feat: Introduce Demo Scripts Demonstrating Usage of load_file and preprocess

src/modules/Load_file&preprocessing_DEMO.ipynb

@@ -0,0 +1,106 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "787e38a9-14a5-41f1-9186-e68008bc80c3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import scanpy as sc\n",
+    "\n",
+    "def load_file_demo(file_path):\n",
+    "    adata = sc.read_h5ad(file_path)  # load h5ad file\n",
+    "    adata.write(\"adata_demo.h5ad\")  # save a new demo file\n",
+    "    print(\"Data saved as adata_demo.h5ad\")\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "32cc9e28-f9df-4a12-bcab-4a152fc18855",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data saved as adata_demo.h5ad\n"
+     ]
+    }
+   ],
+   "source": [
+    "#run\n",
+    "file_path = \"/Users/azratuncay/Desktop/IEEE/untitled folder/Hw3covid_Data_AllCells.h5ad\"\n",
+    "load_file_demo(file_path)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "aa346737-f100-4684-88b8-d971b013624b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import scanpy as sc\n",
+    "\n",
+    "def preprocess_demo(adata_path):\n",
+    "    adata = sc.read_h5ad(adata_path)  # download the saved demo file \n",
+    "    print(\"Data loaded successfully for preprocessing demo.\")\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "8b0be686-d27d-46fa-8142-6ac196f49fcd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data loaded successfully for preprocessing demo.\n"
+     ]
+    }
+   ],
+   "source": [
+    "#run\n",
+    "adata_path = \"adata_demo.h5ad\"\n",
+    "preprocess_demo(adata_path)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "06a5bd7f-f9d5-42c3-b46a-aeda392a4664",
+   "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": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

src/modules/load_file.py

@@ -0,0 +1,5 @@
+import scanpy as sc
+
+def load_file(file_path):
+    adata = sc.read_10x_mtx(file_path, var_names='gene_symbols', cache=True)
+    return adata

src/modules/preprocessing.py

@@ -0,0 +1,11 @@
+import scanpy as sc
+
+def preprocess(adata, target_sum = 1e4, max_value = 10):
+    data_normalization(adata, target_sum, max_value)
+    #other preprocessing methods here
+
+def data_normalization(adata, target_sum, max_value):
+    sc.pp.normalize_total(adata, target_sum)
+    sc.pp.log1p(adata)
+    sc.pp.regress_out(adata, ['total_counts', 'pct_counts_mt'])
+    sc.pp.scale(adata, max_value)