diff --git a/your-code/.ipynb_checkpoints/Q1-checkpoint.ipynb b/your-code/.ipynb_checkpoints/Q1-checkpoint.ipynb
new file mode 100644
index 0000000..dfee27f
--- /dev/null
+++ b/your-code/.ipynb_checkpoints/Q1-checkpoint.ipynb
@@ -0,0 +1,254 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In the cell below, create a Python function that wraps your previous solution for the Bag of Words lab.\n",
+    "\n",
+    "Requirements:\n",
+    "\n",
+    "1. Your function should accept the following parameters:\n",
+    "    * `docs` [REQUIRED] - array of document paths.\n",
+    "    * `stop_words` [OPTIONAL] - array of stop words. The default value is an empty array.\n",
+    "\n",
+    "1. Your function should return a Python object that contains the following:\n",
+    "    * `bag_of_words` - array of strings of normalized unique words in the corpus.\n",
+    "    * `term_freq` - array of the term-frequency vectors."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import required libraries\n",
+    "import re\n",
+    "import pandas as pd\n",
+    "import math\n",
+    "import os\n",
+    "# Define function\n",
+    "docs = ['doc1.txt', 'doc2.txt', 'doc3.txt']\n",
+    "def get_bow_from_docs(docs, stop_words=[]):\n",
+    "    corpus = []\n",
+    "    bag_of_words = []\n",
+    "    term_freq = []\n",
+    "    corpus2 = []\n",
+    "    # In the function, first define the variables you will use such as `corpus`, `bag_of_words`, and `term_freq`.\n",
+    "    for x in docs:\n",
+    "        abrir = open(x).read()\n",
+    "        corpus.append(abrir)\n",
+    "    for x in corpus:\n",
+    "        y = x.lower().replace(\".\", \"\")\n",
+    "        corpus2.append(y)\n",
+    "    \n",
+    "    \"\"\"\n",
+    "    Loop `docs` and read the content of each doc into a string in `corpus`.\n",
+    "    Remember to convert the doc content to lowercases and remove punctuation.\n",
+    "    \"\"\"\n",
+    "    for x in corpus2:\n",
+    "        y = re.split(\" \", x)\n",
+    "        for z in y:\n",
+    "            if z not in bag_of_words and z not in stop_words:\n",
+    "                bag_of_words.append(z)\n",
+    "            else:\n",
+    "                pass\n",
+    "        \n",
+    "    \n",
+    "    \n",
+    "    pieces = []\n",
+    "    for x in corpus2:\n",
+    "        pieces.append(x.split(\" \"))\n",
+    "        \n",
+    "    \n",
+    "    \n",
+    "    \n",
+    "    \"\"\"\n",
+    "    Loop `corpus`. Append the terms in each doc into the `bag_of_words` array. The terms in `bag_of_words` \n",
+    "    should be unique which means before adding each term you need to check if it's already added to the array.\n",
+    "    In addition, check if each term is in the `stop_words` array. Only append the term to `bag_of_words`\n",
+    "    if it is not a stop word.\n",
+    "    \"\"\"\n",
+    "    \n",
+    "    \n",
+    "    \n",
+    "    \n",
+    "    for s in pieces:\n",
+    "        temp = []\n",
+    "        for b in bag_of_words:\n",
+    "            y = s.count(b)\n",
+    "            temp.append(y)\n",
+    "        term_freq.append(temp)\n",
+    "\n",
+    "    \n",
+    "    \n",
+    "    \n",
+    "    \"\"\"\n",
+    "    Loop `corpus` again. For each doc string, count the number of occurrences of each term in `bag_of_words`. \n",
+    "    Create an array for each doc's term frequency and append it to `term_freq`.\n",
+    "    \"\"\"\n",
+    "\n",
+    "    \n",
+    "    \n",
+    "    # Now return your output as an object\n",
+    "    return {\n",
+    "        \"bag_of_words\": bag_of_words,\n",
+    "        \"term_freq\": term_freq\n",
+    "    }\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'bag_of_words': ['ironhack', 'is', 'cool', 'i', 'love', 'am', 'a', 'student', 'at'], 'term_freq': [[1, 1, 1, 0, 0, 0, 0, 0, 0], [1, 0, 0, 1, 1, 0, 0, 0, 0], [1, 0, 0, 1, 0, 1, 1, 1, 1]]}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(get_bow_from_docs(docs, stop_words=[]))\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Test your function without stop words. You should see the output like below:\n",
+    "\n",
+    "```{'bag_of_words': ['ironhack', 'is', 'cool', 'i', 'love', 'am', 'a', 'student', 'at'], 'term_freq': [[1, 1, 1, 0, 0, 0, 0, 0, 0], [1, 0, 0, 1, 1, 0, 0, 0, 0], [1, 0, 0, 1, 0, 1, 1, 1, 1]]}```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'bag_of_words': ['ironhack', 'is', 'cool', 'i', 'love', 'am', 'a', 'student', 'at'], 'term_freq': [[1, 1, 1, 0, 0, 0, 0, 0, 0], [1, 0, 0, 1, 1, 0, 0, 0, 0], [1, 0, 0, 1, 0, 1, 1, 1, 1]]}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Define doc paths array\n",
+    "docs = ['doc1.txt', 'doc2.txt', 'doc3.txt']\n",
+    "\n",
+    "# Obtain BoW from your function\n",
+    "bow = get_bow_from_docs(docs)\n",
+    "\n",
+    "# Print BoW\n",
+    "print(bow)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If your attempt above is successful, nice work done!\n",
+    "\n",
+    "Now test your function again with the stop words. In the previous lab we defined the stop words in a large array. In this lab, we'll import the stop words from Scikit-Learn."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "frozenset({'for', 'up', 'please', 'were', 'so', 'besides', 'beyond', 'against', 'these', 'any', 'has', 'ours', 'although', 'that', 'why', 'then', 'none', 'detail', 'latter', 'herein', 'twelve', 'find', 'myself', 'further', 'which', 'though', 'should', 'he', 'thence', 'yourself', 'side', 'itself', 'are', 'very', 'ourselves', 'your', 'empty', 'hence', 'put', 'across', 'elsewhere', 'this', 'un', 'former', 'out', 'found', 'moreover', 'still', 'rather', 'most', 'afterwards', 'have', 'at', 'now', 'either', 'themselves', 'therein', 'until', 'from', 'both', 'less', 'four', 'i', 'whereas', 'keep', 'even', 'becoming', 're', 'nine', 'been', 'ie', 'around', 'everywhere', 'anyhow', 'con', 'sometimes', 'take', 'where', 'can', 'front', 'several', 'hereafter', 'others', 'over', 'else', 'such', 'before', 'during', 'because', 'they', 'do', 'latterly', 'hers', 'almost', 'under', 'part', 'nobody', 'whither', 'bottom', 'about', 'move', 'done', 'became', 'sincere', 'whereby', 'anything', 'name', 'serious', 'seemed', 'much', 'her', 'through', 'below', 'whatever', 'and', 'being', 'among', 'them', 'therefore', 'show', 'our', 'sometime', 'herself', 'nor', 'after', 'there', 'top', 'least', 'nowhere', 'might', 'whose', 'must', 'every', 'to', 'no', 'also', 'somewhere', 'two', 'enough', 'him', 'on', 'seeming', 'us', 'we', 'without', 'per', 'thereby', 'eleven', 'when', 'ltd', 'those', 'would', 'mostly', 'mine', 'thru', 'amongst', 'perhaps', 'hereupon', 'within', 'never', 'forty', 'along', 'hundred', 'cant', 'becomes', 'due', 'more', 'anyone', 'inc', 'five', 'same', 'down', 'back', 'formerly', 'yours', 'describe', 'etc', 'full', 'neither', 'each', 'could', 'last', 'or', 'whereupon', 'behind', 'it', 'in', 'few', 'noone', 'via', 'thus', 'thereafter', 'alone', 'thick', 'towards', 'somehow', 'twenty', 'anyway', 'three', 'beforehand', 'me', 'call', 'ever', 'amount', 'will', 'whole', 'onto', 'namely', 'she', 'everyone', 'yourselves', 'wherein', 'whether', 'with', 'made', 'cry', 'whenever', 'something', 'his', 'mill', 'first', 'give', 'get', 'become', 'interest', 'than', 'eight', 'had', 'by', 'bill', 'am', 'as', 'go', 'but', 'hereby', 'all', 'nothing', 'thin', 'here', 'beside', 'meanwhile', 'ten', 'was', 'an', 'always', 'who', 'only', 'third', 'fifty', 'toward', 'the', 'see', 'eg', 'since', 'of', 'many', 'some', 'their', 'amoungst', 'system', 'couldnt', 'whence', 'everything', 'one', 'what', 'fire', 'next', 'whom', 'my', 'off', 'six', 'between', 'upon', 'wherever', 'cannot', 'throughout', 'once', 'whoever', 'whereafter', 'indeed', 'seem', 'seems', 'fill', 'himself', 'too', 'its', 'may', 'fifteen', 'you', 'nevertheless', 'except', 'while', 'de', 'sixty', 'thereupon', 'again', 'a', 'co', 'be', 'above', 'often', 'already', 'someone', 'yet', 'together', 'hasnt', 'how', 'anywhere', 'another', 'well', 'if', 'not', 'own', 'otherwise', 'into', 'is', 'however', 'other'})\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.feature_extraction import stop_words\n",
+    "\n",
+    "print(stop_words.ENGLISH_STOP_WORDS)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You should have seen a large list of words that looks like:\n",
+    "\n",
+    "```frozenset({'across', 'mine', 'cannot', ...})```\n",
+    "\n",
+    "`frozenset` is a type of Python object that is immutable. In this lab you can use it just like an array without conversion."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Next, test your function with supplying `stop_words.ENGLISH_STOP_WORDS` as the second parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'bag_of_words': ['ironhack', 'cool', 'love', 'student'], 'term_freq': [[1, 1, 0, 0], [1, 0, 1, 0], [1, 0, 0, 1]]}\n"
+     ]
+    }
+   ],
+   "source": [
+    "bow = get_bow_from_docs(docs, stop_words.ENGLISH_STOP_WORDS)\n",
+    "\n",
+    "print(bow)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You should have seen:\n",
+    "\n",
+    "```{'bag_of_words': ['ironhack', 'cool', 'love', 'student'], 'term_freq': [[1, 1, 0, 0], [1, 0, 1, 0], [1, 0, 0, 1]]}```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/your-code/.ipynb_checkpoints/Q2-checkpoint.ipynb b/your-code/.ipynb_checkpoints/Q2-checkpoint.ipynb
new file mode 100644
index 0000000..6ea0a0b
--- /dev/null
+++ b/your-code/.ipynb_checkpoints/Q2-checkpoint.ipynb
@@ -0,0 +1,188 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now we want to enhance the `get_bow_from_docs` function so that it will work with HTML webpages. In HTML, there are a lot of messy codes such as HTML tags, Javascripts, [unicodes](https://www.w3schools.com/charsets/ref_utf_misc_symbols.asp) that will mess up your bag of words. We need to clean up those junk before generating BoW.\n",
+    "\n",
+    "Next, what you will do is to define several new functions each of which is specialized to clean up the HTML codes in one aspect. For instance, you can have a `strip_html_tags` function to remove all HTML tags, a `remove_punctuation` function to remove all punctuation, a `to_lower_case` function to convert string to lowercase, and a `remove_unicode` function to remove all unicodes.\n",
+    "\n",
+    "Then in your `get_bow_from_doc` function, you will call each of those functions you created to clean up the HTML before you generate the corpus.\n",
+    "\n",
+    "Note: Please use Python string operations and regular expression only in this lab. Do not use extra libraries such as `beautifulsoup` because otherwise you loose the purpose of practicing."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define your string handling functions below\n",
+    "# Minimal 3 functions\n",
+    "import os\n",
+    "import pandas as pd\n",
+    "import re\n",
+    "import math\n",
+    "\n",
+    "def sin_puntuacion(corpus):\n",
+    "    corpus2 = []\n",
+    "    for x in corpus:\n",
+    "        y = x.lower().replace(\".\", \"\")\n",
+    "        corpus2.append(y)\n",
+    "    return corpus2\n",
+    "\n",
+    "def sin_tags(corpus):\n",
+    "    \n",
+    "    \n",
+    "    quotes = re.sub(r\"\\<.*?\\>\", \"\", corpus)\n",
+    "    \n",
+    "    return quotes\n",
+    "\n",
+    "def sin_unicodes(corpus):\n",
+    "    \n",
+    "    sincodes = re.sub(r\"\\&.*?\\;\", \"\", corpus)\n",
+    "    \n",
+    "    return sincodes\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Next, paste your previously written `get_bow_from_docs` function below. Call your functions above at the appropriate place."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_bow_from_docs(docs, stop_words=[]):\n",
+    "    # In the function, first define the variables you will use such as `corpus`, `bag_of_words`, and `term_freq`.\n",
+    "    corpus = []\n",
+    "    corpus2 = []\n",
+    "    bag_of_words = []\n",
+    "    term_freq = []\n",
+    "    \n",
+    "    # write your codes here\n",
+    "    \n",
+    "    for x in docs:\n",
+    "        abrir = open(x).read()\n",
+    "        corpus.append(abrir)\n",
+    "        \n",
+    "    sin_puntuacion(corpus)\n",
+    "    \n",
+    "    sin_tags(corpus2)\n",
+    "    \n",
+    "    sin_unicodes(quotes)\n",
+    "    \n",
+    "    for x in sincodes:\n",
+    "        y = re.split(\" \", x)\n",
+    "        for z in y:\n",
+    "            if z not in bag_of_words and z not in stop_words:\n",
+    "                bag_of_words.append(z)\n",
+    "            else:\n",
+    "                pass\n",
+    "         \n",
+    "    pieces = []\n",
+    "    for x in sincodes:\n",
+    "        pieces.append(x.split(\" \"))\n",
+    "        \n",
+    "    for s in pieces:\n",
+    "        temp = []\n",
+    "        for b in bag_of_words:\n",
+    "            y = s.count(b)\n",
+    "            temp.append(y)\n",
+    "        term_freq.append(temp)\n",
+    "    return {\n",
+    "        \"bag_of_words\": bag_of_words,\n",
+    "        \"term_freq\": term_freq\n",
+    "    }\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Next, read the content from the three HTML webpages in the `your-codes` directory to test your function."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "expected string or bytes-like object",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-22-980d0a5110cf>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      5\u001b[0m         \u001b[0;34m'www.lipsum.com.html'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      6\u001b[0m     ],\n\u001b[0;32m----> 7\u001b[0;31m     \u001b[0mstop_words\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mENGLISH_STOP_WORDS\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      8\u001b[0m )\n\u001b[1;32m      9\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m<ipython-input-21-bfc22781f465>\u001b[0m in \u001b[0;36mget_bow_from_docs\u001b[0;34m(docs, stop_words)\u001b[0m\n\u001b[1;32m     14\u001b[0m     \u001b[0msin_puntuacion\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 16\u001b[0;31m     \u001b[0msin_tags\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     17\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     18\u001b[0m     \u001b[0msin_unicodes\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mquotes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m<ipython-input-20-31142a3fbe77>\u001b[0m in \u001b[0;36msin_tags\u001b[0;34m(corpus)\u001b[0m\n\u001b[1;32m     16\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     17\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m     \u001b[0mquotes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mre\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mr\"\\<.*?\\>\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     19\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     20\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mquotes\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/anaconda3/lib/python3.7/re.py\u001b[0m in \u001b[0;36msub\u001b[0;34m(pattern, repl, string, count, flags)\u001b[0m\n\u001b[1;32m    190\u001b[0m     \u001b[0ma\u001b[0m \u001b[0mcallable\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mit\u001b[0m\u001b[0;31m'\u001b[0m\u001b[0ms\u001b[0m \u001b[0mpassed\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mMatch\u001b[0m \u001b[0mobject\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mmust\u001b[0m \u001b[0;32mreturn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    191\u001b[0m     a replacement string to be used.\"\"\"\n\u001b[0;32m--> 192\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0m_compile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpattern\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrepl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstring\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcount\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    193\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    194\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0msubn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpattern\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrepl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstring\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcount\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mTypeError\u001b[0m: expected string or bytes-like object"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.feature_extraction import stop_words\n",
+    "bow = get_bow_from_docs([\n",
+    "        'www.coursereport.com_ironhack.html',\n",
+    "        'en.wikipedia.org_Data_analysis.html',\n",
+    "        'www.lipsum.com.html'\n",
+    "    ],\n",
+    "    stop_words.ENGLISH_STOP_WORDS\n",
+    ")\n",
+    "\n",
+    "print(bow)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Do you see any problem in the output? How do you improve the output?\n",
+    "\n",
+    "A good way to improve your codes is to look into the HTML data sources and try to understand where the messy output came from. A good data analyst always learns about the data in depth in order to perform the job well.\n",
+    "\n",
+    "Spend 20-30 minutes to improve your functions or until you feel you are good at string operations. This lab is just a practice so you don't need to stress yourself out. If you feel you've practiced enough you can stop and move on the next challenge question."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/your-code/Q1.ipynb b/your-code/Q1.ipynb
index 8b07d3d..c5a0d62 100644
--- a/your-code/Q1.ipynb
+++ b/your-code/Q1.ipynb
@@ -19,49 +19,70 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Import required libraries\n",
-    "\n",
+    "import re\n",
+    "import pandas as pd\n",
+    "import math\n",
+    "import os\n",
     "# Define function\n",
+    "docs = ['doc1.txt', 'doc2.txt', 'doc3.txt']\n",
     "def get_bow_from_docs(docs, stop_words=[]):\n",
-    "    \n",
+    "    corpus = []\n",
+    "    bag_of_words = []\n",
+    "    term_freq = []\n",
+    "    corpus2 = []\n",
     "    # In the function, first define the variables you will use such as `corpus`, `bag_of_words`, and `term_freq`.\n",
+    "    for x in docs:\n",
+    "        abrir = open(x).read()\n",
+    "        corpus.append(abrir)\n",
+    "    for x in corpus:\n",
+    "        y = x.lower().replace(\".\", \"\")\n",
+    "        corpus2.append(y)\n",
     "    \n",
-    "    \n",
-    "    \n",
-    "    \"\"\"\n",
-    "    Loop `docs` and read the content of each doc into a string in `corpus`.\n",
-    "    Remember to convert the doc content to lowercases and remove punctuation.\n",
-    "    \"\"\"\n",
-    "\n",
-    "    \n",
-    "    \n",
-    "    \"\"\"\n",
-    "    Loop `corpus`. Append the terms in each doc into the `bag_of_words` array. The terms in `bag_of_words` \n",
-    "    should be unique which means before adding each term you need to check if it's already added to the array.\n",
-    "    In addition, check if each term is in the `stop_words` array. Only append the term to `bag_of_words`\n",
-    "    if it is not a stop word.\n",
-    "    \"\"\"\n",
+    "    for x in corpus2:\n",
+    "        y = re.split(\" \", x)\n",
+    "        for z in y:\n",
+    "            if z not in bag_of_words and z not in stop_words:\n",
+    "                bag_of_words.append(z)\n",
+    "            else:\n",
+    "                pass\n",
+    "         \n",
+    "    pieces = []\n",
+    "    for x in corpus2:\n",
+    "        pieces.append(x.split(\" \"))\n",
+    "        \n",
+    "    for s in pieces:\n",
+    "        temp = []\n",
+    "        for b in bag_of_words:\n",
+    "            y = s.count(b)\n",
+    "            temp.append(y)\n",
+    "        term_freq.append(temp)\n",
     "\n",
-    "    \n",
-    "    \n",
-    "    \n",
-    "    \"\"\"\n",
-    "    Loop `corpus` again. For each doc string, count the number of occurrences of each term in `bag_of_words`. \n",
-    "    Create an array for each doc's term frequency and append it to `term_freq`.\n",
-    "    \"\"\"\n",
-    "\n",
-    "    \n",
-    "    \n",
-    "    # Now return your output as an object\n",
     "    return {\n",
     "        \"bag_of_words\": bag_of_words,\n",
     "        \"term_freq\": term_freq\n",
-    "    }\n",
-    "    "
+    "    }\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'bag_of_words': ['ironhack', 'is', 'cool', 'i', 'love', 'am', 'a', 'student', 'at'], 'term_freq': [[1, 1, 1, 0, 0, 0, 0, 0, 0], [1, 0, 0, 1, 1, 0, 0, 0, 0], [1, 0, 0, 1, 0, 1, 1, 1, 1]]}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(get_bow_from_docs(docs, stop_words=[]))\n"
    ]
   },
   {
@@ -75,12 +96,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 30,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'bag_of_words': ['ironhack', 'is', 'cool', 'i', 'love', 'am', 'a', 'student', 'at'], 'term_freq': [[1, 1, 1, 0, 0, 0, 0, 0, 0], [1, 0, 0, 1, 1, 0, 0, 0, 0], [1, 0, 0, 1, 0, 1, 1, 1, 1]]}\n"
+     ]
+    }
+   ],
    "source": [
     "# Define doc paths array\n",
-    "docs = []\n",
+    "docs = ['doc1.txt', 'doc2.txt', 'doc3.txt']\n",
     "\n",
     "# Obtain BoW from your function\n",
     "bow = get_bow_from_docs(docs)\n",
@@ -100,12 +129,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 34,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "frozenset({'for', 'up', 'please', 'were', 'so', 'besides', 'beyond', 'against', 'these', 'any', 'has', 'ours', 'although', 'that', 'why', 'then', 'none', 'detail', 'latter', 'herein', 'twelve', 'find', 'myself', 'further', 'which', 'though', 'should', 'he', 'thence', 'yourself', 'side', 'itself', 'are', 'very', 'ourselves', 'your', 'empty', 'hence', 'put', 'across', 'elsewhere', 'this', 'un', 'former', 'out', 'found', 'moreover', 'still', 'rather', 'most', 'afterwards', 'have', 'at', 'now', 'either', 'themselves', 'therein', 'until', 'from', 'both', 'less', 'four', 'i', 'whereas', 'keep', 'even', 'becoming', 're', 'nine', 'been', 'ie', 'around', 'everywhere', 'anyhow', 'con', 'sometimes', 'take', 'where', 'can', 'front', 'several', 'hereafter', 'others', 'over', 'else', 'such', 'before', 'during', 'because', 'they', 'do', 'latterly', 'hers', 'almost', 'under', 'part', 'nobody', 'whither', 'bottom', 'about', 'move', 'done', 'became', 'sincere', 'whereby', 'anything', 'name', 'serious', 'seemed', 'much', 'her', 'through', 'below', 'whatever', 'and', 'being', 'among', 'them', 'therefore', 'show', 'our', 'sometime', 'herself', 'nor', 'after', 'there', 'top', 'least', 'nowhere', 'might', 'whose', 'must', 'every', 'to', 'no', 'also', 'somewhere', 'two', 'enough', 'him', 'on', 'seeming', 'us', 'we', 'without', 'per', 'thereby', 'eleven', 'when', 'ltd', 'those', 'would', 'mostly', 'mine', 'thru', 'amongst', 'perhaps', 'hereupon', 'within', 'never', 'forty', 'along', 'hundred', 'cant', 'becomes', 'due', 'more', 'anyone', 'inc', 'five', 'same', 'down', 'back', 'formerly', 'yours', 'describe', 'etc', 'full', 'neither', 'each', 'could', 'last', 'or', 'whereupon', 'behind', 'it', 'in', 'few', 'noone', 'via', 'thus', 'thereafter', 'alone', 'thick', 'towards', 'somehow', 'twenty', 'anyway', 'three', 'beforehand', 'me', 'call', 'ever', 'amount', 'will', 'whole', 'onto', 'namely', 'she', 'everyone', 'yourselves', 'wherein', 'whether', 'with', 'made', 'cry', 'whenever', 'something', 'his', 'mill', 'first', 'give', 'get', 'become', 'interest', 'than', 'eight', 'had', 'by', 'bill', 'am', 'as', 'go', 'but', 'hereby', 'all', 'nothing', 'thin', 'here', 'beside', 'meanwhile', 'ten', 'was', 'an', 'always', 'who', 'only', 'third', 'fifty', 'toward', 'the', 'see', 'eg', 'since', 'of', 'many', 'some', 'their', 'amoungst', 'system', 'couldnt', 'whence', 'everything', 'one', 'what', 'fire', 'next', 'whom', 'my', 'off', 'six', 'between', 'upon', 'wherever', 'cannot', 'throughout', 'once', 'whoever', 'whereafter', 'indeed', 'seem', 'seems', 'fill', 'himself', 'too', 'its', 'may', 'fifteen', 'you', 'nevertheless', 'except', 'while', 'de', 'sixty', 'thereupon', 'again', 'a', 'co', 'be', 'above', 'often', 'already', 'someone', 'yet', 'together', 'hasnt', 'how', 'anywhere', 'another', 'well', 'if', 'not', 'own', 'otherwise', 'into', 'is', 'however', 'other'})\n"
+     ]
+    }
+   ],
    "source": [
     "from sklearn.feature_extraction import stop_words\n",
-    "print(stop_words.ENGLISH_STOP_WORDS)"
+    "\n",
+    "print(stop_words.ENGLISH_STOP_WORDS)\n"
    ]
   },
   {
@@ -128,11 +166,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 36,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'bag_of_words': ['ironhack', 'cool', 'love', 'student'], 'term_freq': [[1, 1, 0, 0], [1, 0, 1, 0], [1, 0, 0, 1]]}\n"
+     ]
+    }
+   ],
    "source": [
-    "bow = get_bow_from_docs(bow, stop_words.ENGLISH_STOP_WORDS)\n",
+    "bow = get_bow_from_docs(docs, stop_words.ENGLISH_STOP_WORDS)\n",
     "\n",
     "print(bow)"
    ]
@@ -170,7 +216,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.6"
+   "version": "3.7.3"
   }
  },
  "nbformat": 4,
diff --git a/your-code/Q2.ipynb b/your-code/Q2.ipynb
index f50f442..6ea0a0b 100644
--- a/your-code/Q2.ipynb
+++ b/your-code/Q2.ipynb
@@ -15,12 +15,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Define your string handling functions below\n",
-    "# Minimal 3 functions\n"
+    "# Minimal 3 functions\n",
+    "import os\n",
+    "import pandas as pd\n",
+    "import re\n",
+    "import math\n",
+    "\n",
+    "def sin_puntuacion(corpus):\n",
+    "    corpus2 = []\n",
+    "    for x in corpus:\n",
+    "        y = x.lower().replace(\".\", \"\")\n",
+    "        corpus2.append(y)\n",
+    "    return corpus2\n",
+    "\n",
+    "def sin_tags(corpus):\n",
+    "    \n",
+    "    \n",
+    "    quotes = re.sub(r\"\\<.*?\\>\", \"\", corpus)\n",
+    "    \n",
+    "    return quotes\n",
+    "\n",
+    "def sin_unicodes(corpus):\n",
+    "    \n",
+    "    sincodes = re.sub(r\"\\&.*?\\;\", \"\", corpus)\n",
+    "    \n",
+    "    return sincodes\n",
+    "    "
    ]
   },
   {
@@ -32,18 +57,47 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
     "def get_bow_from_docs(docs, stop_words=[]):\n",
     "    # In the function, first define the variables you will use such as `corpus`, `bag_of_words`, and `term_freq`.\n",
     "    corpus = []\n",
+    "    corpus2 = []\n",
     "    bag_of_words = []\n",
     "    term_freq = []\n",
     "    \n",
     "    # write your codes here\n",
     "    \n",
+    "    for x in docs:\n",
+    "        abrir = open(x).read()\n",
+    "        corpus.append(abrir)\n",
+    "        \n",
+    "    sin_puntuacion(corpus)\n",
+    "    \n",
+    "    sin_tags(corpus2)\n",
+    "    \n",
+    "    sin_unicodes(quotes)\n",
+    "    \n",
+    "    for x in sincodes:\n",
+    "        y = re.split(\" \", x)\n",
+    "        for z in y:\n",
+    "            if z not in bag_of_words and z not in stop_words:\n",
+    "                bag_of_words.append(z)\n",
+    "            else:\n",
+    "                pass\n",
+    "         \n",
+    "    pieces = []\n",
+    "    for x in sincodes:\n",
+    "        pieces.append(x.split(\" \"))\n",
+    "        \n",
+    "    for s in pieces:\n",
+    "        temp = []\n",
+    "        for b in bag_of_words:\n",
+    "            y = s.count(b)\n",
+    "            temp.append(y)\n",
+    "        term_freq.append(temp)\n",
     "    return {\n",
     "        \"bag_of_words\": bag_of_words,\n",
     "        \"term_freq\": term_freq\n",
@@ -60,9 +114,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 22,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "expected string or bytes-like object",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-22-980d0a5110cf>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      5\u001b[0m         \u001b[0;34m'www.lipsum.com.html'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      6\u001b[0m     ],\n\u001b[0;32m----> 7\u001b[0;31m     \u001b[0mstop_words\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mENGLISH_STOP_WORDS\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      8\u001b[0m )\n\u001b[1;32m      9\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m<ipython-input-21-bfc22781f465>\u001b[0m in \u001b[0;36mget_bow_from_docs\u001b[0;34m(docs, stop_words)\u001b[0m\n\u001b[1;32m     14\u001b[0m     \u001b[0msin_puntuacion\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 16\u001b[0;31m     \u001b[0msin_tags\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     17\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     18\u001b[0m     \u001b[0msin_unicodes\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mquotes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m<ipython-input-20-31142a3fbe77>\u001b[0m in \u001b[0;36msin_tags\u001b[0;34m(corpus)\u001b[0m\n\u001b[1;32m     16\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     17\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m     \u001b[0mquotes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mre\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mr\"\\<.*?\\>\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     19\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     20\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mquotes\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/anaconda3/lib/python3.7/re.py\u001b[0m in \u001b[0;36msub\u001b[0;34m(pattern, repl, string, count, flags)\u001b[0m\n\u001b[1;32m    190\u001b[0m     \u001b[0ma\u001b[0m \u001b[0mcallable\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mit\u001b[0m\u001b[0;31m'\u001b[0m\u001b[0ms\u001b[0m \u001b[0mpassed\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mMatch\u001b[0m \u001b[0mobject\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mmust\u001b[0m \u001b[0;32mreturn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    191\u001b[0m     a replacement string to be used.\"\"\"\n\u001b[0;32m--> 192\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0m_compile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpattern\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrepl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstring\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcount\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    193\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    194\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0msubn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpattern\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrepl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstring\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcount\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mTypeError\u001b[0m: expected string or bytes-like object"
+     ]
+    }
+   ],
    "source": [
     "from sklearn.feature_extraction import stop_words\n",
     "bow = get_bow_from_docs([\n",
@@ -111,7 +180,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.6"
+   "version": "3.7.3"
   }
  },
  "nbformat": 4,
diff --git a/your-code/doc1.txt b/your-code/doc1.txt
new file mode 100644
index 0000000..e66288d
--- /dev/null
+++ b/your-code/doc1.txt
@@ -0,0 +1 @@
+Ironhack is cool.
\ No newline at end of file
diff --git a/your-code/doc2.txt b/your-code/doc2.txt
new file mode 100644
index 0000000..b21feac
--- /dev/null
+++ b/your-code/doc2.txt
@@ -0,0 +1 @@
+I love Ironhack.
\ No newline at end of file
diff --git a/your-code/doc3.txt b/your-code/doc3.txt
new file mode 100644
index 0000000..653c5b7
--- /dev/null
+++ b/your-code/doc3.txt
@@ -0,0 +1 @@
+I am a student at Ironhack.
\ No newline at end of file