NLP: Update Notebook 04 with windows compatibility

Author: SukeeratSG

Ch7/04_RecommenderSystems.ipynb

@@ -9,49 +9,63 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Collecting gensim\n",
-      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/1d/69/1262ed0050c21f5054702b8e96a2d8c310d4cd059e4a08c9a2fe6a5dae65/gensim-3.8.3-cp35-cp35m-manylinux1_x86_64.whl (24.2MB)\n",
-      "\u001b[K    100% |████████████████████████████████| 24.2MB 930kB/s ta 0:00:011   41% |█████████████▎                  | 10.1MB 5.2MB/s eta 0:00:03\n",
-      "\u001b[?25hCollecting smart-open>=1.8.1 (from gensim)\n",
-      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/74/77/744c79da6e66691e3500b6dffff29bdd787015eae817d594791edc7b719b/smart_open-2.0.0.tar.gz (103kB)\n",
-      "\u001b[K    100% |████████████████████████████████| 112kB 3.4MB/s ta 0:00:01\n",
-      "\u001b[?25hRequirement already satisfied: six>=1.5.0 in /home/etherealenvy/miniconda3/envs/practicalnlp/lib/python3.5/site-packages (from gensim) (1.14.0)\n",
-      "Collecting scipy>=0.18.1 (from gensim)\n",
-      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/c1/60/8cbf00c0deb50a971e6e3a015fb32513960a92867df979870a454481817c/scipy-1.4.1-cp35-cp35m-manylinux1_x86_64.whl (26.0MB)\n",
-      "\u001b[K    100% |████████████████████████████████| 26.0MB 1.0MB/s ta 0:00:011\n",
-      "\u001b[?25hCollecting numpy>=1.11.3 (from gensim)\n",
-      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/38/92/fa5295d9755c7876cb8490eab866e1780154033fa45978d9cf74ffbd4c68/numpy-1.18.4-cp35-cp35m-manylinux1_x86_64.whl (20.0MB)\n",
-      "\u001b[K    100% |████████████████████████████████| 20.0MB 1.8MB/s eta 0:00:01\n",
-      "\u001b[?25hRequirement already satisfied: requests in /home/etherealenvy/miniconda3/envs/practicalnlp/lib/python3.5/site-packages (from smart-open>=1.8.1->gensim) (2.23.0)\n",
-      "Collecting boto (from smart-open>=1.8.1->gensim)\n",
-      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/23/10/c0b78c27298029e4454a472a1919bde20cb182dab1662cec7f2ca1dcc523/boto-2.49.0-py2.py3-none-any.whl (1.4MB)\n",
-      "\u001b[K    100% |████████████████████████████████| 1.4MB 4.6MB/s eta 0:00:01\n",
-      "\u001b[?25hCollecting boto3 (from smart-open>=1.8.1->gensim)\n",
-      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/36/9e/e963605983fc1188c200ce84e2e07a1882c84a9e4c71cba80076b21441bb/boto3-1.13.4-py2.py3-none-any.whl (128kB)\n",
-      "\u001b[K    100% |████████████████████████████████| 133kB 6.7MB/s ta 0:00:01\n",
-      "\u001b[?25hRequirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /home/etherealenvy/miniconda3/envs/practicalnlp/lib/python3.5/site-packages (from requests->smart-open>=1.8.1->gensim) (1.25.9)\n",
-      "Requirement already satisfied: idna<3,>=2.5 in /home/etherealenvy/miniconda3/envs/practicalnlp/lib/python3.5/site-packages (from requests->smart-open>=1.8.1->gensim) (2.9)\n",
-      "Requirement already satisfied: chardet<4,>=3.0.2 in /home/etherealenvy/miniconda3/envs/practicalnlp/lib/python3.5/site-packages (from requests->smart-open>=1.8.1->gensim) (3.0.4)\n",
-      "Requirement already satisfied: certifi>=2017.4.17 in /home/etherealenvy/miniconda3/envs/practicalnlp/lib/python3.5/site-packages (from requests->smart-open>=1.8.1->gensim) (2018.8.24)\n",
-      "Collecting jmespath<1.0.0,>=0.7.1 (from boto3->smart-open>=1.8.1->gensim)\n",
-      "  Using cached https://files.pythonhosted.org/packages/a3/43/1e939e1fcd87b827fe192d0c9fc25b48c5b3368902bfb913de7754b0dc03/jmespath-0.9.5-py2.py3-none-any.whl\n",
-      "Collecting s3transfer<0.4.0,>=0.3.0 (from boto3->smart-open>=1.8.1->gensim)\n",
-      "  Using cached https://files.pythonhosted.org/packages/69/79/e6afb3d8b0b4e96cefbdc690f741d7dd24547ff1f94240c997a26fa908d3/s3transfer-0.3.3-py2.py3-none-any.whl\n",
-      "Collecting botocore<1.17.0,>=1.16.4 (from boto3->smart-open>=1.8.1->gensim)\n"
+      "Requirement already satisfied: gensim in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (4.0.1)\n",
+      "Requirement already satisfied: numpy>=1.11.3 in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from gensim) (1.20.2)\n",
+      "Requirement already satisfied: Cython==0.29.21 in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from gensim) (0.29.21)\n",
+      "Requirement already satisfied: smart-open>=1.8.1 in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from gensim) (3.0.0)\n",
+      "Requirement already satisfied: scipy>=0.18.1 in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from gensim) (1.6.3)\n",
+      "Requirement already satisfied: requests in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from smart-open>=1.8.1->gensim) (2.25.1)\n",
+      "Requirement already satisfied: chardet<5,>=3.0.2 in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from requests->smart-open>=1.8.1->gensim) (4.0.0)\n",
+      "Requirement already satisfied: idna<3,>=2.5 in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from requests->smart-open>=1.8.1->gensim) (2.10)\n",
+      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from requests->smart-open>=1.8.1->gensim) (1.25.9)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from requests->smart-open>=1.8.1->gensim) (2020.12.5)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING: You are using pip version 20.1.1; however, version 21.1.1 is available.\n",
+      "You should consider upgrading via the 'c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\python.exe -m pip install --upgrade pip' command.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: nltk in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (3.6.2)"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING: You are using pip version 20.1.1; however, version 21.1.1 is available.\n",
+      "You should consider upgrading via the 'c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\python.exe -m pip install --upgrade pip' command.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Requirement already satisfied: joblib in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from nltk) (1.0.1)\n",
+      "Requirement already satisfied: tqdm in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from nltk) (4.46.1)\n",
+      "Requirement already satisfied: regex in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from nltk) (2021.4.4)\n",
+      "Requirement already satisfied: click in c:\\users\\sukee\\appdata\\local\\programs\\python\\python37\\lib\\site-packages (from nltk) (7.1.2)\n"
      ]
     }
    ],
    "source": [
     "!pip install gensim\n",
-    "!pip install nltk\n",
-    "#todo: add pip for downloading nltk data?"
+    "!pip install nltk"
    ]
   },
   {
@@ -61,7 +75,7 @@
    "outputs": [],
    "source": [
     "from nltk.tokenize import word_tokenize\n",
-    "from gensim.models.doc2vec import Doc2Vec, TaggedDocument\n"
+    "from gensim.models.doc2vec import Doc2Vec, TaggedDocument"
    ]
   },
   {
@@ -70,13 +84,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#Read the dataset’s README to understand the data format. \n",
+    "# Read the dataset’s README to understand the data format. \n",
+    "\n",
     "data_path = \"booksummaries.txt\"\n",
     "mydata = {} #titles-summaries dictionary object\n",
     "for line in open(data_path, encoding=\"utf-8\"):\n",
     "    temp = line.split(\"\\t\")\n",
-    "    mydata[temp[2]] = temp[6]\n",
-    "\n"
+    "    mydata[temp[2]] = temp[6]"
    ]
   },
   {
@@ -90,8 +104,7 @@
     "model = Doc2Vec(vector_size=50, alpha=0.025, min_count=10, dm =1, epochs=100)\n",
     "model.build_vocab(train_doc2vec)\n",
     "model.train(train_doc2vec, total_examples=model.corpus_count, epochs=model.epochs)\n",
-    "model.save(\"d2v.model\")\n",
-    "\n"
+    "model.save(\"d2v.model\")"
    ]
   },
   {
@@ -117,16 +130,9 @@
     "Napoleon enacts changes to the governance structure of the farm, replacing meetings with a committee of pigs who will run the farm.\n",
     " \"\"\"\n",
     "new_vector = model.infer_vector(word_tokenize(sample))\n",
-    "sims = model.docvecs.most_similar([new_vector]) #gives 10 most similar titles\n",
+    "sims = model.docvecs.most_similar([new_vector])\n",
     "print(sims)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -145,9 +151,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.6"
+   "version": "3.7.9"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }