{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "fatal: destination path 'mieszkania5' already exists and is not an empty directory.\n" ] } ], "source": [ "!git clone git://gonito.net/mieszkania5" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'j:\\\\Desktop\\\\SysInf\\\\mieszkania5\\\\train\\\\train.tsv'" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train = r'j:\\Desktop\\SysInf\\mieszkania5\\train\\train.tsv'\n", "train" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "data=pd.read_csv(train, sep='\\t', header=None)\n" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index([ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17,\n", " 18, 19, 20, 21, 22, 23, 24, 25],\n", " dtype='int64')" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.columns" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "x_train = data[[0,6,8,19]]" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | 0 | \n", "6 | \n", "8 | \n", "19 | \n", "
---|---|---|---|---|
0 | \n", "309000.0 | \n", "2 | \n", "43.44 | \n", "NaN | \n", "
1 | \n", "314900.0 | \n", "2 | \n", "42.60 | \n", "NaN | \n", "
2 | \n", "249000.0 | \n", "2 | \n", "44.30 | \n", "1960.0 | \n", "
3 | \n", "419000.0 | \n", "4 | \n", "88 | \n", "NaN | \n", "
4 | \n", "499000.0 | \n", "3 | \n", "77 | \n", "NaN | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
2542 | \n", "507600.0 | \n", "4 | \n", "94 | \n", "1914.0 | \n", "
2543 | \n", "342400.0 | \n", "2 | \n", "53.50 | \n", "1999.0 | \n", "
2544 | \n", "335000.0 | \n", "3 | \n", "55.25 | \n", "1910.0 | \n", "
2545 | \n", "260000.0 | \n", "3 | \n", "62 | \n", "1930.0 | \n", "
2546 | \n", "1990000.0 | \n", "więcej niż 10 | \n", "392 | \n", "NaN | \n", "
2547 rows × 4 columns
\n", "\n", " | cena | \n", "pokoje | \n", "metraz | \n", "rok | \n", "
---|---|---|---|---|
2 | \n", "249000.0 | \n", "2.0 | \n", "44.30 | \n", "1960.0 | \n", "
6 | \n", "449000.0 | \n", "4.0 | \n", "92.00 | \n", "1930.0 | \n", "
7 | \n", "389000.0 | \n", "3.0 | \n", "63.60 | \n", "1985.0 | \n", "
9 | \n", "260000.0 | \n", "3.0 | \n", "44.20 | \n", "1970.0 | \n", "
10 | \n", "330682.0 | \n", "3.0 | \n", "48.99 | \n", "2019.0 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
2541 | \n", "383680.0 | \n", "3.0 | \n", "70.40 | \n", "2016.0 | \n", "
2542 | \n", "507600.0 | \n", "4.0 | \n", "94.00 | \n", "1914.0 | \n", "
2543 | \n", "342400.0 | \n", "2.0 | \n", "53.50 | \n", "1999.0 | \n", "
2544 | \n", "335000.0 | \n", "3.0 | \n", "55.25 | \n", "1910.0 | \n", "
2545 | \n", "260000.0 | \n", "3.0 | \n", "62.00 | \n", "1930.0 | \n", "
1767 rows × 4 columns
\n", "LinearRegression()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
LinearRegression()