noshot 0.1.0__py3-none-any.whl

noshot/data/AIDS CN NLP/NLP/NLP 3/NLP-LAB-4.ipynb

@@ -0,0 +1,216 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "b443a5d0-8fca-4594-948b-b0882a4d47cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The preposition 'with' attaches to the 'VP'\n"
+     ]
+    }
+   ],
+   "source": [
+    "from collections import defaultdict\n",
+    "\n",
+    "class HindleRoothPPAttachment:\n",
+    "    def __init__(self):\n",
+    "        # Dictionary to store co-occurrence counts\n",
+    "        self.np_p_counts = defaultdict(int)\n",
+    "        self.vp_p_counts = defaultdict(int)\n",
+    "        self.p_counts = defaultdict(int)\n",
+    "    \n",
+    "    def train(self, corpus):\n",
+    "        \"\"\"\n",
+    "        Train the model using a parsed corpus.\n",
+    "        \n",
+    "        :param corpus: A parsed corpus with tuples (NP, VP, P)\n",
+    "        \"\"\"\n",
+    "        for (np, vp, p) in corpus:\n",
+    "            self.np_p_counts[(np, p)] += 1\n",
+    "            self.vp_p_counts[(vp, p)] += 1\n",
+    "            self.p_counts[p] += 1\n",
+    "    \n",
+    "    def calculate_probabilities(self, np, vp, p):\n",
+    "        \"\"\"\n",
+    "        Calculate the probabilities P(NP, P) and P(VP, P).\n",
+    "        \n",
+    "        :param np: Noun phrase\n",
+    "        :param vp: Verb phrase\n",
+    "        :param p: Preposition\n",
+    "        :return: (P(NP, P), P(VP, P))\n",
+    "        \"\"\"\n",
+    "        p_count = self.p_counts[p]\n",
+    "        \n",
+    "        # Avoid division by zero\n",
+    "        if p_count == 0:\n",
+    "            return 0, 0\n",
+    "        \n",
+    "        p_np_p = self.np_p_counts[(np, p)] / p_count\n",
+    "        p_vp_p = self.vp_p_counts[(vp, p)] / p_count\n",
+    "        \n",
+    "        return p_np_p, p_vp_p\n",
+    "    \n",
+    "    def decide_attachment(self, np, vp, p):\n",
+    "        \"\"\"\n",
+    "        Decide whether the preposition attaches to the NP or the VP.\n",
+    "        \n",
+    "        :param np: Noun phrase\n",
+    "        :param vp: Verb phrase\n",
+    "        :param p: Preposition\n",
+    "        :return: 'NP' or 'VP' based on the attachment decision\n",
+    "        \"\"\"\n",
+    "        p_np_p, p_vp_p = self.calculate_probabilities(np, vp, p)\n",
+    "        \n",
+    "        if p_np_p > p_vp_p:\n",
+    "            return 'NP'\n",
+    "        else:\n",
+    "            return 'VP'\n",
+    "\n",
+    "# Example usage\n",
+    "if __name__ == \"__main__\":\n",
+    "    # Example corpus: List of tuples (NP, VP, P)\n",
+    "    corpus = [\n",
+    "        (\"the man\", \"saw\", \"with\"),\n",
+    "        (\"the book\", \"is\", \"on\"),\n",
+    "        (\"the cat\", \"sat\", \"on\"),\n",
+    "        (\"the dog\", \"barked\", \"at\"),\n",
+    "        # More parsed sentences from a corpus...\n",
+    "    ]\n",
+    "    \n",
+    "    hr_model = HindleRoothPPAttachment()\n",
+    "    hr_model.train(corpus)\n",
+    "    \n",
+    "    # Test the model with a new sentence\n",
+    "    np = \"soldiers\"\n",
+    "    vp = \"saw\"\n",
+    "    p = \"with\"\n",
+    "    \n",
+    "    attachment = hr_model.decide_attachment(np, vp, p)\n",
+    "    print(f\"The preposition '{p}' attaches to the '{attachment}'\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "47e7d4c7-1352-47a9-8625-270b1bacdc48",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Enter the verb:  1\n",
+      "Enter the noun:  2\n",
+      "Enter the preposition:  3\n",
+      "Enter the occurrence of the preposition '3' with the verb '1':  4\n",
+      "Enter the total occurrences of the verb '1':  5\n",
+      "Enter the occurrence of the preposition '3' with the noun '2':  6\n",
+      "Enter the total occurrences of the noun '2':  7\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Lambda :(1, 2, 3) = -2.906890595608518\n",
+      "PP attaches with the Noun.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import math\n",
+    "\n",
+    "# Step 1: Ask the user for occurrence counts\n",
+    "def get_user_input():\n",
+    "    verb = input(\"Enter the verb: \").strip()\n",
+    "    noun = input(\"Enter the noun: \").strip()\n",
+    "    prep = input(\"Enter the preposition: \").strip()\n",
+    "    \n",
+    "    verb_prep_count = int(input(f\"Enter the occurrence of the preposition '{prep}' with the verb '{verb}': \"))\n",
+    "    verb_total_count = int(input(f\"Enter the total occurrences of the verb '{verb}': \"))\n",
+    "    \n",
+    "    noun_prep_count = int(input(f\"Enter the occurrence of the preposition '{prep}' with the noun '{noun}': \"))\n",
+    "    noun_total_count = int(input(f\"Enter the total occurrences of the noun '{noun}': \"))\n",
+    "\n",
+    "    return verb, noun, prep, verb_prep_count, verb_total_count, noun_prep_count, noun_total_count\n",
+    "\n",
+    "# Step 2: Calculate Probabilities and λ(v, n, p)\n",
+    "def calculate_lambda(verb, noun, prep, verb_prep_count, verb_total_count, noun_prep_count, noun_total_count):\n",
+    "    # Calculate P(VA_p = 1 | v)\n",
+    "    P_VAp = verb_prep_count / verb_total_count\n",
+    "    \n",
+    "    # Calculate P(NA_p = 1 | n)\n",
+    "    P_NAp = noun_prep_count / noun_total_count\n",
+    "    \n",
+    "    # Calculate P(NA_p = 0 | n)\n",
+    "    P_NAp_0 = 1 - P_NAp\n",
+    "\n",
+    "    # Handle case where probabilities might cause division by zero\n",
+    "    if P_NAp == 0:\n",
+    "        return None, \"Error: Division by zero in log-ratio calculation due to insufficient data.\"\n",
+    "    \n",
+    "    # Calculate λ(v, n, p)\n",
+    "    lambda_value = math.log2((P_VAp * P_NAp_0) / P_NAp)\n",
+    "    \n",
+    "    return lambda_value, None\n",
+    "\n",
+    "# Step 3: Determine the attachment\n",
+    "def determine_attachment(lambda_value):\n",
+    "    if lambda_value > 0:\n",
+    "        return \"PP attaches with the Verb.\"\n",
+    "    else:\n",
+    "        return \"PP attaches with the Noun.\"\n",
+    "\n",
+    "# Step 4: Interactive User Input\n",
+    "def hindle_rooth_algorithm():\n",
+    "    verb, noun, prep, verb_prep_count, verb_total_count, noun_prep_count, noun_total_count = get_user_input()\n",
+    "\n",
+    "    lambda_value, error_message = calculate_lambda(verb, noun, prep, verb_prep_count, verb_total_count, noun_prep_count, noun_total_count)\n",
+    "    \n",
+    "    if error_message:\n",
+    "        print(error_message)\n",
+    "    else:\n",
+    "        result = determine_attachment(lambda_value)\n",
+    "        print(f\"Lambda :({verb}, {noun}, {prep}) = {lambda_value}\")\n",
+    "        print(result)\n",
+    "\n",
+    "# Run the interactive algorithm\n",
+    "hindle_rooth_algorithm()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0cc09162-7ca1-431b-bc2f-923fd94904a5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

noshot/data/AIDS CN NLP/NLP/NLP 3/NLP-LAB-5.ipynb

@@ -0,0 +1,216 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "b443a5d0-8fca-4594-948b-b0882a4d47cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The preposition 'with' attaches to the 'VP'\n"
+     ]
+    }
+   ],
+   "source": [
+    "from collections import defaultdict\n",
+    "\n",
+    "class HindleRoothPPAttachment:\n",
+    "    def __init__(self):\n",
+    "        # Dictionary to store co-occurrence counts\n",
+    "        self.np_p_counts = defaultdict(int)\n",
+    "        self.vp_p_counts = defaultdict(int)\n",
+    "        self.p_counts = defaultdict(int)\n",
+    "    \n",
+    "    def train(self, corpus):\n",
+    "        \"\"\"\n",
+    "        Train the model using a parsed corpus.\n",
+    "        \n",
+    "        :param corpus: A parsed corpus with tuples (NP, VP, P)\n",
+    "        \"\"\"\n",
+    "        for (np, vp, p) in corpus:\n",
+    "            self.np_p_counts[(np, p)] += 1\n",
+    "            self.vp_p_counts[(vp, p)] += 1\n",
+    "            self.p_counts[p] += 1\n",
+    "    \n",
+    "    def calculate_probabilities(self, np, vp, p):\n",
+    "        \"\"\"\n",
+    "        Calculate the probabilities P(NP, P) and P(VP, P).\n",
+    "        \n",
+    "        :param np: Noun phrase\n",
+    "        :param vp: Verb phrase\n",
+    "        :param p: Preposition\n",
+    "        :return: (P(NP, P), P(VP, P))\n",
+    "        \"\"\"\n",
+    "        p_count = self.p_counts[p]\n",
+    "        \n",
+    "        # Avoid division by zero\n",
+    "        if p_count == 0:\n",
+    "            return 0, 0\n",
+    "        \n",
+    "        p_np_p = self.np_p_counts[(np, p)] / p_count\n",
+    "        p_vp_p = self.vp_p_counts[(vp, p)] / p_count\n",
+    "        \n",
+    "        return p_np_p, p_vp_p\n",
+    "    \n",
+    "    def decide_attachment(self, np, vp, p):\n",
+    "        \"\"\"\n",
+    "        Decide whether the preposition attaches to the NP or the VP.\n",
+    "        \n",
+    "        :param np: Noun phrase\n",
+    "        :param vp: Verb phrase\n",
+    "        :param p: Preposition\n",
+    "        :return: 'NP' or 'VP' based on the attachment decision\n",
+    "        \"\"\"\n",
+    "        p_np_p, p_vp_p = self.calculate_probabilities(np, vp, p)\n",
+    "        \n",
+    "        if p_np_p > p_vp_p:\n",
+    "            return 'NP'\n",
+    "        else:\n",
+    "            return 'VP'\n",
+    "\n",
+    "# Example usage\n",
+    "if __name__ == \"__main__\":\n",
+    "    # Example corpus: List of tuples (NP, VP, P)\n",
+    "    corpus = [\n",
+    "        (\"the man\", \"saw\", \"with\"),\n",
+    "        (\"the book\", \"is\", \"on\"),\n",
+    "        (\"the cat\", \"sat\", \"on\"),\n",
+    "        (\"the dog\", \"barked\", \"at\"),\n",
+    "        # More parsed sentences from a corpus...\n",
+    "    ]\n",
+    "    \n",
+    "    hr_model = HindleRoothPPAttachment()\n",
+    "    hr_model.train(corpus)\n",
+    "    \n",
+    "    # Test the model with a new sentence\n",
+    "    np = \"the man\"\n",
+    "    vp = \"saw\"\n",
+    "    p = \"with\"\n",
+    "    \n",
+    "    attachment = hr_model.decide_attachment(np, vp, p)\n",
+    "    print(f\"The preposition '{p}' attaches to the '{attachment}'\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "47e7d4c7-1352-47a9-8625-270b1bacdc48",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Enter the verb:  send\n",
+      "Enter the noun:  soldiers\n",
+      "Enter the preposition:  into\n",
+      "Enter the occurrence of the preposition 'into' with the verb 'send':  86\n",
+      "Enter the total occurrences of the verb 'send':  1742\n",
+      "Enter the occurrence of the preposition 'into' with the noun 'soldiers':  1\n",
+      "Enter the total occurrences of the noun 'soldiers':  1478\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "λ(send, soldiers, into) = 6.1881899568680225\n",
+      "PP attaches with the Verb.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import math\n",
+    "\n",
+    "# Step 1: Ask the user for occurrence counts\n",
+    "def get_user_input():\n",
+    "    verb = input(\"Enter the verb: \").strip()\n",
+    "    noun = input(\"Enter the noun: \").strip()\n",
+    "    prep = input(\"Enter the preposition: \").strip()\n",
+    "    \n",
+    "    verb_prep_count = int(input(f\"Enter the occurrence of the preposition '{prep}' with the verb '{verb}': \"))\n",
+    "    verb_total_count = int(input(f\"Enter the total occurrences of the verb '{verb}': \"))\n",
+    "    \n",
+    "    noun_prep_count = int(input(f\"Enter the occurrence of the preposition '{prep}' with the noun '{noun}': \"))\n",
+    "    noun_total_count = int(input(f\"Enter the total occurrences of the noun '{noun}': \"))\n",
+    "\n",
+    "    return verb, noun, prep, verb_prep_count, verb_total_count, noun_prep_count, noun_total_count\n",
+    "\n",
+    "# Step 2: Calculate Probabilities and λ(v, n, p)\n",
+    "def calculate_lambda(verb, noun, prep, verb_prep_count, verb_total_count, noun_prep_count, noun_total_count):\n",
+    "    # Calculate P(VA_p = 1 | v)\n",
+    "    P_VAp = verb_prep_count / verb_total_count\n",
+    "    \n",
+    "    # Calculate P(NA_p = 1 | n)\n",
+    "    P_NAp = noun_prep_count / noun_total_count\n",
+    "    \n",
+    "    # Calculate P(NA_p = 0 | n)\n",
+    "    P_NAp_0 = 1 - P_NAp\n",
+    "\n",
+    "    # Handle case where probabilities might cause division by zero\n",
+    "    if P_NAp == 0:\n",
+    "        return None, \"Error: Division by zero in log-ratio calculation due to insufficient data.\"\n",
+    "    \n",
+    "    # Calculate λ(v, n, p)\n",
+    "    lambda_value = math.log2((P_VAp * P_NAp_0) / P_NAp)\n",
+    "    \n",
+    "    return lambda_value, None\n",
+    "\n",
+    "# Step 3: Determine the attachment\n",
+    "def determine_attachment(lambda_value):\n",
+    "    if lambda_value > 0:\n",
+    "        return \"PP attaches with the Verb.\"\n",
+    "    else:\n",
+    "        return \"PP attaches with the Noun.\"\n",
+    "\n",
+    "# Step 4: Interactive User Input\n",
+    "def hindle_rooth_algorithm():\n",
+    "    verb, noun, prep, verb_prep_count, verb_total_count, noun_prep_count, noun_total_count = get_user_input()\n",
+    "\n",
+    "    lambda_value, error_message = calculate_lambda(verb, noun, prep, verb_prep_count, verb_total_count, noun_prep_count, noun_total_count)\n",
+    "    \n",
+    "    if error_message:\n",
+    "        print(error_message)\n",
+    "    else:\n",
+    "        result = determine_attachment(lambda_value)\n",
+    "        print(f\"λ({verb}, {noun}, {prep}) = {lambda_value}\")\n",
+    "        print(result)\n",
+    "\n",
+    "# Run the interactive algorithm\n",
+    "hindle_rooth_algorithm()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0cc09162-7ca1-431b-bc2f-923fd94904a5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

noshot/data/AIDS CN NLP/NLP/NLP 3/abc.txt

@@ -0,0 +1,6 @@
+Guy: How old are you?
+Hipster girl: You know, I never answer that question. Because to me, it's about
+how mature you are, you know? I mean, a fourteen year old could be more mature
+than a twenty-five year old, right? I'm sorry, I just never answer that question.
+Guy: But, uh, you're older than eighteen, right?
+Hipster girl: Oh, yeah.