Upload model.ipynb

model.ipynb

@@ -0,0 +1,114 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "ace57031",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.023255813953488372\n",
+      "Prediction: [' is a member of the BC Partners for Mental Health and Addictions Information. The institute is dedicated to the study of substance use in support of community-wide efforts aimed at providing all people with access to healthier lives']\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "\n",
+    "# Step 1: Collect and preprocess data\n",
+    "# Get all the questions from Questions column and responses from Questions column in the dataset data.csv\n",
+    "# questions = data[\"Questions\"].tolist()\n",
+    "# responses = data[\"Responses\"].tolist()\n",
+    "questions = []\n",
+    "responses = []\n",
+    "q_id = []\n",
+    "with open(\"data.csv\", \"r\") as f:\n",
+    "    for line in f:\n",
+    "        \n",
+    "        array = line.split(\",\") \n",
+    "        # questions.append(question)\n",
+    "        # responses.append(response)\n",
+    "        # q_id.append(question_id)\n",
+    "        try:\n",
+    "            question = array[1]\n",
+    "            response = array[2]\n",
+    "            question_id = array[0]\n",
+    "            questions.append(question)\n",
+    "            responses.append(response)\n",
+    "            q_id.append(question_id)\n",
+    "        except:\n",
+    "            pass\n",
+    "\n",
+    "\n",
+    "        \n",
+    "\n",
+    "# print(questions)\n",
+    "# print(responses)\n",
+    "\n",
+    "\n",
+    "# questions = [\"What are some symptoms of depression?\",\n",
+    "#              \"How can I manage my anxiety?\",\n",
+    "#              \"What are the treatments for bipolar disorder?\"]\n",
+    "# responses = [\"Symptoms of depression include sadness, lack of energy, and loss of interest in activities.\",\n",
+    "#              \"You can manage your anxiety through techniques such as deep breathing, meditation, and therapy.\",\n",
+    "#              \"Treatments for bipolar disorder include medication, therapy, and lifestyle changes.\"]\n",
+    "\n",
+    "vectorizer = TfidfVectorizer()\n",
+    "X = vectorizer.fit_transform(questions)\n",
+    "y = responses\n",
+    "\n",
+    "# Step 2: Split data into training and testing sets\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n",
+    "\n",
+    "# Step 3: Choose a machine learning algorithm\n",
+    "model = LogisticRegression()\n",
+    "\n",
+    "# Step 4: Train the model\n",
+    "model.fit(X_train, y_train)\n",
+    "\n",
+    "# Step 5: Evaluate the model\n",
+    "y_pred = model.predict(X_test)\n",
+    "accuracy = accuracy_score(y_test, y_pred)\n",
+    "print(\"Accuracy:\", accuracy)\n",
+    "\n",
+    "# Step 6: Use the model to make predictions\n",
+    "new_question = \"I feel sad\"\n",
+    "new_question_vector = vectorizer.transform([new_question])\n",
+    "prediction = model.predict(new_question_vector)\n",
+    "print(\"Prediction:\", prediction)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.10.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}