[natural-language-processing] Emily Paz

module-3/natural-language-processing/your-code/challenge-1.ipynb

@@ -66,20 +66,43 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 85,
    "metadata": {},
    "outputs": [],
    "source": [
     "def clean_up(s):\n",
-    "    \"\"\"\n",
-    "    Cleans up numbers, URLs, and special characters from a string.\n",
-    "\n",
-    "    Args:\n",
-    "        s: The string to be cleaned up.\n",
-    "\n",
-    "    Returns:\n",
-    "        A string that has been cleaned up.\n",
-    "    \"\"\""
+    "    clean = re.sub('[ ]+', ' ', re.sub('([^a-z])|(http(.*)) ', ' ', s.lower()).lstrip().rstrip())\n",
+    "                   \n",
+    "    return clean"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 86,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'ironhack s q website is'"
+      ]
+     },
+     "execution_count": 86,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean_up(\"\"\"@Ironhack's-#Q website 776-is http://ironhack.com [(2018)]\")\"\"\")"
    ]
   },
   {
@@ -101,20 +124,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 87,
    "metadata": {},
    "outputs": [],
    "source": [
     "def tokenize(s):\n",
-    "    \"\"\"\n",
-    "    Tokenize a string.\n",
-    "\n",
-    "    Args:\n",
-    "        s: String to be tokenized.\n",
-    "\n",
-    "    Returns:\n",
-    "        A list of words as the result of tokenization.\n",
-    "    \"\"\""
+    "    token = s.split(' ')\n",
+    "    return token"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['ironhack', 's', 'q', 'website', 'is']"
+      ]
+     },
+     "execution_count": 88,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tokenize('ironhack s q website is')"
    ]
   },
   {
@@ -145,20 +181,45 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import spacy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
     "def stem_and_lemmatize(l):\n",
-    "    \"\"\"\n",
-    "    Perform stemming and lemmatization on a list of words.\n",
-    "\n",
-    "    Args:\n",
-    "        l: A list of strings.\n",
-    "\n",
-    "    Returns:\n",
-    "        A list of strings after being stemmed and lemmatized.\n",
-    "    \"\"\""
+    "    nlp = spacy.load('en_core_web_sm')\n",
+    "    tokens = nlp(l)\n",
+    "    for token in tokens:\n",
+    "        print(token.text, token.lemma_, token.pos_)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ironhack ironhack NOUN\n",
+      "s s PART\n",
+      "q q NOUN\n",
+      "website website NOUN\n",
+      "is be AUX\n"
+     ]
+    }
+   ],
+   "source": [
+    "stem_and_lemmatize('ironhack s q website is')"
    ]
   },
   {
@@ -176,20 +237,75 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package stopwords to /home/emily/nltk_data...\n",
+      "[nltk_data]   Package stopwords is already up-to-date!\n",
+      "[nltk_data] Downloading package punkt to /home/emily/nltk_data...\n",
+      "[nltk_data]   Package punkt is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import nltk\n",
+    "nltk.download('stopwords')\n",
+    "nltk.download('punkt')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from nltk.corpus import stopwords\n",
+    "from nltk.tokenize import word_tokenize"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
    "metadata": {},
    "outputs": [],
    "source": [
     "def remove_stopwords(l):\n",
-    "    \"\"\"\n",
-    "    Remove English stopwords from a list of strings.\n",
+    "    stop_words = set(stopwords.words('english'))\n",
+    "    word_tokens = word_tokenize(l)\n",
+    "    filtered = [w for w in word_tokens if not w in stop_words]\n",
     "\n",
-    "    Args:\n",
-    "        l: A list of strings.\n",
-    "\n",
-    "    Returns:\n",
-    "        A list of strings after stop words are removed.\n",
-    "    \"\"\""
+    "    print(filtered)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['ironhack', 'q', 'website']\n"
+     ]
+    }
+   ],
+   "source": [
+    "remove_stopwords('ironhack s q website is')"
    ]
   },
   {
@@ -204,9 +320,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python [conda env:ironhack_env]",
    "language": "python",
-   "name": "python3"
+   "name": "conda-env-ironhack_env-py"
   },
   "language_info": {
    "codemirror_mode": {
@@ -218,9 +334,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.8.5"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }