noshot 0.1.0__py3-none-any.whl

noshot/data/AIDS CN NLP/NLP/NLP 4/Collocation (T test).ipynb

@@ -0,0 +1,188 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "DF_ZwwBZYlOy",
+        "outputId": "b520aae1-aca8-419e-d136-bf777f5b9d7f"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
+            "[nltk_data]   Package stopwords is already up-to-date!\n",
+            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
+            "[nltk_data]   Package punkt is already up-to-date!\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "True"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 2
+        }
+      ],
+      "source": [
+        "import nltk\n",
+        "nltk.download('stopwords')\n",
+        "nltk.download('punkt')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from nltk.corpus import stopwords\n",
+        "from nltk.tokenize import word_tokenize\n",
+        "\n",
+        "f=open(\"/content/sample.txt\",\"r\")\n",
+        "text=f.read()\n",
+        "\n",
+        "stop_words = set(stopwords.words(\"english\"))\n",
+        "word_tokens = word_tokenize(text)\n",
+        "fil_text = [word for word in word_tokens if word not in stop_words]\n",
+        "print(word_tokens)\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "p1EFKoWCYmtH",
+        "outputId": "4a56d953-65bf-4924-8bdb-91a976a3af47"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "['hi', 'this', 'is', 'a', 'sample', 'text', 'for', 'natural', 'language', 'processing', 'natural', 'language', 'processing', 'has', 'various', 'advantages', '.']\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def collocation(w1,w2):\n",
+        "  nl=list()\n",
+        "  N=len(word_tokens)\n",
+        "  pw1=word_tokens.count(w1)\n",
+        "  pw2=word_tokens.count(w2)\n",
+        "  md=((pw1/N)*(pw2/N))\n",
+        "  j=0\n",
+        "  for i in range(len(word_tokens)):\n",
+        "    if(word_tokens[i]==w1 and word_tokens[i+1]==w2):\n",
+        "     j=j+1\n",
+        "  pw12=j\n",
+        "  x=pw12/N\n",
+        "  s2=x\n",
+        "  t=(x-md)/(x/N)**0.5\n",
+        "  if(float(t) > float(cv)):\n",
+        "    print(\"hypothesis rejected thus the given words( \",w1,\" \",w2,\" ) form a collocation\")\n",
+        "    print(t)\n",
+        "    nl.append(w1)\n",
+        "    nl.append(w2)\n",
+        "    nl.append(t)\n",
+        "  return nl"
+      ],
+      "metadata": {
+        "id": "F_3yVJF-Ys19"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "cv=input(\"enter the critical value : \")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "A2sGU4O2alhl",
+        "outputId": "dd8df949-19d2-441e-f421-1bca5f1fe98e"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "enter the critical value : 1\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "fcol=list()\n",
+        "for i in range(len(word_tokens)-1):\n",
+        "    w1=word_tokens[i]\n",
+        "    w2=word_tokens[i+1]\n",
+        "    fcol.append(collocation(w1,w2))\n",
+        "for i in fcol:\n",
+        "  if(len(i) > 1):\n",
+        "    if(fcol.count(i)>1):\n",
+        "      fcol.remove(i)\n",
+        "  else:\n",
+        "    fcol.remove(i)\n",
+        "    \n",
+        "for i in fcol:\n",
+        "  if(len(i) > 1):\n",
+        "    print(i)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "rdNNhGmUYzC2",
+        "outputId": "dc8b4b05-c546-4600-ae7c-c62bc3ed5ed5"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "hypothesis rejected thus the given words(  natural   language  ) form a collocation\n",
+            "1.2478354962115543\n",
+            "hypothesis rejected thus the given words(  language   processing  ) form a collocation\n",
+            "1.2478354962115543\n",
+            "hypothesis rejected thus the given words(  natural   language  ) form a collocation\n",
+            "1.2478354962115543\n",
+            "hypothesis rejected thus the given words(  language   processing  ) form a collocation\n",
+            "1.2478354962115543\n",
+            "['natural', 'language', 1.2478354962115543]\n",
+            "['language', 'processing', 1.2478354962115543]\n"
+          ]
+        }
+      ]
+    }
+  ]
+}

noshot/data/AIDS CN NLP/NLP/NLP 4/Experiment 1.ipynb

@@ -0,0 +1,437 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "pp2qf3zYXaiT",
+        "outputId": "873c7148-85ea-4ff2-eca1-5fc88f5af441"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
+            "Requirement already satisfied: spacy in /usr/local/lib/python3.8/dist-packages (3.4.4)\n",
+            "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4 in /usr/local/lib/python3.8/dist-packages (from spacy) (1.10.4)\n",
+            "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.8/dist-packages (from spacy) (2.0.7)\n",
+            "Requirement already satisfied: setuptools in /usr/local/lib/python3.8/dist-packages (from spacy) (57.4.0)\n",
+            "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.8/dist-packages (from spacy) (4.64.1)\n",
+            "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.8/dist-packages (from spacy) (1.0.9)\n",
+            "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.10 in /usr/local/lib/python3.8/dist-packages (from spacy) (3.0.11)\n",
+            "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.8/dist-packages (from spacy) (2.0.8)\n",
+            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.8/dist-packages (from spacy) (21.3)\n",
+            "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.8/dist-packages (from spacy) (3.0.8)\n",
+            "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.8/dist-packages (from spacy) (2.25.1)\n",
+            "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /usr/local/lib/python3.8/dist-packages (from spacy) (2.4.5)\n",
+            "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /usr/local/lib/python3.8/dist-packages (from spacy) (1.0.4)\n",
+            "Requirement already satisfied: typer<0.8.0,>=0.3.0 in /usr/local/lib/python3.8/dist-packages (from spacy) (0.7.0)\n",
+            "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /usr/local/lib/python3.8/dist-packages (from spacy) (3.3.0)\n",
+            "Requirement already satisfied: numpy>=1.15.0 in /usr/local/lib/python3.8/dist-packages (from spacy) (1.21.6)\n",
+            "Requirement already satisfied: pathy>=0.3.5 in /usr/local/lib/python3.8/dist-packages (from spacy) (0.10.1)\n",
+            "Requirement already satisfied: wasabi<1.1.0,>=0.9.1 in /usr/local/lib/python3.8/dist-packages (from spacy) (0.10.1)\n",
+            "Requirement already satisfied: thinc<8.2.0,>=8.1.0 in /usr/local/lib/python3.8/dist-packages (from spacy) (8.1.6)\n",
+            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.8/dist-packages (from spacy) (2.11.3)\n",
+            "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in /usr/local/lib/python3.8/dist-packages (from spacy) (6.3.0)\n",
+            "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.8/dist-packages (from packaging>=20.0->spacy) (3.0.9)\n",
+            "Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.8/dist-packages (from pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4->spacy) (4.4.0)\n",
+            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.8/dist-packages (from requests<3.0.0,>=2.13.0->spacy) (2.10)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.8/dist-packages (from requests<3.0.0,>=2.13.0->spacy) (2022.12.7)\n",
+            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.8/dist-packages (from requests<3.0.0,>=2.13.0->spacy) (1.24.3)\n",
+            "Requirement already satisfied: chardet<5,>=3.0.2 in /usr/local/lib/python3.8/dist-packages (from requests<3.0.0,>=2.13.0->spacy) (4.0.0)\n",
+            "Requirement already satisfied: blis<0.8.0,>=0.7.8 in /usr/local/lib/python3.8/dist-packages (from thinc<8.2.0,>=8.1.0->spacy) (0.7.9)\n",
+            "Requirement already satisfied: confection<1.0.0,>=0.0.1 in /usr/local/lib/python3.8/dist-packages (from thinc<8.2.0,>=8.1.0->spacy) (0.0.3)\n",
+            "Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.8/dist-packages (from typer<0.8.0,>=0.3.0->spacy) (7.1.2)\n",
+            "Requirement already satisfied: MarkupSafe>=0.23 in /usr/local/lib/python3.8/dist-packages (from jinja2->spacy) (2.0.1)\n",
+            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
+            "Requirement already satisfied: nltk in /usr/local/lib/python3.8/dist-packages (3.7)\n",
+            "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.8/dist-packages (from nltk) (2022.6.2)\n",
+            "Requirement already satisfied: tqdm in /usr/local/lib/python3.8/dist-packages (from nltk) (4.64.1)\n",
+            "Requirement already satisfied: click in /usr/local/lib/python3.8/dist-packages (from nltk) (7.1.2)\n",
+            "Requirement already satisfied: joblib in /usr/local/lib/python3.8/dist-packages (from nltk) (1.2.0)\n",
+            "/usr/local/lib/python3.8/dist-packages/torch/cuda/__init__.py:497: UserWarning: Can't initialize NVML\n",
+            "  warnings.warn(\"Can't initialize NVML\")\n",
+            "2023-01-31 10:28:37.313611: E tensorflow/stream_executor/cuda/cuda_driver.cc:271] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected\n",
+            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
+            "Collecting en-core-web-sm==3.4.1\n",
+            "  Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.1/en_core_web_sm-3.4.1-py3-none-any.whl (12.8 MB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.8/12.8 MB\u001b[0m \u001b[31m19.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hRequirement already satisfied: spacy<3.5.0,>=3.4.0 in /usr/local/lib/python3.8/dist-packages (from en-core-web-sm==3.4.1) (3.4.4)\n",
+            "Requirement already satisfied: thinc<8.2.0,>=8.1.0 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (8.1.6)\n",
+            "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.10.4)\n",
+            "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.10 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.0.11)\n",
+            "Requirement already satisfied: setuptools in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (57.4.0)\n",
+            "Requirement already satisfied: pathy>=0.3.5 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.10.1)\n",
+            "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.3.0)\n",
+            "Requirement already satisfied: wasabi<1.1.0,>=0.9.1 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.10.1)\n",
+            "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.0.9)\n",
+            "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.0.8)\n",
+            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (21.3)\n",
+            "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (6.3.0)\n",
+            "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.0.8)\n",
+            "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.4.5)\n",
+            "Requirement already satisfied: numpy>=1.15.0 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.21.6)\n",
+            "Requirement already satisfied: typer<0.8.0,>=0.3.0 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.7.0)\n",
+            "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.0.4)\n",
+            "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (4.64.1)\n",
+            "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.0.7)\n",
+            "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.25.1)\n",
+            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.8/dist-packages (from spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.11.3)\n",
+            "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.8/dist-packages (from packaging>=20.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (3.0.9)\n",
+            "Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.8/dist-packages (from pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (4.4.0)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.8/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2022.12.7)\n",
+            "Requirement already satisfied: chardet<5,>=3.0.2 in /usr/local/lib/python3.8/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (4.0.0)\n",
+            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.8/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (1.24.3)\n",
+            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.8/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.10)\n",
+            "Requirement already satisfied: blis<0.8.0,>=0.7.8 in /usr/local/lib/python3.8/dist-packages (from thinc<8.2.0,>=8.1.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.7.9)\n",
+            "Requirement already satisfied: confection<1.0.0,>=0.0.1 in /usr/local/lib/python3.8/dist-packages (from thinc<8.2.0,>=8.1.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (0.0.3)\n",
+            "Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.8/dist-packages (from typer<0.8.0,>=0.3.0->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (7.1.2)\n",
+            "Requirement already satisfied: MarkupSafe>=0.23 in /usr/local/lib/python3.8/dist-packages (from jinja2->spacy<3.5.0,>=3.4.0->en-core-web-sm==3.4.1) (2.0.1)\n",
+            "\u001b[38;5;2m✔ Download and installation successful\u001b[0m\n",
+            "You can now load the package via spacy.load('en_core_web_sm')\n"
+          ]
+        }
+      ],
+      "source": [
+        "! pip install spacy\n",
+        "! pip install nltk\n",
+        "! python -m spacy download en_core_web_sm"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import spacy\n",
+        "from spacy import displacy\n",
+        "from spacy import tokenizer\n",
+        "nlp = spacy.load('en_core_web_sm')"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "SABsAqWUXegn",
+        "outputId": "2f89e0c5-66b1-4b1d-b901-0551104d9488"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.8/dist-packages/torch/cuda/__init__.py:497: UserWarning: Can't initialize NVML\n",
+            "  warnings.warn(\"Can't initialize NVML\")\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "text =(\"Python is an interpreted, high-level and general-purpose programming language\"\n",
+        "       \"Pythons design philosophy emphasizes code readability with\"\n",
+        "       \"its notable use of significant indentation.\"\n",
+        "       \"Its language constructs and object-oriented approach aim to\"\n",
+        "       \"help programmers write clear and\"\n",
+        "       \"logical code for small and large-scale projects\")"
+      ],
+      "metadata": {
+        "id": "5P2nQrbeXjGu"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "doc = nlp(text)\n",
+        "#doc2 = nlp(text2)\n",
+        "sentences = list(doc.sents)\n",
+        "print(sentences)\n",
+        "# tokenization\n",
+        "for token in doc:\n",
+        "    print(token.text)\n",
+        "# print entities\n",
+        "ents = [(e.text, e.start_char, e.end_char, e.label_) for e in doc.ents]\n",
+        "print(ents)\n",
+        "# now we use displaycy function on doc2\n",
+        "displacy.render(doc, style='ent', jupyter=True)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 975
+        },
+        "id": "J5huMlqAXmam",
+        "outputId": "361b18ee-7b5e-4ede-e824-c548f918555d"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "[Python is an interpreted, high-level and general-purpose programming languagePythons design philosophy emphasizes code readability withits notable use of significant indentation., Its language constructs and object-oriented approach aim tohelp programmers write clear andlogical code for small and large-scale projects]\n",
+            "Python\n",
+            "is\n",
+            "an\n",
+            "interpreted\n",
+            ",\n",
+            "high\n",
+            "-\n",
+            "level\n",
+            "and\n",
+            "general\n",
+            "-\n",
+            "purpose\n",
+            "programming\n",
+            "languagePythons\n",
+            "design\n",
+            "philosophy\n",
+            "emphasizes\n",
+            "code\n",
+            "readability\n",
+            "withits\n",
+            "notable\n",
+            "use\n",
+            "of\n",
+            "significant\n",
+            "indentation\n",
+            ".\n",
+            "Its\n",
+            "language\n",
+            "constructs\n",
+            "and\n",
+            "object\n",
+            "-\n",
+            "oriented\n",
+            "approach\n",
+            "aim\n",
+            "tohelp\n",
+            "programmers\n",
+            "write\n",
+            "clear\n",
+            "andlogical\n",
+            "code\n",
+            "for\n",
+            "small\n",
+            "and\n",
+            "large\n",
+            "-\n",
+            "scale\n",
+            "projects\n",
+            "[('languagePythons', 69, 84, 'PERSON')]\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<IPython.core.display.HTML object>"
+            ],
+            "text/html": [
+              "<span class=\"tex2jax_ignore\"><div class=\"entities\" style=\"line-height: 2.5; direction: ltr\">Python is an interpreted, high-level and general-purpose programming \n",
+              "<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
+              "    languagePythons\n",
+              "    <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
+              "</mark>\n",
+              " design philosophy emphasizes code readability withits notable use of significant indentation.Its language constructs and object-oriented approach aim tohelp programmers write clear andlogical code for small and large-scale projects</div></span>"
+            ]
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import nltk\n",
+        "nltk.download('words')\n",
+        "nltk.download('punkt')\n",
+        "nltk.download('maxent_ne_chunker')\n",
+        "nltk.download('averaged_perceptron_tagger')\n",
+        "nltk.download('state_union')\n",
+        "from nltk.corpus import state_union\n",
+        "from nltk.tokenize import PunktSentenceTokenizer\n",
+        " \n",
+        "# process the text and print Named entities\n",
+        "# tokenization\n",
+        "train_text = state_union.raw()\n",
+        " \n",
+        "sample_text = state_union.raw(\"2006-GWBush.txt\")\n",
+        "custom_sent_tokenizer = PunktSentenceTokenizer(train_text)\n",
+        "tokenized = custom_sent_tokenizer.tokenize(sample_text)\n",
+        "# function"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "szBuYQgmYeQv",
+        "outputId": "28feaa55-ecf8-4842-92ff-5c5bbe390611"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "[nltk_data] Downloading package words to /root/nltk_data...\n",
+            "[nltk_data]   Package words is already up-to-date!\n",
+            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
+            "[nltk_data]   Package punkt is already up-to-date!\n",
+            "[nltk_data] Downloading package maxent_ne_chunker to\n",
+            "[nltk_data]     /root/nltk_data...\n",
+            "[nltk_data]   Package maxent_ne_chunker is already up-to-date!\n",
+            "[nltk_data] Downloading package averaged_perceptron_tagger to\n",
+            "[nltk_data]     /root/nltk_data...\n",
+            "[nltk_data]   Package averaged_perceptron_tagger is already up-to-\n",
+            "[nltk_data]       date!\n",
+            "[nltk_data] Downloading package state_union to /root/nltk_data...\n",
+            "[nltk_data]   Package state_union is already up-to-date!\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "for i in tokenized:\n",
+        "  words = nltk.word_tokenize(i)\n",
+        "  tagged = nltk.pos_tag(words)\n",
+        "  if(tagged[0][1]==\"NN\"):\n",
+        "    print(tagged[0])\n",
+        "     "
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "qtQScPTkZzjw",
+        "outputId": "af00a285-434a-4f53-b406-5af7231a31e8"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "('Tonight', 'NN')\n",
+            "('Today', 'NN')\n",
+            "('Tonight', 'NN')\n",
+            "('Welfare', 'NN')\n",
+            "('Drug', 'NN')\n",
+            "('Today', 'NN')\n",
+            "('Today', 'NN')\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "f=open(\"ex1nlptextdata.txt\",\"r\")\n",
+        "data=f.read()\n"
+      ],
+      "metadata": {
+        "id": "64t3uZ95bFmW"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "txtdat=data.split(\" \")\n",
+        "print(txtdat)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "9c3WplVzdhE_",
+        "outputId": "58c559f7-fdfe-451b-a342-c032f74f00ef"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "['Python', 'is', 'a', 'high-level,', 'general-purpose', 'programming', 'language.', 'Its', 'design', 'philosophy', 'emphasizes', 'code', 'readability', 'with', 'the', 'use', 'of', 'significant', 'indentation.[33]\\n\\nPython', 'is', 'dynamically', 'typed', 'and', 'garbage-collected.', 'It', 'supports', 'multiple', 'programming', 'paradigms,', 'including', 'structured', '(particularly', 'procedural),', 'object-oriented', 'and', 'functional', 'programming.', '\\nRather', 'than', 'building', 'all', 'of', 'its', 'functionality', 'into', 'its', 'core,', '\\nPython', 'was', 'designed', 'to', 'be', 'highly', 'extensible', 'via', 'modules.', 'This\\ncompact', 'modularity', 'has', 'made', 'it', 'particularly', 'popular', 'as', 'a', 'means\\nof', 'adding', 'programmable', 'interfaces', 'to', 'existing', 'applications.\\nVan', \"Rossum's\", 'vision', 'of', 'a', 'small', 'core', 'language', 'with', 'a', 'large', 'standard', 'library', 'and', 'easily', 'extensible', 'interpreter', 'stemmed', 'from', 'his', 'frustrations', 'with', 'ABC,', 'which', 'espoused', 'the', 'opposite', 'approach\\n']\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "for i in txtdat:\n",
+        "  words = nltk.word_tokenize(i)\n",
+        "  tagged = nltk.pos_tag(words)\n",
+        "  if(tagged[0][1]==\"NN\"):\n",
+        "    print(tagged[0])"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "qtfZyvXMdjc2",
+        "outputId": "cc15222b-b340-4140-d6f4-0c0f15c0b3e8"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "('Python', 'NN')\n",
+            "('high-level', 'NN')\n",
+            "('language', 'NN')\n",
+            "('design', 'NN')\n",
+            "('philosophy', 'NN')\n",
+            "('code', 'NN')\n",
+            "('readability', 'NN')\n",
+            "('use', 'NN')\n",
+            "('indentation', 'NN')\n",
+            "('multiple', 'NN')\n",
+            "('paradigms', 'NN')\n",
+            "('procedural', 'NN')\n",
+            "('programming', 'NN')\n",
+            "('building', 'NN')\n",
+            "('functionality', 'NN')\n",
+            "('core', 'NN')\n",
+            "('Python', 'NN')\n",
+            "('modularity', 'NN')\n",
+            "('vision', 'NN')\n",
+            "('core', 'NN')\n",
+            "('language', 'NN')\n",
+            "('standard', 'NN')\n",
+            "('library', 'NN')\n",
+            "('interpreter', 'NN')\n",
+            "('opposite', 'NN')\n",
+            "('approach', 'NN')\n"
+          ]
+        }
+      ]
+    }
+  ]
+}