diff --git a/your-code/challenge-1.ipynb b/your-code/challenge-1.ipynb index c574eba..8c19739 100644 --- a/your-code/challenge-1.ipynb +++ b/your-code/challenge-1.ipynb @@ -15,7 +15,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -33,12 +33,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'Durante un tiempo no estuvo segura de si su marido era su marido.'" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "str_list = ['Durante', 'un', 'tiempo', 'no', 'estuvo', 'segura', 'de', 'si', 'su', 'marido', 'era', 'su', 'marido']\n", - "# Your code here:\n" + "\n", + "\" \".join(str_list) + \".\"" ] }, { @@ -50,12 +62,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'Grocery list: bananas, bread, brownie mix, broccoli.'" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "food_list = ['Bananas', 'Chocolate', 'bread', 'diapers', 'Ice Cream', 'Brownie Mix', 'broccoli']\n", - "# Your code here:\n" + "\n", + "\"Grocery list: \" + \", \".join([food.lower() for food in food_list if food.lower().startswith(\"b\")]) + \".\"" ] }, { @@ -69,9 +93,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'The area of the circle with radius: 4.5 is: 63.61725124'" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "import math\n", "\n", @@ -87,10 +122,9 @@ " # Sample input: 5.0\n", " # Sample Output: 78.53981633\n", " \n", - " # Your code here:\n", - " return pi * (x**2)\n", + " return round(pi * (x**2), 8)\n", " \n", - "# Your output string here:\n" + "f\"{string1} {radius} {string2} {area(radius)}\"" ] }, { @@ -106,9 +140,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'Some': 2, 'say': 3, 'the': 1, 'world': 1, 'will': 1, 'end': 1, 'in': 2, 'fire': 2, 'ice': 2, 'From': 1, 'what': 1, 'I’ve': 1, 'tasted': 1, 'of': 2, 'desire': 1, 'I': 3, 'hold': 1, 'with': 1, 'those': 1, 'who': 1, 'favor': 1, 'But': 1, 'if': 1, 'it': 1, 'had': 1, 'to': 1, 'perish': 1, 'twice': 1, 'think': 1, 'know': 1, 'enough': 1, 'hate': 1, 'To': 1, 'that': 1, 'for': 1, 'destruction': 1, 'Is': 1, 'also': 1, 'great': 1, 'And': 1, 'would': 1, 'suffice': 1}\n" + ] + } + ], "source": [ "poem = \"\"\"Some say the world will end in fire,\n", "Some say in ice.\n", @@ -120,7 +162,10 @@ "Is also great\n", "And would suffice.\"\"\"\n", "\n", - "# Your code here:\n" + "word_list = poem.replace(\",\", \"\").replace(\".\", \"\").replace(\"\\n\", \" \").split()\n", + "\n", + "word_freq_dict = {word:word_list.count(word) for word in word_list}\n", + "print(word_freq_dict)" ] }, { @@ -132,9 +177,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['i', 'was', 'angry', 'with', 'my', 'friend', 'i', 'told', 'my', 'wrath', 'my', 'wrath', 'did', 'end', 'i', 'was', 'angry', 'with', 'my', 'foe', 'i', 'told', 'not', 'my', 'wrath', 'did', 'grow', 'i', 'waterd', 'fears', 'night', 'morning', 'with', 'my', 'tears', 'i', 'sunned', 'with', 'smiles', 'with', 'soft', 'deceitful', 'wiles', 'grew', 'both', 'day', 'night', 'till', 'bore', 'apple', 'bright', 'my', 'foe', 'beheld', 'shine', 'he', 'knew', 'that', 'was', 'mine', 'into', 'my', 'garden', 'stole', 'when', 'night', 'had', 'veild', 'pole', 'morning', 'glad', 'i', 'see', 'my', 'foe', 'outstretched', 'beneath', 'tree']\n" + ] + } + ], "source": [ "blacklist = ['and', 'as', 'an', 'a', 'the', 'in', 'it']\n", "\n", @@ -158,7 +211,10 @@ "In the morning glad I see; \n", "My foe outstretched beneath the tree.\"\"\"\n", "\n", - "# Your code here:\n" + "word_list = poem.replace(\";\", \"\").replace(\",\", \"\").replace(\".\", \"\").replace(\":\", \"\").replace(\"&\", \"\").replace(\"\\n\", \" \").lower().split()\n", + "\n", + "whitelist = [word for word in word_list if word not in blacklist]\n", + "print(whitelist)" ] }, { @@ -172,16 +228,27 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 38, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['T', 'P']\n" + ] + } + ], "source": [ "import re\n", "\n", "poem = \"\"\"The apparition of these faces in the crowd;\n", "Petals on a wet, black bough.\"\"\"\n", "\n", - "# Your code here:\n" + "rule_upper = r\"[A-Z]\"\n", + "\n", + "poem_upper = re.findall(rule_upper, poem)\n", + "print(poem_upper)" ] }, { @@ -193,13 +260,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 46, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['123abc', 'abc123', 'JohnSmith1', 'ABBY4']\n" + ] + } + ], "source": [ "data = ['123abc', 'abc123', 'JohnSmith1', 'ABBY4', 'JANE']\n", "\n", - "# Your code here:\n" + "rule_number = r\"\\d\" # I could also do rule_number = \"[0-9]\"\n", + "\n", + "data_number = [element for element in data if re.search(rule_number, element) is not None]\n", + "print(data_number)" ] }, { @@ -215,18 +293,37 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 50, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['123abc', 'abc123', 'JohnSmith1']\n" + ] + } + ], "source": [ "data = ['123abc', 'abc123', 'JohnSmith1', 'ABBY4', 'JANE']\n", - "# Your code here:\n" + "\n", + "rule = r\"(\\d+.*[a-z]+)|([a-z]+.*\\d+)\"\n", + "\n", + "data_number_lower = [element for element in data if (re.search(rule, element)) is not None]\n", + "print(data_number_lower)" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -240,7 +337,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.8" + "version": "3.10.10" } }, "nbformat": 4, diff --git a/your-code/challenge-2.ipynb b/your-code/challenge-2.ipynb index 6873bd2..3e1045e 100644 --- a/your-code/challenge-2.ipynb +++ b/your-code/challenge-2.ipynb @@ -72,7 +72,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -88,11 +88,16 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ - "# Write your code here\n" + "corpus = []\n", + "\n", + "for doc in docs:\n", + " f = open(doc)\n", + " corpus.append(f.read())\n", + " f.close()" ] }, { @@ -104,10 +109,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['Ironhack is cool.', 'I love Ironhack.', 'I am a student at Ironhack.']\n" + ] + } + ], + "source": [ + "print(corpus)" + ] }, { "cell_type": "markdown", @@ -132,11 +147,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['ironhack is cool', 'i love ironhack', 'i am a student at ironhack']\n" + ] + } + ], "source": [ - "# Write your code here" + "corpus = [element.lower().replace(\".\",\"\") for element in corpus]\n", + "print(corpus)" ] }, { @@ -148,10 +172,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "bag_of_words = []" + ] }, { "cell_type": "markdown", @@ -166,11 +192,15 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ - "# Write your code here\n" + "for element in corpus:\n", + " terms_list = element.split()\n", + " for term in terms_list:\n", + " if term not in bag_of_words:\n", + " bag_of_words.append(term)" ] }, { @@ -186,10 +216,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['ironhack', 'is', 'cool', 'i', 'love', 'am', 'a', 'student', 'at']\n" + ] + } + ], + "source": [ + "print(bag_of_words)" + ] }, { "cell_type": "markdown", @@ -200,11 +240,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ - "# Write your code here\n" + "term_freq = []\n", + "\n", + "for element in corpus:\n", + " freq = []\n", + " for term in bag_of_words:\n", + " freq.append(element.split().count(term))\n", + " term_freq.append(freq)" ] }, { @@ -218,10 +264,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[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(term_freq)" + ] }, { "cell_type": "markdown", @@ -256,13 +312,39 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['ironhack', 'cool', 'love', 'student']\n", + "[[1, 1, 0, 0], [1, 0, 1, 0], [1, 0, 0, 1]]\n" + ] + } + ], "source": [ "stop_words = ['all', 'six', 'less', 'being', 'indeed', 'over', 'move', 'anyway', 'fifty', 'four', 'not', 'own', 'through', 'yourselves', 'go', 'where', 'mill', 'only', 'find', 'before', 'one', 'whose', 'system', 'how', 'somewhere', 'with', 'thick', 'show', 'had', 'enough', 'should', 'to', 'must', 'whom', 'seeming', 'under', 'ours', 'has', 'might', 'thereafter', 'latterly', 'do', 'them', 'his', 'around', 'than', 'get', 'very', 'de', 'none', 'cannot', 'every', 'whether', 'they', 'front', 'during', 'thus', 'now', 'him', 'nor', 'name', 'several', 'hereafter', 'always', 'who', 'cry', 'whither', 'this', 'someone', 'either', 'each', 'become', 'thereupon', 'sometime', 'side', 'two', 'therein', 'twelve', 'because', 'often', 'ten', 'our', 'eg', 'some', 'back', 'up', 'namely', 'towards', 'are', 'further', 'beyond', 'ourselves', 'yet', 'out', 'even', 'will', 'what', 'still', 'for', 'bottom', 'mine', 'since', 'please', 'forty', 'per', 'its', 'everything', 'behind', 'un', 'above', 'between', 'it', 'neither', 'seemed', 'ever', 'across', 'she', 'somehow', 'be', 'we', 'full', 'never', 'sixty', 'however', 'here', 'otherwise', 'were', 'whereupon', 'nowhere', 'although', 'found', 'alone', 're', 'along', 'fifteen', 'by', 'both', 'about', 'last', 'would', 'anything', 'via', 'many', 'could', 'thence', 'put', 'against', 'keep', 'etc', 'amount', 'became', 'ltd', 'hence', 'onto', 'or', 'con', 'among', 'already', 'co', 'afterwards', 'formerly', 'within', 'seems', 'into', 'others', 'while', 'whatever', 'except', 'down', 'hers', 'everyone', 'done', 'least', 'another', 'whoever', 'moreover', 'couldnt', 'throughout', 'anyhow', 'yourself', 'three', 'from', 'her', 'few', 'together', 'top', 'there', 'due', 'been', 'next', 'anyone', 'eleven', 'much', 'call', 'therefore', 'interest', 'then', 'thru', 'themselves', 'hundred', 'was', 'sincere', 'empty', 'more', 'himself', 'elsewhere', 'mostly', 'on', 'fire', 'am', 'becoming', 'hereby', 'amongst', 'else', 'part', 'everywhere', 'too', 'herself', 'former', 'those', 'he', 'me', 'myself', 'made', 'twenty', 'these', 'bill', 'cant', 'us', 'until', 'besides', 'nevertheless', 'below', 'anywhere', 'nine', 'can', 'of', 'your', 'toward', 'my', 'something', 'and', 'whereafter', 'whenever', 'give', 'almost', 'wherever', 'is', 'describe', 'beforehand', 'herein', 'an', 'as', 'itself', 'at', 'have', 'in', 'seem', 'whence', 'ie', 'any', 'fill', 'again', 'hasnt', 'inc', 'thereby', 'thin', 'no', 'perhaps', 'latter', 'meanwhile', 'when', 'detail', 'same', 'wherein', 'beside', 'also', 'that', 'other', 'take', 'which', 'becomes', 'you', 'if', 'nobody', 'see', 'though', 'may', 'after', 'upon', 'most', 'hereupon', 'eight', 'but', 'serious', 'nothing', 'such', 'why', 'a', 'off', 'whereby', 'third', 'i', 'whole', 'noone', 'sometimes', 'well', 'amoungst', 'yours', 'their', 'rather', 'without', 'so', 'five', 'the', 'first', 'whereas', 'once']\n", "\n", - "# Write your code below\n" + "bag_of_words = []\n", + "\n", + "for element in corpus:\n", + " terms_list = element.split()\n", + " for term in terms_list:\n", + " if (term not in bag_of_words) and (term not in stop_words):\n", + " bag_of_words.append(term)\n", + " \n", + "term_freq = []\n", + "\n", + "for element in corpus:\n", + " freq = []\n", + " for term in bag_of_words:\n", + " freq.append(element.split().count(term))\n", + " term_freq.append(freq)\n", + " \n", + "print(bag_of_words)\n", + "print(term_freq)" ] }, { @@ -294,6 +376,47 @@ " ```" ] }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'ironhack': 3, 'is': 4, 'cool': 2, 'love': 5, 'am': 0, 'student': 6, 'at': 1}\n" + ] + } + ], + "source": [ + "from sklearn.feature_extraction.text import CountVectorizer\n", + "\n", + "vectorizer = CountVectorizer()\n", + "X = vectorizer.fit_transform(corpus)\n", + "\n", + "print(vectorizer.vocabulary_)" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[0 0 1 1 1 0 0]\n", + " [0 0 0 1 0 1 0]\n", + " [1 1 0 1 0 0 1]]\n" + ] + } + ], + "source": [ + "print(X.toarray())" + ] + }, { "cell_type": "code", "execution_count": null, @@ -304,7 +427,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -318,7 +441,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.8" + "version": "3.10.10" } }, "nbformat": 4,