Skip to content

Commit

Permalink
Merge pull request #536 from CoderOMaster/main
Browse files Browse the repository at this point in the history 
Vulnerable Cancer Patients
  • Loading branch information
@abhisheks008
abhisheks008 authored Jan 19, 2024
2 parents 6e38a60 + 7586e78 commit 0840e13
Show file tree
Hide file tree
Showing 7 changed files with 13,185 additions and 0 deletions.
10,393 changes: 10,393 additions & 0 deletions Vulnerable Cancer Patient Analysis/Dataset/Mental Health Dataset.csv
View file

Large diffs are not rendered by default.

Binary file added Vulnerable Cancer Patient Analysis/Images/confusion_matrix.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added Vulnerable Cancer Patient Analysis/Images/intensity.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
2,384 changes: 2,384 additions & 0 deletions Vulnerable Cancer Patient Analysis/Model/EDA+ROBERTA.ipynb
View file

Large diffs are not rendered by default.

351 changes: 351 additions & 0 deletions Vulnerable Cancer Patient Analysis/Model/LSTM_GRU.ipynb
View file
Original file line number Diff line number Diff line change
@@ -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
}
Loading

0 comments on commit 0840e13

Please sign in to comment.