{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "5782da1e", "metadata": {}, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 4, "id": "73a1eb00", "metadata": {}, "outputs": [], "source": [ "df=pd.read_csv('pairs.txt', sep=\"\\t\", header=None)" ] }, { "cell_type": "code", "execution_count": 5, "id": "5fe3f547", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | 0 | \n", "1 | \n", "2 | \n", "3 | \n", "
---|---|---|---|---|
0 | \n", "chr1 | \n", "2499 | \n", "chr1 | \n", "2723 | \n", "
1 | \n", "chr1 | \n", "3495 | \n", "chr1 | \n", "3795 | \n", "
2 | \n", "chr1 | \n", "3519 | \n", "chr1 | \n", "3735 | \n", "
3 | \n", "chr1 | \n", "3641 | \n", "chr1 | \n", "72429988 | \n", "
4 | \n", "chr1 | \n", "4866 | \n", "chr1 | \n", "5022 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
4587308 | \n", "chrZ | \n", "82309380 | \n", "chrZ | \n", "82036721 | \n", "
4587309 | \n", "chrZ | \n", "82309559 | \n", "chrZ | \n", "82293151 | \n", "
4587310 | \n", "chrZ | \n", "82309416 | \n", "chrZ | \n", "82309572 | \n", "
4587311 | \n", "chrZ | \n", "82309516 | \n", "chrZ | \n", "82309709 | \n", "
4587312 | \n", "chrZ | \n", "82309887 | \n", "chrZ | \n", "82090383 | \n", "
4587313 rows × 4 columns
\n", "\n", " | c1 | \n", "p1 | \n", "c2 | \n", "p2 | \n", "
---|---|---|---|---|
0 | \n", "chr1 | \n", "2499 | \n", "chr1 | \n", "2723 | \n", "
1 | \n", "chr1 | \n", "3495 | \n", "chr1 | \n", "3795 | \n", "
2 | \n", "chr1 | \n", "3519 | \n", "chr1 | \n", "3735 | \n", "
3 | \n", "chr1 | \n", "3641 | \n", "chr1 | \n", "72429988 | \n", "
4 | \n", "chr1 | \n", "4866 | \n", "chr1 | \n", "5022 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
4587308 | \n", "chrZ | \n", "82309380 | \n", "chrZ | \n", "82036721 | \n", "
4587309 | \n", "chrZ | \n", "82309559 | \n", "chrZ | \n", "82293151 | \n", "
4587310 | \n", "chrZ | \n", "82309416 | \n", "chrZ | \n", "82309572 | \n", "
4587311 | \n", "chrZ | \n", "82309516 | \n", "chrZ | \n", "82309709 | \n", "
4587312 | \n", "chrZ | \n", "82309887 | \n", "chrZ | \n", "82090383 | \n", "
4525219 rows × 4 columns
\n", "\n", " | c1 | \n", "p1 | \n", "c2 | \n", "p2 | \n", "
---|---|---|---|---|
0 | \n", "chr1 | \n", "2499 | \n", "chr1 | \n", "2723 | \n", "
1 | \n", "chr1 | \n", "3495 | \n", "chr1 | \n", "3795 | \n", "
2 | \n", "chr1 | \n", "3519 | \n", "chr1 | \n", "3735 | \n", "
3 | \n", "chr1 | \n", "3641 | \n", "chr1 | \n", "72429988 | \n", "
4 | \n", "chr1 | \n", "4866 | \n", "chr1 | \n", "5022 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
4587285 | \n", "chrZ | \n", "82307023 | \n", "chrZ | \n", "82307302 | \n", "
4587297 | \n", "chrZ | \n", "82308869 | \n", "chrZ | \n", "82309117 | \n", "
4587298 | \n", "chrZ | \n", "82309036 | \n", "chrZ | \n", "82309308 | \n", "
4587310 | \n", "chrZ | \n", "82309416 | \n", "chrZ | \n", "82309572 | \n", "
4587311 | \n", "chrZ | \n", "82309516 | \n", "chrZ | \n", "82309709 | \n", "
4356414 rows × 4 columns
\n", "\n", " | c1 | \n", "p1 | \n", "c2 | \n", "p2 | \n", "
---|---|---|---|---|
11 | \n", "chr1 | \n", "20091 | \n", "chr1 | \n", "9288 | \n", "
12 | \n", "chr1 | \n", "28807 | \n", "chr1 | \n", "17707 | \n", "
13 | \n", "chr1 | \n", "28819 | \n", "chr1 | \n", "17703 | \n", "
14 | \n", "chr1 | \n", "28842 | \n", "chr1 | \n", "17796 | \n", "
15 | \n", "chr1 | \n", "28851 | \n", "chr1 | \n", "17818 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
4587306 | \n", "chrZ | \n", "82309120 | \n", "chrZ | \n", "82292613 | \n", "
4587307 | \n", "chrZ | \n", "82309669 | \n", "chrZ | \n", "82020370 | \n", "
4587308 | \n", "chrZ | \n", "82309380 | \n", "chrZ | \n", "82036721 | \n", "
4587309 | \n", "chrZ | \n", "82309559 | \n", "chrZ | \n", "82293151 | \n", "
4587312 | \n", "chrZ | \n", "82309887 | \n", "chrZ | \n", "82090383 | \n", "
168638 rows × 4 columns
\n", "" ], "text/plain": [ " c1 p1 c2 p2\n", "11 chr1 20091 chr1 9288\n", "12 chr1 28807 chr1 17707\n", "13 chr1 28819 chr1 17703\n", "14 chr1 28842 chr1 17796\n", "15 chr1 28851 chr1 17818\n", "... ... ... ... ...\n", "4587306 chrZ 82309120 chrZ 82292613\n", "4587307 chrZ 82309669 chrZ 82020370\n", "4587308 chrZ 82309380 chrZ 82036721\n", "4587309 chrZ 82309559 chrZ 82293151\n", "4587312 chrZ 82309887 chrZ 82090383\n", "\n", "[168638 rows x 4 columns]" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.query('c1==c2 & p1>p2')" ] }, { "cell_type": "code", "execution_count": null, "id": "a5194909", "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": "3.7.10" } }, "nbformat": 4, "nbformat_minor": 5 }