Upload 35 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/cleaned_data.csv filter=lfs diff=lfs merge=lfs -text
+data/Combined_Data.csv filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+samh_venv
+.env

Dockerfile

@@ -0,0 +1,23 @@
+# Use an official Python runtime as a parent image
+FROM python:3.10-slim
+
+# Set the working directory
+WORKDIR /app
+
+# Copy the requirements file into the container
+COPY requirements.txt /app/requirements.txt
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the current directory contents into the container at /app
+COPY . /app
+
+# Download NLTK data
+RUN python -c "import nltk; nltk.download('stopwords'); nltk.download('wordnet')"
+
+# Make port 8000 available to the world outside this container
+EXPOSE 8000
+
+# Run the entrypoint script
+CMD ["sh", "./entrypoint.sh"]

README.md

@@ -1,11 +1,42 @@
----
-title: SAMH
-emoji: 📚
-colorFrom: indigo
-colorTo: blue
-sdk: docker
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Sentiment Analysis API
+![alt text](image.png)
+
+This project provides a sentiment analysis API using FastAPI and a machine learning model trained on textual data.
+
+## Features
+
+- Data ingestion and preprocessing
+- Model training and saving
+- FastAPI application for serving predictions
+- Dockerized for easy deployment
+
+## Setup
+
+### Prerequisites
+
+- Docker installed on your system
+
+### Build and Run
+
+1. Build the Docker image:
+
+    ```bash
+    docker build -t sentiment-analysis-api .
+    ```
+
+2. Run the Docker container:
+
+    ```bash
+    docker run -p 8000:8000 sentiment-analysis-api
+    ```
+
+3. Access the API:
+
+    - Home: [http://localhost:8000](http://localhost:8000)
+    - Health Check: [http://localhost:8000/health](http://localhost:8000/health)
+    - Predict Sentiment: Use a POST request to [http://localhost:8000/predict_sentiment](http://localhost:8000/predict_sentiment) with a JSON body.
+
+## Example cURL Command
+
+```bash
+curl -X POST "http://localhost:8000/predict_sentiment" -H "Content-Type: application/json" -d '{"text": "I love programming in Python."}'

data/Combined_Data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0700996d814af3ec77ef31870b68c6cdf991217eb76e259c7196df7f2e0e27ba
+size 31469552

data/cleaned_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8b9a23caf50bd71eb2e02f6b49447f247791e66b0936f0cb47e479736b0c17e
+size 49456310

data_pipeline/data_ingestion.py

@@ -0,0 +1,38 @@
+import os
+import sys
+import requests
+
+# Add the root directory to sys.path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+from logging_config.logger_config import get_logger
+
+# Get the logger
+logger = get_logger(__name__)
+
+def download_data(url, save_path):
+    # Ensure the save directory exists
+    os.makedirs(os.path.dirname(save_path), exist_ok=True)
+
+    # Send a GET request to the URL
+    logger.info(f"Sending GET request to {url}")
+    response = requests.get(url)
+
+    # Check if the request was successful
+    if response.status_code == 200:
+        # Write the content to the specified file
+        with open(save_path, 'wb') as file:
+            file.write(response.content)
+        logger.info(f"Data downloaded successfully and saved to {save_path}")
+    else:
+        logger.error(f"Failed to download data. Status code: {response.status_code}")
+
+if __name__ == "__main__":
+    # URL of the dataset
+    dataset_url = "https://raw.githubusercontent.com/timothyafolami/SAMH-Sentiment-Analysis-For-Mental-Health/master/data/Combined_Data.csv"
+    
+    # Path to save the dataset
+    save_file_path = os.path.join("./data", "Combined_Data.csv")
+
+    # Download the dataset
+    download_data(dataset_url, save_file_path)

data_pipeline/data_preprocessor.py

@@ -0,0 +1,89 @@
+import os
+import sys
+import re
+import string
+import pandas as pd
+import nltk
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+
+# Add the root directory to sys.path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+from logging_config.logger_config import get_logger
+
+
+# Download necessary NLTK data files
+nltk.download('stopwords')
+nltk.download('wordnet')
+
+# Get the logger
+logger = get_logger(__name__)
+
+# Custom Preprocessor Class
+class TextPreprocessor:
+    def __init__(self):
+        self.stop_words = set(stopwords.words('english'))
+        self.lemmatizer = WordNetLemmatizer()
+        logger.info("TextPreprocessor initialized.")
+    
+    def preprocess_text(self, text):
+        # logger.info(f"Original text: {text}")
+        # Lowercase the text
+        text = text.lower()
+        # logger.info(f"Lowercased text: {text}")
+        
+        # Remove punctuation
+        text = re.sub(f'[{re.escape(string.punctuation)}]', '', text)
+        # logger.info(f"Text after punctuation removal: {text}")
+        
+        # Remove numbers
+        text = re.sub(r'\d+', '', text)
+        # logger.info(f"Text after number removal: {text}")
+        
+        # Tokenize the text
+        words = text.split()
+        # logger.info(f"Tokenized text: {words}")
+        
+        # Remove stopwords and apply lemmatization
+        words = [self.lemmatizer.lemmatize(word) for word in words if word not in self.stop_words]
+        # logger.info(f"Text after stopword removal and lemmatization: {words}")
+        
+        # Join words back into a single string
+        cleaned_text = ' '.join(words)
+        # logger.info(f"Cleaned text: {cleaned_text}")
+        
+        return cleaned_text
+
+def load_and_preprocess_data(file_path):
+    # Load the data
+    logger.info(f"Loading data from {file_path}")
+    df = pd.read_csv(file_path)
+    # dropping missing values
+    logger.info("Dropping missing values")
+    df.dropna(inplace=True)
+    
+    # Check if the necessary column exists
+    if 'statement' not in df.columns:
+        logger.error("The required column 'statement' is missing from the dataset.")
+        return
+    
+    # Initialize the text preprocessor
+    preprocessor = TextPreprocessor()
+    
+    # Apply the preprocessing to the 'statement' column
+    logger.info("Starting text preprocessing...")
+    df['cleaned_statement'] = df['statement'].apply(preprocessor.preprocess_text)
+    logger.info("Text preprocessing completed.")
+    
+    # Save the cleaned data to a new CSV file
+    cleaned_file_path = os.path.join('./data', 'cleaned_data.csv')
+    df.to_csv(cleaned_file_path, index=False)
+    logger.info(f"Cleaned data saved to {cleaned_file_path}")
+
+if __name__ == "__main__":
+    # Path to the downloaded dataset
+    dataset_path = os.path.join("./data", "Combined_Data.csv")
+    
+    # Preprocess the data
+    load_and_preprocess_data(dataset_path)

db_connection.py

@@ -0,0 +1,40 @@
+import os, sys
+from supabase import create_client, Client
+
+# Add the root directory to sys.path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+from logging_config.logger_config import get_logger
+
+# Get the logger
+logger = get_logger(__name__)
+
+
+#connecting to the database
+url: str = os.environ.get("SUPABASE_PROJECT_URL")
+key: str = os.environ.get("SUPABASE_API_KEY")
+supabase: Client = create_client(url, key)
+
+# creating a function to update the database
+def insert_db(data: dict, table='Interaction History'):
+    try:
+        logger.info(f"Inserting data into the database: {data}")
+        response = supabase.table(table).insert(data).execute()
+        logger.info(f"Data inserted successfully: {response}")
+        return response
+    except Exception as e:
+        logger.error(f"Error inserting data into the database: {e}")
+        return None
+    
+if __name__ == "__main__":
+    # Test the insert_db function
+    data = {
+    "Input_text" : "I feel incredibly anxious about everything and can't stop worrying",
+    "Model_prediction" : "Anxiety",
+    "Llama_3_Prediction" : "Anxiety",
+    "Llama_3_Explanation" : "After my analysis, i concluded that the user is suffering from anxiety",
+    "User Rating" : 5,
+    }
+    
+    response = insert_db(data)
+    print(response)
+    

entrypoint.sh

@@ -0,0 +1,20 @@
+#!/bin/sh
+
+# Exit immediately if a command exits with a non-zero status
+set -e
+
+# Step 1: Data Ingestion
+echo "Running data ingestion..."
+python data_pipeline/data_ingestion.py
+
+# Step 2: Data Preprocessing
+echo "Running data preprocessing..."
+python data_pipeline/data_preprocessor.py
+
+# Step 3: Model Training
+echo "Running model training..."
+python model_pipeline/model_trainer.py
+
+# Step 4: Run FastAPI App
+echo "Starting FastAPI app..."
+uvicorn fastapi_app.main:app --host 0.0.0.0 --port 8000

experiment.ipynb

@@ -0,0 +1,1871 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# data loading\n",
+    "data = pd.read_csv('data//Combined_Data.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Unnamed: 0</th>\n",
+       "      <th>statement</th>\n",
+       "      <th>status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>oh my gosh</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>trouble sleeping, confused mind, restless hear...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>All wrong, back off dear, forward doubt. Stay ...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>I've shifted my focus to something else but I'...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>I'm restless and restless, it's been a month n...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Unnamed: 0                                          statement   status\n",
+       "0           0                                         oh my gosh  Anxiety\n",
+       "1           1  trouble sleeping, confused mind, restless hear...  Anxiety\n",
+       "2           2  All wrong, back off dear, forward doubt. Stay ...  Anxiety\n",
+       "3           3  I've shifted my focus to something else but I'...  Anxiety\n",
+       "4           4  I'm restless and restless, it's been a month n...  Anxiety"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'I recently watched my dad die a gruesome death due to cancer this week, and I am sure something similar is in my future, I do not have any real friends and I do not have a home, I have been living in a hotel the past 6 months. I do not want to live anymore I just want to see my dad again and I do not want to suffer like he did I do not want to live anymore'"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data['statement'].values[19230]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>statement</th>\n",
+       "      <th>status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>oh my gosh</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>trouble sleeping, confused mind, restless hear...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>All wrong, back off dear, forward doubt. Stay ...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>I've shifted my focus to something else but I'...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>I'm restless and restless, it's been a month n...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                           statement   status\n",
+       "0                                         oh my gosh  Anxiety\n",
+       "1  trouble sleeping, confused mind, restless hear...  Anxiety\n",
+       "2  All wrong, back off dear, forward doubt. Stay ...  Anxiety\n",
+       "3  I've shifted my focus to something else but I'...  Anxiety\n",
+       "4  I'm restless and restless, it's been a month n...  Anxiety"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# selecting needed columns\n",
+    "df = data[['statement', 'status']]\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "status\n",
+       "Normal                  16351\n",
+       "Depression              15404\n",
+       "Suicidal                10653\n",
+       "Anxiety                  3888\n",
+       "Bipolar                  2877\n",
+       "Stress                   2669\n",
+       "Personality disorder     1201\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# value counts for the status\n",
+    "df['status'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(53043, 2)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "statement    362\n",
+       "status         0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# checking for nan values\n",
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "statement    0\n",
+       "status       0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# dropping nan values\n",
+    "df_1 = df.dropna()\n",
+    "df_1.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package stopwords to\n",
+      "[nltk_data]     C:\\Users\\timmy\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Package stopwords is already up-to-date!\n",
+      "[nltk_data] Downloading package wordnet to\n",
+      "[nltk_data]     C:\\Users\\timmy\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Package wordnet is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import re\n",
+    "import string\n",
+    "import nltk\n",
+    "from nltk.corpus import stopwords\n",
+    "from nltk.stem import PorterStemmer, WordNetLemmatizer\n",
+    "\n",
+    "# Download necessary NLTK data files\n",
+    "nltk.download('stopwords')\n",
+    "nltk.download('wordnet')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "example sentence demonstrate text preprocessing python includes number like punctuation\n"
+     ]
+    }
+   ],
+   "source": [
+    "# creating a cleaning pipeline for the statement column\n",
+    "def preprocess_text(text, use_stemming=False, use_lemmatization=True):\n",
+    "    # Lowercase the text\n",
+    "    text = text.lower()\n",
+    "    \n",
+    "    # Remove punctuation\n",
+    "    text = re.sub(f'[{re.escape(string.punctuation)}]', '', text)\n",
+    "    \n",
+    "    # Remove numbers\n",
+    "    text = re.sub(r'\\d+', '', text)\n",
+    "    \n",
+    "    # Tokenize the text\n",
+    "    words = text.split()\n",
+    "    \n",
+    "    # Remove stopwords\n",
+    "    stop_words = set(stopwords.words('english'))\n",
+    "    words = [word for word in words if word not in stop_words]\n",
+    "    \n",
+    "    # Initialize stemmer and lemmatizer\n",
+    "    stemmer = PorterStemmer()\n",
+    "    lemmatizer = WordNetLemmatizer()\n",
+    "    \n",
+    "    if use_stemming:\n",
+    "        # Apply stemming\n",
+    "        words = [stemmer.stem(word) for word in words]\n",
+    "    elif use_lemmatization:\n",
+    "        # Apply lemmatization\n",
+    "        words = [lemmatizer.lemmatize(word) for word in words]\n",
+    "    \n",
+    "    # Join words back into a single string\n",
+    "    cleaned_text = ' '.join(words)\n",
+    "    \n",
+    "    return cleaned_text\n",
+    "\n",
+    "# Example usage\n",
+    "text = \"This is an example sentence to demonstrate text preprocessing in Python. It includes numbers like 123 and punctuation!\"\n",
+    "cleaned_text = preprocess_text(text)\n",
+    "print(cleaned_text)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\timmy\\AppData\\Local\\Temp\\ipykernel_4184\\637849828.py:2: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  df_1['cleaned_statement'] = df_1['statement'].apply(preprocess_text)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# implementing on the statement column\n",
+    "df_1['cleaned_statement'] = df_1['statement'].apply(preprocess_text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>statement</th>\n",
+       "      <th>status</th>\n",
+       "      <th>cleaned_statement</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>oh my gosh</td>\n",
+       "      <td>Anxiety</td>\n",
+       "      <td>oh gosh</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>trouble sleeping, confused mind, restless hear...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "      <td>trouble sleeping confused mind restless heart ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>All wrong, back off dear, forward doubt. Stay ...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "      <td>wrong back dear forward doubt stay restless re...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>I've shifted my focus to something else but I'...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "      <td>ive shifted focus something else im still worried</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>I'm restless and restless, it's been a month n...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "      <td>im restless restless month boy mean</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                           statement   status  \\\n",
+       "0                                         oh my gosh  Anxiety   \n",
+       "1  trouble sleeping, confused mind, restless hear...  Anxiety   \n",
+       "2  All wrong, back off dear, forward doubt. Stay ...  Anxiety   \n",
+       "3  I've shifted my focus to something else but I'...  Anxiety   \n",
+       "4  I'm restless and restless, it's been a month n...  Anxiety   \n",
+       "\n",
+       "                                   cleaned_statement  \n",
+       "0                                            oh gosh  \n",
+       "1  trouble sleeping confused mind restless heart ...  \n",
+       "2  wrong back dear forward doubt stay restless re...  \n",
+       "3  ive shifted focus something else im still worried  \n",
+       "4                im restless restless month boy mean  "
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_1.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>cleaned_statement</th>\n",
+       "      <th>status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>oh gosh</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>trouble sleeping confused mind restless heart ...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>wrong back dear forward doubt stay restless re...</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ive shifted focus something else im still worried</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>im restless restless month boy mean</td>\n",
+       "      <td>Anxiety</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                   cleaned_statement   status\n",
+       "0                                            oh gosh  Anxiety\n",
+       "1  trouble sleeping confused mind restless heart ...  Anxiety\n",
+       "2  wrong back dear forward doubt stay restless re...  Anxiety\n",
+       "3  ive shifted focus something else im still worried  Anxiety\n",
+       "4                im restless restless month boy mean  Anxiety"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_2 = df_1[['cleaned_statement', 'status']]\n",
+    "df_2.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\timmy\\AppData\\Local\\Temp\\ipykernel_4184\\858368390.py:4: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  df_2['status'] = encoder.fit_transform(df_2['status'])\n"
+     ]
+    }
+   ],
+   "source": [
+    "# encoding the status column\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "encoder = LabelEncoder()\n",
+    "df_2['status'] = encoder.fit_transform(df_2['status'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['Anxiety', 'Bipolar', 'Depression', 'Normal',\n",
+       "       'Personality disorder', 'Stress', 'Suicidal'], dtype=object)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "encoder.classes_"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'Anxiety': np.int64(0),\n",
+       " 'Bipolar': np.int64(1),\n",
+       " 'Depression': np.int64(2),\n",
+       " 'Normal': np.int64(3),\n",
+       " 'Personality disorder': np.int64(4),\n",
+       " 'Stress': np.int64(5),\n",
+       " 'Suicidal': np.int64(6)}"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "label_mapping = dict(zip(encoder.classes_, encoder.transform(encoder.classes_)))\n",
+    "label_mapping"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>cleaned_statement</th>\n",
+       "      <th>status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>oh gosh</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>trouble sleeping confused mind restless heart ...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>wrong back dear forward doubt stay restless re...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ive shifted focus something else im still worried</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>im restless restless month boy mean</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                   cleaned_statement  status\n",
+       "0                                            oh gosh       0\n",
+       "1  trouble sleeping confused mind restless heart ...       0\n",
+       "2  wrong back dear forward doubt stay restless re...       0\n",
+       "3  ive shifted focus something else im still worried       0\n",
+       "4                im restless restless month boy mean       0"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_2.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# splitting the data \n",
+    "from sklearn.model_selection import train_test_split\n",
+    "X = df_2['cleaned_statement']\n",
+    "y = df_2['status']\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# creating vectors for the cleaned_statement column\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "\n",
+    "# Vectorize the text using TF-IDF\n",
+    "vectorizer = TfidfVectorizer()\n",
+    "X_train_tfidf = vectorizer.fit_transform(X_train)\n",
+    "X_test_tfidf = vectorizer.transform(X_test)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-2 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-2 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-2 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-2 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;RandomForestClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier()</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "RandomForestClassifier()"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# random forest classifier\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "\n",
+    "# Initialize the model\n",
+    "model = RandomForestClassifier()\n",
+    "\n",
+    "# Train the model\n",
+    "model.fit(X_train_tfidf, y_train)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.688715953307393\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       0.90      0.50      0.64       768\n",
+      "           1       0.97      0.37      0.53       556\n",
+      "           2       0.55      0.82      0.66      3081\n",
+      "           3       0.79      0.95      0.86      3269\n",
+      "           4       1.00      0.26      0.41       215\n",
+      "           5       0.97      0.21      0.35       517\n",
+      "           6       0.71      0.40      0.52      2131\n",
+      "\n",
+      "    accuracy                           0.69     10537\n",
+      "   macro avg       0.84      0.50      0.57     10537\n",
+      "weighted avg       0.74      0.69      0.67     10537\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import classification_report, accuracy_score\n",
+    "# making predictions\n",
+    "y_pred = model.predict(X_test_tfidf)\n",
+    "\n",
+    "# checking the accuracy\n",
+    "accuracy = accuracy_score(y_test, y_pred)\n",
+    "print('Accuracy:', accuracy)\n",
+    "\n",
+    "# classification report\n",
+    "report = classification_report(y_test, y_pred)\n",
+    "print(report)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# creating a pipeline\n",
+    "from sklearn.base import BaseEstimator, TransformerMixin\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "\n",
+    "# Custom transformer for text preprocessing\n",
+    "class TextPreprocessor(BaseEstimator, TransformerMixin):\n",
+    "    def __init__(self):\n",
+    "        self.stop_words = set(stopwords.words('english'))\n",
+    "        self.lemmatizer = WordNetLemmatizer()\n",
+    "    \n",
+    "    def preprocess_text(self, text):\n",
+    "        # Lowercase the text\n",
+    "        text = text.lower()\n",
+    "        \n",
+    "        # Remove punctuation\n",
+    "        text = re.sub(f'[{re.escape(string.punctuation)}]', '', text)\n",
+    "        \n",
+    "        # Remove numbers\n",
+    "        text = re.sub(r'\\d+', '', text)\n",
+    "        \n",
+    "        # Tokenize the text\n",
+    "        words = text.split()\n",
+    "        \n",
+    "        # Remove stopwords and apply lemmatization\n",
+    "        words = [self.lemmatizer.lemmatize(word) for word in words if word not in self.stop_words]\n",
+    "        \n",
+    "        # Join words back into a single string\n",
+    "        cleaned_text = ' '.join(words)\n",
+    "        \n",
+    "        return cleaned_text\n",
+    "    \n",
+    "    def fit(self, X, y=None):\n",
+    "        return self\n",
+    "    \n",
+    "    def transform(self, X, y=None):\n",
+    "        return [self.preprocess_text(text) for text in X]\n",
+    "    \n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pipeline = Pipeline([\n",
+    "    ('preprocessor', TextPreprocessor()),\n",
+    "    ('vectorizer', TfidfVectorizer()),\n",
+    "    ('classifier', RandomForestClassifier())\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = df_1['statement']\n",
+    "y = df_2['status']\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-3 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-3 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-3 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-3 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-3 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-3 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-3 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-3 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-3 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-3 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-3 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-3 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-3 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-3 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;preprocessor&#x27;, TextPreprocessor()),\n",
+       "                (&#x27;vectorizer&#x27;, TfidfVectorizer()),\n",
+       "                (&#x27;classifier&#x27;, RandomForestClassifier())])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;Pipeline<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.pipeline.Pipeline.html\">?<span>Documentation for Pipeline</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>Pipeline(steps=[(&#x27;preprocessor&#x27;, TextPreprocessor()),\n",
+       "                (&#x27;vectorizer&#x27;, TfidfVectorizer()),\n",
+       "                (&#x27;classifier&#x27;, RandomForestClassifier())])</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">TextPreprocessor</label><div class=\"sk-toggleable__content fitted\"><pre>TextPreprocessor()</pre></div> </div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;TfidfVectorizer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html\">?<span>Documentation for TfidfVectorizer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>TfidfVectorizer()</pre></div> </div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;RandomForestClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier()</pre></div> </div></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "Pipeline(steps=[('preprocessor', TextPreprocessor()),\n",
+       "                ('vectorizer', TfidfVectorizer()),\n",
+       "                ('classifier', RandomForestClassifier())])"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Train the model\n",
+    "pipeline.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Make predictions\n",
+    "y_pred = pipeline.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.6797950080668121\n",
+      "Classification Report:\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       0.89      0.49      0.63       768\n",
+      "           1       0.98      0.36      0.52       556\n",
+      "           2       0.54      0.82      0.65      3081\n",
+      "           3       0.79      0.95      0.86      3269\n",
+      "           4       1.00      0.26      0.41       215\n",
+      "           5       0.97      0.21      0.34       517\n",
+      "           6       0.69      0.38      0.49      2131\n",
+      "\n",
+      "    accuracy                           0.68     10537\n",
+      "   macro avg       0.84      0.49      0.56     10537\n",
+      "weighted avg       0.73      0.68      0.66     10537\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Evaluate the model\n",
+    "accuracy = accuracy_score(y_test, y_pred)\n",
+    "report = classification_report(y_test, y_pred)\n",
+    "\n",
+    "print(f'Accuracy: {accuracy}')\n",
+    "print('Classification Report:')\n",
+    "print(report)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'text': 'A lot of times if I am feeling sad, I immediately think of how others will respond to it. Or I am looking for comfort.. my father is a homophobic, racist, sexist piece of shit and my mother takes care of everything in the house. I hate my dad, when he started saying things like \"there is only two genders\" and \"you are looking for attention\" and making things seem like I was in the wrong no matter how much I was right, I realized how much of a shitbag he was and really felt desperate. I felt desperate for love and so I am confusing that with wanting attention.. am I in the wrong for doing this? Am I depressed or wanting attention?', 'prediction': 'Depression'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import requests\n",
+    "text = 'A lot of times if I am feeling sad, I immediately think of how others will respond to it. Or I am looking for comfort.. my father is a homophobic, racist, sexist piece of shit and my mother takes care of everything in the house. I hate my dad, when he started saying things like \"there is only two genders\" and \"you are looking for attention\" and making things seem like I was in the wrong no matter how much I was right, I realized how much of a shitbag he was and really felt desperate. I felt desperate for love and so I am confusing that with wanting attention.. am I in the wrong for doing this? Am I depressed or wanting attention?'\n",
+    "url = \"http://127.0.0.1:8000/predict_sentiment\"\n",
+    "data = {\"text\": text}\n",
+    "response = requests.post(url, json=data)\n",
+    "\n",
+    "print(response.json())\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.10.14"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

fastapi_app/main.py

@@ -0,0 +1,91 @@
+from fastapi import FastAPI, Request
+from fastapi.responses import HTMLResponse
+from fastapi.staticfiles import StaticFiles
+from pydantic import BaseModel
+import uvicorn
+import os, sys
+
+# Add the root directory to sys.path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+from model_pipeline.model_predict import load_model, predict as initial_predict
+from llama_pipeline.llama_predict import predict as llama_predict
+from db_connection import insert_db
+from logging_config.logger_config import get_logger
+
+# Initialize the FastAPI app
+app = FastAPI()
+
+# Initialize the logger
+logger = get_logger(__name__)
+
+# Load the latest model at startup
+model = load_model()
+
+# Mount the static files directory
+app.mount("/static", StaticFiles(directory="fastapi_app/static"), name="static")
+
+@app.get("/", response_class=HTMLResponse)
+def read_root():
+    with open("fastapi_app/static/index.html") as f:
+        html_content = f.read()
+    return HTMLResponse(content=html_content, status_code=200)
+
+@app.get("/health")
+def health_check():
+    logger.info("Health check endpoint accessed.")
+    return {"status": "ok"}
+
+class TextInput(BaseModel):
+    text: str
+
+class PredictionInput(BaseModel):
+    text: str
+    initial_prediction: str
+    llama_category: str
+    llama_explanation: str
+    user_rating: int
+
+@app.post("/predict_sentiment")
+def predict_sentiment(input_data: TextInput):
+    logger.info(f"Prediction request received with text: {input_data.text}")
+    
+    # Initial model prediction
+    initial_prediction = initial_predict(input_data.text, model = model)
+    
+    # LLaMA 3 prediction
+    llama_prediction = llama_predict(input_data.text)
+    
+    # Prepare response
+    response = {
+        "text": input_data.text,
+        "initial_prediction": initial_prediction,
+        "llama_category": llama_prediction['Category'],
+        "llama_explanation": llama_prediction['Explanation']
+    }
+    
+    logger.info(f"Prediction response: {response}")
+    return response
+
+@app.post("/submit_interaction")
+def submit_interaction(data: PredictionInput):
+    logger.info(f"Received interaction data: {data}")
+    logger.info(f"Received text: {data.text}")
+    logger.info(f"Received initial_prediction: {data.initial_prediction}")
+    logger.info(f"Received llama_category: {data.llama_category}")
+    logger.info(f"Received llama_explanation: {data.llama_explanation}")
+    logger.info(f"Received user_rating: {data.user_rating}")
+
+    interaction_data = {
+        "Input_text": data.text,
+        "Model_prediction": data.initial_prediction,
+        "Llama_3_Prediction": data.llama_category,
+        "Llama_3_Explanation": data.llama_explanation,
+        "User Rating": data.user_rating,
+    }
+    
+    response = insert_db(interaction_data)
+    logger.info(f"Database response: {response}")
+    return {"status": "success", "response": response}
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=8000)

fastapi_app/static/index.html

@@ -0,0 +1,41 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Sentiment Analysis for Mental Health</title>
+    <link rel="stylesheet" href="/static/style.css">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/animate.css/4.1.1/animate.min.css">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/all.min.css">
+</head>
+<body>
+    <div class="container animate__animated animate__fadeIn">
+        <h1>Sentiment Analysis for Mental Health</h1>
+        <p>This application uses a machine learning model to analyze the sentiment of text data related to mental health. It helps in understanding the sentiment expressed in user-generated content, such as social media posts or survey responses.</p>
+        <p>Enter a sentence below to predict its sentiment as Normal, Depression, Suicidal, Anxiety, Stress, Bi-Polar, or Personality Disorder.</p>
+        
+        <textarea id="textInput" rows="4" placeholder="Enter your text here..." class="animate__animated animate__fadeInLeft"></textarea>
+        <button onclick="predictSentiment()" class="animate__animated animate__fadeInRight">Predict Sentiment</button>
+        
+        <div id="results" class="animate__animated animate__fadeInUp">
+            <h2>Results:</h2>
+            <p><strong>Initial Model Prediction:</strong> <span id="initialPrediction"></span></p>
+            <p><strong>LLaMA 3 Category:</strong> <span id="llamaCategory"></span></p>
+            <p><strong>LLaMA 3 Explanation:</strong> <span id="llamaExplanation"></span></p>
+            
+            <h2>Rate the Accuracy of the Prediction:</h2>
+            <div class="rating animate__animated animate__fadeIn">
+                <i class="fas fa-star" onclick="rate(1)"></i>
+                <i class="fas fa-star" onclick="rate(2)"></i>
+                <i class="fas fa-star" onclick="rate(3)"></i>
+                <i class="fas fa-star" onclick="rate(4)"></i>
+                <i class="fas fa-star" onclick="rate(5)"></i>
+            </div>
+            <input type="hidden" id="userRating" value="0">
+        </div>
+        
+        <button onclick="submitInteraction()" class="animate__animated animate__fadeIn">Submit Rating</button>
+    </div>
+    <script src="/static/script.js"></script>
+</body>
+</html>

fastapi_app/static/script.js

@@ -0,0 +1,53 @@
+async function predictSentiment() {
+    const textInput = document.getElementById("textInput").value;
+    const response = await fetch("/predict_sentiment", {
+        method: "POST",
+        headers: {
+            "Content-Type": "application/json"
+        },
+        body: JSON.stringify({ text: textInput })
+    });
+    const result = await response.json();
+    document.getElementById("initialPrediction").innerText = result.initial_prediction;
+    document.getElementById("llamaCategory").innerText = result.llama_category;
+    document.getElementById("llamaExplanation").innerText = result.llama_explanation;
+}
+
+function rate(rating) {
+    document.getElementById("userRating").value = rating;
+    const stars = document.querySelectorAll(".rating .fa-star");
+    stars.forEach((star, index) => {
+        star.classList.toggle("selected", index < rating);
+    });
+}
+
+async function submitInteraction() {
+    const textInput = document.getElementById("textInput").value;
+    const initialPrediction = document.getElementById("initialPrediction").innerText;
+    const llamaCategory = document.getElementById("llamaCategory").innerText;
+    const llamaExplanation = document.getElementById("llamaExplanation").innerText;
+    const userRating = document.getElementById("userRating").value;
+
+    const data = {
+        text: textInput,
+        initial_prediction: initialPrediction,
+        llama_category: llamaCategory,
+        llama_explanation: llamaExplanation,
+        user_rating: parseInt(userRating),
+    };
+
+    // display the data in the console
+    console.log(data);
+
+    const response = await fetch("/submit_interaction", {
+        method: "POST",
+        headers: {
+            "Content-Type": "application/json"
+        },
+        body: JSON.stringify(data)
+    });
+
+    const result = await response.json();
+    alert("Thank you for your feedback!");
+}
+

fastapi_app/static/style.css

@@ -0,0 +1,78 @@
+body {
+    font-family: Arial, sans-serif;
+    background: linear-gradient(to right, #6a11cb, #2575fc);
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    height: 100vh;
+    margin: 0;
+    color: #fff;
+    text-align: center;
+}
+
+.container {
+    background-color: rgba(255, 255, 255, 0.1);
+    padding: 20px;
+    border-radius: 10px;
+    box-shadow: 0 0 20px rgba(0, 0, 0, 0.2);
+    width: 80%;
+    max-width: 600px;
+}
+
+h1 {
+    color: #fff;
+}
+
+textarea {
+    width: 100%;
+    padding: 10px;
+    margin: 10px 0;
+    border-radius: 8px;
+    border: none;
+    outline: none;
+    background-color: rgba(255, 255, 255, 0.2);
+    color: #fff;
+}
+
+button {
+    padding: 10px 20px;
+    background-color: #28a745;
+    color: white;
+    border: none;
+    border-radius: 8px;
+    cursor: pointer;
+    transition: background-color 0.3s ease;
+    margin-top: 20px;
+}
+
+button:hover {
+    background-color: #218838;
+}
+
+#results {
+    margin-top: 20px;
+    text-align: left;
+    color: #fff;
+}
+
+.rating {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    font-size: 2em;
+}
+
+.rating .fa-star {
+    cursor: pointer;
+    color: #ccc;
+    transition: color 0.3s;
+}
+
+.rating .fa-star:hover,
+.rating .fa-star:hover ~ .fa-star {
+    color: #ffd700;
+}
+
+.rating .fa-star.selected {
+    color: #ffd700;
+}

llama_pipeline/llama_predict.py

@@ -0,0 +1,96 @@
+from dotenv import load_dotenv
+import os, sys
+from langchain_groq import ChatGroq
+from langchain_core.output_parsers import StrOutputParser, JsonOutputParser
+from langchain_core.prompts.prompt import PromptTemplate
+
+# Add the root directory to sys.path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+from logging_config.logger_config import get_logger
+
+# Get the logger
+logger = get_logger(__name__)
+
+# environment variables
+load_dotenv()
+groq_api_key=os.getenv('GROQ_API_KEY')
+
+# initialize the ChatGroq object
+llm=ChatGroq(groq_api_key=groq_api_key,
+             model_name="Llama3-8b-8192")
+
+# Sentiment Classification
+def sentiment_analyzer(input_text: str) -> str:
+    template = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+    You are a highly specialized AI trained in clinical psychology and mental health assessment. Your task is to analyze textual input and categorize it into one of the following mental health conditions:
+    - Normal
+    - Depression
+    - Suicidal
+    - Anxiety
+    - Stress
+    - Bi-Polar
+    - Personality Disorder
+
+    Your analysis should be based on clinical symptoms and diagnostic criteria commonly used in mental health practice. Here are some detailed examples:
+
+    Example 1:
+    Text: "I feel an overwhelming sense of sadness and hopelessness. I have lost interest in activities I once enjoyed and find it hard to get out of bed."
+    Category: Depression
+
+    Example 2:
+    Text: "I constantly worry about various aspects of my life. My heart races, and I experience physical symptoms like sweating and trembling even when there is no apparent danger."
+    Category: Anxiety
+
+    Example 3:
+    Text: "I have thoughts about ending my life. I feel that there is no other way to escape my pain, and I often think about how I might end it."
+    Category: Suicidal
+
+    Example 4:
+    Text: "I feel extremely stressed and overwhelmed by my responsibilities. I find it difficult to relax, and I often experience headaches and tension."
+    Category: Stress
+
+    Example 5:
+    Text: "I go through periods of extreme happiness and high energy, followed by episodes of deep depression and low energy. These mood swings affect my daily functioning."
+    Category: Bi-Polar
+
+    Example 6:
+    Text: "I have trouble maintaining stable relationships and often experience intense emotional reactions. My self-image frequently changes, and I engage in impulsive behaviors."
+    Category: Personality Disorder
+
+    Example 7:
+    Text: "I feel generally content and am able to manage my daily activities without significant distress or impairment."
+    Category: Normal
+
+    
+    Return as out the Category and a brief explanation of your decision in a json format.
+    
+    Now, analyze the following text and determine the most appropriate category from the list above:
+    <|eot_id|><|start_header_id|>user<|end_header_id|>
+    Human: {input_text}
+    <|eot_id|><|start_header_id|>assistant<|end_header_id|>
+    AI Assistant:"""
+
+    sentiment_prompt = PromptTemplate(input_variables=["input_text"], template=template)
+    initiator_router = sentiment_prompt | llm | JsonOutputParser()
+    output = initiator_router.invoke({"input_text":input_text})
+    return output
+
+
+# making predictions
+def predict(text: str) -> str:
+    try:
+        logger.info("Making prediction...")
+        prediction = sentiment_analyzer(text)
+        logger.info(f"Prediction: {prediction}")
+        return prediction
+    except Exception as e:
+        logger.error(f"An error occurred while making the prediction: {e}")
+        return str('The prediction could not be made due to an error., Please try again later.')
+    
+if __name__ == "__main__":
+    # Example text input
+    example_text = "I feel incredibly anxious about everything and can't stop worrying"
+    
+    # Make a prediction
+    prediction = predict(example_text)
+    print(prediction)

logging_config/logger_config.py

@@ -0,0 +1,39 @@
+import logging
+import os
+
+# Ensure the log directory exists
+log_directory = 'logs'
+os.makedirs(log_directory, exist_ok=True)
+
+# Define the logging configuration
+logging.basicConfig(
+    filename=os.path.join(log_directory, 'app.log'),
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    datefmt='%Y-%m-%d %H:%M:%S'
+)
+
+# Get a custom logger
+def get_logger(name):
+    logger = logging.getLogger(name)
+    logger.setLevel(logging.DEBUG)
+    
+    if not logger.hasHandlers():
+        # Create a file handler
+        file_handler = logging.FileHandler('logs/app.log')
+        file_handler.setLevel(logging.DEBUG)
+        
+        # Create a console handler
+        console_handler = logging.StreamHandler()
+        console_handler.setLevel(logging.DEBUG)
+        
+        # Create a logging format
+        formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+        file_handler.setFormatter(formatter)
+        console_handler.setFormatter(formatter)
+        
+        # Add the handlers to the logger
+        logger.addHandler(file_handler)
+        logger.addHandler(console_handler)
+    
+    return logger

model_pipeline/model_predict.py

@@ -0,0 +1,100 @@
+import os
+import sys
+import re
+import string
+import joblib
+import pandas as pd
+import numpy as np
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+import nltk
+from glob import glob
+
+# Add the root directory to sys.path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+from logging_config.logger_config import get_logger
+
+# Download necessary NLTK data files
+nltk.download('stopwords')
+nltk.download('wordnet')
+
+# Get the logger
+logger = get_logger(__name__)
+
+# Custom Preprocessor Class
+class TextPreprocessor:
+    def __init__(self):
+        self.stop_words = set(stopwords.words('english'))
+        self.lemmatizer = WordNetLemmatizer()
+        logger.info("TextPreprocessor initialized.")
+    
+    def preprocess_text(self, text):
+        logger.info(f"Original text: {text}")
+        # Lowercase the text
+        text = text.lower()
+        logger.info(f"Lowercased text: {text}")
+        
+        # Remove punctuation
+        text = re.sub(f'[{re.escape(string.punctuation)}]', '', text)
+        logger.info(f"Text after punctuation removal: {text}")
+        
+        # Remove numbers
+        text = re.sub(r'\d+', '', text)
+        logger.info(f"Text after number removal: {text}")
+        
+        # Tokenize the text
+        words = text.split()
+        logger.info(f"Tokenized text: {words}")
+        
+        # Remove stopwords and apply lemmatization
+        words = [self.lemmatizer.lemmatize(word) for word in words if word not in self.stop_words]
+        logger.info(f"Text after stopword removal and lemmatization: {words}")
+        
+        # Join words back into a single string
+        cleaned_text = ' '.join(words)
+        logger.info(f"Cleaned text: {cleaned_text}")
+        
+        return cleaned_text
+
+def get_latest_model_path(models_dir='./models'):
+    model_files = glob(os.path.join(models_dir, 'model_v*.joblib'))
+    if not model_files:
+        logger.error("No model files found in the models directory.")
+        raise FileNotFoundError("No model files found in the models directory.")
+    
+    latest_model_file = max(model_files, key=os.path.getctime)
+    logger.info(f"Latest model file found: {latest_model_file}")
+    return latest_model_file
+
+def load_model():
+    model_path = get_latest_model_path()
+    logger.info(f"Loading model from {model_path}")
+    return joblib.load(model_path)
+
+def predict(text, model):
+    # Initialize the text preprocessor
+    preprocessor = TextPreprocessor()
+    
+    # Preprocess the input text
+    logger.info("Preprocessing input text...")
+    cleaned_text = preprocessor.preprocess_text(text)
+    
+    # Make a prediction
+    logger.info("Making prediction...")
+    prediction = model.predict([cleaned_text])
+    
+    logger.info(f"Prediction: {prediction}")
+    return prediction[0]
+
+if __name__ == "__main__":
+    # Example text input
+    example_text = "I love programming in Python."
+    
+    # Load the latest model
+    model = load_model()
+    
+    # Make a prediction
+    prediction = predict(example_text, model)
+    
+    # Print the prediction
+    print(f"Prediction: {prediction}")

model_pipeline/model_trainer.py

@@ -0,0 +1,93 @@
+import os
+import sys
+import pandas as pd
+import joblib
+from datetime import datetime
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+from sklearn.metrics import classification_report, accuracy_score
+
+# Add the root directory to sys.path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+from logging_config.logger_config import get_logger
+
+# Get the logger
+logger = get_logger(__name__)
+
+def load_data(file_path):
+    logger.info(f"Loading data from {file_path}")
+    return pd.read_csv(file_path)
+
+def train_model(data):
+    logger.info("Starting model training...")
+    # check for missing values
+    if data.isnull().sum().sum() > 0:
+        logger.error("Missing values found in the dataset.")
+        # Drop missing values
+        data.dropna(inplace=True)
+        logger.info("Missing values dropped.")
+        # checking the shape of the data
+        logger.info(f"Data shape: {data.shape}")
+    
+    # Split data into features and labels
+    X = data['cleaned_statement']
+    y = data['status']  # Assuming 'sentiment' is the target column
+    
+    # Split data into training and test sets
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    
+    # Create a pipeline with TF-IDF Vectorizer and Logistic Regression
+    pipeline = Pipeline([
+        ('tfidf', TfidfVectorizer()),
+        ('clf', LogisticRegression())
+    ])
+    
+    # Train the pipeline
+    pipeline.fit(X_train, y_train)
+    logger.info("Model training completed.")
+    
+    # Make predictions
+    y_pred = pipeline.predict(X_test)
+    
+    # Evaluate the model
+    accuracy = accuracy_score(y_test, y_pred)
+    report = classification_report(y_test, y_pred)
+    
+    logger.info(f"Accuracy: {accuracy}")
+    logger.info(f"Classification Report:\n{report}")
+    
+    return pipeline, accuracy, report
+
+def save_model(pipeline, version):
+    # Create the models directory if it doesn't exist
+    os.makedirs('./models', exist_ok=True)
+    
+    # Save the pipeline with versioning
+    model_filename = f'model_v{version}.joblib'
+    model_path = os.path.join('models', model_filename)
+    joblib.dump(pipeline, model_path)
+    logger.info(f"Model saved as {model_path}")
+
+if __name__ == "__main__":
+    # Path to the cleaned dataset
+    cleaned_data_path = os.path.join('./data', 'cleaned_data.csv')
+    
+    # Load the data
+    data = load_data(cleaned_data_path)
+    
+    # Train the model
+    pipeline, accuracy, report = train_model(data)
+    
+    # Define the model version based on the current datetime
+    version = datetime.now().strftime("%Y%m%d%H%M%S")
+    
+    # Save the model
+    save_model(pipeline, version)
+    
+    # Print the results
+    print(f"Model version: {version}")
+    print(f"Accuracy: {accuracy}")
+    print(f"Classification Report:\n{report}")

models/model_v20240717014315.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac9de0ec670007da30e6e8ef8433064f1f347e1e94ef861d4fdaa871cd310d5
+size 5326113

new_experiement.ipynb

@@ -0,0 +1,282 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "import os\n",
+    "from langchain_groq import ChatGroq\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts.prompt import PromptTemplate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groq_api_key=os.getenv('GROQ_API_KEY')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm=ChatGroq(groq_api_key=groq_api_key,\n",
+    "             model_name=\"Llama3-8b-8192\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sentiment_analyzer(input_text: str) -> list:\n",
+    "    template = \"\"\"<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n",
+    "    You are a highly specialized AI trained in clinical psychology and mental health assessment. Your task is to analyze textual input and categorize it into one of the following mental health conditions:\n",
+    "    - Normal\n",
+    "    - Depression\n",
+    "    - Suicidal\n",
+    "    - Anxiety\n",
+    "    - Stress\n",
+    "    - Bi-Polar\n",
+    "    - Personality Disorder\n",
+    "\n",
+    "    Your analysis should be based on clinical symptoms and diagnostic criteria commonly used in mental health practice. Here are some detailed examples:\n",
+    "\n",
+    "    Example 1:\n",
+    "    Text: \"I feel an overwhelming sense of sadness and hopelessness. I have lost interest in activities I once enjoyed and find it hard to get out of bed.\"\n",
+    "    Category: Depression\n",
+    "\n",
+    "    Example 2:\n",
+    "    Text: \"I constantly worry about various aspects of my life. My heart races, and I experience physical symptoms like sweating and trembling even when there is no apparent danger.\"\n",
+    "    Category: Anxiety\n",
+    "\n",
+    "    Example 3:\n",
+    "    Text: \"I have thoughts about ending my life. I feel that there is no other way to escape my pain, and I often think about how I might end it.\"\n",
+    "    Category: Suicidal\n",
+    "\n",
+    "    Example 4:\n",
+    "    Text: \"I feel extremely stressed and overwhelmed by my responsibilities. I find it difficult to relax, and I often experience headaches and tension.\"\n",
+    "    Category: Stress\n",
+    "\n",
+    "    Example 5:\n",
+    "    Text: \"I go through periods of extreme happiness and high energy, followed by episodes of deep depression and low energy. These mood swings affect my daily functioning.\"\n",
+    "    Category: Bi-Polar\n",
+    "\n",
+    "    Example 6:\n",
+    "    Text: \"I have trouble maintaining stable relationships and often experience intense emotional reactions. My self-image frequently changes, and I engage in impulsive behaviors.\"\n",
+    "    Category: Personality Disorder\n",
+    "\n",
+    "    Example 7:\n",
+    "    Text: \"I feel generally content and am able to manage my daily activities without significant distress or impairment.\"\n",
+    "    Category: Normal\n",
+    "\n",
+    "    Now, analyze the following text and determine the most appropriate category from the list above, and return the Category and a brief explanation of your decision:\n",
+    "    <|eot_id|><|start_header_id|>user<|end_header_id|>\n",
+    "    Human: {input_text}\n",
+    "    <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n",
+    "    AI Assistant:\"\"\"\n",
+    "\n",
+    "    sentiment_prompt = PromptTemplate(input_variables=[\"input_text\"], template=template)\n",
+    "    initiator_router = sentiment_prompt | llm | StrOutputParser()\n",
+    "    output = initiator_router.invoke({\"input_text\":input_text})\n",
+    "    return output\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Category: Anxiety\n",
+      "\n",
+      "Explanation: The text indicates that the person is experiencing excessive and persistent worry, which is a hallmark symptom of anxiety disorder. The phrase \"can't stop worrying\" suggests that the individual is unable to control their worries, which is a common feature of anxiety disorders. Additionally, the phrase \"anxious about everything\" implies that the person is experiencing a pervasive and excessive anxiety that is interfering with their daily life. While anxiety can be a normal response to stressful situations, the severity and pervasiveness described in the text suggest that it may be a clinical concern.\n"
+     ]
+    }
+   ],
+   "source": [
+    "sentiment = sentiment_analyzer(\"I feel incredibly anxious about everything and can't stop worrying\")\n",
+    "print(sentiment)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Category: Anxiety\n",
+      "\n",
+      "My assessment is based on the following symptoms mentioned in the text:\n",
+      "\n",
+      "* \"Constantly worried\" - This suggests that the individual is experiencing excessive and persistent worry, which is a hallmark symptom of anxiety.\n",
+      "* \"Can't seem to find any peace\" - This implies a sense of perpetual unease and inability to relax, which is also characteristic of anxiety.\n",
+      "* \"Disturbed sleep\" - Sleep disturbances are a common symptom of anxiety, often caused by racing thoughts and difficulty relaxing.\n",
+      "* \"Overwhelmed by even the smallest tasks\" - This suggests that the individual is experiencing feelings of excessive anxiety and difficulty coping with everyday activities, which is another common symptom of anxiety.\n",
+      "\n",
+      "Overall, the text suggests that the individual is experiencing symptoms that are consistent with an anxiety disorder, such as generalized anxiety disorder or anxiety disorder not otherwise specified.\n"
+     ]
+    }
+   ],
+   "source": [
+    "sentiment = sentiment_analyzer(\"I feel like everything is falling apart around me. I'm constantly worried and can't seem to find any peace. My sleep is disturbed, and I often feel overwhelmed by even the smallest tasks.\")\n",
+    "print(sentiment)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Connecting to database"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from supabase import create_client, Client\n",
+    "\n",
+    "url: str = os.environ.get(\"SUPABASE_PROJECT_URL\")\n",
+    "key: str = os.environ.get(\"SUPABASE_API_KEY\")\n",
+    "supabase: Client = create_client(url, key)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# signinh in with email and password\n",
+    "data = supabase.table(\"Interaction History\").select(\"*\").execute()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "APIResponse[~_ReturnT](data=[], count=None)"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_row = {\n",
+    "    \"Input_text\" : \"I feel incredibly anxious about everything and can't stop worrying\",\n",
+    "    \"Model_prediction\" : \"Anxiety\",\n",
+    "    \"Llama_3_Prediction\" : \"Anxiety\",\n",
+    "    \"Llama_3_Explanation\" : \"Anxiety\",\n",
+    "    \"User Rating\" : 5,\n",
+    "}\n",
+    "\n",
+    "data = supabase.table(\"Interaction History\").insert(new_row).execute()\n",
+    "\n",
+    "# Assert we pulled real data.\n",
+    "assert len(data.data) > 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "APIResponse[~_ReturnT](data=[{'id': 2, 'Input_text': \"I feel incredibly anxious about everything and can't stop worrying\", 'Model_prediction': 'Anxiety', 'Llama_3_Prediction': 'Anxiety', 'User Rating': 5, 'Llama_3_Explanation': 'Anxiety'}], count=None)"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.10.14"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,14 @@
+fastapi==0.111.1
+scikit-learn==1.4.2
+pandas==2.2.2
+uvicorn==0.30.1
+notebook==7.2.1
+nltk==3.8.1
+langchain_community==0.2.7
+langchain==0.2.9
+langchain_groq==0.1.6
+langchain_core==0.2.21
+llama-parse==0.4.9
+python-dotenv==1.0.1
+groq==0.9.0
+supabase==2.5.3

todo.txt

@@ -0,0 +1,4 @@
+1. connect a database
+2. save the data to a database
+3. add llm api_prediction to the project using Groq and llama 3 8b 
+4. Update the output into two outputs, one for the model prediction, the other for llm prediction. 

utils.py

@@ -0,0 +1,57 @@
+import pandas as pd
+import numpy as np
+import re
+import string
+import nltk
+from nltk.corpus import stopwords
+from nltk.stem import PorterStemmer, WordNetLemmatizer
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.pipeline import Pipeline
+
+# Download necessary NLTK data files
+nltk.download('stopwords')
+nltk.download('wordnet')
+
+# Custom transformer for text preprocessing
+class TextPreprocessor(BaseEstimator, TransformerMixin):
+    def __init__(self):
+        self.stop_words = set(stopwords.words('english'))
+        self.lemmatizer = WordNetLemmatizer()
+    
+    def preprocess_text(self, text):
+        # Lowercase the text
+        text = text.lower()
+        
+        # Remove punctuation
+        text = re.sub(f'[{re.escape(string.punctuation)}]', '', text)
+        
+        # Remove numbers
+        text = re.sub(r'\d+', '', text)
+        
+        # Tokenize the text
+        words = text.split()
+        
+        # Remove stopwords and apply lemmatization
+        words = [self.lemmatizer.lemmatize(word) for word in words if word not in self.stop_words]
+        
+        # Join words back into a single string
+        cleaned_text = ' '.join(words)
+        
+        return cleaned_text
+    
+    def fit(self, X, y=None):
+        return self
+    
+    def transform(self, X, y=None):
+        return [self.preprocess_text(text) for text in X]
+    
+
+# Model pipeline
+pipeline = Pipeline([
+    ('preprocessor', TextPreprocessor()),
+    ('vectorizer', TfidfVectorizer()),
+    ('classifier', RandomForestClassifier())
+])
+