Add RF, gitignore and update Readme

.gitignore

@@ -0,0 +1,2 @@
+*.pkl
+*.csv

README.md

@@ -1 +1,161 @@
-# 
+## Overview
+
+This project is my implementation of [this research paper](https://ernest-bonat.medium.com/rna-seq-gene-expression-classification-using-machine-learning-algorithms-de862e60bfd0#4592) from scratch. The objective of this project is to identify gene expression patterns associated with different conditions or diseases, leveraging advanced data processing and model training techniques. RNA sequencing (RNA-Seq) is a teachnique used to quantify and analyze gene expression levels across different conditions or samples. The classification of RNA-Seq data can be used to identify which genes are differently expressed between healthy and diseased samples, or between different diseased states, thus aiding in the diagnosis, treatment, and understanding of various diseases and conditions.
+
+## Table of Contents
+
+- [Overview](#overview)
+- [Dataset](#dataset)
+- [Project Structure](#project-structure)
+- [Running the project](#running-the-project)
+- [Models Used](#models-used)
+- [Results](#results)
+- [Contributing](#contributing)
+- [Acknowledgements](#acknowledgements)
+
+## Dataset
+
+The dataset used in this project:
+
+- **Source**: https://archive.ics.uci.edu/dataset/401/gene+expression+cancer+rna+seq
+
+- **Description**: This dataset is part of the RNA-Seq (HiSeq) PANCAN data set. It is a random extraction of gene expressions of patients having different types of tumor: BRCA (Breast invasive carcinoma), KIRC (Kidney renal clear cell carcinoma), COAD (Colon adenocarcinoma), LUAD (Lung adenocarcinoma) and PRAD (Prostate adenocarcinoma). 
+
+  The downloaded dataset file TCGA-PANCAN-HiSeq-801x20531.tar.gz contains two CSV files. 
+
+  - **data.csv**: Contains the feature set (X) representing gene expression data. 
+  - **labels.csv**: Contains the target labels (y) corresponding to the samples in the feature set.
+
+## Project Structure
+
+The outline of the project repository:
+
+```
+RNASeq-GeneExpression-ML/
+├── data/
+│   ├── raw/
+│   ├── processed/
+│   │   ├── split_data
+│   │   ├── transformed
+├── notebooks/
+│   ├── data_preprocessing.ipynb
+│   ├── model_training.ipynb
+│   ├── model_evaluation.ipynb
+├── src/
+│   ├── load_data.py
+│   ├── split.py
+│   ├── smote.py
+│   ├── pca.py
+│   ├── models/
+│   │   ├── logistic_regression.py
+│   │   ├── decision_tree.py
+│   │   ├── random_forest.py
+│   │   ├── svm.py
+│   │   ├── naive_bayes.py
+│   │   ├── knn.py
+│   │   ├── mlp.py
+│   │   ├── gradient_boosting.py
+│   │   ├── ada_boost.py
+│   │   ├── xgboost.py
+│   │   ├── lightgbm.py
+│   │   ├── catboost.py
+│   ├── evaluate_models.py
+├── results/
+│   ├── logistic_regression.txt
+│   ├── decision_tree.txt
+│   ├── random_forest.txt/
+│   ├── svm.txt/
+│   ├── naive_bayes.txt/
+│   ├── knn.txt/
+│   ├── mlp.txt/
+│   ├── gradient_boosting.txt/
+│   ├── ada_boost.txt/
+│   ├── xgboost.txt/
+│   ├── lightgbm.txt/
+│   ├── catboost.txt/
+├── README.md
+├── requirements.txt
+```
+
+## Running the Project
+
+1. **Clone the repository:**
+
+```
+git clone [email protected]:shalinis602/RNASeq-GeneExpression-ML.git
+cd RNASeq-GeneExpression-ML
+```
+
+2. **Install dependencies:** 
+```
+pip install -r requirements.txt
+```
+
+3. **Fast load the dataset and verify its contents:**
+
+```
+python src/load_data.py
+```
+
+4. **Split the data into training, testing and validation sets:**
+
+```
+python src/split.py
+```
+
+5. **Preprocess the dataset:**
+
+```
+python src/smote.py
+python src/pca.py
+```
+
+6. **Train the models:**
+
+```
+python src/models/random_forest.py
+```
+
+7. **Evaluate the models:**
+
+```
+python src/model_evaluation.py
+```
+
+Alternatively, you can run the Jupyter notebooks located in the `notebooks/` directory to interactively execute the code.
+
+## Models Used
+
+- **Logistic Regression**
+- **Decision Tree**
+- **Random Forest**
+- **Support Vector Machine (SVM)**
+- **Naive Bayes**
+- **k-Nearest Neighbors (KNN)**
+- **Multilayer Perceptron (MLP)**
+- **Gradient Boosting**
+- **AdaBoost**
+- **XGBoost**
+- **LightGBM**
+- **CatBoost**
+
+## Results
+
+- **Accuracy**
+- **Precision**
+- **Recall**
+- **F1-Score**
+- **Confusion Matrix**
+
+## Contributing
+
+If you find any issues or have suggestions for improvements or expanding the project, feel free to open an issue or submit a pull request.
+
+1. Fork the repository.
+2. Create a new branch (`git checkout -b feature-branch`).
+3. Commit your changes (`git commit -am 'Add new feature'`).
+4. Push to the branch (`git push origin feature-branch`).
+5. Create a new Pull Request.
+
+## **Acknowledgements**
+

notebooks/.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/.ipynb_checkpoints/data_preprocessing-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/data_preprocessing.ipynb

@@ -0,0 +1,137 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "07816290",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data information:\n",
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 801 entries, 0 to 800\n",
+      "Columns: 20532 entries, Unnamed: 0 to gene_20530\n",
+      "dtypes: float64(20531), object(1)\n",
+      "memory usage: 125.5+ MB\n",
+      "None\n",
+      "\n",
+      "Label information:\n",
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 801 entries, 0 to 800\n",
+      "Data columns (total 1 columns):\n",
+      " #   Column  Non-Null Count  Dtype \n",
+      "---  ------  --------------  ----- \n",
+      " 0   Class   801 non-null    object\n",
+      "dtypes: object(1)\n",
+      "memory usage: 6.4+ KB\n",
+      "None\n",
+      "\n",
+      "Deserialized X:\n",
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 801 entries, 0 to 800\n",
+      "Columns: 20531 entries, gene_0 to gene_20530\n",
+      "dtypes: float64(20531)\n",
+      "memory usage: 125.5 MB\n",
+      "None\n",
+      "\n",
+      "Deserialized y:\n",
+      "0    PRAD\n",
+      "1    LUAD\n",
+      "2    PRAD\n",
+      "3    PRAD\n",
+      "4    BRCA\n",
+      "Name: Class, dtype: object\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import pandas as pd\n",
+    "import pickle\n",
+    "\n",
+    "# Define serialization functions\n",
+    "def pickle_serialize_object(filename, obj):\n",
+    "    with open(filename, 'wb') as f:\n",
+    "        pickle.dump(obj, f)\n",
+    "\n",
+    "def pickle_deserialize_object(filename):\n",
+    "    with open(filename, 'rb') as f:\n",
+    "        return pickle.load(f)\n",
+    "\n",
+    "# Step 1: Load the CSV files\n",
+    "data_path = '../data/raw/data.csv'\n",
+    "labels_path = '../data/raw/labels.csv'\n",
+    "\n",
+    "data = pd.read_csv(data_path)\n",
+    "label = pd.read_csv(labels_path)\n",
+    "\n",
+    "# Step 2: Prepare data for serialization\n",
+    "X = data.drop(columns=['Unnamed: 0'])  # Drop the 'Unnamed: 0' column if it's not needed\n",
+    "\n",
+    "# Drop the 'Unnamed: 0' column from label if present\n",
+    "if 'Unnamed: 0' in label.columns:\n",
+    "    label = label.drop(columns=['Unnamed: 0'])\n",
+    "\n",
+    "y = label['Class']  # Use the 'Class' column as the target\n",
+    "\n",
+    "# Step 3: Inspect the data\n",
+    "print(\"Data information:\")\n",
+    "print(data.info())\n",
+    "print(\"\\nLabel information:\")\n",
+    "print(label.info())\n",
+    "\n",
+    "# Serialize the features and target\n",
+    "processed_data_dir = '../data/processed/'\n",
+    "\n",
+    "if not os.path.exists(processed_data_dir):\n",
+    "    os.makedirs(processed_data_dir)\n",
+    "\n",
+    "pickle_serialize_object(os.path.join(processed_data_dir, 'rna_seq_X.pkl'), X)\n",
+    "pickle_serialize_object(os.path.join(processed_data_dir, 'rna_seq_y.pkl'), y)\n",
+    "\n",
+    "# Step 4: Deserialize the data\n",
+    "X = pickle_deserialize_object(os.path.join(processed_data_dir, 'rna_seq_X.pkl'))\n",
+    "y = pickle_deserialize_object(os.path.join(processed_data_dir, 'rna_seq_y.pkl'))\n",
+    "\n",
+    "# Verify the deserialized data\n",
+    "print(\"\\nDeserialized X:\")\n",
+    "print(X.info())\n",
+    "\n",
+    "print(\"\\nDeserialized y:\")\n",
+    "print(y.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "41c68f93",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}