Vulnerable Cancer Patients

Vulnerable Cancer Patient Analysis/Model/LSTM_GRU.ipynb

@@ -0,0 +1,351 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "v7KQqli6SXxZ"
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import tensorflow as tf\n",
+    "import re\n",
+    "from tensorflow.keras.preprocessing.text import one_hot\n",
+    "import matplotlib.pyplot as py\n",
+    "from tensorflow.keras.preprocessing.text import Tokenizer\n",
+    "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
+    "from tensorflow.keras.models import Sequential,load_model\n",
+    "from tensorflow.keras.layers import Embedding,LSTM,Dense,Dropout\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from tensorflow.keras.layers import Flatten\n",
+    "from tensorflow.keras.layers import Embedding"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "UXGmVN1VSbBN"
+   },
+   "outputs": [],
+   "source": [
+    "df=pd.read_csv(\"Mental Health Dataset.csv\")\n",
+    "df.posts=df.posts.astype(str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "rPl1uMVXUPSx",
+    "outputId": "f6eb9b04-02cb-4b89-b4da-3dc98dad6436"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                                                   posts      predicted  \\\n",
+      "10387  hey everyone I am a 25 year old male I work ou...       negative   \n",
+      "10388  have surgery for stage 1 colon cancer 1 year a...  very negative   \n",
+      "10389  the doctor advise we he could not remove the a...        neutral   \n",
+      "10390  my 66 year old father have been through so muc...        neutral   \n",
+      "10391  I have bein have a bloody stool since last yea...       negative   \n",
+      "\n",
+      "       intensity  \n",
+      "10387         -1  \n",
+      "10388         -2  \n",
+      "10389          0  \n",
+      "10390          0  \n",
+      "10391         -1  \n"
+     ]
+    }
+   ],
+   "source": [
+    "df.isnull().sum()\n",
+    "print(df.tail())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "id": "F4C1iyuEUVNK"
+   },
+   "outputs": [],
+   "source": [
+    "def clean_text(text):\n",
+    "    text=text.lower()\n",
+    "    text=re.sub(r'[^a-zA-Z0-9\\s]','',text)\n",
+    "    return text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "PgotztcoUW-t"
+   },
+   "outputs": [],
+   "source": [
+    "df['posts']=df['posts'].apply(clean_text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "id": "8--MaQ6nUXE9"
+   },
+   "outputs": [],
+   "source": [
+    "from tensorflow.keras.preprocessing.text import Tokenizer\n",
+    "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
+    "\n",
+    "# Assuming df.posts is your text data\n",
+    "vocab_size=500\n",
+    "max_length = 200\n",
+    "embed_vector_size=200\n",
+    "tokenizer = Tokenizer(num_words=vocab_size, oov_token='<OOV>')\n",
+    "tokenizer.fit_on_texts(df.posts)\n",
+    "\n",
+    "# Convert text to sequences\n",
+    "encoded_reviews = tokenizer.texts_to_sequences(df.posts)\n",
+    "\n",
+    "# Pad sequences\n",
+    "padded_reviews = pad_sequences(encoded_reviews, maxlen=max_length, padding='post')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "3BOM7QOiUc-1",
+    "outputId": "9dbbf3c5-3131-4c94-e337-84694392c8e0"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/5\n",
+      "260/260 [==============================] - 13s 39ms/step - loss: 0.9201 - accuracy: 0.6200 - val_loss: 0.7941 - val_accuracy: 0.6720\n",
+      "Epoch 2/5\n",
+      "260/260 [==============================] - 3s 10ms/step - loss: 0.5993 - accuracy: 0.7702 - val_loss: 0.7475 - val_accuracy: 0.6965\n",
+      "Epoch 3/5\n",
+      "260/260 [==============================] - 2s 8ms/step - loss: 0.3824 - accuracy: 0.8818 - val_loss: 0.7725 - val_accuracy: 0.6917\n",
+      "Epoch 4/5\n",
+      "260/260 [==============================] - 1s 5ms/step - loss: 0.2382 - accuracy: 0.9364 - val_loss: 0.8379 - val_accuracy: 0.6797\n",
+      "Epoch 5/5\n",
+      "260/260 [==============================] - 1s 6ms/step - loss: 0.1588 - accuracy: 0.9651 - val_loss: 0.8689 - val_accuracy: 0.6768\n",
+      "65/65 [==============================] - 0s 4ms/step - loss: 0.8689 - accuracy: 0.6768\n",
+      "Accuracy on Test Set: 0.6767676472663879\n"
+     ]
+    }
+   ],
+   "source": [
+    "#ANN BASED MODEL IS HERE\n",
+    "from tensorflow.keras.utils import to_categorical\n",
+    "\n",
+    "# Split the data into training and testing sets\n",
+    "X_train, X_test, y_train, y_test = train_test_split(padded_reviews, df['intensity'], test_size=0.2, random_state=42)\n",
+    "\n",
+    "# Build the model with Dropout layers\n",
+    "model = Sequential()\n",
+    "model.add(Embedding(vocab_size, embed_vector_size, input_length=max_length, name=\"embedding\"))\n",
+    "model.add(Flatten())\n",
+    "model.add(Dropout(0.5))  # Adding dropout with a dropout rate of 0.5\n",
+    "model.add(Dense(4, activation='softmax'))  # Assuming you have 4 classes\n",
+    "\n",
+    "# Compile the model\n",
+    "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "# Train the model on the oversampled data\n",
+    "model.fit(X_train, to_categorical(y_train,num_classes=4), epochs=5, validation_data=(X_test, to_categorical(y_test, num_classes=4)))\n",
+    "\n",
+    "# Evaluate the model\n",
+    "loss, accuracy = model.evaluate(X_test, to_categorical(y_test, num_classes=4))\n",
+    "print(f\"Accuracy on Test Set: {accuracy}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "XgP6hLYOpoBZ",
+    "outputId": "6ec0cd75-23bb-441c-93ad-7e6250ff9952"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/15\n",
+      "260/260 [==============================] - 15s 39ms/step - loss: 1.1118 - accuracy: 0.5254 - val_loss: 1.0045 - val_accuracy: 0.6123\n",
+      "Epoch 2/15\n",
+      "260/260 [==============================] - 6s 22ms/step - loss: 1.0912 - accuracy: 0.4992 - val_loss: 1.0932 - val_accuracy: 0.4598\n",
+      "Epoch 3/15\n",
+      "260/260 [==============================] - 5s 18ms/step - loss: 1.0079 - accuracy: 0.5809 - val_loss: 0.8843 - val_accuracy: 0.6494\n",
+      "Epoch 4/15\n",
+      "260/260 [==============================] - 6s 22ms/step - loss: 0.8847 - accuracy: 0.6542 - val_loss: 0.8469 - val_accuracy: 0.6522\n",
+      "Epoch 5/15\n",
+      "260/260 [==============================] - 4s 17ms/step - loss: 0.8212 - accuracy: 0.6751 - val_loss: 0.7992 - val_accuracy: 0.6888\n",
+      "Epoch 6/15\n",
+      "260/260 [==============================] - 4s 17ms/step - loss: 0.7563 - accuracy: 0.7058 - val_loss: 0.7528 - val_accuracy: 0.6931\n",
+      "Epoch 7/15\n",
+      "260/260 [==============================] - 6s 21ms/step - loss: 0.7399 - accuracy: 0.7131 - val_loss: 0.7206 - val_accuracy: 0.7003\n",
+      "Epoch 8/15\n",
+      "260/260 [==============================] - 4s 17ms/step - loss: 0.6795 - accuracy: 0.7378 - val_loss: 0.7090 - val_accuracy: 0.7095\n",
+      "Epoch 9/15\n",
+      "260/260 [==============================] - 5s 20ms/step - loss: 0.6676 - accuracy: 0.7437 - val_loss: 0.6944 - val_accuracy: 0.7109\n",
+      "Epoch 10/15\n",
+      "260/260 [==============================] - 5s 19ms/step - loss: 0.6346 - accuracy: 0.7564 - val_loss: 0.7330 - val_accuracy: 0.7114\n",
+      "Epoch 11/15\n",
+      "260/260 [==============================] - 4s 17ms/step - loss: 0.6257 - accuracy: 0.7616 - val_loss: 0.6922 - val_accuracy: 0.7085\n",
+      "Epoch 12/15\n",
+      "260/260 [==============================] - 5s 20ms/step - loss: 0.6012 - accuracy: 0.7736 - val_loss: 0.7449 - val_accuracy: 0.6955\n",
+      "Epoch 13/15\n",
+      "260/260 [==============================] - 5s 18ms/step - loss: 0.5886 - accuracy: 0.7785 - val_loss: 0.6919 - val_accuracy: 0.7133\n",
+      "Epoch 14/15\n",
+      "260/260 [==============================] - 5s 18ms/step - loss: 0.5754 - accuracy: 0.7824 - val_loss: 0.7149 - val_accuracy: 0.7172\n",
+      "Epoch 15/15\n",
+      "260/260 [==============================] - 6s 21ms/step - loss: 0.5603 - accuracy: 0.7902 - val_loss: 0.7128 - val_accuracy: 0.7201\n",
+      "65/65 [==============================] - 0s 7ms/step - loss: 0.7128 - accuracy: 0.7201\n",
+      "Accuracy on Test Set: 0.7200577259063721\n"
+     ]
+    }
+   ],
+   "source": [
+    "#DOUBLE LAYERED LSTM \n",
+    "\n",
+    "from tensorflow.keras.layers import LSTM\n",
+    "\n",
+    "# Build the model with LSTM and Dropout layers\n",
+    "model = Sequential()\n",
+    "model.add(Embedding(vocab_size, embed_vector_size, input_length=max_length, name=\"embedding\"))\n",
+    "model.add(LSTM(64, return_sequences=True))\n",
+    "model.add(LSTM(32))\n",
+    "model.add(Dropout(0.2))  # Adding dropout with a dropout rate of 0.2\n",
+    "model.add(Dense(4, activation='softmax'))  # Assuming you have 4 classes\n",
+    "\n",
+    "# Compile the model\n",
+    "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])  # Use categorical_crossentropy for classification\n",
+    "\n",
+    "# Train the model on the oversampled data\n",
+    "model.fit(X_train, to_categorical(y_train, num_classes=4), epochs=15, validation_data=(X_test, to_categorical(y_test, num_classes=4)))\n",
+    "\n",
+    "# Evaluate the model\n",
+    "loss, accuracy = model.evaluate(X_test, to_categorical(y_test, num_classes=4))\n",
+    "print(f\"Accuracy on Test Set: {accuracy}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "RPUWSzSY1Vjo",
+    "outputId": "0239db05-8953-4f76-bbd2-ca9017d9a4c5"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/15\n",
+      "260/260 [==============================] - 15s 45ms/step - loss: 1.1295 - accuracy: 0.4896 - val_loss: 0.9466 - val_accuracy: 0.6219\n",
+      "Epoch 2/15\n",
+      "260/260 [==============================] - 5s 17ms/step - loss: 0.9124 - accuracy: 0.6427 - val_loss: 0.8370 - val_accuracy: 0.6652\n",
+      "Epoch 3/15\n",
+      "260/260 [==============================] - 6s 22ms/step - loss: 0.8356 - accuracy: 0.6738 - val_loss: 0.8008 - val_accuracy: 0.6734\n",
+      "Epoch 4/15\n",
+      "260/260 [==============================] - 6s 22ms/step - loss: 0.7830 - accuracy: 0.6951 - val_loss: 0.8152 - val_accuracy: 0.6537\n",
+      "Epoch 5/15\n",
+      "260/260 [==============================] - 5s 19ms/step - loss: 0.7538 - accuracy: 0.7119 - val_loss: 0.7658 - val_accuracy: 0.7003\n",
+      "Epoch 6/15\n",
+      "260/260 [==============================] - 5s 19ms/step - loss: 0.7325 - accuracy: 0.7263 - val_loss: 0.7631 - val_accuracy: 0.7018\n",
+      "Epoch 7/15\n",
+      "260/260 [==============================] - 5s 18ms/step - loss: 0.7165 - accuracy: 0.7329 - val_loss: 0.7431 - val_accuracy: 0.7003\n",
+      "Epoch 8/15\n",
+      "260/260 [==============================] - 5s 21ms/step - loss: 0.6951 - accuracy: 0.7374 - val_loss: 0.7777 - val_accuracy: 0.6922\n",
+      "Epoch 9/15\n",
+      "260/260 [==============================] - 5s 17ms/step - loss: 0.6751 - accuracy: 0.7427 - val_loss: 0.7564 - val_accuracy: 0.7023\n",
+      "Epoch 10/15\n",
+      "260/260 [==============================] - 4s 17ms/step - loss: 0.6509 - accuracy: 0.7465 - val_loss: 0.7279 - val_accuracy: 0.7047\n",
+      "Epoch 11/15\n",
+      "260/260 [==============================] - 5s 21ms/step - loss: 0.6305 - accuracy: 0.7592 - val_loss: 0.7105 - val_accuracy: 0.7013\n",
+      "Epoch 12/15\n",
+      "260/260 [==============================] - 5s 18ms/step - loss: 0.6107 - accuracy: 0.7707 - val_loss: 0.7059 - val_accuracy: 0.7133\n",
+      "Epoch 13/15\n",
+      "260/260 [==============================] - 5s 20ms/step - loss: 0.5945 - accuracy: 0.7707 - val_loss: 0.7101 - val_accuracy: 0.7076\n",
+      "Epoch 14/15\n",
+      "260/260 [==============================] - 5s 19ms/step - loss: 0.5850 - accuracy: 0.7776 - val_loss: 0.7368 - val_accuracy: 0.7037\n",
+      "Epoch 15/15\n",
+      "260/260 [==============================] - 4s 17ms/step - loss: 0.5728 - accuracy: 0.7848 - val_loss: 0.7234 - val_accuracy: 0.7124\n",
+      "65/65 [==============================] - 0s 7ms/step - loss: 0.7234 - accuracy: 0.7124\n",
+      "Accuracy on Test Set: 0.7123616933822632\n"
+     ]
+    }
+   ],
+   "source": [
+    "#GRU BASED MODEL\n",
+    "from tensorflow.keras.layers import Embedding, GRU\n",
+    "model = Sequential()\n",
+    "model.add(Embedding(input_dim=vocab_size, output_dim=16, input_length=max_length))\n",
+    "model.add(GRU(units=64, return_sequences=True))\n",
+    "model.add(GRU(units=32))\n",
+    "model.add(Dropout(0.2))\n",
+    "model.add(Dense(units=4, activation='softmax'))\n",
+    "\n",
+    "# Compile the model\n",
+    "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "# Train the model on the oversampled data\n",
+    "model.fit(X_train, to_categorical(y_train,num_classes=4), epochs=15, validation_data=(X_test, to_categorical(y_test, num_classes=4)))\n",
+    "\n",
+    "# Evaluate the model\n",
+    "loss, accuracy = model.evaluate(X_test, to_categorical(y_test, num_classes=4))\n",
+    "print(f\"Accuracy on Test Set: {accuracy}\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": []
+  },
+  "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": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}