{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from __init__scr import *\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import glob"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD12.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_DM2.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD10.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD14.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD8.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD5.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD6.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD4.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD9.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD15.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD2.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD13.tsv.gz',\n",
       " '/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/allc_AD11.tsv.gz']"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "files = glob.glob('/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/*.gz')\n",
    "files = glob.glob('/cndd2/fangming/projects/cfdna/desplats_combined_2021/allc/test_merge/AD/*.gz')\n",
    "files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n",
      "(10, 6)\n"
     ]
    }
   ],
   "source": [
    "dfs = []\n",
    "for f in files:\n",
    "    df = pd.read_csv(f, sep='\\t', header=None).drop(6, axis=1)\n",
    "    dfs.append(df)\n",
    "    print(df.shape)\n",
    "    \n",
    "dfs = pd.concat(dfs).groupby([0,1,2,3]).sum().reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(52, 6)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dfs.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>chr10</td>\n",
       "      <td>60377</td>\n",
       "      <td>-</td>\n",
       "      <td>CTT</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>chr10</td>\n",
       "      <td>60385</td>\n",
       "      <td>-</td>\n",
       "      <td>CTA</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>chr10</td>\n",
       "      <td>60391</td>\n",
       "      <td>-</td>\n",
       "      <td>CAT</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>chr10</td>\n",
       "      <td>60393</td>\n",
       "      <td>-</td>\n",
       "      <td>CAC</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>chr10</td>\n",
       "      <td>60394</td>\n",
       "      <td>-</td>\n",
       "      <td>CCA</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       0      1  2    3  4  5\n",
       "0  chr10  60377  -  CTT  0  2\n",
       "1  chr10  60385  -  CTA  0  4\n",
       "2  chr10  60391  -  CAT  0  4\n",
       "3  chr10  60393  -  CAC  0  4\n",
       "4  chr10  60394  -  CCA  1  4"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dfs.head()"
   ]
  },
  {
   "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": "3.8.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}