{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true }, "outputs": [], "source": [ "%matplotlib notebook\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "import numpy as np\n", "import calendar" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "collapsed": true }, "outputs": [], "source": [ "def procesing(df):\n", " ''' Adds lags and day_of_week and month columns to dataframe'''\n", " \n", " # Add Lags\n", " df_shifted = pd.concat([df]+[df['P'].shift(i) for i in range(24,49)]+[df['P'].shift(i) for i in range(168,193)], axis=1)\n", " df_shifted.columns = ['P']+['Ph-{}'.format(i) for i in range(24,49)] + ['Ph-{}'.format(i) for i in range(168,193)]\n", " \n", " # Add day_of_week column\n", " df_shifted['day_of_week'] = df.index.weekday_name\n", " \n", " # Add month abbreviature column\n", " df_shifted['month'] = df_shifted.index.month\n", " df_shifted['month'] = df_shifted['month'].apply(lambda x: calendar.month_abbr[x])\n", " \n", " # Add one-hot Encoding\n", " df = pd.get_dummies(df_shifted)\n", " \n", " return df.dropna()\n", " " ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
| \n", " | P | \n", "Ph-1 | \n", "Ph-2 | \n", "Ph-3 | \n", "Ph-24 | \n", "Ph-48 | \n", "Ph-168 | \n", "lun | \n", "mmjv | \n", "sab | \n", "dom | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|
| Fecha_hora | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
| 2016-08-01 00:00:00 | \n", "55.4450 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-01 01:00:00 | \n", "40.1169 | \n", "55.4450 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-01 02:00:00 | \n", "34.0645 | \n", "40.1169 | \n", "55.4450 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-01 03:00:00 | \n", "31.1261 | \n", "34.0645 | \n", "40.1169 | \n", "55.4450 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-01 04:00:00 | \n", "29.7240 | \n", "31.1261 | \n", "34.0645 | \n", "40.1169 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-01 05:00:00 | \n", "32.3707 | \n", "29.7240 | \n", "31.1261 | \n", "34.0645 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-01 06:00:00 | \n", "35.1250 | \n", "32.3707 | \n", "29.7240 | \n", "31.1261 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-01 07:00:00 | \n", "38.6416 | \n", "35.1250 | \n", "32.3707 | \n", "29.7240 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-01 08:00:00 | \n", "48.4632 | \n", "38.6416 | \n", "35.1250 | \n", "32.3707 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-01 09:00:00 | \n", "49.4265 | \n", "48.4632 | \n", "38.6416 | \n", "35.1250 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "
| \n", " | P | \n", "Ph-24 | \n", "Ph-25 | \n", "Ph-26 | \n", "Ph-27 | \n", "Ph-28 | \n", "Ph-29 | \n", "Ph-30 | \n", "Ph-31 | \n", "Ph-32 | \n", "... | \n", "month_Dec | \n", "month_Feb | \n", "month_Jan | \n", "month_Jul | \n", "month_Jun | \n", "month_Mar | \n", "month_May | \n", "month_Nov | \n", "month_Oct | \n", "month_Sep | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Fecha_hora | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
| 2016-08-09 00:00:00 | \n", "95.3264 | \n", "54.8461 | \n", "45.1982 | \n", "44.7123 | \n", "46.2995 | \n", "42.9422 | \n", "44.3551 | \n", "46.3440 | \n", "45.6826 | \n", "42.6676 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-09 01:00:00 | \n", "82.8532 | \n", "52.2179 | \n", "54.8461 | \n", "45.1982 | \n", "44.7123 | \n", "46.2995 | \n", "42.9422 | \n", "44.3551 | \n", "46.3440 | \n", "45.6826 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-09 02:00:00 | \n", "57.9764 | \n", "61.9198 | \n", "52.2179 | \n", "54.8461 | \n", "45.1982 | \n", "44.7123 | \n", "46.2995 | \n", "42.9422 | \n", "44.3551 | \n", "46.3440 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-09 03:00:00 | \n", "67.6407 | \n", "36.8105 | \n", "61.9198 | \n", "52.2179 | \n", "54.8461 | \n", "45.1982 | \n", "44.7123 | \n", "46.2995 | \n", "42.9422 | \n", "44.3551 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-08-09 04:00:00 | \n", "66.4892 | \n", "34.8274 | \n", "36.8105 | \n", "61.9198 | \n", "52.2179 | \n", "54.8461 | \n", "45.1982 | \n", "44.7123 | \n", "46.2995 | \n", "42.9422 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "
5 rows × 70 columns
\n", "| \n", " | Ph-24 | \n", "Ph-25 | \n", "Ph-26 | \n", "Ph-27 | \n", "Ph-28 | \n", "Ph-29 | \n", "Ph-30 | \n", "Ph-31 | \n", "Ph-32 | \n", "Ph-33 | \n", "... | \n", "month_Dec | \n", "month_Feb | \n", "month_Jan | \n", "month_Jul | \n", "month_Jun | \n", "month_Mar | \n", "month_May | \n", "month_Nov | \n", "month_Oct | \n", "month_Sep | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Fecha_hora | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
| 2018-10-24 04:00:00 | \n", "62.0336 | \n", "63.7085 | \n", "70.2444 | \n", "70.7946 | \n", "90.6795 | \n", "96.1702 | \n", "102.8210 | \n", "110.3368 | \n", "104.6051 | \n", "114.0036 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "
| 2018-09-07 05:00:00 | \n", "79.1030 | \n", "63.9443 | \n", "66.2582 | \n", "96.2362 | \n", "116.4281 | \n", "128.8701 | \n", "119.1240 | \n", "119.6116 | \n", "120.0424 | \n", "153.5935 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
| 2017-01-09 19:00:00 | \n", "39.2683 | \n", "38.4852 | \n", "30.3583 | \n", "30.0168 | \n", "30.2148 | \n", "30.1679 | \n", "32.7229 | \n", "33.1058 | \n", "31.2826 | \n", "29.9553 | \n", "... | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2016-12-05 06:00:00 | \n", "29.6552 | \n", "30.0035 | \n", "29.9686 | \n", "30.2936 | \n", "30.5585 | \n", "30.3091 | \n", "35.3114 | \n", "39.8265 | \n", "46.5319 | \n", "51.0830 | \n", "... | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "
| 2018-11-13 10:00:00 | \n", "108.4272 | \n", "106.4169 | \n", "98.9055 | \n", "79.6178 | \n", "62.6484 | \n", "45.0183 | \n", "38.0118 | \n", "37.6738 | \n", "38.3037 | \n", "44.2274 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "
5 rows × 69 columns
\n", "