{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 1. Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "import os\n",
    "import pandas as pd\n",
    "from IPython.display import display\n",
    "\n",
    "\n",
    "sys.path.append(os.path.abspath(os.path.join(os.getcwd(), \"..\", \"..\")))\n",
    "\n",
    "from Seq_Sim.utils.seq_sim_utils import (\n",
    "    load_config,\n",
    "    generate_and_save_features\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2. Specify Number of Samples and Fold Change"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# specify the number of samples to generate\n",
    "num_samples = 10\n",
    "\n",
    "# specify the fold change between the two classes\n",
    "fold_change = 0.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 3. Specify Configuration File Parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# config_file = \"../config.yml\"\n",
    "# config = load_config(config_file)\n",
    "\n",
    "# or\n",
    "\n",
    "config = {\n",
    "    \"log_file\": \"error.log\",\n",
    "    \"data_file_path\": \"./data/\",\n",
    "    \"file_path_to_simulation\": \"Seq_Sim/seq_sim.py\",\n",
    "    \"functions_script_path\": \"Seq_Sim/utils/seq_sim_utils.py\",\n",
    "    \"file_prefix\": \"sim_data\",\n",
    "    \"num_samples\": [10, 20, 30],\n",
    "    \"fold_changes\": [0.1, 0.75, 1.5, 3],\n",
    "    \"n_threads\": 4,\n",
    "    \"dummy_dataset_params\": {\n",
    "        \"n_cells\": 100,\n",
    "        \"sd_celltypes\": 0.1,\n",
    "        \"n_major_cell_types\": 7,\n",
    "        \"n_minor_cell_types\": 3,\n",
    "        \"relative_abundance\": 0.4,\n",
    "        \"n_major_diff_celltypes\": 1,\n",
    "        \"n_minor_diff_celltypes\": 1,\n",
    "        \"n_batchs\": 4,\n",
    "        \"prop_sex\": 0.5,\n",
    "        \"prop_disease\": 0.5,\n",
    "        \"seed\": 1234,\n",
    "        \"n_features\": 1000,\n",
    "    },\n",
    "    \"variance_attributes\": {\"cluster_ratio\": 0.7},\n",
    "    \"ratio_variance\": 0.1,\n",
    "    \"column_information\": {\n",
    "        \"cluster_col\": \"cell_type\",\n",
    "        \"disease_col\": \"disease\",\n",
    "        \"individual_col\": \"subject_id\",\n",
    "    },\n",
    "    \"files_to_save\": {\"feature_matrix\": True, \"latent_factors\": True},\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 4. Generate and Save Sequencing Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "try:\n",
    "    # run the simulation\n",
    "    generate_and_save_features(num_samples, fold_change, config)\n",
    "\n",
    "except Exception as e:\n",
    "    # log the error\n",
    "    print(e)\n",
    "    sys.exit(1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 5. Ensure files were saved properly"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Preview of sim_data_pseudo_feature_num_samples_10_fc_0.1.csv:\n"
     ]
    },
    {
     "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>Feature1</th>\n",
       "      <th>Feature2</th>\n",
       "      <th>Feature3</th>\n",
       "      <th>Feature4</th>\n",
       "      <th>Feature5</th>\n",
       "      <th>Feature6</th>\n",
       "      <th>Feature7</th>\n",
       "      <th>Feature8</th>\n",
       "      <th>Feature9</th>\n",
       "      <th>Feature10</th>\n",
       "      <th>...</th>\n",
       "      <th>Feature991</th>\n",
       "      <th>Feature992</th>\n",
       "      <th>Feature993</th>\n",
       "      <th>Feature994</th>\n",
       "      <th>Feature995</th>\n",
       "      <th>Feature996</th>\n",
       "      <th>Feature997</th>\n",
       "      <th>Feature998</th>\n",
       "      <th>Feature999</th>\n",
       "      <th>Feature1000</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-11942.239893</td>\n",
       "      <td>12.943553</td>\n",
       "      <td>-318.847654</td>\n",
       "      <td>2695.776328</td>\n",
       "      <td>-2139.814545</td>\n",
       "      <td>-717.146778</td>\n",
       "      <td>1539.996661</td>\n",
       "      <td>-4706.707206</td>\n",
       "      <td>23.007149</td>\n",
       "      <td>1162.154929</td>\n",
       "      <td>...</td>\n",
       "      <td>-2224.586927</td>\n",
       "      <td>1495.867963</td>\n",
       "      <td>-2690.879528</td>\n",
       "      <td>37.646723</td>\n",
       "      <td>1435.085427</td>\n",
       "      <td>13271.111625</td>\n",
       "      <td>659.564345</td>\n",
       "      <td>-5542.467489</td>\n",
       "      <td>-3158.842850</td>\n",
       "      <td>4542.571977</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2439.293515</td>\n",
       "      <td>-10658.214127</td>\n",
       "      <td>4404.059579</td>\n",
       "      <td>1752.411046</td>\n",
       "      <td>-1133.866572</td>\n",
       "      <td>-3194.139650</td>\n",
       "      <td>4731.903754</td>\n",
       "      <td>-5268.524990</td>\n",
       "      <td>7.737832</td>\n",
       "      <td>-5783.376093</td>\n",
       "      <td>...</td>\n",
       "      <td>8555.393323</td>\n",
       "      <td>-5691.212264</td>\n",
       "      <td>4472.742030</td>\n",
       "      <td>30.222789</td>\n",
       "      <td>5634.529341</td>\n",
       "      <td>-3354.225469</td>\n",
       "      <td>-4704.306326</td>\n",
       "      <td>-1173.377176</td>\n",
       "      <td>11995.770742</td>\n",
       "      <td>-1147.780931</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4031.830996</td>\n",
       "      <td>-1820.018802</td>\n",
       "      <td>-10320.317301</td>\n",
       "      <td>-11446.265464</td>\n",
       "      <td>3671.921902</td>\n",
       "      <td>11080.449494</td>\n",
       "      <td>9256.739749</td>\n",
       "      <td>-5847.214536</td>\n",
       "      <td>-2693.503273</td>\n",
       "      <td>4293.121097</td>\n",
       "      <td>...</td>\n",
       "      <td>-5144.520559</td>\n",
       "      <td>3127.773453</td>\n",
       "      <td>-122.378148</td>\n",
       "      <td>11404.342330</td>\n",
       "      <td>3453.546819</td>\n",
       "      <td>1726.924090</td>\n",
       "      <td>3215.562899</td>\n",
       "      <td>3018.529486</td>\n",
       "      <td>-3643.919678</td>\n",
       "      <td>-3268.666481</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2237.486889</td>\n",
       "      <td>25.665411</td>\n",
       "      <td>-3193.970434</td>\n",
       "      <td>6601.299042</td>\n",
       "      <td>11282.278936</td>\n",
       "      <td>2098.872337</td>\n",
       "      <td>684.774436</td>\n",
       "      <td>-2661.093197</td>\n",
       "      <td>4053.436800</td>\n",
       "      <td>-2418.361719</td>\n",
       "      <td>...</td>\n",
       "      <td>-3363.379895</td>\n",
       "      <td>-271.982509</td>\n",
       "      <td>-2515.471402</td>\n",
       "      <td>30.658347</td>\n",
       "      <td>-3878.675356</td>\n",
       "      <td>5441.705662</td>\n",
       "      <td>-15459.669432</td>\n",
       "      <td>-3635.072480</td>\n",
       "      <td>-223.881934</td>\n",
       "      <td>-8847.167633</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>21.487903</td>\n",
       "      <td>4117.289188</td>\n",
       "      <td>2853.703536</td>\n",
       "      <td>-14819.088168</td>\n",
       "      <td>3315.687257</td>\n",
       "      <td>1110.804968</td>\n",
       "      <td>5206.448494</td>\n",
       "      <td>1028.313768</td>\n",
       "      <td>-4602.918356</td>\n",
       "      <td>-4420.918656</td>\n",
       "      <td>...</td>\n",
       "      <td>-3415.907445</td>\n",
       "      <td>2830.855292</td>\n",
       "      <td>1928.415578</td>\n",
       "      <td>37.842845</td>\n",
       "      <td>1249.763068</td>\n",
       "      <td>64.976906</td>\n",
       "      <td>-12450.703767</td>\n",
       "      <td>-3026.076038</td>\n",
       "      <td>-345.078986</td>\n",
       "      <td>-9825.684247</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 1000 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Feature1      Feature2      Feature3      Feature4      Feature5  \\\n",
       "0 -11942.239893     12.943553   -318.847654   2695.776328  -2139.814545   \n",
       "1   2439.293515 -10658.214127   4404.059579   1752.411046  -1133.866572   \n",
       "2   4031.830996  -1820.018802 -10320.317301 -11446.265464   3671.921902   \n",
       "3   2237.486889     25.665411  -3193.970434   6601.299042  11282.278936   \n",
       "4     21.487903   4117.289188   2853.703536 -14819.088168   3315.687257   \n",
       "\n",
       "       Feature6     Feature7     Feature8     Feature9    Feature10  ...  \\\n",
       "0   -717.146778  1539.996661 -4706.707206    23.007149  1162.154929  ...   \n",
       "1  -3194.139650  4731.903754 -5268.524990     7.737832 -5783.376093  ...   \n",
       "2  11080.449494  9256.739749 -5847.214536 -2693.503273  4293.121097  ...   \n",
       "3   2098.872337   684.774436 -2661.093197  4053.436800 -2418.361719  ...   \n",
       "4   1110.804968  5206.448494  1028.313768 -4602.918356 -4420.918656  ...   \n",
       "\n",
       "    Feature991   Feature992   Feature993    Feature994   Feature995  \\\n",
       "0 -2224.586927  1495.867963 -2690.879528     37.646723  1435.085427   \n",
       "1  8555.393323 -5691.212264  4472.742030     30.222789  5634.529341   \n",
       "2 -5144.520559  3127.773453  -122.378148  11404.342330  3453.546819   \n",
       "3 -3363.379895  -271.982509 -2515.471402     30.658347 -3878.675356   \n",
       "4 -3415.907445  2830.855292  1928.415578     37.842845  1249.763068   \n",
       "\n",
       "     Feature996    Feature997   Feature998    Feature999  Feature1000  \n",
       "0  13271.111625    659.564345 -5542.467489  -3158.842850  4542.571977  \n",
       "1  -3354.225469  -4704.306326 -1173.377176  11995.770742 -1147.780931  \n",
       "2   1726.924090   3215.562899  3018.529486  -3643.919678 -3268.666481  \n",
       "3   5441.705662 -15459.669432 -3635.072480   -223.881934 -8847.167633  \n",
       "4     64.976906 -12450.703767 -3026.076038   -345.078986 -9825.684247  \n",
       "\n",
       "[5 rows x 1000 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "Preview of sim_data_latent_data_num_samples_10_fc_0.1.csv:\n"
     ]
    },
    {
     "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>subject_id</th>\n",
       "      <th>sex</th>\n",
       "      <th>disease</th>\n",
       "      <th>age</th>\n",
       "      <th>batch</th>\n",
       "      <th>bmi</th>\n",
       "      <th>cell_type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>SUB_3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>18</td>\n",
       "      <td>3</td>\n",
       "      <td>34</td>\n",
       "      <td>E</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>SUB_3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>18</td>\n",
       "      <td>3</td>\n",
       "      <td>34</td>\n",
       "      <td>G</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>SUB_5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>29</td>\n",
       "      <td>1</td>\n",
       "      <td>32</td>\n",
       "      <td>F</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>SUB_7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>21</td>\n",
       "      <td>3</td>\n",
       "      <td>34</td>\n",
       "      <td>G</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>SUB_1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>57</td>\n",
       "      <td>1</td>\n",
       "      <td>16</td>\n",
       "      <td>E</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  subject_id  sex  disease  age  batch  bmi cell_type\n",
       "0      SUB_3    0        1   18      3   34         E\n",
       "1      SUB_3    0        1   18      3   34         G\n",
       "2      SUB_5    1        0   29      1   32         F\n",
       "3      SUB_7    0        1   21      3   34         G\n",
       "4      SUB_1    0        0   57      1   16         E"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# List all files in the directory specified in the configuration\n",
    "files = os.listdir(config[\"data_file_path\"])\n",
    "\n",
    "# Loop through the files and display their content\n",
    "for file in files:\n",
    "    file_path = os.path.join(config[\"data_file_path\"], file)\n",
    "\n",
    "    # Check if the file is a CSV (to avoid errors)\n",
    "    if file.endswith(\".csv\"):\n",
    "        df = pd.read_csv(file_path)\n",
    "\n",
    "        # Display the first few rows of the DataFrame\n",
    "        print(f\"Preview of {file}:\")\n",
    "        display(df.head())  # Prettier display in Jupyter Notebook\n",
    "        print(\"\\n\")  # Add some spacing between tables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "chen5150",
   "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": "3.12.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}