Delete chatbot.ipynb

chatbot.ipynb

@@ -1,357 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import random\n",
-    "import json\n",
-    "\n",
-    "import torch\n",
-    "import torch.nn as nn\n",
-    "import nltk\n",
-    "nltk.download('punkt')\n",
-    "\n",
-    "from torch.utils.data import Dataset, DataLoader\n",
-    "\n",
-    "import numpy as np\n",
-    "from nltk.stem.porter import PorterStemmer\n",
-    "stemmer = PorterStemmer()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class NeuralNet(nn.Module):\n",
-    "    def __init__(self, input_size, hidden_size, num_classes):\n",
-    "        super(NeuralNet, self).__init__()\n",
-    "        self.l1 = nn.Linear(input_size, hidden_size) \n",
-    "        self.l2 = nn.Linear(hidden_size, hidden_size) \n",
-    "        self.l3 = nn.Linear(hidden_size, num_classes)\n",
-    "        self.relu = nn.ReLU()\n",
-    "    \n",
-    "    def forward(self, x):\n",
-    "        out = self.l1(x)\n",
-    "        out = self.relu(out)\n",
-    "        out = self.l2(out)\n",
-    "        out = self.relu(out)\n",
-    "        out = self.l3(out)\n",
-    "        return out"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import json\n",
-    "\n",
-    "\n",
-    "intents_file_path = 'data\\intents.json'\n",
-    "\n",
-    "\n",
-    "with open(intents_file_path, 'r') as f:\n",
-    "    intents = json.load(f)\n",
-    "\n",
-    "\n",
-    "print(intents)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def tokenize(sentence):\n",
-    "    return nltk.word_tokenize(sentence)\n",
-    "\n",
-    "\n",
-    "def stem(word):\n",
-    "    return stemmer.stem(word.lower())\n",
-    "\n",
-    "\n",
-    "def bag_of_words(tokenized_sentence, words):\n",
-    "    sentence_words = [stem(word) for word in tokenized_sentence]\n",
-    "    bag = np.zeros(len(words), dtype=np.float32)\n",
-    "    for idx, w in enumerate(words):\n",
-    "        if w in sentence_words: \n",
-    "            bag[idx] = 1\n",
-    "\n",
-    "    return bag"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "all_words = []\n",
-    "tags = []\n",
-    "xy = []\n",
-    "for intent in intents['intents']:\n",
-    "    tag = intent['tag']\n",
-    "    tags.append(tag)\n",
-    "    for pattern in intent['patterns']:\n",
-    "        w = tokenize(pattern)\n",
-    "        all_words.extend(w)\n",
-    "        xy.append((w, tag))\n",
-    "\n",
-    "ignore_words = ['?', '.', '!']\n",
-    "all_words = [stem(w) for w in all_words if w not in ignore_words]\n",
-    "all_words = sorted(set(all_words))\n",
-    "tags = sorted(set(tags))\n",
-    "\n",
-    "print(len(xy), \"patterns\")\n",
-    "print(len(tags), \"tags:\", tags)\n",
-    "print(len(all_words), \"unique stemmed words:\", all_words)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "X_train = []\n",
-    "y_train = []\n",
-    "for (pattern_sentence, tag) in xy:\n",
-    "    bag = bag_of_words(pattern_sentence, all_words)\n",
-    "    X_train.append(bag)\n",
-    "    label = tags.index(tag)\n",
-    "    y_train.append(label)\n",
-    "\n",
-    "X_train = np.array(X_train)\n",
-    "y_train = np.array(y_train)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "num_epochs = 1000\n",
-    "batch_size = 8\n",
-    "learning_rate = 0.001\n",
-    "input_size = len(X_train[0])\n",
-    "hidden_size = 8\n",
-    "output_size = len(tags)\n",
-    "print(input_size, output_size)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class ChatDataset(Dataset):\n",
-    "\n",
-    "    def __init__(self):\n",
-    "        self.n_samples = len(X_train)\n",
-    "        self.x_data = X_train\n",
-    "        self.y_data = y_train\n",
-    "\n",
-    "    def __getitem__(self, index):\n",
-    "        return self.x_data[index], self.y_data[index]\n",
-    "    def __len__(self):\n",
-    "        return self.n_samples"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dataset = ChatDataset()\n",
-    "train_loader = DataLoader(dataset=dataset,\n",
-    "                          batch_size=batch_size,\n",
-    "                          shuffle=True,\n",
-    "                          num_workers=0)\n",
-    "\n",
-    "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
-    "\n",
-    "model = NeuralNet(input_size, hidden_size, output_size).to(device)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "criterion = nn.CrossEntropyLoss()\n",
-    "optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)\n",
-    "\n",
-    "for epoch in range(num_epochs):\n",
-    "    for (words, labels) in train_loader:\n",
-    "        words = words.to(device)\n",
-    "        labels = labels.to(dtype=torch.long).to(device)\n",
-    "\n",
-    "        outputs = model(words)\n",
-    "        loss = criterion(outputs, labels)\n",
-    "        \n",
-    "        optimizer.zero_grad()\n",
-    "        loss.backward()\n",
-    "        optimizer.step()\n",
-    "        \n",
-    "    if (epoch+1) % 100 == 0:\n",
-    "        print (f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')\n",
-    "\n",
-    "\n",
-    "print(f'final loss: {loss.item():.4f}')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = {\n",
-    "\"model_state\": model.state_dict(),\n",
-    "\"input_size\": input_size,\n",
-    "\"hidden_size\": hidden_size,\n",
-    "\"output_size\": output_size,\n",
-    "\"all_words\": all_words,\n",
-    "\"tags\": tags\n",
-    "}\n",
-    "\n",
-    "FILE = \"data.pth\"\n",
-    "torch.save(data, FILE)\n",
-    "\n",
-    "print(f'training complete. file saved to {FILE}')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "Interrupted by user",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-      "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_7908\\3081624382.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     20\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Let's chat! (type 'quit' to exit)\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     21\u001b[0m \u001b[1;32mwhile\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 22\u001b[1;33m     \u001b[0msentence\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"You: \"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     23\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0msentence\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m\"quit\"\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     24\u001b[0m         \u001b[1;32mbreak\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
-      "\u001b[1;32mc:\\Users\\Anuj Bohra\\anaconda3\\envs\\anuj\\lib\\site-packages\\ipykernel\\kernelbase.py\u001b[0m in \u001b[0;36mraw_input\u001b[1;34m(self, prompt)\u001b[0m\n\u001b[0;32m   1179\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_parent_ident\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"shell\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1180\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_parent\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"shell\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1181\u001b[1;33m             \u001b[0mpassword\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1182\u001b[0m         )\n\u001b[0;32m   1183\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
-      "\u001b[1;32mc:\\Users\\Anuj Bohra\\anaconda3\\envs\\anuj\\lib\\site-packages\\ipykernel\\kernelbase.py\u001b[0m in \u001b[0;36m_input_request\u001b[1;34m(self, prompt, ident, parent, password)\u001b[0m\n\u001b[0;32m   1217\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mKeyboardInterrupt\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1218\u001b[0m                 \u001b[1;31m# re-raise KeyboardInterrupt, to truncate traceback\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1219\u001b[1;33m                 \u001b[1;32mraise\u001b[0m \u001b[0mKeyboardInterrupt\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Interrupted by user\"\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1220\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1221\u001b[0m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlog\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwarning\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Invalid Message:\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexc_info\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
-      "\u001b[1;31mKeyboardInterrupt\u001b[0m: Interrupted by user"
-     ]
-    }
-   ],
-   "source": [
-    "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
-    "\n",
-    "\n",
-    "\n",
-    "FILE = \"data.pth\"\n",
-    "data = torch.load(FILE)\n",
-    "\n",
-    "input_size = data[\"input_size\"]\n",
-    "hidden_size = data[\"hidden_size\"]\n",
-    "output_size = data[\"output_size\"]\n",
-    "all_words = data['all_words']\n",
-    "tags = data['tags']\n",
-    "model_state = data[\"model_state\"]\n",
-    "\n",
-    "model = NeuralNet(input_size, hidden_size, output_size).to(device)\n",
-    "model.load_state_dict(model_state)\n",
-    "model.eval()\n",
-    "\n",
-    "bot_name = \"Medical ChatBot\"\n",
-    "print(\"Let's chat! (type 'quit' to exit)\")\n",
-    "while True:\n",
-    "    sentence = input(\"You: \")\n",
-    "    if sentence == \"quit\":\n",
-    "        break\n",
-    "\n",
-    "    sentence = tokenize(sentence)\n",
-    "    X = bag_of_words(sentence, all_words)\n",
-    "    X = X.reshape(1, X.shape[0])\n",
-    "    X = torch.from_numpy(X).to(device)\n",
-    "\n",
-    "    output = model(X)\n",
-    "    _, predicted = torch.max(output, dim=1)\n",
-    "\n",
-    "    tag = tags[predicted.item()]\n",
-    "\n",
-    "    probs = torch.softmax(output, dim=1)\n",
-    "    prob = probs[0][predicted.item()]\n",
-    "    if prob.item() > 0.75:\n",
-    "        for intent in intents['intents']:\n",
-    "            if tag == intent[\"tag\"]:\n",
-    "                print(f\"{bot_name}: {random.choice(intent['responses'])}\")\n",
-    "    else:\n",
-    "        print(f\"{bot_name}: I do not understand...\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "anuj",
-   "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": "3.7.16"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}