          1019,
+          987,
+          994,
+          976,
+          961,
+          959,
+          961,
+          938,
+          968,
+          971,
+          943,
+          949,
+          978,
+          943,
+          977,
+          1015,
+          949,
+          968,
+          968,
+          947,
+          976,
+          960,
+          954,
+          1011,
+          970,
+          912,
+          972,
+          985,
+          927,
+          996,
+          926,
+          934,
+          977,
+          954,
+          1005,
+          982,
+          961,
+          966,
+          949,
+          985,
+          963,
+          987,
+          989,
+          975,
+          948,
+          1001,
+          1007,
+          956,
+          999,
+          972,
+          984,
+          997,
+          1026,
+          940,
+          945,
+          964,
+          973,
+          1040,
+          976,
+          995,
+          962,
+          915,
+          992,
+          956,
+          990,
+          972,
+          977,
+          1035,
+          1009,
+          999,
+          979,
+          1025,
+          982,
+          947,
+          993,
+          956,
+          981,
+          1019,
+          1004,
+          973,
+          906,
+          948,
+          952,
+          971,
+          1014,
+          979,
+          969,
+          948,
+          937,
+          964,
+          995,
+          946,
+          1002,
+          967,
+          1006,
+          949,
+          978,
+          989,
+          909,
+          967,
+          955,
+          1025,
+          981,
+          995,
+          1014,
+          966,
+          978,
+          956,
+          973,
+          914,
+          954,
+          975,
+          1001,
+          986,
+          950,
+          955,
+          941,
+          958,
+          981,
+          965,
+          940,
+          971,
+          989,
+          1048,
+          986,
+          990,
+          982,
+          1000,
+          961,
+          1012,
+          942,
+          968,
+          958,
+          1015,
+          960,
+          952,
+          936,
+          979,
+          971,
+          945,
+          949,
+          946,
+          949,
+          1028,
+          966,
+          1053,
+          1006,
+          967,
+          994,
+          995,
+          941,
+          1002,
+          971,
+          968,
+          963,
+          1011,
+          936,
+          999,
+          986,
+          945,
+          973,
+          999,
+          1020,
+          969,
+          988,
+          979,
+          903,
+          998,
+          1030,
+          1016,
+          960,
+          977,
+          1008,
+          1044,
+          939,
+          1005,
+          990,
+          955,
+          1005,
+          986,
+          1017,
+          1054,
+          970,
+          951,
+          977,
+          1000,
+          1018,
+          949,
+          952
+         ]
+        }
+       ],
+       "layout": {
+        "template": {
+         "data": {
+          "bar": [
+           {
+            "error_x": {
+             "color": "#2a3f5f"
+            },
+            "error_y": {
+             "color": "#2a3f5f"
+            },
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             },
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "bar"
+           }
+          ],
+          "barpolar": [
+           {
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             },
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "barpolar"
+           }
+          ],
+          "carpet": [
+           {
+            "aaxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "baxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "type": "carpet"
+           }
+          ],
+          "choropleth": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "choropleth"
+           }
+          ],
+          "contour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "contour"
+           }
+          ],
+          "contourcarpet": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "contourcarpet"
+           }
+          ],
+          "heatmap": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmap"
+           }
+          ],
+          "heatmapgl": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmapgl"
+           }
+          ],
+          "histogram": [
+           {
+            "marker": {
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "histogram"
+           }
+          ],
+          "histogram2d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2d"
+           }
+          ],
+          "histogram2dcontour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2dcontour"
+           }
+          ],
+          "mesh3d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "mesh3d"
+           }
+          ],
+          "parcoords": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "parcoords"
+           }
+          ],
+          "pie": [
+           {
+            "automargin": true,
+            "type": "pie"
+           }
+          ],
+          "scatter": [
+           {
+            "fillpattern": {
+             "fillmode": "overlay",
+             "size": 10,
+             "solidity": 0.2
+            },
+            "type": "scatter"
+           }
+          ],
+          "scatter3d": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatter3d"
+           }
+          ],
+          "scattercarpet": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattercarpet"
+           }
+          ],
+          "scattergeo": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergeo"
+           }
+          ],
+          "scattergl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergl"
+           }
+          ],
+          "scattermapbox": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattermapbox"
+           }
+          ],
+          "scatterpolar": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolar"
+           }
+          ],
+          "scatterpolargl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolargl"
+           }
+          ],
+          "scatterternary": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterternary"
+           }
+          ],
+          "surface": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "surface"
+           }
+          ],
+          "table": [
+           {
+            "cells": {
+             "fill": {
+              "color": "#EBF0F8"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "header": {
+             "fill": {
+              "color": "#C8D4E3"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "type": "table"
+           }
+          ]
+         },
+         "layout": {
+          "annotationdefaults": {
+           "arrowcolor": "#2a3f5f",
+           "arrowhead": 0,
+           "arrowwidth": 1
+          },
+          "autotypenumbers": "strict",
+          "coloraxis": {
+           "colorbar": {
+            "outlinewidth": 0,
+            "ticks": ""
+           }
+          },
+          "colorscale": {
+           "diverging": [
+            [
+             0,
+             "#8e0152"
+            ],
+            [
+             0.1,
+             "#c51b7d"
+            ],
+            [
+             0.2,
+             "#de77ae"
+            ],
+            [
+             0.3,
+             "#f1b6da"
+            ],
+            [
+             0.4,
+             "#fde0ef"
+            ],
+            [
+             0.5,
+             "#f7f7f7"
+            ],
+            [
+             0.6,
+             "#e6f5d0"
+            ],
+            [
+             0.7,
+             "#b8e186"
+            ],
+            [
+             0.8,
+             "#7fbc41"
+            ],
+            [
+             0.9,
+             "#4d9221"
+            ],
+            [
+             1,
+             "#276419"
+            ]
+           ],
+           "sequential": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ],
+           "sequentialminus": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ]
+          },
+          "colorway": [
+           "#636efa",
+           "#EF553B",
+           "#00cc96",
+           "#ab63fa",
+           "#FFA15A",
+           "#19d3f3",
+           "#FF6692",
+           "#B6E880",
+           "#FF97FF",
+           "#FECB52"
+          ],
+          "font": {
+           "color": "#2a3f5f"
+          },
+          "geo": {
+           "bgcolor": "white",
+           "lakecolor": "white",
+           "landcolor": "#E5ECF6",
+           "showlakes": true,
+           "showland": true,
+           "subunitcolor": "white"
+          },
+          "hoverlabel": {
+           "align": "left"
+          },
+          "hovermode": "closest",
+          "mapbox": {
+           "style": "light"
+          },
+          "paper_bgcolor": "white",
+          "plot_bgcolor": "#E5ECF6",
+          "polar": {
+           "angularaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "radialaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "scene": {
+           "xaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "yaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "zaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           }
+          },
+          "shapedefaults": {
+           "line": {
+            "color": "#2a3f5f"
+           }
+          },
+          "ternary": {
+           "aaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "baxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "caxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "title": {
+           "x": 0.05
+          },
+          "xaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          },
+          "yaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          }
+         }
+        },
+        "title": {
+         "text": "1024 Kmer Distribution for 5-mers"
+        },
+        "xaxis": {
+         "title": {
+          "text": "Kmer"
+         }
+        },
+        "yaxis": {
+         "title": {
+          "text": "Count"
+         }
+        }
+       }
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "No unique k-mers found\n",
+      "Most common 10% kmers: \n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.plotly.v1+json": {
+       "config": {
+        "plotlyServerURL": "https://plot.ly"
+       },
+       "data": [
+        {
+         "type": "bar",
+         "x": [
+          "GCTGA",
+          "GGGTG",
+          "GGGGT",
+          "GAGGC",
+          "AATGG",
+          "TTCAG",
+          "CCAAT",
+          "AAGGA",
+          "TTGAC",
+          "GATAT",
+          "GTAGC",
+          "GAGCG",
+          "CAACC",
+          "GCAGT",
+          "GGCCA",
+          "AGGAG",
+          "GGGTC",
+          "GTATG",
+          "ATCTA",
+          "AACCT",
+          "TGGGT",
+          "TCTCG",
+          "TTTGA",
+          "CCTTG",
+          "TGCTG",
+          "CTAGA",
+          "GCGCA",
+          "GGTTC",
+          "CATGT",
+          "TATGA",
+          "TGACG",
+          "ATGAC",
+          "ACCAA",
+          "TCTAC",
+          "CTCGC",
+          "CGAAT",
+          "TTCGT",
+          "ATGGG",
+          "TCCCC",
+          "AAATG",
+          "TTTGT",
+          "ATGGC",
+          "GGTGT",
+          "GGTGA",
+          "CGCTG",
+          "CGAGC",
+          "GAGAT",
+          "CTTTA",
+          "CCGAG",
+          "AGATC",
+          "AACCA",
+          "CAAAC",
+          "ATTGC",
+          "TCATG",
+          "TGAGC",
+          "AAAAT",
+          "GCTGC",
+          "GCAGG",
+          "GACAC",
+          "CGTGC",
+          "GGGCC",
+          "AGCTG",
+          "CTCGA",
+          "TCTAG",
+          "TTGCT",
+          "TGATC",
+          "GCACC",
+          "CTGTG",
+          "ACTCT",
+          "TTCCC",
+          "TGACC",
+          "TGAAT",
+          "AACGC",
+          "GACGG",
+          "GGAAG",
+          "AGTTA",
+          "TGCAG",
+          "AATCT",
+          "TAAGG",
+          "GGCCG",
+          "TCTTC",
+          "CGGGG",
+          "CTCTG",
+          "GAGTT",
+          "CTAGG",
+          "TAGAC",
+          "TTGGA",
+          "TTGTC",
+          "CGAGA",
+          "CACAG",
+          "GCGGC",
+          "GGGTT",
+          "CGGCG",
+          "CGGCC",
+          "TCGGG",
+          "GAGCA",
+          "AAACA",
+          "TTTAG",
+          "GCATA",
+          "GGTCA",
+          "ACACA",
+          "TCGTT"
+         ],
+         "y": [
+          1085,
+          1084,
+          1071,
+          1066,
+          1062,
+          1062,
+          1058,
+          1054,
+          1053,
+          1050,
+          1050,
+          1049,
+          1049,
+          1048,
+          1048,
+          1048,
+          1046,
+          1046,
+          1045,
+          1045,
+          1044,
+          1043,
+          1042,
+          1042,
+          1041,
+          1040,
+          1040,
+          1040,
+          1039,
+          1039,
+          1039,
+          1038,
+          1038,
+          1038,
+          1038,
+          1036,
+          1035,
+          1033,
+          1033,
+          1033,
+          1032,
+          1032,
+          1030,
+          1030,
+          1030,
+          1030,
+          1029,
+          1029,
+          1029,
+          1028,
+          1028,
+          1028,
+          1028,
+          1027,
+          1027,
+          1027,
+          1027,
+          1026,
+          1026,
+          1026,
+          1026,
+          1025,
+          1025,
+          1025,
+          1025,
+          1025,
+          1024,
+          1024,
+          1024,
+          1023,
+          1022,
+          1022,
+          1022,
+          1022,
+          1022,
+          1021,
+          1021,
+          1020,
+          1020,
+          1020,
+          1019,
+          1019,
+          1019,
+          1019,
+          1019,
+          1019,
+          1019,
+          1019,
+          1018,
+          1018,
+          1018,
+          1018,
+          1018,
+          1018,
+          1017,
+          1017,
+          1016,
+          1016,
+          1016,
+          1016,
+          1016,
+          1016
+         ]
+        }
+       ],
+       "layout": {
+        "template": {
+         "data": {
+          "bar": [
+           {
+            "error_x": {
+             "color": "#2a3f5f"
+            },
+            "error_y": {
+             "color": "#2a3f5f"
+            },
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             },
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "bar"
+           }
+          ],
+          "barpolar": [
+           {
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             },
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "barpolar"
+           }
+          ],
+          "carpet": [
+           {
+            "aaxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "baxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "type": "carpet"
+           }
+          ],
+          "choropleth": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "choropleth"
+           }
+          ],
+          "contour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "contour"
+           }
+          ],
+          "contourcarpet": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "contourcarpet"
+           }
+          ],
+          "heatmap": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmap"
+           }
+          ],
+          "heatmapgl": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmapgl"
+           }
+          ],
+          "histogram": [
+           {
+            "marker": {
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "histogram"
+           }
+          ],
+          "histogram2d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2d"
+           }
+          ],
+          "histogram2dcontour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2dcontour"
+           }
+          ],
+          "mesh3d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "mesh3d"
+           }
+          ],
+          "parcoords": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "parcoords"
+           }
+          ],
+          "pie": [
+           {
+            "automargin": true,
+            "type": "pie"
+           }
+          ],
+          "scatter": [
+           {
+            "fillpattern": {
+             "fillmode": "overlay",
+             "size": 10,
+             "solidity": 0.2
+            },
+            "type": "scatter"
+           }
+          ],
+          "scatter3d": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatter3d"
+           }
+          ],
+          "scattercarpet": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattercarpet"
+           }
+          ],
+          "scattergeo": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergeo"
+           }
+          ],
+          "scattergl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergl"
+           }
+          ],
+          "scattermapbox": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattermapbox"
+           }
+          ],
+          "scatterpolar": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolar"
+           }
+          ],
+          "scatterpolargl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolargl"
+           }
+          ],
+          "scatterternary": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterternary"
+           }
+          ],
+          "surface": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "surface"
+           }
+          ],
+          "table": [
+           {
+            "cells": {
+             "fill": {
+              "color": "#EBF0F8"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "header": {
+             "fill": {
+              "color": "#C8D4E3"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "type": "table"
+           }
+          ]
+         },
+         "layout": {
+          "annotationdefaults": {
+           "arrowcolor": "#2a3f5f",
+           "arrowhead": 0,
+           "arrowwidth": 1
+          },
+          "autotypenumbers": "strict",
+          "coloraxis": {
+           "colorbar": {
+            "outlinewidth": 0,
+            "ticks": ""
+           }
+          },
+          "colorscale": {
+           "diverging": [
+            [
+             0,
+             "#8e0152"
+            ],
+            [
+             0.1,
+             "#c51b7d"
+            ],
+            [
+             0.2,
+             "#de77ae"
+            ],
+            [
+             0.3,
+             "#f1b6da"
+            ],
+            [
+             0.4,
+             "#fde0ef"
+            ],
+            [
+             0.5,
+             "#f7f7f7"
+            ],
+            [
+             0.6,
+             "#e6f5d0"
+            ],
+            [
+             0.7,
+             "#b8e186"
+            ],
+            [
+             0.8,
+             "#7fbc41"
+            ],
+            [
+             0.9,
+             "#4d9221"
+            ],
+            [
+             1,
+             "#276419"
+            ]
+           ],
+           "sequential": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ],
+           "sequentialminus": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ]
+          },
+          "colorway": [
+           "#636efa",
+           "#EF553B",
+           "#00cc96",
+           "#ab63fa",
+           "#FFA15A",
+           "#19d3f3",
+           "#FF6692",
+           "#B6E880",
+           "#FF97FF",
+           "#FECB52"
+          ],
+          "font": {
+           "color": "#2a3f5f"
+          },
+          "geo": {
+           "bgcolor": "white",
+           "lakecolor": "white",
+           "landcolor": "#E5ECF6",
+           "showlakes": true,
+           "showland": true,
+           "subunitcolor": "white"
+          },
+          "hoverlabel": {
+           "align": "left"
+          },
+          "hovermode": "closest",
+          "mapbox": {
+           "style": "light"
+          },
+          "paper_bgcolor": "white",
+          "plot_bgcolor": "#E5ECF6",
+          "polar": {
+           "angularaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "radialaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "scene": {
+           "xaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "yaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "zaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           }
+          },
+          "shapedefaults": {
+           "line": {
+            "color": "#2a3f5f"
+           }
+          },
+          "ternary": {
+           "aaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "baxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "caxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "title": {
+           "x": 0.05
+          },
+          "xaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          },
+          "yaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          }
+         }
+        },
+        "title": {
+         "text": "102 Kmer Distribution for 5-mers"
+        },
+        "xaxis": {
+         "title": {
+          "text": "Kmer"
+         }
+        },
+        "yaxis": {
+         "title": {
+          "text": "Count"
+         }
+        }
+       }
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "def main():\n",
+    "    test_hash_table(dna_string, dna_len, kmer_size)\n",
+    "    # # uncomment if you would like to enter your own values \n",
+    "    # test_hash_table(None, None, None)\n",
+    "\n",
+    "main()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.10.8 64-bit",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,9 @@
+matplotlib==3.6.2
+mmh3==3.0.0
+plotly==5.11.0
+prettytable==3.5.0
+xxhash==3.1.0
+mljar-mercury
+nbformat==5.7.0
+jupyterlab==3.2.4
+jupyter==1.0.0